Memory controller: resource counters

With fixes from David Rientjes <rientjes@google.com>

Introduce generic structures and routines for resource accounting.

Each resource accounting cgroup is supposed to aggregate it,
cgroup_subsystem_state and its resource-specific members within.

Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 230 insertions, 0 deletions

diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
new file mode 100644
index 0000000..eeb3f77
--- /dev/null
+++ b/include/linux/res_counter.h
@@ -0,0 +1,102 @@
+#ifndef __RES_COUNTER_H__
+#define __RES_COUNTER_H__
+
+/*
+ * Resource Counters
+ * Contain common data types and routines for resource accounting
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+#include <linux/cgroup.h>
+
+/*
+ * The core object. the cgroup that wishes to account for some
+ * resource may include this counter into its structures and use
+ * the helpers described beyond
+ */
+
+struct res_counter {
+	/*
+	 * the current resource consumption level
+	 */
+	unsigned long usage;
+	/*
+	 * the limit that usage cannot exceed
+	 */
+	unsigned long limit;
+	/*
+	 * the number of unsuccessful attempts to consume the resource
+	 */
+	unsigned long failcnt;
+	/*
+	 * the lock to protect all of the above.
+	 * the routines below consider this to be IRQ-safe
+	 */
+	spinlock_t lock;
+};
+
+/*
+ * Helpers to interact with userspace
+ * res_counter_read/_write - put/get the specified fields from the
+ * res_counter struct to/from the user
+ *
+ * @counter:     the counter in question
+ * @member:  the field to work with (see RES_xxx below)
+ * @buf:     the buffer to opeate on,...
+ * @nbytes:  its size...
+ * @pos:     and the offset.
+ */
+
+ssize_t res_counter_read(struct res_counter *counter, int member,
+		const char __user *buf, size_t nbytes, loff_t *pos);
+ssize_t res_counter_write(struct res_counter *counter, int member,
+		const char __user *buf, size_t nbytes, loff_t *pos);
+
+/*
+ * the field descriptors. one for each member of res_counter
+ */
+
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_FAILCNT,
+};
+
+/*
+ * helpers for accounting
+ */
+
+void res_counter_init(struct res_counter *counter);
+
+/*
+ * charge - try to consume more resource.
+ *
+ * @counter: the counter
+ * @val: the amount of the resource. each controller defines its own
+ *       units, e.g. numbers, bytes, Kbytes, etc
+ *
+ * returns 0 on success and <0 if the counter->usage will exceed the
+ * counter->limit _locked call expects the counter->lock to be taken
+ */
+
+int res_counter_charge_locked(struct res_counter *counter, unsigned long val);
+int res_counter_charge(struct res_counter *counter, unsigned long val);
+
+/*
+ * uncharge - tell that some portion of the resource is released
+ *
+ * @counter: the counter
+ * @val: the amount of the resource
+ *
+ * these calls check for usage underflow and show a warning on the console
+ * _locked call expects the counter->lock to be taken
+ */
+
+void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
+void res_counter_uncharge(struct res_counter *counter, unsigned long val);
+
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index 92b23e2..d372bd6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -369,6 +369,13 @@ config CGROUP_CPUACCT
 	  Provides a simple Resource Controller for monitoring the
 	  total CPU consumed by the tasks in a cgroup
 
+config RESOURCE_COUNTERS
+	bool "Resource counters"
+	help
+	  This option enables controller independent resource accounting
+          infrastructure that works with cgroups
+	depends on CGROUPS
+
 config SYSFS_DEPRECATED
 	bool "Create deprecated sysfs files"
 	depends on SYSFS
diff --git a/kernel/Makefile b/kernel/Makefile
index 135a1b9..685697c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_IKCONFIG) += configs.o
+obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
new file mode 100644
index 0000000..722c484
--- /dev/null
+++ b/kernel/res_counter.c
@@ -0,0 +1,120 @@
+/*
+ * resource cgroups
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/parser.h>
+#include <linux/fs.h>
+#include <linux/res_counter.h>
+#include <linux/uaccess.h>
+
+void res_counter_init(struct res_counter *counter)
+{
+	spin_lock_init(&counter->lock);
+	counter->limit = (unsigned long)LONG_MAX;
+}
+
+int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
+{
+	if (counter->usage + val > counter->limit) {
+		counter->failcnt++;
+		return -ENOMEM;
+	}
+
+	counter->usage += val;
+	return 0;
+}
+
+int res_counter_charge(struct res_counter *counter, unsigned long val)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&counter->lock, flags);
+	ret = res_counter_charge_locked(counter, val);
+	spin_unlock_irqrestore(&counter->lock, flags);
+	return ret;
+}
+
+void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
+{
+	if (WARN_ON(counter->usage < val))
+		val = counter->usage;
+
+	counter->usage -= val;
+}
+
+void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&counter->lock, flags);
+	res_counter_uncharge_locked(counter, val);
+	spin_unlock_irqrestore(&counter->lock, flags);
+}
+
+
+static inline unsigned long *res_counter_member(struct res_counter *counter,
+						int member)
+{
+	switch (member) {
+	case RES_USAGE:
+		return &counter->usage;
+	case RES_LIMIT:
+		return &counter->limit;
+	case RES_FAILCNT:
+		return &counter->failcnt;
+	};
+
+	BUG();
+	return NULL;
+}
+
+ssize_t res_counter_read(struct res_counter *counter, int member,
+		const char __user *userbuf, size_t nbytes, loff_t *pos)
+{
+	unsigned long *val;
+	char buf[64], *s;
+
+	s = buf;
+	val = res_counter_member(counter, member);
+	s += sprintf(s, "%lu\n", *val);
+	return simple_read_from_buffer((void __user *)userbuf, nbytes,
+			pos, buf, s - buf);
+}
+
+ssize_t res_counter_write(struct res_counter *counter, int member,
+		const char __user *userbuf, size_t nbytes, loff_t *pos)
+{
+	int ret;
+	char *buf, *end;
+	unsigned long tmp, *val;
+
+	buf = kmalloc(nbytes + 1, GFP_KERNEL);
+	ret = -ENOMEM;
+	if (buf == NULL)
+		goto out;
+
+	buf[nbytes] = '\0';
+	ret = -EFAULT;
+	if (copy_from_user(buf, userbuf, nbytes))
+		goto out_free;
+
+	ret = -EINVAL;
+	tmp = simple_strtoul(buf, &end, 10);
+	if (*end != '\0')
+		goto out_free;
+
+	val = res_counter_member(counter, member);
+	*val = tmp;
+	ret = nbytes;
+out_free:
+	kfree(buf);
+out:
+	return ret;
+}