}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
+struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
+{
+ return container_of(task_subsys_state(tsk, blkio_subsys_id),
+ struct blkio_cgroup, css);
+}
+EXPORT_SYMBOL_GPL(task_blkio_cgroup);
+
static inline void
blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
{
if (blkiop->plid != blkg->plid)
continue;
if (blkiop->ops.blkio_update_group_weight_fn)
- blkiop->ops.blkio_update_group_weight_fn(blkg, weight);
+ blkiop->ops.blkio_update_group_weight_fn(blkg->key,
+ blkg, weight);
}
}
if (fileid == BLKIO_THROTL_read_bps_device
&& blkiop->ops.blkio_update_group_read_bps_fn)
- blkiop->ops.blkio_update_group_read_bps_fn(blkg, bps);
+ blkiop->ops.blkio_update_group_read_bps_fn(blkg->key,
+ blkg, bps);
if (fileid == BLKIO_THROTL_write_bps_device
&& blkiop->ops.blkio_update_group_write_bps_fn)
- blkiop->ops.blkio_update_group_write_bps_fn(blkg, bps);
+ blkiop->ops.blkio_update_group_write_bps_fn(blkg->key,
+ blkg, bps);
}
}
if (fileid == BLKIO_THROTL_read_iops_device
&& blkiop->ops.blkio_update_group_read_iops_fn)
- blkiop->ops.blkio_update_group_read_iops_fn(blkg, iops);
+ blkiop->ops.blkio_update_group_read_iops_fn(blkg->key,
+ blkg, iops);
if (fileid == BLKIO_THROTL_write_iops_device
&& blkiop->ops.blkio_update_group_write_iops_fn)
- blkiop->ops.blkio_update_group_write_iops_fn(blkg,iops);
+ blkiop->ops.blkio_update_group_write_iops_fn(blkg->key,
+ blkg,iops);
}
}
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
-void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
+void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time,
+ unsigned long unaccounted_time)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkg->stats.time += time;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+ blkg->stats.unaccounted_time += unaccounted_time;
+#endif
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
+/*
+ * should be called under rcu read lock or queue lock to make sure blkg pointer
+ * is valid.
+ */
void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
uint64_t bytes, bool direction, bool sync)
{
- struct blkio_group_stats *stats;
+ struct blkio_group_stats_cpu *stats_cpu;
unsigned long flags;
- spin_lock_irqsave(&blkg->stats_lock, flags);
- stats = &blkg->stats;
- stats->sectors += bytes >> 9;
- blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction,
- sync);
- blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes,
- direction, sync);
- spin_unlock_irqrestore(&blkg->stats_lock, flags);
+ /*
+ * Disabling interrupts to provide mutual exclusion between two
+ * writes on same cpu. It probably is not needed for 64bit. Not
+ * optimizing that case yet.
+ */
+ local_irq_save(flags);
+
+ stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+ u64_stats_update_begin(&stats_cpu->syncp);
+ stats_cpu->sectors += bytes >> 9;
+ blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICED],
+ 1, direction, sync);
+ blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICE_BYTES],
+ bytes, direction, sync);
+ u64_stats_update_end(&stats_cpu->syncp);
+ local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
}
EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
+/* Merged stats are per cpu. */
void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
bool sync)
{
+ struct blkio_group_stats_cpu *stats_cpu;
unsigned long flags;
- spin_lock_irqsave(&blkg->stats_lock, flags);
- blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction,
- sync);
- spin_unlock_irqrestore(&blkg->stats_lock, flags);
+ /*
+ * Disabling interrupts to provide mutual exclusion between two
+ * writes on same cpu. It probably is not needed for 64bit. Not
+ * optimizing that case yet.
+ */
+ local_irq_save(flags);
+
+ stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+ u64_stats_update_begin(&stats_cpu->syncp);
+ blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
+ direction, sync);
+ u64_stats_update_end(&stats_cpu->syncp);
+ local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
+/*
+ * This function allocates the per cpu stats for blkio_group. Should be called
+ * from sleepable context as alloc_per_cpu() requires that.
+ */
+int blkio_alloc_blkg_stats(struct blkio_group *blkg)
+{
+ /* Allocate memory for per cpu stats */
+ blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
+ if (!blkg->stats_cpu)
+ return -ENOMEM;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
+
void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev,
enum blkio_policy_id plid)
}
EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
+static void blkio_reset_stats_cpu(struct blkio_group *blkg)
+{
+ struct blkio_group_stats_cpu *stats_cpu;
+ int i, j, k;
+ /*
+ * Note: On 64 bit arch this should not be an issue. This has the
+ * possibility of returning some inconsistent value on 32bit arch
+ * as 64bit update on 32bit is non atomic. Taking care of this
+ * corner case makes code very complicated, like sending IPIs to
+ * cpus, taking care of stats of offline cpus etc.
