diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index ce3e05e41724..2d7c5907e0ce 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1483,8 +1483,7 @@ IO Interface Files ~~~~~~~~~~~~~~~~~~ io.stat - A read-only nested-keyed file which exists on non-root - cgroups. + A read-only nested-keyed file. Lines are keyed by $MAJ:$MIN device numbers and not ordered. The following nested keys are defined. diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 696d28151c9a..619a79b51068 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -782,12 +782,66 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) rcu_read_unlock(); } +/* + * The rstat algorithms intentionally don't handle the root cgroup to avoid + * incurring overhead when no cgroups are defined. For that reason, + * cgroup_rstat_flush in blkcg_print_stat does not actually fill out the + * iostat in the root cgroup's blkcg_gq. + * + * However, we would like to re-use the printing code between the root and + * non-root cgroups to the extent possible. For that reason, we simulate + * flushing the root cgroup's stats by explicitly filling in the iostat + * with disk level statistics. + */ +static void blkcg_fill_root_iostats(void) +{ + struct class_dev_iter iter; + struct device *dev; + + class_dev_iter_init(&iter, &block_class, NULL, &disk_type); + while ((dev = class_dev_iter_next(&iter))) { + struct gendisk *disk = dev_to_disk(dev); + struct hd_struct *part = disk_get_part(disk, 0); + struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue); + struct blkg_iostat tmp; + int cpu; + + memset(&tmp, 0, sizeof(tmp)); + for_each_possible_cpu(cpu) { + struct disk_stats *cpu_dkstats; + + cpu_dkstats = per_cpu_ptr(part->dkstats, cpu); + tmp.ios[BLKG_IOSTAT_READ] += + cpu_dkstats->ios[STAT_READ]; + tmp.ios[BLKG_IOSTAT_WRITE] += + cpu_dkstats->ios[STAT_WRITE]; + tmp.ios[BLKG_IOSTAT_DISCARD] += + cpu_dkstats->ios[STAT_DISCARD]; + // convert sectors to bytes + tmp.bytes[BLKG_IOSTAT_READ] += + cpu_dkstats->sectors[STAT_READ] << 9; + tmp.bytes[BLKG_IOSTAT_WRITE] += + cpu_dkstats->sectors[STAT_WRITE] << 9; + tmp.bytes[BLKG_IOSTAT_DISCARD] += + cpu_dkstats->sectors[STAT_DISCARD] << 9; + + u64_stats_update_begin(&blkg->iostat.sync); + blkg_iostat_set(&blkg->iostat.cur, &tmp); + u64_stats_update_end(&blkg->iostat.sync); + } + } +} + static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; - cgroup_rstat_flush(blkcg->css.cgroup); + if (!seq_css(sf)->parent) + blkcg_fill_root_iostats(); + else + cgroup_rstat_flush(blkcg->css.cgroup); + rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { @@ -876,7 +930,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) static struct cftype blkcg_files[] = { { .name = "stat", - .flags = CFTYPE_NOT_ON_ROOT, .seq_show = blkcg_print_stat, }, { } /* terminate */ diff --git a/block/genhd.c b/block/genhd.c index c42a49f2f537..8b1e9f48957c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -38,8 +38,6 @@ static struct kobject *block_depr; static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); -static const struct device_type disk_type; - static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr); static void disk_alloc_events(struct gendisk *disk); @@ -1587,7 +1585,7 @@ static char *block_devnode(struct device *dev, umode_t *mode, return NULL; } -static const struct device_type disk_type = { +const struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 31a54072ffd6..4ab853461dff 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -24,6 +24,7 @@ #define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) +extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class;