summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile5
-rw-r--r--kernel/audit.c4
-rw-r--r--kernel/audit_tree.c20
-rw-r--r--kernel/audit_watch.c24
-rw-r--r--kernel/auditfilter.c2
-rw-r--r--kernel/auditsc.c2
-rw-r--r--kernel/capability.c29
-rw-r--r--kernel/cgroup.c4678
-rw-r--r--kernel/cgroup_freezer.c47
-rw-r--r--kernel/compat.c212
-rw-r--r--kernel/context_tracking.c8
-rw-r--r--kernel/cpu.c38
-rw-r--r--kernel/cpu/Makefile1
-rw-r--r--kernel/cpu/idle.c141
-rw-r--r--kernel/cpuset.c345
-rw-r--r--kernel/debug/debug_core.c21
-rw-r--r--kernel/debug/debug_core.h2
-rw-r--r--kernel/events/core.c107
-rw-r--r--kernel/events/ring_buffer.c42
-rw-r--r--kernel/events/uprobes.c73
-rw-r--r--kernel/exit.c113
-rw-r--r--kernel/extable.c2
-rw-r--r--kernel/fork.c69
-rw-r--r--kernel/futex.c254
-rw-r--r--kernel/futex_compat.c2
-rw-r--r--kernel/groups.c14
-rw-r--r--kernel/hrtimer.c18
-rw-r--r--kernel/hung_task.c9
-rw-r--r--kernel/irq/Kconfig1
-rw-r--r--kernel/irq/chip.c48
-rw-r--r--kernel/irq/devres.c45
-rw-r--r--kernel/irq/handle.c5
-rw-r--r--kernel/irq/internals.h9
-rw-r--r--kernel/irq/irqdesc.c6
-rw-r--r--kernel/irq/irqdomain.c1
-rw-r--r--kernel/irq/manage.c132
-rw-r--r--kernel/irq/proc.c8
-rw-r--r--kernel/irq_work.c6
-rw-r--r--kernel/kallsyms.c11
-rw-r--r--kernel/kexec.c22
-rw-r--r--kernel/kmod.c2
-rw-r--r--kernel/ksysfs.c9
-rw-r--r--kernel/kthread.c4
-rw-r--r--kernel/locking/Makefile4
-rw-r--r--kernel/locking/lockdep.c27
-rw-r--r--kernel/locking/locktorture.c452
-rw-r--r--kernel/locking/mcs_spinlock.c178
-rw-r--r--kernel/locking/mcs_spinlock.h129
-rw-r--r--kernel/locking/mutex-debug.c13
-rw-r--r--kernel/locking/mutex.c104
-rw-r--r--kernel/locking/rtmutex-debug.c8
-rw-r--r--kernel/locking/rtmutex.c178
-rw-r--r--kernel/locking/rtmutex_common.h23
-rw-r--r--kernel/locking/rwsem-xadd.c4
-rw-r--r--kernel/module.c24
-rw-r--r--kernel/notifier.c2
-rw-r--r--kernel/padata.c2
-rw-r--r--kernel/panic.c21
-rw-r--r--kernel/params.c25
-rw-r--r--kernel/pid_namespace.c4
-rw-r--r--kernel/posix-cpu-timers.c327
-rw-r--r--kernel/power/block_io.c2
-rw-r--r--kernel/power/console.c1
-rw-r--r--kernel/power/hibernate.c29
-rw-r--r--kernel/power/main.c4
-rw-r--r--kernel/power/power.h5
-rw-r--r--kernel/power/qos.c18
-rw-r--r--kernel/power/snapshot.c7
-rw-r--r--kernel/power/suspend.c7
-rw-r--r--kernel/power/swap.c2
-rw-r--r--kernel/power/wakelock.c2
-rw-r--r--kernel/printk/printk.c36
-rw-r--r--kernel/profile.c26
-rw-r--r--kernel/ptrace.c4
-rw-r--r--kernel/rcu/Makefile2
-rw-r--r--kernel/rcu/rcu.h12
-rw-r--r--kernel/rcu/rcutorture.c (renamed from kernel/rcu/torture.c)1077
-rw-r--r--kernel/rcu/srcu.c68
-rw-r--r--kernel/rcu/tiny.c8
-rw-r--r--kernel/rcu/tiny_plugin.h4
-rw-r--r--kernel/rcu/tree.c173
-rw-r--r--kernel/rcu/tree.h16
-rw-r--r--kernel/rcu/tree_plugin.h119
-rw-r--r--kernel/rcu/tree_trace.c9
-rw-r--r--kernel/rcu/update.c21
-rw-r--r--kernel/relay.c2
-rw-r--r--kernel/res_counter.c23
-rw-r--r--kernel/resource.c14
-rw-r--r--kernel/sched/Makefile7
-rw-r--r--kernel/sched/auto_group.c2
-rw-r--r--kernel/sched/clock.c110
-rw-r--r--kernel/sched/core.c1143
-rw-r--r--kernel/sched/cpuacct.c24
-rw-r--r--kernel/sched/cpudeadline.c216
-rw-r--r--kernel/sched/cpudeadline.h33
-rw-r--r--kernel/sched/cputime.c20
-rw-r--r--kernel/sched/deadline.c1665
-rw-r--r--kernel/sched/debug.c14