+ *
+ * reset stats is anyway more of a debug feature and this sounds a
+ * corner case. So I am not complicating the code yet until and
+ * unless this becomes a real issue.
+ */
+ for_each_possible_cpu(i) {
+ stats_cpu = per_cpu_ptr(blkg->stats_cpu, i);
+ stats_cpu->sectors = 0;
+ for(j = 0; j < BLKIO_STAT_CPU_NR; j++)
+ for (k = 0; k < BLKIO_STAT_TOTAL; k++)
+ stats_cpu->stat_arr_cpu[j][k] = 0;
+ }
+}
+
static int
blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
}
#endif
spin_unlock(&blkg->stats_lock);
+
+ /* Reset Per cpu stats which don't take blkg->stats_lock */
+ blkio_reset_stats_cpu(blkg);
}
+
spin_unlock_irq(&blkcg->lock);
return 0;
}
return val;
}
+
+static uint64_t blkio_read_stat_cpu(struct blkio_group *blkg,
+ enum stat_type_cpu type, enum stat_sub_type sub_type)
+{
+ int cpu;
+ struct blkio_group_stats_cpu *stats_cpu;
+ u64 val = 0, tval;
+
+ for_each_possible_cpu(cpu) {
+ unsigned int start;
+ stats_cpu = per_cpu_ptr(blkg->stats_cpu, cpu);
+
+ do {
+ start = u64_stats_fetch_begin(&stats_cpu->syncp);
+ if (type == BLKIO_STAT_CPU_SECTORS)
+ tval = stats_cpu->sectors;
+ else
+ tval = stats_cpu->stat_arr_cpu[type][sub_type];
+ } while(u64_stats_fetch_retry(&stats_cpu->syncp, start));
+
+ val += tval;
+ }
+
+ return val;
+}
+
+static uint64_t blkio_get_stat_cpu(struct blkio_group *blkg,
+ struct cgroup_map_cb *cb, dev_t dev, enum stat_type_cpu type)
+{
+ uint64_t disk_total, val;
+ char key_str[MAX_KEY_LEN];
+ enum stat_sub_type sub_type;
+
+ if (type == BLKIO_STAT_CPU_SECTORS) {
+ val = blkio_read_stat_cpu(blkg, type, 0);
+ return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, val, cb, dev);
+ }
+
+ for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
+ sub_type++) {
+ blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
+ val = blkio_read_stat_cpu(blkg, type, sub_type);
+ cb->fill(cb, key_str, val);
+ }
+
+ disk_total = blkio_read_stat_cpu(blkg, type, BLKIO_STAT_READ) +
+ blkio_read_stat_cpu(blkg, type, BLKIO_STAT_WRITE);
+
+ blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
+ cb->fill(cb, key_str, disk_total);
+ return disk_total;
+}
+
/* This should be called with blkg->stats_lock held */
static uint64_t blkio_get_stat(struct blkio_group *blkg,
struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
if (type == BLKIO_STAT_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.time, cb, dev);
- if (type == BLKIO_STAT_SECTORS)
- return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
- blkg->stats.sectors, cb, dev);
#ifdef CONFIG_DEBUG_BLK_CGROUP
+ if (type == BLKIO_STAT_UNACCOUNTED_TIME)
+ return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+ blkg->stats.unaccounted_time, cb, dev);
if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {
uint64_t sum = blkg->stats.avg_queue_size_sum;
uint64_t samples = blkg->stats.avg_queue_size_samples;
{
char *s[4], *p, *major_s = NULL, *minor_s = NULL;
int ret;
- unsigned long major, minor, temp, iops;
+ unsigned long major, minor, temp;
int i = 0;
dev_t dev;
- u64 bps;
+ u64 bps, iops;
memset(s, 0, sizeof(s));
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
- ret = strict_strtoul(s[1], 10, &iops);
+ ret = strict_strtoull(s[1], 10, &iops);
if (ret)
return -EINVAL;
+ if (iops > THROTL_IOPS_MAX)
+ return -EINVAL;
+
newpn->plid = plid;
newpn->fileid = fileid;
- newpn->val.iops = iops;
+ newpn->val.iops = (unsigned int)iops;
break;
}
break;
}
/*
- * Some rules/values in blkg have changed. Propogate those to respective
+ * Some rules/values in blkg have changed. Propagate those to respective
* policies.
*/
static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
}
/*
- * A policy node rule has been updated. Propogate this update to all the
+ * A policy node rule has been updated. Propagate this update to all the
* block groups which might be affected by this update.
