3 files changed, 88 insertions, 26 deletions

diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
index d89b4fe724d7..a5eb7d19a65d 100644
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@@ -102,6 +102,64 @@ processing of request. Therefore, increasing the value can imporve the
 performace although this can cause the latency of some I/O to increase due
 to more number of requests.
 
+CFQ Group scheduling
+====================
+
+CFQ supports blkio cgroup and has "blkio." prefixed files in each
+blkio cgroup directory. It is weight-based and there are four knobs
+for configuration - weight[_device] and leaf_weight[_device].
+Internal cgroup nodes (the ones with children) can also have tasks in
+them, so the former two configure how much proportion the cgroup as a
+whole is entitled to at its parent's level while the latter two
+configure how much proportion the tasks in the cgroup have compared to
+its direct children.
+
+Another way to think about it is assuming that each internal node has
+an implicit leaf child node which hosts all the tasks whose weight is
+configured by leaf_weight[_device]. Let's assume a blkio hierarchy
+composed of five cgroups - root, A, B, AA and AB - with the following
+weights where the names represent the hierarchy.
+
+        weight leaf_weight
+ root :  125    125
+ A    :  500    750
+ B    :  250    500
+ AA   :  500    500
+ AB   : 1000    500
+
+root never has a parent making its weight is meaningless. For backward
+compatibility, weight is always kept in sync with leaf_weight. B, AA
+and AB have no child and thus its tasks have no children cgroup to
+compete with. They always get 100% of what the cgroup won at the
+parent level. Considering only the weights which matter, the hierarchy
+looks like the following.
+
+          root
+       /    |   \
+      A     B    leaf
+     500   250   125
+   /  |  \
+  AA  AB  leaf
+ 500 1000 750
+
+If all cgroups have active IOs and competing with each other, disk
+time will be distributed like the following.
+
+Distribution below root. The total active weight at this level is
+A:500 + B:250 + C:125 = 875.
+
+ root-leaf :   125 /  875      =~ 14%
+ A         :   500 /  875      =~ 57%
+ B(-leaf)  :   250 /  875      =~ 28%
+
+A has children and further distributes its 57% among the children and
+the implicit leaf node. The total active weight at this level is
+AA:500 + AB:1000 + A-leaf:750 = 2250.
+
+ A-leaf    : ( 750 / 2250) * A =~ 19%
+ AA(-leaf) : ( 500 / 2250) * A =~ 12%
+ AB(-leaf) : (1000 / 2250) * A =~ 25%
+
 CFQ IOPS Mode for group scheduling
 ===================================
 Basic CFQ design is to provide priority based time slices. Higher priority
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index b4b1fb3a83f0..1b70843c574e 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -94,13 +94,11 @@ Throttling/Upper Limit policy
 
 Hierarchical Cgroups
 ====================
-- Currently none of the IO control policy supports hierarchical groups. But
-  cgroup interface does allow creation of hierarchical cgroups and internally
-  IO policies treat them as flat hierarchy.
+- Currently only CFQ supports hierarchical groups. For throttling,
+  cgroup interface does allow creation of hierarchical cgroups and
+  internally it treats them as flat hierarchy.
 
-  So this patch will allow creation of cgroup hierarchcy but at the backend
-  everything will be treated as flat. So if somebody created a hierarchy like
-  as follows.
+  If somebody created a hierarchy like as follows.
 
                         root
                         /  \
@@ -108,16 +106,20 @@ Hierarchical Cgroups
                         |
                      test3
 
-  CFQ and throttling will practically treat all groups at same level.
+  CFQ will handle the hierarchy correctly but and throttling will
+  practically treat all groups at same level. For details on CFQ
+  hierarchy support, refer to Documentation/block/cfq-iosched.txt.
+  Throttling will treat the hierarchy as if it looks like the
+  following.
 
                                 pivot
                              /  /   \  \
                         root  test1 test2  test3
 
-  Down the line we can implement hierarchical accounting/control support
-  and also introduce a new cgroup file "use_hierarchy" which will control
-  whether cgroup hierarchy is viewed as flat or hierarchical by the policy..
-  This is how memory controller also has implemented the things.
+  Nesting cgroups, while allowed, isn't officially supported and blkio
+  genereates warning when cgroups nest. Once throttling implements
+  hierarchy support, hierarchy will be supported and the warning will
+  be removed.
 
 Various user visible config options
 ===================================
@@ -172,6 +174,12 @@ Proportional weight policy files
           dev     weight
           8:16    300
 
+- blkio.leaf_weight[_device]
+        - Equivalents of blkio.weight[_device] for the purpose of
+          deciding how much weight tasks in the given cgroup has while
+          competing with the cgroup's child cgroups. For details,
+          please refer to Documentation/block/cfq-iosched.txt.
+
 - blkio.time
         - disk time allocated to cgroup per device in milliseconds. First
           two fields specify the major and minor number of the device and
@@ -279,6 +287,11 @@ Proportional weight policy files
           and minor number of the device and third field specifies the number
           of times a group was dequeued from a particular device.
 
+- blkio.*_recursive
+        - Recursive version of various stats. These files show the
+          same information as their non-recursive counterparts but
+          include stats from all the descendant cgroups.
+
 Throttling/Upper limit policy files
 -----------------------------------
 - blkio.throttle.read_bps_device
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ee342826fd98..e8f31069b379 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -606,20 +606,11 @@ static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
         return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
 }
 
-/*
- * Determine the parent cfqg for weight calculation.  Currently, cfqg
- * scheduling is flat and the root is the parent of everyone else.
- */
-static inline struct cfq_group *cfqg_flat_parent(struct cfq_group *cfqg)
+static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg)
 {
-        struct blkcg_gq *blkg = cfqg_to_blkg(cfqg);
-        struct cfq_group *root;
-
-        while (blkg->parent)
-                blkg = blkg->parent;
-        root = blkg_to_cfqg(blkg);
+        struct blkcg_gq *pblkg = cfqg_to_blkg(cfqg)->parent;
 
-        return root != cfqg ? root : NULL;
+        return pblkg ? blkg_to_cfqg(pblkg) : NULL;
 }
 
 static inline void cfqg_get(struct cfq_group *cfqg)
@@ -722,7 +713,7 @@ static void cfq_pd_reset_stats(struct blkcg_gq *blkg)
 
 #else   /* CONFIG_CFQ_GROUP_IOSCHED */
 
-static inline struct cfq_group *cfqg_flat_parent(struct cfq_group *cfqg) { return NULL; }
+static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg) { return NULL; }
 static inline void cfqg_get(struct cfq_group *cfqg) { }
 static inline void cfqg_put(struct cfq_group *cfqg) { }
 
@@ -1290,7 +1281,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
          * stops once an already activated node is met.  vfraction
          * calculation should always continue to the root.
          */
-        while ((parent = cfqg_flat_parent(pos))) {
+        while ((parent = cfqg_parent(pos))) {
                 if (propagate) {
                         propagate = !parent->nr_active++;
                         parent->children_weight += pos->weight;
@@ -1341,7 +1332,7 @@ cfq_group_service_tree_del(struct cfq_rb_root *st, struct cfq_group *cfqg)
         pos->children_weight -= pos->leaf_weight;
 
         while (propagate) {
-                struct cfq_group *parent = cfqg_flat_parent(pos);
+                struct cfq_group *parent = cfqg_parent(pos);
 
                 /* @pos has 0 nr_active at this point */
                 WARN_ON_ONCE(pos->children_weight);