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>

2 files changed, 121 insertions, 0 deletions

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;
+}