#include <linux/elevator.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
+#include <linux/blktrace_api.h>
/*
* tunables
*/
-static const int cfq_quantum = 4; /* max queue in one round of service */
+/* max queue in one round of service */
+static const int cfq_quantum = 4;
static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
-static const int cfq_back_max = 16 * 1024; /* maximum backwards seek, in KiB */
-static const int cfq_back_penalty = 2; /* penalty of a backwards seek */
-
+/* maximum backwards seek, in KiB */
+static const int cfq_back_max = 16 * 1024;
+/* penalty of a backwards seek */
+static const int cfq_back_penalty = 2;
static const int cfq_slice_sync = HZ / 10;
static int cfq_slice_async = HZ / 25;
static const int cfq_slice_async_rq = 2;
static int cfq_slice_idle = HZ / 125;
/*
- * grace period before allowing idle class to get disk access
+ * offset from end of service tree
*/
-#define CFQ_IDLE_GRACE (HZ / 10)
+#define CFQ_IDLE_DELAY (HZ / 5)
/*
* below this threshold, we consider thinktime immediate
#define CFQ_SLICE_SCALE (5)
-#define RQ_CIC(rq) ((struct cfq_io_context*)(rq)->elevator_private)
-#define RQ_CFQQ(rq) ((rq)->elevator_private2)
+#define RQ_CIC(rq) \
+ ((struct cfq_io_context *) (rq)->elevator_private)
+#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2)
static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;
static DEFINE_PER_CPU(unsigned long, ioc_count);
static struct completion *ioc_gone;
+static DEFINE_SPINLOCK(ioc_gone_lock);
#define CFQ_PRIO_LISTS IOPRIO_BE_NR
#define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
struct cfq_queue *async_idle_cfqq;
- struct timer_list idle_class_timer;
-
sector_t last_position;
unsigned long last_end_request;
struct cfq_queue {
/* reference count */
atomic_t ref;
+ /* various state flags, see below */
+ unsigned int flags;
/* parent cfq_data */
struct cfq_data *cfqd;
/* service_tree member */
int queued[2];
/* currently allocated requests */
int allocated[2];
- /* pending metadata requests */
- int meta_pending;
/* fifo list of requests in sort_list */
struct list_head fifo;
unsigned long slice_end;
long slice_resid;
+ /* pending metadata requests */
+ int meta_pending;
/* number of requests that are on the dispatch list or inside driver */
int dispatched;
unsigned short ioprio, org_ioprio;
unsigned short ioprio_class, org_ioprio_class;
- /* various state flags, see below */
- unsigned int flags;
+ pid_t pid;
};
enum cfqq_state_flags {
#define CFQ_CFQQ_FNS(name) \
static inline void cfq_mark_cfqq_##name(struct cfq_queue *cfqq) \
{ \
- cfqq->flags |= (1 << CFQ_CFQQ_FLAG_##name); \
+ (cfqq)->flags |= (1 << CFQ_CFQQ_FLAG_##name); \
} \
static inline void cfq_clear_cfqq_##name(struct cfq_queue *cfqq) \
{ \
- cfqq->flags &= ~(1 << CFQ_CFQQ_FLAG_##name); \
+ (cfqq)->flags &= ~(1 << CFQ_CFQQ_FLAG_##name); \
} \
static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq) \
{ \
- return (cfqq->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0; \
+ return ((cfqq)->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0; \
}
CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(sync);
#undef CFQ_CFQQ_FNS
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log(cfqd, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
+
static void cfq_dispatch_insert(struct request_queue *, struct request *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
struct io_context *, gfp_t);
*/
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
- if (cfqd->busy_queues)
+ if (cfqd->busy_queues) {
+ cfq_log(cfqd, "schedule dispatch");
kblockd_schedule_work(&cfqd->unplug_work);
+ }
}
static int cfq_queue_empty(struct request_queue *q)
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
+ cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}
/*
/*
* The below is leftmost cache rbtree addon
*/
-static struct rb_node *cfq_rb_first(struct cfq_rb_root *root)
+static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
{
if (!root->left)
root->left = rb_first(&root->rb);
- return root->left;
+ if (root->left)
+ return rb_entry(root->left, struct cfq_queue, rb_node);
+
+ return NULL;
}
static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
static void cfq_service_tree_add(struct cfq_data *cfqd,
struct cfq_queue *cfqq, int add_front)
{
- struct rb_node **p = &cfqd->service_tree.rb.rb_node;
- struct rb_node *parent = NULL;
+ struct rb_node **p, *parent;
+ struct cfq_queue *__cfqq;
unsigned long rb_key;
int left;
- if (!add_front) {
+ if (cfq_class_idle(cfqq)) {
+ rb_key = CFQ_IDLE_DELAY;
+ parent = rb_last(&cfqd->service_tree.rb);
+ if (parent && parent != &cfqq->rb_node) {
+ __cfqq = rb_entry(parent, struct cfq_queue, rb_node);
+ rb_key += __cfqq->rb_key;
+ } else
+ rb_key += jiffies;
+ } else if (!add_front) {
rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
rb_key += cfqq->slice_resid;
cfqq->slice_resid = 0;
}
left = 1;
+ parent = NULL;
+ p = &cfqd->service_tree.rb.rb_node;
while (*p) {
- struct cfq_queue *__cfqq;
struct rb_node **n;
parent = *p;
* add to busy list of queues for service, trying to be fair in ordering
* the pending list according to last request service
*/
-static inline void
-cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
BUG_ON(cfq_cfqq_on_rr(cfqq));
cfq_mark_cfqq_on_rr(cfqq);
cfqd->busy_queues++;
* Called when the cfqq no longer has requests pending, remove it from
* the service tree.
