diff options
Diffstat (limited to 'include')
-rw-r--r-- | include/asm-generic/cputime.h | 4 | ||||
-rw-r--r-- | include/linux/alarmtimer.h | 51 | ||||
-rw-r--r-- | include/linux/clockchips.h | 12 | ||||
-rw-r--r-- | include/linux/dw_apb_timer.h | 2 | ||||
-rw-r--r-- | include/linux/interrupt.h | 41 | ||||
-rw-r--r-- | include/linux/irq.h | 18 | ||||
-rw-r--r-- | include/linux/irq_work.h | 15 | ||||
-rw-r--r-- | include/linux/irqdesc.h | 1 | ||||
-rw-r--r-- | include/linux/jiffies.h | 2 | ||||
-rw-r--r-- | include/linux/llist.h | 77 | ||||
-rw-r--r-- | include/linux/lockdep.h | 2 | ||||
-rw-r--r-- | include/linux/module.h | 12 | ||||
-rw-r--r-- | include/linux/perf_event.h | 5 | ||||
-rw-r--r-- | include/linux/posix-timers.h | 5 | ||||
-rw-r--r-- | include/linux/rcupdate.h | 300 | ||||
-rw-r--r-- | include/linux/rcutiny.h | 20 | ||||
-rw-r--r-- | include/linux/rcutree.h | 2 | ||||
-rw-r--r-- | include/linux/ring_buffer.h | 2 | ||||
-rw-r--r-- | include/linux/sched.h | 11 | ||||
-rw-r--r-- | include/linux/trace_clock.h | 1 | ||||
-rw-r--r-- | include/linux/tracepoint.h | 25 | ||||
-rw-r--r-- | include/linux/types.h | 10 | ||||
-rw-r--r-- | include/scsi/osd_ore.h | 80 | ||||
-rw-r--r-- | include/trace/events/rcu.h | 459 | ||||
-rw-r--r-- | include/trace/events/sched.h | 9 | ||||
-rw-r--r-- | include/trace/ftrace.h | 3 |
26 files changed, 924 insertions, 245 deletions
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h index 61e03dd..62ce682 100644 --- a/include/asm-generic/cputime.h +++ b/include/asm-generic/cputime.h @@ -38,8 +38,8 @@ typedef u64 cputime64_t; /* * Convert cputime to microseconds and back. */ -#define cputime_to_usecs(__ct) jiffies_to_usecs(__ct); -#define usecs_to_cputime(__msecs) usecs_to_jiffies(__msecs); +#define cputime_to_usecs(__ct) jiffies_to_usecs(__ct) +#define usecs_to_cputime(__msecs) usecs_to_jiffies(__msecs) /* * Convert cputime to seconds and back. diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index c5d6095..975009e 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -13,6 +13,16 @@ enum alarmtimer_type { ALARM_NUMTYPE, }; +enum alarmtimer_restart { + ALARMTIMER_NORESTART, + ALARMTIMER_RESTART, +}; + + +#define ALARMTIMER_STATE_INACTIVE 0x00 +#define ALARMTIMER_STATE_ENQUEUED 0x01 +#define ALARMTIMER_STATE_CALLBACK 0x02 + /** * struct alarm - Alarm timer structure * @node: timerqueue node for adding to the event list this value @@ -25,16 +35,45 @@ enum alarmtimer_type { */ struct alarm { struct timerqueue_node node; - ktime_t period; - void (*function)(struct alarm *); + enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; - bool enabled; + int state; void *data; }; void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - void (*function)(struct alarm *)); -void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period); -void alarm_cancel(struct alarm *alarm); + enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); +void alarm_start(struct alarm *alarm, ktime_t start); +int alarm_try_to_cancel(struct alarm *alarm); +int alarm_cancel(struct alarm *alarm); + +u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); + +/* + * A alarmtimer is active, when it is enqueued into timerqueue or the + * callback function is running. + */ +static inline int alarmtimer_active(const struct alarm *timer) +{ + return timer->state != ALARMTIMER_STATE_INACTIVE; +} + +/* + * Helper function to check, whether the timer is on one of the queues + */ +static inline int alarmtimer_is_queued(struct alarm *timer) +{ + return timer->state & ALARMTIMER_STATE_ENQUEUED; +} + +/* + * Helper function to check, whether the timer is running the callback + * function + */ +static inline int alarmtimer_callback_running(struct alarm *timer) +{ + return timer->state & ALARMTIMER_STATE_CALLBACK; +} + #endif diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index d6733e2..81e803e 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -45,20 +45,22 @@ enum clock_event_nofitiers { */ #define CLOCK_EVT_FEAT_PERIODIC 0x000001 #define CLOCK_EVT_FEAT_ONESHOT 0x000002 +#define CLOCK_EVT_FEAT_KTIME 0x000004 /* * x86(64) specific misfeatures: * * - Clockevent source stops in C3 State and needs broadcast support. * - Local APIC timer is used as a dummy device. */ -#define CLOCK_EVT_FEAT_C3STOP 0x000004 -#define CLOCK_EVT_FEAT_DUMMY 0x000008 +#define CLOCK_EVT_FEAT_C3STOP 0x000008 +#define CLOCK_EVT_FEAT_DUMMY 0x000010 /** * struct clock_event_device - clock event device descriptor * @event_handler: Assigned by the framework to be called by the low * level handler of the event source - * @set_next_event: set next event function + * @set_next_event: set next event function using a clocksource delta + * @set_next_ktime: set next event function using a direct ktime value * @next_event: local storage for the next event in oneshot mode * @max_delta_ns: maximum delta value in ns * @min_delta_ns: minimum delta value in ns @@ -81,6 +83,8 @@ struct clock_event_device { void (*event_handler)(struct clock_event_device *); int (*set_next_event)(unsigned long evt, struct clock_event_device *); + int (*set_next_ktime)(ktime_t expires, + struct clock_event_device *); ktime_t next_event; u64 max_delta_ns; u64 min_delta_ns; @@ -140,7 +144,7 @@ extern void clockevents_set_mode(struct clock_event_device *dev, enum clock_event_mode mode); extern int clockevents_register_notifier(struct notifier_block *nb); extern int clockevents_program_event(struct clock_event_device *dev, - ktime_t expires, ktime_t now); + ktime_t expires, bool force); extern void clockevents_handle_noop(struct clock_event_device *dev); diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index 49638ea..07261d5 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -46,7 +46,7 @@ struct dw_apb_clock_event_device * dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, void __iomem *base, int irq, unsigned long freq); struct dw_apb_clocksource * -dw_apb_clocksource_init(unsigned rating, char *name, void __iomem *base, +dw_apb_clocksource_init(unsigned rating, const char *name, void __iomem *base, unsigned long freq); void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs); void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a103732..a64b00e 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -59,6 +59,8 @@ * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set * IRQF_NO_THREAD - Interrupt cannot be threaded + * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device + * resume time. */ #define