-rw-r--r--kernel/sched/fair.c703
-rw-r--r--kernel/sched/idle.c265
-rw-r--r--kernel/sched/idle_task.c25
-rw-r--r--kernel/sched/rt.c112
-rw-r--r--kernel/sched/sched.h220
-rw-r--r--kernel/sched/stats.c2
-rw-r--r--kernel/sched/stop_task.c17
-rw-r--r--kernel/seccomp.c121
-rw-r--r--kernel/signal.c13
-rw-r--r--kernel/smp.c191
-rw-r--r--kernel/softirq.c165
-rw-r--r--kernel/stop_machine.c2
-rw-r--r--kernel/sys.c31
-rw-r--r--kernel/sys_ni.c2
-rw-r--r--kernel/sysctl.c72
-rw-r--r--kernel/time/Kconfig2
-rw-r--r--kernel/time/Makefile5
-rw-r--r--kernel/time/clockevents.c40
-rw-r--r--kernel/time/jiffies.c6
-rw-r--r--kernel/time/ntp.c5
-rw-r--r--kernel/time/sched_clock.c46
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c106
-rw-r--r--kernel/time/tick-broadcast.c92
-rw-r--r--kernel/time/tick-common.c17
-rw-r--r--kernel/time/tick-internal.h16
-rw-r--r--kernel/time/tick-sched.c61
-rw-r--r--kernel/time/timekeeping.c59
-rw-r--r--kernel/time/timekeeping_debug.c2
-rw-r--r--kernel/timer.c59
-rw-r--r--kernel/torture.c719
-rw-r--r--kernel/trace/Kconfig1
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/blktrace.c38
-rw-r--r--kernel/trace/ftrace.c377
-rw-r--r--kernel/trace/ring_buffer.c28
-rw-r--r--kernel/trace/ring_buffer_benchmark.c6
-rw-r--r--kernel/trace/trace.c384
-rw-r--r--kernel/trace/trace.h234
-rw-r--r--kernel/trace/trace_event_perf.c22
-rw-r--r--kernel/trace/trace_events.c95
-rw-r--r--kernel/trace/trace_events_filter.c12
-rw-r--r--kernel/trace/trace_events_trigger.c1437
-rw-r--r--kernel/trace/trace_export.c7
-rw-r--r--kernel/trace/trace_functions.c143
-rw-r--r--kernel/trace/trace_functions_graph.c3
-rw-r--r--kernel/trace/trace_irqsoff.c14
-rw-r--r--kernel/trace/trace_kprobe.c855
-rw-r--r--kernel/trace/trace_nop.c5
-rw-r--r--kernel/trace/trace_output.c31
-rw-r--r--kernel/trace/trace_probe.c440
-rw-r--r--kernel/trace/trace_probe.h241
-rw-r--r--kernel/trace/trace_sched_wakeup.c75
-rw-r--r--kernel/trace/trace_selftest.c33
-rw-r--r--kernel/trace/trace_stack.c5
-rw-r--r--kernel/trace/trace_syscalls.c14
-rw-r--r--kernel/trace/trace_uprobe.c624
-rw-r--r--kernel/tracepoint.c255
-rw-r--r--kernel/up.c6
-rw-r--r--kernel/user.c3
-rw-r--r--kernel/user_namespace.c4
-rw-r--r--kernel/watchdog.c19
-rw-r--r--kernel/workqueue.c18
160 files changed, 14152 insertions, 7495 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index bc010ee272b6..f2a8b6246ce9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -18,11 +18,13 @@ CFLAGS_REMOVE_cgroup-debug.o = -pg
CFLAGS_REMOVE_irq_work.o = -pg
endif
+# cond_syscall is currently not LTO compatible
+CFLAGS_sys_ni.o = $(DISABLE_LTO)
+
obj-y += sched/
obj-y += locking/
obj-y += power/
obj-y += printk/
-obj-y += cpu/
obj-y += irq/
obj-y += rcu/
@@ -93,6 +95,7 @@ obj-$(CONFIG_PADATA) += padata.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
+obj-$(CONFIG_TORTURE_TEST) += torture.o
$(obj)/configs.o: $(obj)/config_data.h
diff --git a/kernel/audit.c b/kernel/audit.c
index 873b965fdc58..7c2893602d06 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -559,7 +559,7 @@ static int audit_send_reply_thread(void *arg)
}
/**
* audit_send_reply - send an audit reply message via netlink
- * @portid: netlink port to which to send reply
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: sequence number