*/
static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
}
static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
- struct cftype *cft, struct cgroup_map_cb *cb, enum stat_type type,
- bool show_total)
+ struct cftype *cft, struct cgroup_map_cb *cb,
+ enum stat_type type, bool show_total, bool pcpu)
{
struct blkio_group *blkg;
struct hlist_node *n;
if (blkg->dev) {
if (!cftype_blkg_same_policy(cft, blkg))
continue;
- spin_lock_irq(&blkg->stats_lock);
- cgroup_total += blkio_get_stat(blkg, cb, blkg->dev,
- type);
- spin_unlock_irq(&blkg->stats_lock);
+ if (pcpu)
+ cgroup_total += blkio_get_stat_cpu(blkg, cb,
+ blkg->dev, type);
+ else {
+ spin_lock_irq(&blkg->stats_lock);
+ cgroup_total += blkio_get_stat(blkg, cb,
+ blkg->dev, type);
+ spin_unlock_irq(&blkg->stats_lock);
+ }
}
}
if (show_total)
switch(name) {
case BLKIO_PROP_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_TIME, 0);
+ BLKIO_STAT_TIME, 0, 0);
case BLKIO_PROP_sectors:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_SECTORS, 0);
+ BLKIO_STAT_CPU_SECTORS, 0, 1);
case BLKIO_PROP_io_service_bytes:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_SERVICE_BYTES, 1);
+ BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
case BLKIO_PROP_io_serviced:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_SERVICED, 1);
+ BLKIO_STAT_CPU_SERVICED, 1, 1);
case BLKIO_PROP_io_service_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_SERVICE_TIME, 1);
+ BLKIO_STAT_SERVICE_TIME, 1, 0);
case BLKIO_PROP_io_wait_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_WAIT_TIME, 1);
+ BLKIO_STAT_WAIT_TIME, 1, 0);
case BLKIO_PROP_io_merged:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_MERGED, 1);
+ BLKIO_STAT_CPU_MERGED, 1, 1);
case BLKIO_PROP_io_queued:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_QUEUED, 1);
+ BLKIO_STAT_QUEUED, 1, 0);
#ifdef CONFIG_DEBUG_BLK_CGROUP
+ case BLKIO_PROP_unaccounted_time:
+ return blkio_read_blkg_stats(blkcg, cft, cb,
+ BLKIO_STAT_UNACCOUNTED_TIME, 0, 0);
case BLKIO_PROP_dequeue:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_DEQUEUE, 0);
+ BLKIO_STAT_DEQUEUE, 0, 0);
case BLKIO_PROP_avg_queue_size:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+ BLKIO_STAT_AVG_QUEUE_SIZE, 0, 0);
case BLKIO_PROP_group_wait_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_GROUP_WAIT_TIME, 0);
+ BLKIO_STAT_GROUP_WAIT_TIME, 0, 0);
case BLKIO_PROP_idle_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_IDLE_TIME, 0);
+ BLKIO_STAT_IDLE_TIME, 0, 0);
case BLKIO_PROP_empty_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_EMPTY_TIME, 0);
+ BLKIO_STAT_EMPTY_TIME, 0, 0);
#endif
default:
BUG();
switch(name){
case BLKIO_THROTL_io_service_bytes:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_SERVICE_BYTES, 1);
+ BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
case BLKIO_THROTL_io_serviced:
return blkio_read_blkg_stats(blkcg, cft, cb,
- BLKIO_STAT_SERVICED, 1);
+ BLKIO_STAT_CPU_SERVICED, 1, 1);
default:
BUG();
}
BLKIO_PROP_dequeue),
.read_map = blkiocg_file_read_map,
},
+ {
+ .name = "unaccounted_time",
+ .private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+ BLKIO_PROP_unaccounted_time),
+ .read_map = blkiocg_file_read_map,
+ },
#endif
};
/*
* This blkio_group is being unlinked as associated cgroup is
* going away. Let all the IO controlling policies know about
- * this event. Currently this is static call to one io
- * controlling policy. Once we have more policies in place, we
- * need some dynamic registration of callback function.
+ * this event.
*/
spin_lock(&blkio_list_lock);
- list_for_each_entry(blkiop, &blkio_list, list)
+ list_for_each_entry(blkiop, &blkio_list, list) {
+ if (blkiop->plid != blkg->plid)
+ continue;
blkiop->ops.blkio_unlink_group_fn(key, blkg);
+ }
spin_unlock(&blkio_list_lock);
} while (1);
goto done;
}
- /* Currently we do not support hierarchy deeper than two level (0,1) */
- if (parent != cgroup->top_cgroup)
- return ERR_PTR(-EINVAL);
-
blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
if (!blkcg)
return ERR_PTR(-ENOMEM);