The patch titled
Memory controller: resource counters
has been removed from the -mm tree. Its filename was
memory-controller-resource-counters-v7.patch
This patch was dropped because it was merged into mainline or a subsystem tree
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: Memory controller: resource counters
From: Pavel Emelianov <xemul@xxxxxxxxxx>
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@xxxxxxxxxx>
Signed-off-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Kirill Korotaev <dev@xxxxx>
Cc: Herbert Poetzl <herbert@xxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vaidyanathan Srinivasan <svaidy@xxxxxxxxxxxxxxxxxx>
DESC
memory-controller-resource-counters-v7 fix
EDESC
There's a gotcha in res_counter_charge_locked() because of C99 6.3.1.8(1)
since both counter->limit and 'val' are of unsigned long type, the result
of the subtraction will be the same; no promotion is required. So if
'val' is greater than counter->limit, it will always be larger than
counter->usage and the conditional will fail. Simply casting this to
signed doesn't work since counter->usage is also unsigned and thus the
result of the subtraction will be promoted to unsigned since the ranks are
the same.
Even though the only (current) use of res_counter_charge() is with a 'val'
actual of 1, this still fails if you set counter->limit to 0. No chance
of overflow unless you're running on a machine with 4KB pages and 16TB of
memory.
Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Pavel Emelianov <xemul@xxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/res_counter.h | 102 ++++++++++++++++++++++++++++
init/Kconfig | 7 +
kernel/Makefile | 1
kernel/res_counter.c | 120 ++++++++++++++++++++++++++++++++++
4 files changed, 230 insertions(+)
diff -puN /dev/null include/linux/res_counter.h
--- /dev/null
+++ a/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@xxxxxxxxxx>
+ *
+ */
+
+#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 -puN init/Kconfig~memory-controller-resource-counters-v7 init/Kconfig
--- a/init/Kconfig~memory-controller-resource-counters-v7
+++ a/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 -puN kernel/Makefile~memory-controller-resource-counters-v7 kernel/Makefile
--- a/kernel/Makefile~memory-controller-resource-counters-v7
+++ a/kernel/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_CGROUP_DEBUG) += cgroup_deb
obj-$(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 -puN /dev/null kernel/res_counter.c
--- /dev/null
+++ a/kernel/res_counter.c
@@ -0,0 +1,120 @@
+/*
+ * resource cgroups
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@xxxxxxxxxx>
+ *
+ */
+
+#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;
+}
_
Patches currently in -mm which might be from xemul@xxxxxxxxxx are
origin.patch
use-find_task_by_vpid-in-audit-code.patch
ia64-fix-ptrace-inside-a-namespace.patch
mips-use-find_task_by_vpid-in-system-calls.patch
deprecate-find_task_by_pid-kgdb.patch
add-the-namespaces-config-option.patch
move-the-uts-namespace-under-uts_ns-option.patch
move-the-ipc-namespace-under-ipc_ns-option.patch
cleanup-the-code-managed-with-the-user_ns-option.patch
cleanup-the-code-managed-with-the-user_ns-option-checkpatch-fixes.patch
cleanup-the-code-managed-with-pid_ns-option.patch
cleanup-the-code-managed-with-pid_ns-option-checkpatch-fixes.patch
mark-net_ns-with-depends-on-namespaces.patch
proc-seqfile-convert-proc_pid_status-to-properly-handle-pid-namespaces.patch
proc-seqfile-convert-proc_pid_status-to-properly-handle-pid-namespaces-checkpatch-fixes.patch
proc-seqfile-convert-proc_pid_status-to-properly-handle-pid-namespaces-nommu-fix.patch
proc-proper-pidns-handling-for-proc-self.patch
proc-fix-the-threaded-proc-self.patch
ipc-uninline-some-code-from-utilh.patch
ipc-make-struct-ipc_ids-static-in-ipc_namespace.patch
ipc-consolidate-sem_exit_ns-msg_exit_ns-and-shm_exit_ns.patch
sys_setpgid-simplify-pid-ns-interaction.patch
fix-setsid-for-sub-namespace-sbin-init.patch
teach-set_special_pids-to-use-struct-pid.patch
move-daemonized-kernel-threads-into-the-swappers-session.patch
start-the-global-sbin-init-with-00-special-pids.patch
pid-sys_wait-fixes-v2.patch
pid-extend-fix-pid_vnr.patch
sys_getsid-dont-use-nsproxy-directly.patch
pid-fix-mips-irix-emulation-pid-usage.patch
pid-fix-mips-irix-emulation-pid-usage-fix.patch
pid-fix-solaris_procids.patch
uglify-kill_pid_info-to-fix-kill-vs-exec-race.patch
uglify-while_each_pid_task-to-make-sure-we-dont-count-the-execing-pricess-twice.patch
itimer_real-convert-to-use-struct-pid.patch
pidns-make-full-use-of-xxx_vnr-calls.patch
pidns-fix-badly-converted-mqueues-pid-handling.patch
clean-up-the-kill_something_info.patch
get-rid-of-the-kill_pgrp_info-function.patch
use-find_task_by_vpid-in-posix-timers.patch
use-find_task_by_vpid-in-taskstats.patch
dont-operate-with-pid_t-in-rtmutex-tester.patch
deprecate-find_task_by_pid.patch
reiser4.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