* @type: audit message type
* @done: done (last) flag
@@ -618,7 +618,7 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
* userspace will reject all logins. This should be removed when we
* support non init namespaces!!
*/
- if ((current_user_ns() != &init_user_ns))
+ if (current_user_ns() != &init_user_ns)
return -ECONNREFUSED;
switch (msg_type) {
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 43c307dc9453..135944a7b28a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -912,12 +912,13 @@ static void evict_chunk(struct audit_chunk *chunk)
}
static int audit_tree_handle_event(struct fsnotify_group *group,
+ struct inode *to_tell,
struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmonut_mark,
- struct fsnotify_event *event)
+ struct fsnotify_mark *vfsmount_mark,
+ u32 mask, void *data, int data_type,
+ const unsigned char *file_name, u32 cookie)
{
- BUG();
- return -EOPNOTSUPP;
+ return 0;
}
static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify_group *group)
@@ -933,19 +934,8 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify
BUG_ON(atomic_read(&entry->refcnt) < 1);
}
-static bool audit_tree_send_event(struct fsnotify_group *group, struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
- __u32 mask, void *data, int data_type)
-{
- return false;
-}
-
static const struct fsnotify_ops audit_tree_ops = {
.handle_event = audit_tree_handle_event,
- .should_send_event = audit_tree_send_event,
- .free_group_priv = NULL,
- .free_event_priv = NULL,
.freeing_mark = audit_tree_freeing_mark,
};
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 22831c4d369c..70b4554d2fbe 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -465,35 +465,27 @@ void audit_remove_watch_rule(struct audit_krule *krule)
}
}
-static bool audit_watch_should_send_event(struct fsnotify_group *group, struct inode *inode,
- struct fsnotify_mark *inode_mark,
- struct fsnotify_mark *vfsmount_mark,
- __u32 mask, void *data, int data_type)
-{
- return true;
-}
-
/* Update watch data in audit rules based on fsnotify events. */
static int audit_watch_handle_event(struct fsnotify_group *group,
+ struct inode *to_tell,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
- struct fsnotify_event *event)
+ u32 mask, void *data, int data_type,
+ const unsigned char *dname, u32 cookie)
{
struct inode *inode;
- __u32 mask = event->mask;
- const char *dname = event->file_name;
struct audit_parent *parent;
parent = container_of(inode_mark, struct audit_parent, mark);
BUG_ON(group != audit_watch_group);
- switch (event->data_type) {
+ switch (data_type) {
case (FSNOTIFY_EVENT_PATH):
- inode = event->path.dentry->d_inode;
+ inode = ((struct path *)data)->dentry->d_inode;
break;
case (FSNOTIFY_EVENT_INODE):
- inode = event->inode;
+ inode = (struct inode *)data;
break;
default:
BUG();
@@ -512,11 +504,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
}
static const struct fsnotify_ops audit_watch_fsnotify_ops = {
- .should_send_event = audit_watch_should_send_event,
.handle_event = audit_watch_handle_event,
- .free_group_priv = NULL,
- .freeing_mark = NULL,
- .free_event_priv = NULL,
};
static int __init audit_watch_init(void)
