Revision 2548d546d40c0014efdde88a53bf7896e917dcce authored by Peter Zijlstra on 21 April 2016, 16:03:15 UTC, committed by Ingo Molnar on 28 April 2016, 08:28:55 UTC
Chris Metcalf reported a that sched_can_stop_tick() sometimes fails to
re-enable the tick.
His observed problem is that rq->cfs.nr_running can be 1 even though
there are multiple runnable CFS tasks. This happens in the cgroup
case, in which case cfs.nr_running is the number of runnable entities
for that level.
If there is a single runnable cgroup (which can have an arbitrary
number of runnable child entries itself) rq->cfs.nr_running will be 1.
However, looking at that function I think there's more problems with it.
It seems to assume that if there's FIFO tasks, those will run. This is
incorrect. The FIFO task can have a lower prio than an RR task, in which
case the RR task will run.
So the whole fifo_nr_running test seems misplaced, it should go after
the rr_nr_running tests. That is, only if !rr_nr_running, can we use
fifo_nr_running like this.
Reported-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Chris Metcalf <cmetcalf@mellanox.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Wanpeng Li <kernellwp@gmail.com>
Fixes: 76d92ac305f2 ("sched: Migrate sched to use new tick dependency mask model")
Link: http://lkml.kernel.org/r/20160421160315.GK24771@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
1 parent 02da2d7
blk-mq.h
#ifndef INT_BLK_MQ_H
#define INT_BLK_MQ_H
struct blk_mq_tag_set;
struct blk_mq_ctx {
struct {
spinlock_t lock;
struct list_head rq_list;
} ____cacheline_aligned_in_smp;
unsigned int cpu;
unsigned int index_hw;
unsigned int last_tag ____cacheline_aligned_in_smp;
/* incremented at dispatch time */
unsigned long rq_dispatched[2];
unsigned long rq_merged;
/* incremented at completion time */
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
struct request_queue *queue;
struct kobject kobj;
} ____cacheline_aligned_in_smp;
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
/*
* CPU hotplug helpers
*/
struct blk_mq_cpu_notifier;
void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
int (*fn)(void *, unsigned long, unsigned int),
void *data);
void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
void blk_mq_cpu_init(void);
void blk_mq_enable_hotplug(void);
void blk_mq_disable_hotplug(void);
/*
* CPU -> queue mappings
*/
extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
const struct cpumask *online_mask);
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
/*
* sysfs helpers
*/
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
void blk_mq_release(struct request_queue *q);
/*
* Basic implementation of sparser bitmap, allowing the user to spread
* the bits over more cachelines.
*/
struct blk_align_bitmap {
unsigned long word;
unsigned long depth;
} ____cacheline_aligned_in_smp;
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
unsigned int cpu)
{
return per_cpu_ptr(q->queue_ctx, cpu);
}
/*
* This assumes per-cpu software queueing queues. They could be per-node
* as well, for instance. For now this is hardcoded as-is. Note that we don't
* care about preemption, since we know the ctx's are persistent. This does
* mean that we can't rely on ctx always matching the currently running CPU.
*/
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
return __blk_mq_get_ctx(q, get_cpu());
}
static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
{
put_cpu();
}
struct blk_mq_alloc_data {
/* input parameter */
struct request_queue *q;
unsigned int flags;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
struct request_queue *q, unsigned int flags,
struct blk_mq_ctx *ctx, struct blk_mq_hw_ctx *hctx)
{
data->q = q;
data->flags = flags;
data->ctx = ctx;
data->hctx = hctx;
}
static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
{
return hctx->nr_ctx && hctx->tags;
}
#endif
Computing file changes ...