*/
-static inline void
-cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
BUG_ON(!cfq_cfqq_on_rr(cfqq));
cfq_clear_cfqq_on_rr(cfqq);
/*
* rb tree support functions
*/
-static inline void cfq_del_rq_rb(struct request *rq)
+static void cfq_del_rq_rb(struct request *rq)
{
struct cfq_queue *cfqq = RQ_CFQQ(rq);
struct cfq_data *cfqd = cfqq->cfqd;
BUG_ON(!cfqq->next_rq);
}
-static inline void
-cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
+static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
{
elv_rb_del(&cfqq->sort_list, rq);
cfqq->queued[rq_is_sync(rq)]--;
struct cfq_data *cfqd = q->elevator->elevator_data;
cfqd->rq_in_driver++;
+ cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
+ cfqd->rq_in_driver);
/*
* If the depth is larger 1, it really could be queueing. But lets
WARN_ON(!cfqd->rq_in_driver);
cfqd->rq_in_driver--;
+ cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
+ cfqd->rq_in_driver);
}
static void cfq_remove_request(struct request *rq)
return 0;
}
-static inline void
-__cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+static void __cfq_set_active_queue(struct cfq_data *cfqd,
+ struct cfq_queue *cfqq)
{
if (cfqq) {
- /*
- * stop potential idle class queues waiting service
- */
- del_timer(&cfqd->idle_class_timer);
-
+ cfq_log_cfqq(cfqd, cfqq, "set_active");
cfqq->slice_end = 0;
cfq_clear_cfqq_must_alloc_slice(cfqq);
cfq_clear_cfqq_fifo_expire(cfqq);
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
int timed_out)
{
+ cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);
+
if (cfq_cfqq_wait_request(cfqq))
del_timer(&cfqd->idle_slice_timer);
/*
* store what was left of this slice, if the queue idled/timed out
*/
- if (timed_out && !cfq_cfqq_slice_new(cfqq))
+ if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
cfqq->slice_resid = cfqq->slice_end - jiffies;
+ cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+ }
cfq_resort_rr_list(cfqd, cfqq);
__cfq_slice_expired(cfqd, cfqq, timed_out);
}
-static int start_idle_class_timer(struct cfq_data *cfqd)
-{
- unsigned long end = cfqd->last_end_request + CFQ_IDLE_GRACE;
- unsigned long now = jiffies;
-
- if (time_before(now, end) &&
- time_after_eq(now, cfqd->last_end_request)) {
- mod_timer(&cfqd->idle_class_timer, end);
- return 1;
- }
-
- return 0;
-}
-
/*
* Get next queue for service. Unless we have a queue preemption,
* we'll simply select the first cfqq in the service tree.