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 70101e0b184a..8e9bc9c3dbb7 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1082,7 +1082,7 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data,
/**
* audit_list_rules_send - list the audit rules
- * @portid: target portid for netlink audit messages
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: netlink audit message sequence (serial) number
*/
int audit_list_rules_send(struct sk_buff *request_skb, int seq)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 254ce2063d1d..f251a5e8d17a 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1789,7 +1789,7 @@ void audit_putname(struct filename *name)
struct audit_context *context = current->audit_context;
BUG_ON(!context);
- if (!context->in_syscall) {
+ if (!name->aname || !context->in_syscall) {
#if AUDIT_DEBUG == 2
pr_err("%s:%d(:%d): final_putname(%p)\n",
__FILE__, __LINE__, context->serial, name);
diff --git a/kernel/capability.c b/kernel/capability.c
index 34019c57888d..a8d63df0c322 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -7,6 +7,8 @@
* 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/mm.h>
@@ -42,15 +44,10 @@ __setup("no_file_caps", file_caps_disable);
static void warn_legacy_capability_use(void)
{
- static int warned;
- if (!warned) {
- char name[sizeof(current->comm)];
-
- printk(KERN_INFO "warning: `%s' uses 32-bit capabilities"
- " (legacy support in use)\n",
- get_task_comm(name, current));
- warned = 1;
- }
+ char name[sizeof(current->comm)];
+
+ pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n",
+ get_task_comm(name, current));
}
/*
@@ -71,16 +68,10 @@ static void warn_legacy_capability_use(void)
static void warn_deprecated_v2(void)
{
- static int warned;
+ char name[sizeof(current->comm)];
- if (!warned) {
- char name[sizeof(current->comm)];
-
- printk(KERN_INFO "warning: `%s' uses deprecated v2"
- " capabilities in a way that may be insecure.\n",
- get_task_comm(name, current));
- warned = 1;
- }
+ pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n",
+ get_task_comm(name, current));
}
/*
@@ -380,7 +371,7 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
bool ns_capable(struct user_namespace *ns, int cap)
{
if (unlikely(!cap_valid(cap))) {
- printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
+ pr_crit("capable() called with invalid cap=%u\n", cap);
BUG();
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index bc1dcabe9217..9fcdaa705b6c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -40,54 +40,74 @@
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
-#include <linux/backing-dev.h>
-#include <linux/seq_file.h>
#include <linux/slab.h>
-#include <linux/magic.h>
#include <linux/spinlock.h>
+#include <linux/rwsem.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
-#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hashtable.h>
-#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/eventfd.h>
-#include <linux/poll.h>
-#include <linux/flex_array.h> /* used in cgroup_attach_task */
#include <linux/kthread.h>
-#include <linux/file.h>
+#include <linux/delay.h>
#include <linux/atomic.h>
/*
+ * pidlists linger the following amount before being destroyed. The goal
+ * is avoiding frequent destruction in the middle of consecutive read calls
+ * Expiring in the middle is a performance problem not a correctness one.