IRQF_DISABLED 0x00000020 #define IRQF_SAMPLE_RANDOM 0x00000040 @@ -72,6 +74,7 @@ #define IRQF_NO_SUSPEND 0x00004000 #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 +#define IRQF_EARLY_RESUME 0x00020000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) @@ -95,6 +98,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @flags: flags (see IRQF_* above) * @name: name of the device * @dev_id: cookie to identify the device + * @percpu_dev_id: cookie to identify the device * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @dir: pointer to the proc/irq/NN/name entry @@ -104,17 +108,18 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @thread_mask: bitmask for keeping track of @thread activity */ struct irqaction { - irq_handler_t handler; - unsigned long flags; - void *dev_id; - struct irqaction *next; - int irq; - irq_handler_t thread_fn; - struct task_struct *thread; - unsigned long thread_flags; - unsigned long thread_mask; - const char *name; - struct proc_dir_entry *dir; + irq_handler_t handler; + unsigned long flags; + void *dev_id; + void __percpu *percpu_dev_id; + struct irqaction *next; + int irq; + irq_handler_t thread_fn; + struct task_struct *thread; + unsigned long thread_flags; + unsigned long thread_mask; + const char *name; + struct proc_dir_entry *dir; } ____cacheline_internodealigned_in_smp; extern irqreturn_t no_action(int cpl, void *dev_id); @@ -136,6 +141,10 @@ extern int __must_check request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); +extern int __must_check +request_percpu_irq(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *percpu_dev_id); + extern void exit_irq_thread(void); #else @@ -164,10 +173,18 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, return request_irq(irq, handler, flags, name, dev_id); } +static inline int __must_check +request_percpu_irq(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *percpu_dev_id) +{ + return request_irq(irq, handler, 0, devname, percpu_dev_id); +} + static inline void exit_irq_thread(void) { } #endif extern void free_irq(unsigned int, void *); +extern void free_percpu_irq(unsigned int, void __percpu *); struct device; @@ -207,7 +224,9 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); extern void disable_irq_nosync(unsigned int irq); extern void disable_irq(unsigned int irq); +extern void disable_percpu_irq(unsigned int irq); extern void enable_irq(unsigned int irq); +extern void enable_percpu_irq(unsigned int irq, unsigned int type); /* The following three functions are for the core kernel use only. */ #ifdef CONFIG_GENERIC_HARDIRQS diff --git a/include/linux/irq.h b/include/linux/irq.h index 5951730..59e49c8 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -66,6 +66,7 @@ typedef void (*irq_preflow_handler_t)(struct irq_data *data); * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) * 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 */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -88,12 +89,13 @@ enum { IRQ_MOVE_PCNTXT = (1 << 14), IRQ_NESTED_THREAD = (1 << 15), IRQ_NOTHREAD = (1 << 16), + IRQ_PER_CPU_DEVID = (1 << 17), }; #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_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) @@ -336,12 +338,14 @@ struct irq_chip { * IRQCHIP_MASK_ON_SUSPEND: Mask non wake irqs in the suspend path * IRQCHIP_ONOFFLINE_ENABLED: Only call irq_on/off_line callbacks * when irq enabled + * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), IRQCHIP_EOI_IF_HANDLED = (1 << 1), IRQCHIP_MASK_ON_SUSPEND = (1 << 2), IRQCHIP_ONOFFLINE_ENABLED = (1 << 3), + IRQCHIP_SKIP_SET_WAKE = (1 << 4), }; /* This include will go away once we isolated irq_desc usage to core code */ @@ -365,6 +369,8 @@ enum { struct irqaction; extern int setup_irq(unsigned int irq, struct irqaction *new); extern void remove_irq(unsigned int irq, struct irqaction *act); +extern int setup_percpu_irq(unsigned int irq, struct irqaction *new); +extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); extern void irq_cpu_online(void); extern void irq_cpu_offline(void); @@ -392,6 +398,7 @@ extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc); extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc); extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc); extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc); +extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); @@ -420,6 +427,8 @@ static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *c irq_set_chip_and_handler_name(irq, chip, handle, NULL); } +extern int irq_set_percpu_devid(unsigned int irq); + extern void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, const char *name); @@ -481,6 +490,13 @@ static inline void irq_set_nested_thread(unsigned int irq, bool nest) irq_clear_status_flags(irq, IRQ_NESTED_THREAD); } +static inline void irq_set_percpu_devid_flags(unsigned int irq) +{ + irq_set_status_flags(irq, + IRQ_NOAUTOEN | IRQ_PER_CPU | IRQ_NOTHREAD | + IRQ_NOPROBE | IRQ_PER_CPU_DEVID); +} + /* Handle dynamic irq creation and destruction */ extern unsigned int create_irq_nr(unsigned int irq_want, int node); extern int create_irq(void); diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 4fa09d4..6a9e8f5 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -1,20 +1,23 @@ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H +#include <linux/llist.h> + struct irq_work { - struct irq_work *next; + unsigned long flags; + struct llist_node llnode; void (*func)(struct irq_work *); }; static inline -void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *)) +void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) { - entry->next = NULL; - entry->func = func; + work->flags = 0; + work->func = func; } -bool irq_work_queue(struct irq_work *entry); +bool irq_work_queue(struct irq_work *work); void irq_work_run(void); -void irq_work_sync(struct irq_work *entry); +void irq_work_sync(struct irq_work *work); #endif /* _LINUX_IRQ_WORK_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 150134a..6b69c2c 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -53,6 +53,7 @@ struct irq_desc { unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; raw_spinlock_t lock; + struct cpumask *percpu_enabled; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; struct irq_affinity_notify *affinity_notify; diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index f97672a..265e2c3 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -303,7 +303,7 @@ extern void jiffies_to_timespec(const