core: add io controller support on the unified hierarchy

On the unified hierarchy, blkio controller is renamed to io and the interface
is changed significantly.

* blkio.weight and blkio.weight_device are consolidated into io.weight which
  uses the standardized weight range [1, 10000] with 100 as the default value.

* blkio.throttle.{read|write}_{bps|iops}_device are consolidated into io.max.
  Expansion of throttling features is being worked on to support
  work-conserving absolute limits (io.low and io.high).

* All stats are consolidated into io.stats.

This patchset adds support for the new interface.  As the interface has been
revamped and new features are expected to be added, it seems best to treat it
as a separate controller rather than trying to expand the blkio settings
although we might add automatic translation if only blkio settings are
specified.

* io.weight handling is mostly identical to blkio.weight[_device] handling
  except that the weight range is different.

* Both read and write bandwidth settings are consolidated into
  CGroupIODeviceLimit which describes all limits applicable to the device.
  This makes it less painful to add new limits.

* "max" can be used to specify the maximum limit which is equivalent to no
  config for max limits and treated as such.  If a given CGroupIODeviceLimit
  doesn't contain any non-default configs, the config struct is discarded once
  the no limit config is applied to cgroup.

* lookup_blkio_device() is renamed to lookup_block_device().

Signed-off-by: Tejun Heo <htejun@fb.com>

2 files changed, 41 insertions, 2 deletions

diff --git a/src/basic/cgroup-util.c b/src/basic/cgroup-util.c
index 5043180747..ff57cf30b7 100644
--- a/src/basic/cgroup-util.c
+++ b/src/basic/cgroup-util.c
@@ -2060,10 +2060,10 @@ int cg_mask_supported(CGroupMask *ret) {
                         mask |= CGROUP_CONTROLLER_TO_MASK(v);
                 }
 
-                /* Currently, we only support the memory and pids
+                /* Currently, we only support the memory, io and pids
                  * controller in the unified hierarchy, mask
                  * everything else off. */
-                mask &= CGROUP_MASK_MEMORY | CGROUP_MASK_PIDS;
+                mask &= CGROUP_MASK_MEMORY | CGROUP_MASK_IO | CGROUP_MASK_PIDS;
 
         } else {
                 CGroupController c;
@@ -2249,6 +2249,26 @@ bool cg_is_legacy_wanted(void) {
         return !cg_is_unified_wanted();
 }
 
+int cg_weight_parse(const char *s, uint64_t *ret) {
+        uint64_t u;
+        int r;
+
+        if (isempty(s)) {
+                *ret = CGROUP_WEIGHT_INVALID;
+                return 0;
+        }
+
+        r = safe_atou64(s, &u);
+        if (r < 0)
+                return r;
+
+        if (u < CGROUP_WEIGHT_MIN || u > CGROUP_WEIGHT_MAX)
+                return -ERANGE;
+
+        *ret = u;
+        return 0;
+}
+
 int cg_cpu_shares_parse(const char *s, uint64_t *ret) {
         uint64_t u;
         int r;
@@ -2292,6 +2312,7 @@ int cg_blkio_weight_parse(const char *s, uint64_t *ret) {
 static const char *cgroup_controller_table[_CGROUP_CONTROLLER_MAX] = {
         [CGROUP_CONTROLLER_CPU] = "cpu",
         [CGROUP_CONTROLLER_CPUACCT] = "cpuacct",
+        [CGROUP_CONTROLLER_IO] = "io",
         [CGROUP_CONTROLLER_BLKIO] = "blkio",
         [CGROUP_CONTROLLER_MEMORY] = "memory",
         [CGROUP_CONTROLLER_DEVICES] = "devices",
diff --git a/src/basic/cgroup-util.h b/src/basic/cgroup-util.h
index 4254e51e5d..a696c1fa60 100644
--- a/src/basic/cgroup-util.h
+++ b/src/basic/cgroup-util.h
@@ -34,6 +34,7 @@
 typedef enum CGroupController {
         CGROUP_CONTROLLER_CPU,
         CGROUP_CONTROLLER_CPUACCT,
+        CGROUP_CONTROLLER_IO,
         CGROUP_CONTROLLER_BLKIO,
         CGROUP_CONTROLLER_MEMORY,
         CGROUP_CONTROLLER_DEVICES,
@@ -48,6 +49,7 @@ typedef enum CGroupController {
 typedef enum CGroupMask {
         CGROUP_MASK_CPU = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_CPU),
         CGROUP_MASK_CPUACCT = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_CPUACCT),
+        CGROUP_MASK_IO = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_IO),
         CGROUP_MASK_BLKIO = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_BLKIO),
         CGROUP_MASK_MEMORY = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_MEMORY),
         CGROUP_MASK_DEVICES = CGROUP_CONTROLLER_TO_MASK(CGROUP_CONTROLLER_DEVICES),
@@ -55,6 +57,21 @@ typedef enum CGroupMask {
         _CGROUP_MASK_ALL = CGROUP_CONTROLLER_TO_MASK(_CGROUP_CONTROLLER_MAX) - 1
 } CGroupMask;
 
+/* Special values for all weight knobs on unified hierarchy */
+#define CGROUP_WEIGHT_INVALID ((uint64_t) -1)
+#define CGROUP_WEIGHT_MIN UINT64_C(1)
+#define CGROUP_WEIGHT_MAX UINT64_C(10000)
+#define CGROUP_WEIGHT_DEFAULT UINT64_C(100)
+
+#define CGROUP_LIMIT_MIN UINT64_C(0)
+#define CGROUP_LIMIT_MAX ((uint64_t) -1)
+
+static inline bool CGROUP_WEIGHT_IS_OK(uint64_t x) {
+        return
+            x == CGROUP_WEIGHT_INVALID ||
+            (x >= CGROUP_WEIGHT_MIN && x <= CGROUP_WEIGHT_MAX);
+}
+
 /* Special values for the cpu.shares attribute */
 #define CGROUP_CPU_SHARES_INVALID ((uint64_t) -1)
 #define CGROUP_CPU_SHARES_MIN UINT64_C(2)
@@ -190,5 +207,6 @@ bool cg_is_legacy_wanted(void);
 const char* cgroup_controller_to_string(CGroupController c) _const_;
 CGroupController cgroup_controller_from_string(const char *s) _pure_;
 
+int cg_weight_parse(const char *s, uint64_t *ret);
 int cg_cpu_shares_parse(const char *s, uint64_t *ret);
 int cg_blkio_weight_parse(const char *s, uint64_t *ret);