+ * 1 sec should be enough.
+ */
+#define CGROUP_PIDLIST_DESTROY_DELAY HZ
+
+#define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \
+ MAX_CFTYPE_NAME + 2)
+
+/*
+ * cgroup_tree_mutex nests above cgroup_mutex and protects cftypes, file
+ * creation/removal and hierarchy changing operations including cgroup
+ * creation, removal, css association and controller rebinding. This outer
+ * lock is needed mainly to resolve the circular dependency between kernfs
+ * active ref and cgroup_mutex. cgroup_tree_mutex nests above both.
+ */
+static DEFINE_MUTEX(cgroup_tree_mutex);
+
+/*
* cgroup_mutex is the master lock. Any modification to cgroup or its
* hierarchy must be performed while holding it.
*
- * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify
- * cgroupfs_root of any cgroup hierarchy - subsys list, flags,
- * release_agent_path and so on. Modifying requires both cgroup_mutex and
- * cgroup_root_mutex. Readers can acquire either of the two. This is to
- * break the following locking order cycle.
+ * css_set_rwsem protects task->cgroups pointer, the list of css_set
+ * objects, and the chain of tasks off each css_set.
*
- * A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem
- * B. namespace_sem -> cgroup_mutex
- *
- * B happens only through cgroup_show_options() and using cgroup_root_mutex
- * breaks it.
+ * These locks are exported if CONFIG_PROVE_RCU so that accessors in
+ * cgroup.h can use them for lockdep annotations.
*/
#ifdef CONFIG_PROVE_RCU
DEFINE_MUTEX(cgroup_mutex);
-EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for lockdep */
+DECLARE_RWSEM(css_set_rwsem);
+EXPORT_SYMBOL_GPL(cgroup_mutex);
+EXPORT_SYMBOL_GPL(css_set_rwsem);
#else
static DEFINE_MUTEX(cgroup_mutex);
+static DECLARE_RWSEM(css_set_rwsem);
#endif
-static DEFINE_MUTEX(cgroup_root_mutex);
+/*
+ * Protects cgroup_subsys->release_agent_path. Modifying it also requires
+ * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock.
+ */
+static DEFINE_SPINLOCK(release_agent_path_lock);
+
+#define cgroup_assert_mutexes_or_rcu_locked() \
+ rcu_lockdep_assert(rcu_read_lock_held() || \
+ lockdep_is_held(&cgroup_tree_mutex) || \
+ lockdep_is_held(&cgroup_mutex), \
+ "cgroup_[tree_]mutex or RCU read lock required");
/*
* cgroup destruction makes heavy use of work items and there can be a lot
@@ -98,84 +118,46 @@ static DEFINE_MUTEX(cgroup_root_mutex);
static struct workqueue_struct *cgroup_destroy_wq;
/*
- * Generate an array of cgroup subsystem pointers. At boot time, this is
- * populated with the built in subsystems, and modular subsystems are
- * registered after that. The mutable section of this array is protected by
- * cgroup_mutex.
+ * pidlist destructions need to be flushed on cgroup destruction. Use a
+ * separate workqueue as flush domain.
*/
-#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
-#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
-static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = {
+static struct workqueue_struct *cgroup_pidlist_destroy_wq;
+
+/* generate an array of cgroup subsystem pointers */
+#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
+static struct cgroup_subsys *cgroup_subsys[] = {
#include <linux/cgroup_subsys.h>
};
+#undef SUBSYS
+
+/* array of cgroup subsystem names */
+#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
+static const char *cgroup_subsys_name[] = {
+#include <linux/cgroup_subsys.h>
+};
+#undef SUBSYS
/*
- * The dummy hierarchy, reserved for the subsystems that are otherwise
+ * The default hierarchy, reserved for the subsystems that are otherwise
* unattached - it never has more than a single cgroup, and all tasks are
* part of that cgroup.