unsigned long jiffies, extern unsigned long timeval_to_jiffies(const struct timeval *value); extern void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value); -extern clock_t jiffies_to_clock_t(long x); +extern clock_t jiffies_to_clock_t(unsigned long x); extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); diff --git a/include/linux/llist.h b/include/linux/llist.h index aa0c8b5..7287734 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -35,10 +35,30 @@ * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the - * list can NOT be used in NMI handler. So code uses the list in NMI - * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + * list can NOT be used in NMI handlers. So code that uses the list in + * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + * + * Copyright 2010,2011 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation; + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/kernel.h> +#include <asm/system.h> +#include <asm/processor.h> + struct llist_head { struct llist_node *first; }; @@ -113,14 +133,55 @@ static inline void init_llist_head(struct llist_head *list) * test whether the list is empty without deleting something from the * list. */ -static inline int llist_empty(const struct llist_head *head) +static inline bool llist_empty(const struct llist_head *head) { return ACCESS_ONCE(head->first) == NULL; } -void llist_add(struct llist_node *new, struct llist_head *head); -void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, - struct llist_head *head); -struct llist_node *llist_del_first(struct llist_head *head); -struct llist_node *llist_del_all(struct llist_head *head); +static inline struct llist_node *llist_next(struct llist_node *node) +{ + return node->next; +} + +/** + * llist_add - add a new entry + * @new: new entry to be added + * @head: the head for your lock-less list + * + * Return whether list is empty before adding. + */ +static inline bool llist_add(struct llist_node *new, struct llist_head *head) +{ + struct llist_node *entry, *old_entry; + + entry = head->first; + for (;;) { + old_entry = entry; + new->next = entry; + entry = cmpxchg(&head->first, old_entry, new); + if (entry == old_entry) + break; + } + + return old_entry == NULL; +} + +/** + * llist_del_all - delete all entries from lock-less list + * @head: the head of lock-less list to delete all entries + * + * If list is empty, return NULL, otherwise, delete all entries and + * return the pointer to the first entry. The order of entries + * deleted is from the newest to the oldest added one. + */ +static inline struct llist_node *llist_del_all(struct llist_head *head) +{ + return xchg(&head->first, NULL); +} + +extern bool llist_add_batch(struct llist_node *new_first, + struct llist_node *new_last, + struct llist_head *head); +extern struct llist_node *llist_del_first(struct llist_head *head); + #endif /* LLIST_H */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index ef820a3..b6a56e3 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -548,7 +548,7 @@ do { \ #endif #ifdef CONFIG_PROVE_RCU -extern void lockdep_rcu_dereference(const char *file, const int line); +void lockdep_rcu_suspicious(const char *file, const int line, const char *s); #endif #endif /* __LINUX_LOCKDEP_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 1c30087..8639216 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -580,9 +580,6 @@ int unregister_module_notifier(struct notifier_block * nb); extern void print_modules(void); -extern void module_update_tracepoints(void); -extern int module_get_iter_tracepoints(struct tracepoint_iter *iter); - #else /* !CONFIG_MODULES... */ #define EXPORT_SYMBOL(sym) #define EXPORT_SYMBOL_GPL(sym) @@ -698,15 +695,6 @@ static inline int unregister_module_notifier(struct notifier_block * nb) static inline void print_modules(void) { } - -static inline void module_update_tracepoints(void) -{ -} - -static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter) -{ - return 0; -} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c816075..1e9ebe5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -220,7 +220,10 @@ struct perf_event_attr { mmap_data : 1, /* non-exec mmap data */ sample_id_all : 1, /* sample_type all events */ - __reserved_1 : 45; + exclude_host : 1, /* don't count in host */ + exclude_guest : 1, /* don't count in guest */ + + __reserved_1 : 43; union { __u32 wakeup_events; /* wakeup every n events */ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 959c141..042058f 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -81,7 +81,10 @@ struct k_itimer { unsigned long incr; unsigned long expires; } mmtimer; - struct alarm alarmtimer; + struct { + struct alarm alarmtimer; + ktime_t interval; + } alarm; struct rcu_head rcu; } it; }; diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8f4f881..2cf4226 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -33,6 +33,7 @@ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H +#include <linux/types.h> #include <linux/cache.h> #include <linux/spinlock.h> #include <linux/threads.h> @@ -64,32 +65,74 @@ static inline void rcutorture_record_progress(unsigned long vernum) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) +/* Exported common interfaces */ + +#ifdef CONFIG_PREEMPT_RCU + /** - * struct rcu_head - callback structure for use with RCU - * @next: next update requests in a list - * @func: actual update function to call after the grace period. + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. */ -struct rcu_head { - struct rcu_head *next; - void (*func)(struct rcu_head *head); -}; +extern void call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *head)); -/* Exported common interfaces */ +#else /* #ifdef CONFIG_PREEMPT_RCU */ + +/* In classic RCU, call_rcu() is just call_rcu_sched(). */ +#define call_rcu call_rcu_sched + +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + +/** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_bh() assumes + * that the read-side critical sections end on completion of a softirq + * handler. This means that read-side critical sections in process + * context must not be interrupted by softirqs. This interface is to be + * used when most of the read-side critical sections are in softirq context. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. + * OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * These may be nested. + */ +extern void call_rcu_bh(struct rcu_head *head, + void (*func)(struct rcu_head *head)); + +/** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_sched() assumes + * that the read-side critical sections end on enabling of preemption + * or on voluntary preemption. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), + * OR + * anything that disables preemption. + * These may be nested. + */ extern void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); -extern void synchronize_sched(void); -extern void rcu_barrier_bh(void); -extern void rcu_barrier_sched(void); - -static inline void __rcu_read_lock_bh(void) -{ - local_bh_disable(); -} -static inline void __rcu_read_unlock_bh(void) -{ - local_bh_enable(); -} +extern void synchronize_sched(void); #ifdef CONFIG_PREEMPT_RCU @@ -152,6 +195,15 @@ static inline void rcu_exit_nohz(void) #endif /* #else #ifdef CONFIG_NO_HZ */ +/* + * Infrastructure to implement the synchronize_() primitives in + * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. + */ + +typedef void call_rcu_func_t(struct rcu_head *head, + void (*func)(struct rcu_head *head)); +void wait_rcu_gp(call_rcu_func_t crf); + #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU) @@ -297,19 +349,31 @@ extern int rcu_my_thread_group_empty(void); /** * rcu_lockdep_assert - emit lockdep splat if specified condition not met * @c: condition to check + * @s: informative message */ -#define rcu_lockdep_assert(c) \ +#define rcu_lockdep_assert(c, s) \ do { \ static bool __warned; \ if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \ __warned = true; \ - lockdep_rcu_dereference(__FILE__, __LINE__); \ + lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) +#define rcu_sleep_check() \ + do { \ + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ + "Illegal context switch in RCU-bh" \ + " read-side critical section"); \ + rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), \ + "Illegal context switch in RCU-sched"\ + " read-side critical section"); \ + } while (0) + #else /* #ifdef CONFIG_PROVE_RCU */ -#define rcu_lockdep_assert(c) do { } while (0) +#define rcu_lockdep_assert(c, s) do { } while (0) +#define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ @@ -338,14 +402,16 @@ extern int rcu_my_thread_group_empty(void); #define __rcu_dereference_check(p, c, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - rcu_lockdep_assert(c); \ + rcu_lockdep_assert(c, "suspicious rcu_dereference_check()" \ + " usage"); \ rcu_dereference_sparse(p, space); \ smp_read_barrier_depends(); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ - rcu_lockdep_assert(c); \ + rcu_lockdep_assert(c, "suspicious rcu_dereference_protected()" \ + " usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) @@ -359,15 +425,15 @@ extern int rcu_my_thread_group_empty(void); #define __rcu_dereference_index_check(p, c) \ ({ \ typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_lockdep_assert(c); \ + rcu_lockdep_assert(c, \ + "suspicious rcu_dereference_index_check()" \ + " usage"); \ smp_read_barrier_depends(); \ (_________p1); \ }) #define __rcu_assign_pointer(p, v, space) \ ({ \ - if (!__builtin_constant_p(v) || \ - ((v) != NULL)) \ - smp_wmb(); \ + smp_wmb(); \ (p) = (typeof(*v) __force space *)(v); \ }) @@ -500,26 +566,6 @@ extern int rcu_my_thread_group_empty(void); #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) -/** - * rcu_dereference_bh_protected() - fetch RCU-bh pointer when updates prevented - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * This is the RCU-bh counterpart to rcu_dereference_protected(). - */ -#define rcu_dereference_bh_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) - -/** - * rcu_dereference_sched_protected() - fetch RCU-sched pointer when updates prevented - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * This is the RCU-sched counterpart to rcu_dereference_protected(). - */ -#define rcu_dereference_sched_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) - /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing @@ -630,7 +676,7 @@ static inline void rcu_read_unlock(void) */ static inline void rcu_read_lock_bh(void) { - __rcu_read_lock_bh(); + local_bh_disable(); __acquire(RCU_BH); rcu_read_acquire_bh(); } @@ -644,7 +690,7 @@ static inline void rcu_read_unlock_bh(void) { rcu_read_release_bh(); __release(RCU_BH); - __rcu_read_unlock_bh(); + local_bh_enable(); } /** @@ -698,11 +744,18 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * any prior initialization. Returns the value assigned. * * Inserts memory barriers on architectures that require them - * (pretty much all of them other than x86), and also prevents - * the compiler from reordering the code that initializes the - * structure after the pointer assignment. More importantly, this - * call documents which pointers will be dereferenced by RCU read-side - * code. + * (which is most of them), and also prevents the compiler from + * reordering the code that initializes the structure after the pointer + * assignment. More importantly, this call documents which pointers + * will be dereferenced by RCU read-side code. + * + * In some special cases, you may use RCU_INIT_POINTER() instead + * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due + * to the fact that it does not constrain either the CPU or the compiler. + * That said, using RCU_INIT_POINTER() when you should have used + * rcu_assign_pointer() is a very bad thing that results in + * impossible-to-diagnose memory corruption. So please be careful. + * See the RCU_INIT_POINTER() comment header for details. */ #define rcu_assign_pointer(p, v) \ __rcu_assign_pointer((p), (v), __rcu) @@ -710,105 +763,38 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * - * Initialize an RCU-protected pointer in such a way to avoid RCU-lockdep - * splats. + * Initialize an RCU-protected pointer in special cases where readers + * do not need ordering constraints on the CPU or the compiler. These + * special cases are: + * + * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer -or- + * 2. The caller has taken whatever steps are required to prevent + * RCU readers from concurrently accessing this pointer -or- + * 3. The referenced data structure has already been exposed to + * readers either at compile time or via rcu_assign_pointer() -and- + * a. You have not made -any- reader-visible changes to + * this structure since then -or- + * b. It is OK for readers accessing this structure from its + * new location to see the old state of the structure. (For + * example, the changes were to statistical