*/
static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
{
- struct cfq_queue *cfqq;
- struct rb_node *n;
-
if (RB_EMPTY_ROOT(&cfqd->service_tree.rb))
return NULL;
- n = cfq_rb_first(&cfqd->service_tree);
- cfqq = rb_entry(n, struct cfq_queue, rb_node);
-
- if (cfq_class_idle(cfqq)) {
- /*
- * if we have idle queues and no rt or be queues had
- * pending requests, either allow immediate service if
- * the grace period has passed or arm the idle grace
- * timer
- */
- if (start_idle_class_timer(cfqd))
- cfqq = NULL;
- }
-
- return cfqq;
+ return cfq_rb_first(&cfqd->service_tree);
}
/*
return;
/*
+ * still requests with the driver, don't idle
+ */
+ if (cfqd->rq_in_driver)
+ return;
+
+ /*
* task has exited, don't wait
*/
cic = cfqd->active_cic;
sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+ cfq_log(cfqd, "arm_idle: %lu", sl);
}
/*
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = RQ_CFQQ(rq);
+ cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");
+
cfq_remove_request(rq);
cfqq->dispatched++;
elv_dispatch_sort(q, rq);
/*
* return expired entry, or NULL to just start from scratch in rbtree
*/
-static inline struct request *cfq_check_fifo(struct cfq_queue *cfqq)
+static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
{
struct cfq_data *cfqd = cfqq->cfqd;
struct request *rq;
rq = rq_entry_fifo(cfqq->fifo.next);
if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
- return NULL;
+ rq = NULL;
+ cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq);
return rq;
}
/*
* follow expired path, else get first next available
*/
- if ((rq = cfq_check_fifo(cfqq)) == NULL)
+ rq = cfq_check_fifo(cfqq);
+ if (rq == NULL)
rq = cfqq->next_rq;
/*
return dispatched;
}
-static inline int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
+static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
{
int dispatched = 0;
*/
static int cfq_forced_dispatch(struct cfq_data *cfqd)
{
+ struct cfq_queue *cfqq;
int dispatched = 0;
- struct rb_node *n;
-
- while ((n = cfq_rb_first(&cfqd->service_tree)) != NULL) {
- struct cfq_queue *cfqq = rb_entry(n, struct cfq_queue, rb_node);
+ while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL)
dispatched += __cfq_forced_dispatch_cfqq(cfqq);
- }
cfq_slice_expired(cfqd, 0);
BUG_ON(cfqd->busy_queues);
+ cfq_log(cfqd, "forced_dispatch=%d\n", dispatched);
return dispatched;
}
dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
}
+ cfq_log(cfqd, "dispatched=%d", dispatched);
return dispatched;
}
if (!atomic_dec_and_test(&cfqq->ref))
return;
+ cfq_log_cfqq(cfqd, cfqq, "put_queue");
BUG_ON(rb_first(&cfqq->sort_list));
BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
BUG_ON(cfq_cfqq_on_rr(cfqq));
}
/*
- * Call func for each cic attached to this ioc. Returns number of cic's seen.
+ * Must always be called with the rcu_read_lock() held
*/
-#define CIC_GANG_NR 16
-static unsigned int
+static void
+__call_for_each_cic(struct io_context *ioc,
+ void (*func)(struct io_context *, struct cfq_io_context *))
+{
+ struct cfq_io_context *cic;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list)
+ func(ioc, cic);
+}
+
+/*
+ * Call func for each cic attached to this ioc.
+ */
+static void
call_for_each_cic(struct io_context *ioc,
void (*func)(struct io_context *, struct cfq_io_context *))
{
- struct cfq_io_context *cics[CIC_GANG_NR];
- unsigned long index = 0;
- unsigned int called = 0;
- int nr;
-
rcu_read_lock();
+ __call_for_each_cic(ioc, func);
+ rcu_read_unlock();
+}
- do {
- int i;
-
- /*
- * Perhaps there's a better way - this just gang lookups from
- * 0 to the end, restarting after each CIC_GANG_NR from the
- * last key + 1.