*/
-static struct cgroupfs_root cgroup_dummy_root;
-
-/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
-static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
+struct cgroup_root cgrp_dfl_root;
/*
- * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.
+ * The default hierarchy always exists but is hidden until mounted for the
+ * first time. This is for backward compatibility.
*/
-struct cfent {
- struct list_head node;
- struct dentry *dentry;
- struct cftype *type;
- struct cgroup_subsys_state *css;
-
- /* file xattrs */
- struct simple_xattrs xattrs;
-};
-
-/*
- * cgroup_event represents events which userspace want to receive.
- */
-struct cgroup_event {
- /*
- * css which the event belongs to.
- */
- struct cgroup_subsys_state *css;
- /*
- * Control file which the event associated.
- */
- struct cftype *cft;
- /*
- * eventfd to signal userspace about the event.
- */
- struct eventfd_ctx *eventfd;
- /*
- * Each of these stored in a list by the cgroup.
- */
- struct list_head list;
- /*
- * All fields below needed to unregister event when
- * userspace closes eventfd.
- */
- poll_table pt;
- wait_queue_head_t *wqh;
- wait_queue_t wait;
- struct work_struct remove;
-};
+static bool cgrp_dfl_root_visible;
/* The list of hierarchy roots */
static LIST_HEAD(cgroup_roots);
static int cgroup_root_count;
-/*
- * Hierarchy ID allocation and mapping. It follows the same exclusion
- * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for
- * writes, either for reads.
- */
+/* hierarchy ID allocation and mapping, protected by cgroup_mutex */
static DEFINE_IDR(cgroup_hierarchy_idr);
-static struct cgroup_name root_cgroup_name = { .name = "/" };
-
/*
* Assign a monotonically increasing serial number to cgroups. It
* guarantees cgroups with bigger numbers are newer than those with smaller
@@ -195,11 +177,14 @@ static int need_forkexit_callback __read_mostly;
static struct cftype cgroup_base_files[];
+static void cgroup_put(struct cgroup *cgrp);
+static int rebind_subsystems(struct cgroup_root *dst_root,
+ unsigned long ss_mask);
static void cgroup_destroy_css_killed(struct cgroup *cgrp);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
bool is_add);
-static int cgroup_file_release(struct inode *inode, struct file *file);
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
/**
* cgroup_css - obtain a cgroup's css for the specified subsystem
@@ -216,8 +201,9 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
{
if (ss)
- return rcu_dereference_check(cgrp->subsys[ss->subsys_id],
- lockdep_is_held(&cgroup_mutex));
+ return rcu_dereference_check(cgrp->subsys[ss->id],
+ lockdep_is_held(&cgroup_tree_mutex) ||
+ lockdep_is_held(&cgroup_mutex));
else
return &cgrp->dummy_css;
}
@@ -228,6 +214,27 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
return test_bit(CGRP_DEAD, &cgrp->flags);
}
+struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+ struct kernfs_open_file *of = seq->private;
+ struct cgroup *cgrp = of->kn->parent->priv;
+ struct cftype *cft = seq_cft(seq);
+
+ /*
+ * This is open and unprotected implementation of cgroup_css().
+ * seq_css() is only called from a kernfs file operation which has
+ * an active reference on the file. Because all the subsystem
+ * files are drained before a css is disassociated with a cgroup,
+ * the matching css from the cgroup's subsys table is guaranteed to
+ * be and stay valid until the enclosing operation is complete.