counters or to + * other state where exact synchronization is not required.) + * + * Failure to follow these rules governing use of RCU_INIT_POINTER() will + * result in impossible-to-diagnose memory corruption. As in the structures + * will look OK in crash dumps, but any concurrent RCU readers might + * see pre-initialized values of the referenced data structure. So + * please be very careful how you use RCU_INIT_POINTER()!!! + * + * If you are creating an RCU-protected linked structure that is accessed + * by a single external-to-structure RCU-protected pointer, then you may + * use RCU_INIT_POINTER() to initialize the internal RCU-protected + * pointers, but you must use rcu_assign_pointer() to initialize the + * external-to-structure pointer -after- you have completely initialized + * the reader-accessible portions of the linked structure. */ #define RCU_INIT_POINTER(p, v) \ p = (typeof(*v) __force __rcu *)(v) -/* Infrastructure to implement the synchronize_() primitives. */ - -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; -}; - -extern void wakeme_after_rcu(struct rcu_head *head); - -#ifdef CONFIG_PREEMPT_RCU - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - */ -extern void call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *head)); - -#else /* #ifdef CONFIG_PREEMPT_RCU */ - -/* In classic RCU, call_rcu() is just call_rcu_sched(). */ -#define call_rcu call_rcu_sched - -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. - */ -extern void call_rcu_bh(struct rcu_head *head, - void (*func)(struct rcu_head *head)); - -/* - * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally - * by call_rcu() and rcu callback execution, and are therefore not part of the - * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. - */ - -#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD -# define STATE_RCU_HEAD_READY 0 -# define STATE_RCU_HEAD_QUEUED 1 - -extern struct debug_obj_descr rcuhead_debug_descr; - -static inline void debug_rcu_head_queue(struct rcu_head *head) -{ - WARN_ON_ONCE((unsigned long)head & 0x3); - debug_object_activate(head, &rcuhead_debug_descr); - debug_object_active_state(head, &rcuhead_debug_descr, - STATE_RCU_HEAD_READY, - STATE_RCU_HEAD_QUEUED); -} - -static inline void debug_rcu_head_unqueue(struct rcu_head *head) -{ - debug_object_active_state(head, &rcuhead_debug_descr, - STATE_RCU_HEAD_QUEUED, - STATE_RCU_HEAD_READY); - debug_object_deactivate(head, &rcuhead_debug_descr); -} -#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -static inline void debug_rcu_head_queue(struct rcu_head *head) -{ -} - -static inline void debug_rcu_head_unqueue(struct rcu_head *head) -{ -} -#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ - static __always_inline bool __is_kfree_rcu_offset(unsigned long offset) { return offset < 4096; @@ -827,18 +813,6 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) call_rcu(head, (rcu_callback)offset); } -extern void kfree(const void *); - -static inline void __rcu_reclaim(struct rcu_head *head) -{ - unsigned long offset = (unsigned long)head->func; - - if (__is_kfree_rcu_offset(offset)) - kfree((void *)head - offset); - else - head->func(head); -} - /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 52b3e02..00b7a5e 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,9 +27,23 @@ #include <linux/cache.h> +#ifdef CONFIG_RCU_BOOST static inline void rcu_init(void) { } +#else /* #ifdef CONFIG_RCU_BOOST */ +void rcu_init(void); +#endif /* #else #ifdef CONFIG_RCU_BOOST */ + +static inline void rcu_barrier_bh(void) +{ + wait_rcu_gp(call_rcu_bh); +} + +static inline void rcu_barrier_sched(void) +{ + wait_rcu_gp(call_rcu_sched); +} #ifdef CONFIG_TINY_RCU @@ -45,9 +59,13 @@ static inline void rcu_barrier(void) #else /* #ifdef CONFIG_TINY_RCU */ -void rcu_barrier(void); void synchronize_rcu_expedited(void); +static inline void rcu_barrier(void) +{ + wait_rcu_gp(call_rcu); +} + #endif /* #else #ifdef CONFIG_TINY_RCU */ static inline void synchronize_rcu_bh(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index e65d066..6745846 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -67,6 +67,8 @@ static inline void synchronize_rcu_bh_expedited(void) } extern void rcu_barrier(void); +extern void rcu_barrier_bh(void); +extern void rcu_barrier_sched(void); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b891de9..67be037 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -154,6 +154,8 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); +unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu); +unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_entries(struct ring_buffer *buffer); unsigned long ring_buffer_overruns(struct ring_buffer *buffer); unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu); diff --git a/include/linux/sched.h b/include/linux/sched.h index 1be699d..e8acce7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -90,6 +90,7 @@ struct sched_param { #include <linux/task_io_accounting.h> #include <linux/latencytop.h> #include <linux/cred.h> +#include <linux/llist.h> #include <asm/processor.h> @@ -270,7 +271,6 @@ extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(int cpu); -extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) extern void select_nohz_load_balancer(int stop_tick); extern int get_nohz_timer_target(void); @@ -1225,7 +1225,7 @@ struct task_struct { unsigned int ptrace; #ifdef CONFIG_SMP - struct task_struct *wake_entry; + struct llist_node wake_entry; int on_cpu; #endif int on_rq; @@ -1260,9 +1260,6 @@ struct task_struct { #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; char rcu_read_unlock_special; -#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) - int rcu_boosted; -#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */ struct list_head rcu_node_entry; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TREE_PREEMPT_RCU @@ -2039,6 +2036,10 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { } static inline void sched_autogroup_exit(struct signal_struct *sig) { } #endif +#ifdef CONFIG_CFS_BANDWIDTH +extern unsigned int sysctl_sched_cfs_bandwidth_slice; +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h index 7a81303..4eb4902 100644 --- a/include/linux/trace_clock.h +++ b/include/linux/trace_clock.h @@ -15,5 +15,6 @@ extern u64 notrace trace_clock_local(void); extern u64 notrace trace_clock(void); extern u64 notrace trace_clock_global(void); +extern u64 notrace trace_clock_counter(void); #endif /* _LINUX_TRACE_CLOCK_H */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index d530a44..df0a779 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -54,8 +54,18 @@ extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe, void *data); extern void tracepoint_probe_update_all(void); +#ifdef CONFIG_MODULES +struct tp_module { + struct list_head list; + unsigned int num_tracepoints; + struct tracepoint * const *tracepoints_ptrs; +}; +#endif /* CONFIG_MODULES */ + struct tracepoint_iter { - struct module *module; +#ifdef CONFIG_MODULES + struct tp_module *module; +#endif /* CONFIG_MODULES */ struct tracepoint * const *tracepoint; }; @@ -63,8 +73,6 @@ extern void tracepoint_iter_start(struct tracepoint_iter *iter); extern void tracepoint_iter_next(struct tracepoint_iter *iter); extern void tracepoint_iter_stop(struct tracepoint_iter *iter); extern void tracepoint_iter_reset(struct tracepoint_iter *iter); -extern int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, - struct tracepoint * const *begin, struct tracepoint * const *end); /* * tracepoint_synchronize_unregister must be called between the last tracepoint @@ -78,17 +86,6 @@ static inline void tracepoint_synchronize_unregister(void) #define PARAMS(args...) args -#ifdef CONFIG_TRACEPOINTS -extern -void tracepoint_update_probe_range(struct tracepoint * const *begin, - struct tracepoint * const *end); -#else -static inline -void tracepoint_update_probe_range(struct tracepoint * const *begin, - struct tracepoint * const *end) -{ } -#endif /* CONFIG_TRACEPOINTS */ - #endif /* _LINUX_TRACEPOINT_H */ /* diff --git a/include/linux/types.h b/include/linux/types.h index 176da8c..57a9723 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -238,6 +238,16 @@ struct ustat { char f_fpack[6]; }; +/** + * struct rcu_head - callback structure for use with RCU + * @next: next update requests in a list + * @func: actual update function to call after the grace period. + */ +struct rcu_head { + struct rcu_head *next; + void (*func)(struct rcu_head *head); +}; + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ #endif /* _LINUX_TYPES_H */ diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h index c5c5e00..f05fa82 100644 --- a/include/scsi/osd_ore.h +++ b/include/scsi/osd_ore.h @@ -34,15 +34,30 @@ struct ore_comp { struct ore_layout { /* Our way of looking at the data_map */ + enum pnfs_osd_raid_algorithm4 + raid_algorithm; unsigned stripe_unit; unsigned mirrors_p1; unsigned group_width; + unsigned parity; u64 group_depth; unsigned group_count; + + /* Cached often needed calculations filled in by + * ore_verify_layout + */ + unsigned long max_io_length; /* Max length that should be passed to + * ore_get_rw_state + */ +}; + +struct ore_dev { + struct osd_dev *od; }; struct ore_components { + unsigned first_dev; /* First logical device no */ unsigned numdevs; /* Num of devices in array */ /* If @single_comp == EC_SINGLE_COMP, @comps points to a single * component. else there are @numdevs components @@ -51,20 +66,60 @@ struct ore_components { EC_SINGLE_COMP = 0, EC_MULTPLE_COMPS = 0xffffffff } single_comp; struct ore_comp *comps; - struct osd_dev **ods; /* osd_dev array */ + + /* Array of pointers to ore_dev-* . User will usually have these pointed + * too a bigger struct which contain an "ore_dev ored" member and use + * container_of(oc->ods[i], struct foo_dev, ored) to access the bigger + * structure. + */ + struct ore_dev **ods; +}; + +/* ore_comp_dev Recievies a logical device index */ +static inline struct osd_dev *ore_comp_dev( + const struct ore_components *oc, unsigned i) +{ + BUG_ON((i < oc->first_dev) || (oc->first_dev + oc->numdevs <= i)); + return oc->ods[i - oc->first_dev]->od; +} + +static inline void ore_comp_set_dev( + struct ore_components *oc, unsigned i, struct osd_dev *od) +{ + oc->ods[i - oc->first_dev]->od = od; +} + +struct ore_striping_info { + u64 offset; + u64 obj_offset; + u64 length; + u64 first_stripe_start; /* only used in raid writes */ + u64 M; /* for truncate */ + unsigned bytes_in_stripe; + unsigned dev; + unsigned par_dev; + unsigned unit_off; + unsigned cur_pg; + unsigned cur_comp; }; struct ore_io_state; typedef void (*ore_io_done_fn)(struct ore_io_state *ios, void *private); +struct _ore_r4w_op { + /* @Priv given here is passed ios->private */ + struct page * (*get_page)(void *priv, u64 page_index, bool *uptodate); + void (*put_page)(void *priv, struct page *page); +}; struct ore_io_state { struct kref kref; + struct ore_striping_info si; void *private; ore_io_done_fn done; struct ore_layout *layout; - struct ore_components *comps; + struct ore_components *oc; /* Global read/write IO*/ loff_t offset; @@ -84,6 +139,16 @@ struct ore_io_state { bool reading; + /* House keeping of Parity pages */ + bool extra_part_alloc; + struct page **parity_pages; + unsigned max_par_pages; + unsigned cur_par_page; + unsigned sgs_per_dev; + struct __stripe_pages_2d *sp2d; + struct ore_io_state *ios_read_4_write; + const struct _ore_r4w_op *r4w; + /* Variable array of size numdevs */ unsigned numdevs; struct ore_per_dev_state { @@ -91,7 +156,10 @@ struct ore_io_state { struct bio *bio; loff_t offset; unsigned length; + unsigned last_sgs_total; unsigned dev; + struct osd_sg_entry *sglist; + unsigned cur_sg; } per_dev[]; }; @@ -102,6 +170,9 @@ static inline unsigned ore_io_state_size(unsigned numdevs) } /* ore.c */ +int ore_verify_layout(unsigned total_comps, struct ore_layout *layout); +void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset, + u64 length, struct ore_striping_info *si); int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps, bool is_reading, u64 offset, u64 length, struct ore_io_state **ios); @@ -109,7 +180,10 @@ int ore_get_io_state(struct ore_layout *layout, struct ore_components *comps, struct ore_io_state **ios); void ore_put_io_state(struct ore_io_state *ios); -int ore_check_io(struct ore_io_state *ios, u64 *resid); +typedef void (*ore_on_dev_error)(struct ore_io_state *ios, struct ore_dev *od, + unsigned dev_index, enum osd_err_priority oep, + u64 dev_offset, u64 dev_len); +int ore_check_io(struct ore_io_state *ios, ore_on_dev_error rep); int ore_create(struct ore_io_state *ios); int ore_remove(struct ore_io_state *ios); diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h new file mode 100644 index 0000000..669fbd6 --- /dev/null +++ b/include/trace/events/rcu.h @@ -0,0 +1,459 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rcu + +#if !defined(_TRACE_RCU_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RCU_H + +#include <linux/tracepoint.h> + +/* + * Tracepoint for start/end markers used for utilization calculations. + * By convention, the string is of the following forms: + * + * "Start <activity>" -- Mark the start of the specified activity, + * such as "context switch". Nesting is permitted. + * "End <activity>" -- Mark the end of the specified activity. + * + * An "@" character within "<activity>" is a comment character: Data + * reduction scripts will ignore the "@" and the remainder of the line. + */ +TRACE_EVENT(rcu_utilization, + + TP_PROTO(char *s), + + TP_ARGS(s), + + TP_STRUCT__entry( + __field(char *, s) + ), + + TP_fast_assign( + __entry->s = s; + ), + + TP_printk("%s", __entry->s) +); + +#ifdef CONFIG_RCU_TRACE + +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) + +/* + * Tracepoint for grace-period events: starting and ending a grace + * period ("start" and "end", respectively), a CPU noting the start + * of a new grace period or the end of an old grace period ("cpustart" + * and "cpuend", respectively), a CPU passing through a quiescent + * state ("cpuqs"), a CPU coming online or going offline ("cpuonl" + * and "cpuofl", respectively), and a CPU being kicked for being too + * long in dyntick-idle mode ("kick"). + */ +TRACE_EVENT(rcu_grace_period, + + TP_PROTO(char *rcuname, unsigned long gpnum, char *gpevent), + + TP_ARGS(rcuname, gpnum, gpevent), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(unsigned long, gpnum) + __field(char *, gpevent) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpnum = gpnum; + __entry->gpevent = gpevent; + ), + + TP_printk("%s %lu %s", + __entry->rcuname, __entry->gpnum, __entry->gpevent) +); + +/* + * Tracepoint for grace-period-initialization events. These are + * distinguished by the type of RCU, the new grace-period number, the + * rcu_node structure level, the starting and ending CPU covered by the + * rcu_node structure, and the mask of CPUs that will be waited for. + * All but the type of RCU are extracted from the rcu_node structure. + */ +TRACE_EVENT(rcu_grace_period_init, + + TP_PROTO(char *rcuname, unsigned long gpnum, u8 level, + int grplo, int grphi, unsigned long qsmask), + + TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(unsigned long, gpnum) + __field(u8, level) + __field(int, grplo) + __field(int, grphi) + __field(unsigned long, qsmask) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpnum = gpnum; + __entry->level = level; + __entry->grplo = grplo; + __entry->grphi = grphi; + __entry->qsmask = qsmask; + ), + + TP_printk("%s %lu %u %d %d %lx", + __entry->rcuname, __entry->gpnum, __entry->level, + __entry->grplo, __entry->grphi, __entry->qsmask) +); + +/* + * Tracepoint for tasks blocking within preemptible-RCU read-side + * critical sections. Track the type of RCU (which one day might + * include SRCU), the grace-period number that the task is blocking + * (the current or the next), and the task's PID. + */ +TRACE_EVENT(rcu_preempt_task, + + TP_PROTO(char *rcuname, int pid, unsigned long gpnum), + + TP_ARGS(rcuname, pid, gpnum), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(unsigned long, gpnum) + __field(int, pid) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpnum = gpnum; + __entry->pid = pid; + ), + + TP_printk("%s %lu %d", + __entry->rcuname, __entry->gpnum, __entry->pid) +); + +/* + * Tracepoint for tasks that blocked within a given preemptible-RCU + * read-side critical section exiting that critical section. Track the + * type of RCU (which one day might include SRCU) and the task's PID. + */ +TRACE_EVENT(rcu_unlock_preempted_task, + + TP_PROTO(char *rcuname, unsigned long gpnum, int pid), + + TP_ARGS(rcuname, gpnum, pid), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(unsigned long, gpnum) + __field(int, pid) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpnum = gpnum; + __entry->pid = pid; + ), + + TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid) +); + +/* + * Tracepoint for quiescent-state-reporting events. These are + * distinguished by the type of RCU, the grace-period number, the + * mask of quiescent lower-level entities, the rcu_node structure level, + * the starting and ending CPU covered by the rcu_node structure, and + * whether there are any blocked tasks blocking the current grace period. + * All but the type of RCU are extracted from the rcu_node structure. + */ +TRACE_EVENT(rcu_quiescent_state_report, + + TP_PROTO(char *rcuname, unsigned long gpnum, + unsigned long mask, unsigned long qsmask, + u8 level, int grplo, int grphi, int gp_tasks), + + TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(unsigned long, gpnum) + __field(unsigned long, mask) + __field(unsigned long, qsmask) + __field(u8, level) + __field(int, grplo) + __field(int, grphi) + __field(u8, gp_tasks) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpnum = gpnum; + __entry->mask = mask; + __entry->qsmask = qsmask; + __entry->level = level; + __entry->grplo = grplo; + __entry->grphi = grphi; + __entry->gp_tasks = gp_tasks; + ), + + TP_printk("%s %lu %lx>%lx %u %d %d %u", + __entry->rcuname, __entry->gpnum, + __entry->mask, __entry->qsmask, __entry->level, + __entry->grplo, __entry->grphi, __entry->gp_tasks) +); + +/* + * Tracepoint for quiescent states detected by force_quiescent_state(). + * These trace events include the type of RCU, the grace-period number + * that was blocked by the CPU, the CPU itself, and the type of quiescent + * state, which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, + * or "kick" when kicking a CPU that has been in dyntick-idle mode for + * too long. + */ +TRACE_EVENT(rcu_fqs, + + TP_PROTO(char *rcuname, unsigned long gpnum, int cpu, char *qsevent), + + TP_ARGS(rcuname, gpnum, cpu, qsevent), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(unsigned long, gpnum) + __field(int, cpu) + __field(char *, qsevent) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->gpnum = gpnum; + __entry->cpu = cpu; + __entry->qsevent = qsevent; + ), + + TP_printk("%s %lu %d %s", + __entry->rcuname, __entry->gpnum, + __entry->cpu, __entry->qsevent) +); + +#endif /* #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) */ + +/* + * Tracepoint for dyntick-idle entry/exit events. These take a string + * as argument: "Start" for entering dyntick-idle mode and "End" for + * leaving it. + */ +TRACE_EVENT(rcu_dyntick, + + TP_PROTO(char *polarity), + + TP_ARGS(polarity), + + TP_STRUCT__entry( + __field(char *, polarity) + ), + + TP_fast_assign( + __entry->polarity = polarity; + ), + + TP_printk("%s", __entry->polarity) +); + +/* + * Tracepoint for the registration of a single RCU callback function. + * The first argument is the type of RCU, the second argument is + * a pointer to the RCU callback itself, and the third element is the + * new RCU callback queue length for the current CPU. + */ +TRACE_EVENT(rcu_callback, + + TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen), + + TP_ARGS(rcuname, rhp, qlen), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(void *, rhp) + __field(void *, func) + __field(long, qlen) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->rhp = rhp; + __entry->func = rhp->func; + __entry->qlen = qlen; + ), + + TP_printk("%s rhp=%p func=%pf %ld", + __entry->rcuname, __entry->rhp, __entry->func, __entry->qlen) +); + +/* + * Tracepoint for the registration of a single RCU callback of the special + * kfree() form. The first argument is the RCU type, the second argument + * is a pointer to the RCU callback, the third argument is the offset + * of the callback within the enclosing RCU-protected data structure, + * and the fourth argument is the new RCU callback queue length for the + * current CPU. + */ +TRACE_EVENT(rcu_kfree_callback, + + TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset, + long qlen), + + TP_ARGS(rcuname, rhp, offset, qlen), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(void *, rhp) + __field(unsigned long, offset) + __field(long, qlen) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->rhp = rhp; + __entry->offset = offset; + __entry->qlen = qlen; + ), + + TP_printk("%s rhp=%p func=%ld %ld", + __entry->rcuname, __entry->rhp, __entry->offset, + __entry->qlen) +); + +/* + * Tracepoint for marking the beginning rcu_do_batch, performed to start + * RCU callback invocation. The first argument is the RCU flavor, + * the second is the total number of callbacks (including those that + * are not yet ready to be invoked), and the third argument is the + * current RCU-callback batch limit. + */ +TRACE_EVENT(rcu_batch_start, + + TP_PROTO(char *rcuname, long qlen, int blimit), + + TP_ARGS(rcuname, qlen, blimit), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(long, qlen) + __field(int, blimit) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->qlen = qlen; + __entry->blimit = blimit; + ), + + TP_printk("%s CBs=%ld bl=%d", + __entry->rcuname, __entry->qlen, __entry->blimit) +); + +/* + * Tracepoint for the invocation of a single RCU callback function. + * The first argument is the type of RCU, and the second argument is + * a pointer to the RCU callback itself. + */ +TRACE_EVENT(rcu_invoke_callback, + + TP_PROTO(char *rcuname, struct rcu_head *rhp), + + TP_ARGS(rcuname, rhp), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(void *, rhp) + __field(void *, func) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->rhp = rhp; + __entry->func = rhp->func; + ), + + TP_printk("%s rhp=%p func=%pf", + __entry->rcuname, __entry->rhp, __entry->func) +); + +/* + * Tracepoint for the invocation of a single RCU callback of the special + * kfree() form. The first argument is the RCU flavor, the second + * argument is a pointer to the RCU callback, and the third argument + * is the offset of the callback within the enclosing RCU-protected + * data structure. + */ +TRACE_EVENT(rcu_invoke_kfree_callback, + + TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset), + + TP_ARGS(rcuname, rhp, offset), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(void *, rhp) + __field(unsigned long, offset) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->rhp = rhp; + __entry->offset = offset; + ), + + TP_printk("%s rhp=%p func=%ld", + __entry->rcuname, __entry->rhp, __entry->offset) +); + +/* + * Tracepoint for exiting rcu_do_batch after RCU callbacks have been + * invoked. The first argument is the name of the RCU flavor and + * the second argument is number of callbacks actually invoked. + */ +TRACE_EVENT(rcu_batch_end, + + TP_PROTO(char *rcuname, int callbacks_invoked), + + TP_ARGS(rcuname, callbacks_invoked), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(int, callbacks_invoked) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->callbacks_invoked = callbacks_invoked; + ), + + TP_printk("%s CBs-invoked=%d", + __entry->rcuname, __entry->callbacks_invoked) +); + +#else /* #ifdef CONFIG_RCU_TRACE */ + +#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) +#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, qsmask) do { } while (0) +#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) +#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) +#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0) +#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) +#define trace_rcu_dyntick(polarity) do { } while (0) +#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0) +#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0) +#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0) +#define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0) +#define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0) +#define trace_rcu_batch_end(rcuname, callbacks_invoked) do { } while (0) + +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +#endif /* _TRACE_RCU_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index f633478..959ff18 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p) * For all intents and purposes a preempted task is a running task. */ if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE) - state = TASK_RUNNING; + state = TASK_RUNNING | TASK_STATE_MAX; #endif return state; @@ -137,13 +137,14 @@ TRACE_EVENT(sched_switch, __entry->next_prio = next->prio; ), - TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s ==> next_comm=%s next_pid=%d next_prio=%d", + TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - __entry->prev_state ? - __print_flags(__entry->prev_state, "|", + __entry->prev_state & (TASK_STATE_MAX-1) ? + __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, { 16, "Z" }, { 32, "X" }, { 64, "x" }, { 128, "W" }) : "R", + __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 533c49f..7697249 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -711,6 +711,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call #undef __perf_count #define __perf_count(c) __count = (c) +#undef TP_perf_assign +#define TP_perf_assign(args...) args + #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ |