AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-12 08:56:47 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
b3a084b9b6
linux_dsm_epyc7002/include/linux/workqueue.h
Tejun Heo 8a2e8e5dec workqueue: fix cwq->nr_active underflow 
cwq->nr_active is used to keep track of how many work items are active
for the cpu workqueue, where 'active' is defined as either pending on
global worklist or executing.  This is used to implement the
max_active limit and workqueue freezing.  If a work item is queued
after nr_active has already reached max_active, the work item doesn't
increment nr_active and is put on the delayed queue and gets activated
later as previous active work items retire.

try_to_grab_pending() which is used in the cancellation path
unconditionally decremented nr_active whether the work item being
cancelled is currently active or delayed, so cancelling a delayed work
item makes nr_active underflow.  This breaks max_active enforcement
and triggers BUG_ON() in destroy_workqueue() later on.

This patch fixes this bug by adding a flag WORK_STRUCT_DELAYED, which
is set while a work item in on the delayed list and making
try_to_grab_pending() decrement nr_active iff the work item is
currently active.

The addition of the flag enlarges cwq alignment to 256 bytes which is
getting a bit too large.  It's scheduled to be reduced back to 128
bytes by merging WORK_STRUCT_PENDING and WORK_STRUCT_CWQ in the next
devel cycle.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Johannes Berg <johannes@sipsolutions.net>
2010-08-25 10:33:56 +02:00

413 lines
12 KiB
C
Raw Blame History

/*
* workqueue.h --- work queue handling for Linux.
*/
#ifndef _LINUX_WORKQUEUE_H
#define _LINUX_WORKQUEUE_H
#include <linux/timer.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/lockdep.h>
#include <linux/threads.h>
#include <asm/atomic.h>
struct workqueue_struct;
struct work_struct;
typedef void (*work_func_t)(struct work_struct *work);
/*
* The first word is the work queue pointer and the flags rolled into
* one
*/
#define work_data_bits(work) ((unsigned long *)(&(work)->data))
enum {
WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */
WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */
WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */
WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */
#ifdef CONFIG_DEBUG_OBJECTS_WORK
WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */
WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */
#else
WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */
#endif
WORK_STRUCT_COLOR_BITS = 4,
WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT,
WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT,
WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT,
WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT,
#ifdef CONFIG_DEBUG_OBJECTS_WORK
WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT,
#else
WORK_STRUCT_STATIC = 0,
#endif
/*
* The last color is no color used for works which don't
* participate in workqueue flushing.
*/
WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1,
WORK_NO_COLOR = WORK_NR_COLORS,
/* special cpu IDs */
WORK_CPU_UNBOUND = NR_CPUS,
WORK_CPU_NONE = NR_CPUS + 1,
WORK_CPU_LAST = WORK_CPU_NONE,
/*
* Reserve 7 bits off of cwq pointer w/ debugobjects turned
* off. This makes cwqs aligned to 256 bytes and allows 15
* workqueue flush colors.
*/
WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT +
WORK_STRUCT_COLOR_BITS,
WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1,
WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
WORK_STRUCT_NO_CPU = WORK_CPU_NONE << WORK_STRUCT_FLAG_BITS,
/* bit mask for work_busy() return values */
WORK_BUSY_PENDING = 1 << 0,
WORK_BUSY_RUNNING = 1 << 1,
};
struct work_struct {
atomic_long_t data;
struct list_head entry;
work_func_t func;
#ifdef CONFIG_LOCKDEP
struct lockdep_map lockdep_map;
#endif
};
#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU)
#define WORK_DATA_STATIC_INIT() \
ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC)
struct delayed_work {
struct work_struct work;
struct timer_list timer;
};
static inline struct delayed_work *to_delayed_work(struct work_struct *work)
{
return container_of(work, struct delayed_work, work);
}
struct execute_work {
struct work_struct work;
};
#ifdef CONFIG_LOCKDEP
/*
* NB: because we have to copy the lockdep_map, setting _key
* here is required, otherwise it could get initialised to the
* copy of the lockdep_map!
*/
#define __WORK_INIT_LOCKDEP_MAP(n, k) \
.lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k),
#else
#define __WORK_INIT_LOCKDEP_MAP(n, k)
#endif
#define __WORK_INITIALIZER(n, f) { \
.data = WORK_DATA_STATIC_INIT(), \
.entry = { &(n).entry, &(n).entry }, \
.func = (f), \
__WORK_INIT_LOCKDEP_MAP(#n, &(n)) \
}
#define __DELAYED_WORK_INITIALIZER(n, f) { \
.work = __WORK_INITIALIZER((n).work, (f)), \
.timer = TIMER_INITIALIZER(NULL, 0, 0), \
}
#define DECLARE_WORK(n, f) \
struct work_struct n = __WORK_INITIALIZER(n, f)
#define DECLARE_DELAYED_WORK(n, f) \
struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f)
/*
* initialize a work item's function pointer
*/
#define PREPARE_WORK(_work, _func) \
do { \
(_work)->func = (_func); \
} while (0)
#define PREPARE_DELAYED_WORK(_work, _func) \
PREPARE_WORK(&(_work)->work, (_func))
#ifdef CONFIG_DEBUG_OBJECTS_WORK
extern void __init_work(struct work_struct *work, int onstack);
extern void destroy_work_on_stack(struct work_struct *work);
static inline unsigned int work_static(struct work_struct *work)
{
return *work_data_bits(work) & WORK_STRUCT_STATIC;
}
#else
static inline void __init_work(struct work_struct *work, int onstack) { }
static inline void destroy_work_on_stack(struct work_struct *work) { }
static inline unsigned int work_static(struct work_struct *work) { return 0; }
#endif
/*
* initialize all of a work item in one go
*
* NOTE! No point in using "atomic_long_set()": using a direct
* assignment of the work data initializer allows the compiler
* to generate better code.
*/
#ifdef CONFIG_LOCKDEP
#define __INIT_WORK(_work, _func, _onstack) \
do { \
static struct lock_class_key __key; \
\
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0);\
INIT_LIST_HEAD(&(_work)->entry); \
PREPARE_WORK((_work), (_func)); \
} while (0)
#else
#define __INIT_WORK(_work, _func, _onstack) \
do { \
__init_work((_work), _onstack); \
(_work)->data = (atomic_long_t) WORK_DATA_INIT(); \
INIT_LIST_HEAD(&(_work)->entry); \
PREPARE_WORK((_work), (_func)); \
} while (0)
#endif
#define INIT_WORK(_work, _func) \
do { \
__INIT_WORK((_work), (_func), 0); \
} while (0)
#define INIT_WORK_ON_STACK(_work, _func) \
do { \
__INIT_WORK((_work), (_func), 1); \
} while (0)
#define INIT_DELAYED_WORK(_work, _func) \
do { \
INIT_WORK(&(_work)->work, (_func)); \
init_timer(&(_work)->timer); \
} while (0)
#define INIT_DELAYED_WORK_ON_STACK(_work, _func) \
do { \
INIT_WORK_ON_STACK(&(_work)->work, (_func)); \
init_timer_on_stack(&(_work)->timer); \
} while (0)
#define INIT_DELAYED_WORK_DEFERRABLE(_work, _func) \
do { \
INIT_WORK(&(_work)->work, (_func)); \
init_timer_deferrable(&(_work)->timer); \
} while (0)
/**
* work_pending - Find out whether a work item is currently pending
* @work: The work item in question
*/
#define work_pending(work) \
test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
/**
* delayed_work_pending - Find out whether a delayable work item is currently
* pending
* @work: The work item in question
*/
#define delayed_work_pending(w) \
work_pending(&(w)->work)
/**
* work_clear_pending - for internal use only, mark a work item as not pending
* @work: The work item in question
*/
#define work_clear_pending(work) \
clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
enum {
WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */
WQ_UNBOUND = 1 << 1, /* not bound to any cpu */
WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */
WQ_RESCUER = 1 << 3, /* has an rescue worker */
WQ_HIGHPRI = 1 << 4, /* high priority */
WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */
WQ_DYING = 1 << 6, /* internal: workqueue is dying */
WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2,
};
/* unbound wq's aren't per-cpu, scale max_active according to #cpus */
#define WQ_UNBOUND_MAX_ACTIVE \
max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU)
/*
* System-wide workqueues which are always present.
*
* system_wq is the one used by schedule[_delayed]_work[_on]().
* Multi-CPU multi-threaded. There are users which expect relatively
* short queue flush time. Don't queue works which can run for too
* long.
*
* system_long_wq is similar to system_wq but may host long running
* works. Queue flushing might take relatively long.
*
* system_nrt_wq is non-reentrant and guarantees that any given work
* item is never executed in parallel by multiple CPUs. Queue
* flushing might take relatively long.
*
* system_unbound_wq is unbound workqueue. Workers are not bound to
* any specific CPU, not concurrency managed, and all queued works are
* executed immediately as long as max_active limit is not reached and
* resources are available.
*/
extern struct workqueue_struct *system_wq;
extern struct workqueue_struct *system_long_wq;
extern struct workqueue_struct *system_nrt_wq;
extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *
__alloc_workqueue_key(const char *name, unsigned int flags, int max_active,
struct lock_class_key *key, const char *lock_name);
#ifdef CONFIG_LOCKDEP
#define alloc_workqueue(name, flags, max_active) \
({ \
static struct lock_class_key __key; \
const char *__lock_name; \
\
if (__builtin_constant_p(name)) \
__lock_name = (name); \
else \
__lock_name = #name; \
\
__alloc_workqueue_key((name), (flags), (max_active), \
&__key, __lock_name); \
})
#else
#define alloc_workqueue(name, flags, max_active) \
__alloc_workqueue_key((name), (flags), (max_active), NULL, NULL)
#endif
#define create_workqueue(name) \
alloc_workqueue((name), WQ_RESCUER, 1)
#define create_freezeable_workqueue(name) \
alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1)
#define create_singlethread_workqueue(name) \
alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1)
extern void destroy_workqueue(struct workqueue_struct *wq);
extern int queue_work(struct workqueue_struct *wq, struct work_struct *work);
extern int queue_work_on(int cpu, struct workqueue_struct *wq,
struct work_struct *work);
extern int queue_delayed_work(struct workqueue_struct *wq,
struct delayed_work *work, unsigned long delay);
extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *work, unsigned long delay);
extern void flush_workqueue(struct workqueue_struct *wq);
extern void flush_scheduled_work(void);
extern void flush_delayed_work(struct delayed_work *work);
extern int schedule_work(struct work_struct *work);
extern int schedule_work_on(int cpu, struct work_struct *work);
extern int schedule_delayed_work(struct delayed_work *work, unsigned long delay);
extern int schedule_delayed_work_on(int cpu, struct delayed_work *work,
unsigned long delay);
extern int schedule_on_each_cpu(work_func_t func);
extern int keventd_up(void);
int execute_in_process_context(work_func_t fn, struct execute_work *);
extern int flush_work(struct work_struct *work);
extern int cancel_work_sync(struct work_struct *work);
extern void workqueue_set_max_active(struct workqueue_struct *wq,
int max_active);
extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq);
extern unsigned int work_cpu(struct work_struct *work);
extern unsigned int work_busy(struct work_struct *work);
/*
* Kill off a pending schedule_delayed_work(). Note that the work callback
* function may still be running on return from cancel_delayed_work(), unless
* it returns 1 and the work doesn't re-arm itself. Run flush_workqueue() or
* cancel_work_sync() to wait on it.
*/
static inline int cancel_delayed_work(struct delayed_work *work)
{
int ret;
ret = del_timer_sync(&work->timer);
if (ret)
work_clear_pending(&work->work);
return ret;
}
/*
* Like above, but uses del_timer() instead of del_timer_sync(). This means,
* if it returns 0 the timer function may be running and the queueing is in
* progress.
*/
static inline int __cancel_delayed_work(struct delayed_work *work)
{
int ret;
ret = del_timer(&work->timer);
if (ret)
work_clear_pending(&work->work);
return ret;
}
extern int cancel_delayed_work_sync(struct delayed_work *work);
/* Obsolete. use cancel_delayed_work_sync() */
static inline
void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq,
struct delayed_work *work)
{
cancel_delayed_work_sync(work);
}
/* Obsolete. use cancel_delayed_work_sync() */
static inline
void cancel_rearming_delayed_work(struct delayed_work *work)
{
cancel_delayed_work_sync(work);
}
#ifndef CONFIG_SMP
static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
return fn(arg);
}
#else
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
extern void freeze_workqueues_begin(void);
extern bool freeze_workqueues_busy(void);
extern void thaw_workqueues(void);
#endif /* CONFIG_FREEZER */
#ifdef CONFIG_LOCKDEP
int in_workqueue_context(struct workqueue_struct *wq);
#endif
#endif
Reference in New Issue View Git Blame Copy Permalink