- */
- nr = radix_tree_gang_lookup(&ioc->radix_root, (void **) cics,
- index, CIC_GANG_NR);
- if (!nr)
- break;
+static void cfq_cic_free_rcu(struct rcu_head *head)
+{
+ struct cfq_io_context *cic;
- called += nr;
- index = 1 + (unsigned long) cics[nr - 1]->key;
+ cic = container_of(head, struct cfq_io_context, rcu_head);
- for (i = 0; i < nr; i++)
- func(ioc, cics[i]);
- } while (nr == CIC_GANG_NR);
+ kmem_cache_free(cfq_ioc_pool, cic);
+ elv_ioc_count_dec(ioc_count);
- rcu_read_unlock();
+ if (ioc_gone) {
+ /*
+ * CFQ scheduler is exiting, grab exit lock and check
+ * the pending io context count. If it hits zero,
+ * complete ioc_gone and set it back to NULL
+ */
+ spin_lock(&ioc_gone_lock);
+ if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+ complete(ioc_gone);
+ ioc_gone = NULL;
+ }
+ spin_unlock(&ioc_gone_lock);
+ }
+}
- return called;
+static void cfq_cic_free(struct cfq_io_context *cic)
+{
+ call_rcu(&cic->rcu_head, cfq_cic_free_rcu);
}
static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
spin_lock_irqsave(&ioc->lock, flags);
radix_tree_delete(&ioc->radix_root, cic->dead_key);
+ hlist_del_rcu(&cic->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
- kmem_cache_free(cfq_ioc_pool, cic);
+ cfq_cic_free(cic);
}
+/*
+ * Must be called with rcu_read_lock() held or preemption otherwise disabled.
+ * Only two callers of this - ->dtor() which is called with the rcu_read_lock(),
+ * and ->trim() which is called with the task lock held
+ */
static void cfq_free_io_context(struct io_context *ioc)
{
- int freed;
-
/*
- * ioc->refcount is zero here, so no more cic's are allowed to be
- * linked into this ioc. So it should be ok to iterate over the known
- * list, we will see all cic's since no new ones are added.
+ * ioc->refcount is zero here, or we are called from elv_unregister(),
+ * so no more cic's are allowed to be linked into this ioc. So it
+ * should be ok to iterate over the known list, we will see all cic's
+ * since no new ones are added.
*/
- freed = call_for_each_cic(ioc, cic_free_func);
-
- elv_ioc_count_mod(ioc_count, -freed);
-
- if (ioc_gone && !elv_ioc_count_read(ioc_count))
- complete(ioc_gone);
+ __call_for_each_cic(ioc, cic_free_func);
}
static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
struct cfq_io_context *cic)
{
+ struct io_context *ioc = cic->ioc;
+
list_del_init(&cic->queue_list);
/*
cic->dead_key = (unsigned long) cic->key;
cic->key = NULL;
+ if (ioc->ioc_data == cic)
+ rcu_assign_pointer(ioc->ioc_data, NULL);
+
if (cic->cfqq[ASYNC]) {
cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
cic->cfqq[ASYNC] = NULL;
*/
static void cfq_exit_io_context(struct io_context *ioc)
{
- rcu_assign_pointer(ioc->ioc_data, NULL);
call_for_each_cic(ioc, cfq_exit_single_io_context);
}
if (cic) {
cic->last_end_request = jiffies;
INIT_LIST_HEAD(&cic->queue_list);
+ INIT_HLIST_NODE(&cic->cic_list);
cic->dtor = cfq_free_io_context;
cic->exit = cfq_exit_io_context;
elv_ioc_count_inc(ioc_count);
ioprio_class = IOPRIO_PRIO_CLASS(ioc->ioprio);
switch (ioprio_class) {
- default:
- printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
- case IOPRIO_CLASS_NONE:
- /*
- * no prio set, place us in the middle of the BE classes
- */
- cfqq->ioprio = task_nice_ioprio(tsk);
- cfqq->ioprio_class = IOPRIO_CLASS_BE;
- break;
- case IOPRIO_CLASS_RT:
- cfqq->ioprio = task_ioprio(ioc);
- cfqq->ioprio_class = IOPRIO_CLASS_RT;
- break;
- case IOPRIO_CLASS_BE:
- cfqq->ioprio = task_ioprio(ioc);
- cfqq->ioprio_class = IOPRIO_CLASS_BE;
- break;
- case IOPRIO_CLASS_IDLE:
- cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
- cfqq->ioprio = 7;
- cfq_clear_cfqq_idle_window(cfqq);
- break;
+ default:
+ printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
+ case IOPRIO_CLASS_NONE:
+ /*
+ * no prio set, inherit CPU scheduling settings
+ */
+ cfqq->ioprio = task_nice_ioprio(tsk);
+ cfqq->ioprio_class = task_nice_ioclass(tsk);
+ break;
+ case IOPRIO_CLASS_RT:
+ cfqq->ioprio = task_ioprio(ioc);
+ cfqq->ioprio_class = IOPRIO_CLASS_RT;
+ break;
+ case IOPRIO_CLASS_BE:
+ cfqq->ioprio = task_ioprio(ioc);
+ cfqq->ioprio_class = IOPRIO_CLASS_BE;
+ break;
+ case IOPRIO_CLASS_IDLE:
+ cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
+ cfqq->ioprio = 7;
+ cfq_clear_cfqq_idle_window(cfqq);
+ break;
}
/*
cfq_clear_cfqq_prio_changed(cfqq);
}
-static inline void changed_ioprio(struct io_context *ioc,
- struct cfq_io_context *cic)
+static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
{
struct cfq_data *cfqd = cic->key;
struct cfq_queue *cfqq;
atomic_set(&cfqq->ref, 0);
cfqq->cfqd = cfqd;
- if (is_sync) {
- cfq_mark_cfqq_idle_window(cfqq);
- cfq_mark_cfqq_sync(cfqq);
- }
-
cfq_mark_cfqq_prio_changed(cfqq);
cfq_mark_cfqq_queue_new(cfqq);
cfq_init_prio_data(cfqq, ioc);
+
+ if (is_sync) {
+ if (!cfq_class_idle(cfqq))
+ cfq_mark_cfqq_idle_window(cfqq);
+ cfq_mark_cfqq_sync(cfqq);
+ }
+ cfqq->pid = current->pid;
+ cfq_log_cfqq(cfqd, cfqq, "alloced");
}
if (new_cfqq)
static struct cfq_queue **
cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
{
- switch(ioprio_class) {
+ switch (ioprio_class) {
case IOPRIO_CLASS_RT:
return &cfqd->async_cfqq[0][ioprio];
case IOPRIO_CLASS_BE:
return cfqq;
}
-static void cfq_cic_free(struct cfq_io_context *cic)
-{
- kmem_cache_free(cfq_ioc_pool, cic);
- elv_ioc_count_dec(ioc_count);
-
- if (ioc_gone && !elv_ioc_count_read(ioc_count))
- complete(ioc_gone);
-}
-
/*
* We drop cfq io contexts lazily, so we may find a dead one.
*/
spin_lock_irqsave(&ioc->lock, flags);
- if (ioc->ioc_data == cic)
- rcu_assign_pointer(ioc->ioc_data, NULL);
+ BUG_ON(ioc->ioc_data == cic);
radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
+ hlist_del_rcu(&cic->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
cfq_cic_free(cic);
cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
{
struct cfq_io_context *cic;
+ unsigned long flags;
void *k;
if (unlikely(!ioc))
return NULL;
+ rcu_read_lock();
+
/*
* we maintain a last-hit cache, to avoid browsing over the tree
*/
cic = rcu_dereference(ioc->ioc_data);
- if (cic && cic->key == cfqd)
+ if (cic && cic->key == cfqd) {
+ rcu_read_unlock();
return cic;
+ }
do {
- rcu_read_lock();
cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
rcu_read_unlock();
if (!cic)
k = cic->key;
if (unlikely(!k)) {
cfq_drop_dead_cic(cfqd, ioc, cic);
+ rcu_read_lock();
continue;
}
+ spin_lock_irqsave(&ioc->lock, flags);
rcu_assign_pointer(ioc->ioc_data, cic);
+ spin_unlock_irqrestore(&ioc->lock, flags);
break;
} while (1);
* the process specific cfq io context when entered from the block layer.
* Also adds the cic to a per-cfqd list, used when this queue is removed.
*/
-static inline int
-cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
- struct cfq_io_context *cic, gfp_t gfp_mask)
+static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
+ struct cfq_io_context *cic, gfp_t gfp_mask)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&ioc->lock, flags);
ret = radix_tree_insert(&ioc->radix_root,
(unsigned long) cfqd, cic);
+ if (!ret)
+ hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
radix_tree_preload_end();
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct cfq_io_context *cic)
{
- int enable_idle;
+ int old_idle, enable_idle;
- if (!cfq_cfqq_sync(cfqq))
+ /*
+ * Don't idle for async or idle io prio class
+ */
+ if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
return;
- enable_idle = cfq_cfqq_idle_window(cfqq);
+ enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
(cfqd->hw_tag && CIC_SEEKY(cic)))
enable_idle = 1;
}
- if (enable_idle)
- cfq_mark_cfqq_idle_window(cfqq);
- else
- cfq_clear_cfqq_idle_window(cfqq);
+ if (old_idle != enable_idle) {
+ cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
+ if (enable_idle)
+ cfq_mark_cfqq_idle_window(cfqq);
+ else
+ cfq_clear_cfqq_idle_window(cfqq);
+ }
}
/*
*/
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ cfq_log_cfqq(cfqd, cfqq, "preempt");
cfq_slice_expired(cfqd, 1);
/*
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = RQ_CFQQ(rq);
+ cfq_log_cfqq(cfqd, cfqq, "insert_request");
cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);
cfq_add_rq_rb(rq);
unsigned long now;
now = jiffies;
+ cfq_log_cfqq(cfqd, cfqq, "complete");
WARN_ON(!cfqd->rq_in_driver);
WARN_ON(!cfqq->dispatched);
cfq_set_prio_slice(cfqd, cfqq);
cfq_clear_cfqq_slice_new(cfqq);
}
- if (cfq_slice_used(cfqq))
+ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
cfq_slice_expired(cfqd, 1);
else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
cfq_arm_slice_timer(cfqd);
cfq_schedule_dispatch(cfqd);
spin_unlock_irqrestore(q->queue_lock, flags);
+ cfq_log(cfqd, "set_request fail");
return 1;
}
unsigned long flags;
int timed_out = 1;
+ cfq_log(cfqd, "idle timer fired");
+
spin_lock_irqsave(cfqd->queue->queue_lock, flags);
- if ((cfqq = cfqd->active_queue) != NULL) {
+ cfqq = cfqd->active_queue;
+ if (cfqq) {
timed_out = 0;
/*
spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}
-/*
- * Timer running if an idle class queue is waiting for service
- */
-static void cfq_idle_class_timer(unsigned long data)
-{
- struct cfq_data *cfqd = (struct cfq_data *) data;
- unsigned long flags;
-
- spin_lock_irqsave(cfqd->queue->queue_lock, flags);
-
- /*
- * race with a non-idle queue, reset timer
- */
- if (!start_idle_class_timer(cfqd))
- cfq_schedule_dispatch(cfqd);
-
- spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
-}
-
static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
del_timer_sync(&cfqd->idle_slice_timer);
- del_timer_sync(&cfqd->idle_class_timer);
kblockd_flush_work(&cfqd->unplug_work);
}
cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
cfqd->idle_slice_timer.data = (unsigned long) cfqd;
- init_timer(&cfqd->idle_class_timer);
- cfqd->idle_class_timer.function = cfq_idle_class_timer;
- cfqd->idle_class_timer.data = (unsigned long) cfqd;
-
INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
cfqd->last_end_request = jiffies;
static void cfq_slab_kill(void)
{
+ /*
+ * Caller already ensured that pending RCU callbacks are completed,
+ * so we should have no busy allocations at this point.
+ */
if (cfq_pool)
kmem_cache_destroy(cfq_pool);
if (cfq_ioc_pool)
if (!cfq_pool)
goto fail;
- cfq_ioc_pool = KMEM_CACHE(cfq_io_context, SLAB_DESTROY_BY_RCU);
+ cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0);
if (!cfq_ioc_pool)
goto fail;
return ret; \
}
STORE_FUNCTION(cfq_quantum_store, &cfqd->cfq_quantum, 1, UINT_MAX, 0);
-STORE_FUNCTION(cfq_fifo_expire_sync_store, &cfqd->cfq_fifo_expire[1], 1, UINT_MAX, 1);
-STORE_FUNCTION(cfq_fifo_expire_async_store, &cfqd->cfq_fifo_expire[0], 1, UINT_MAX, 1);
+STORE_FUNCTION(cfq_fifo_expire_sync_store, &cfqd->cfq_fifo_expire[1], 1,
+ UINT_MAX, 1);
+STORE_FUNCTION(cfq_fifo_expire_async_store, &cfqd->cfq_fifo_expire[0], 1,
+ UINT_MAX, 1);
STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
-STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0);
+STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
+ UINT_MAX, 0);
STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
-STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0);
+STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
+ UINT_MAX, 0);
#undef STORE_FUNCTION
#define CFQ_ATTR(name) \
ioc_gone = &all_gone;
/* ioc_gone's update must be visible before reading ioc_count */
smp_wmb();
+
+ /*
+ * this also protects us from entering cfq_slab_kill() with
+ * pending RCU callbacks
+ */
if (elv_ioc_count_read(ioc_count))
- wait_for_completion(ioc_gone);
- synchronize_rcu();
+ wait_for_completion(&all_gone);
cfq_slab_kill();
}