+ */
+ if (cft->ss)
+ return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
+ else
+ return &cgrp->dummy_css;
+}
+EXPORT_SYMBOL_GPL(seq_css);
+
/**
* cgroup_is_descendant - test ancestry
* @cgrp: the cgroup to be tested
@@ -246,7 +253,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
}
return false;
}
-EXPORT_SYMBOL_GPL(cgroup_is_descendant);
static int cgroup_is_releasable(const struct cgroup *cgrp)
{
@@ -262,53 +268,34 @@ static int notify_on_release(const struct cgroup *cgrp)
}
/**
- * for_each_subsys - iterate all loaded cgroup subsystems
- * @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ * for_each_css - iterate all css's of a cgroup
+ * @css: the iteration cursor
+ * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
+ * @cgrp: the target cgroup to iterate css's of
*
* Should be called under cgroup_mutex.
*/
-#define for_each_subsys(ss, i) \
- for ((i) = 0; (i) < CGROUP_SUBSYS_COUNT; (i)++) \
- if (({ lockdep_assert_held(&cgroup_mutex); \
- !((ss) = cgroup_subsys[i]); })) { } \
+#define for_each_css(css, ssid, cgrp) \
+ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \
+ if (!((css) = rcu_dereference_check( \
+ (cgrp)->subsys[(ssid)], \
+ lockdep_is_held(&cgroup_tree_mutex) || \
+ lockdep_is_held(&cgroup_mutex)))) { } \
else
/**
- * for_each_builtin_subsys - iterate all built-in cgroup subsystems
+ * for_each_subsys - iterate all enabled cgroup subsystems
* @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end
- *
- * Bulit-in subsystems are always present and iteration itself doesn't
- * require any synchronization.
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
*/
-#define for_each_builtin_subsys(ss, i) \
- for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT && \
- (((ss) = cgroup_subsys[i]) || true); (i)++)
-
-/* iterate each subsystem attached to a hierarchy */
-#define for_each_root_subsys(root, ss) \
- list_for_each_entry((ss), &(root)->subsys_list, sibling)
+#define for_each_subsys(ss, ssid) \
+ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \
+ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
-/* iterate across the active hierarchies */
-#define for_each_active_root(root) \
+/* iterate across the hierarchies */
+#define for_each_root(root) \
list_for_each_entry((root), &cgroup_roots, root_list)
-static inline struct cgroup *__d_cgrp(struct dentry *dentry)
-{
- return dentry->d_fsdata;
-}
-
-static inline struct cfent *__d_cfe(struct dentry *dentry)
-{
- return dentry->d_fsdata;
-}
-
-static inline struct cftype *__d_cft(struct dentry *dentry)
-{
- return __d_cfe(dentry)->type;
-}
-
/**
* cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
* @cgrp: the cgroup to be checked for liveness
@@ -354,23 +341,23 @@ struct cgrp_cset_link {
struct list_head cgrp_link;
};
-/* The default css_set - used by init and its children prior to any
+/*
+ * The default css_set - used by init and its children prior to any
* hierarchies being mounted. It contains a pointer to the root state
* for each subsystem. Also used to anchor the list of css_sets. Not
* reference-counted, to improve performance when child cgroups
* haven't been created.
*/
+static struct css_set init_css_set = {
+ .refcount = ATOMIC_INIT(1),
+ .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
+ .tasks = LIST_HEAD_INIT(init_css_set.tasks),
+ .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks),
+ .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+ .mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
+};
-static struct css_set init_css_set;
-static struct cgrp_cset_link init_cgrp_cset_link;
-
-/*
- * css_set_lock protects the list of css_set objects, and the chain of
- * tasks off each css_set. Nests outside task->alloc_lock due to
- * css_task_iter_start().
- */
-static DEFINE_RWLOCK(css_set_lock);
-static int css_set_count;
+static int css_set_count = 1; /* 1 for init_css_set */
/*
* hash table for cgroup groups. This improves the performance to find
@@ -393,30 +380,14 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
return key;
}
-/*
- * We don't maintain the lists running through each css_set to its task
- * until after the first call to css_task_iter_start(). This reduces the
- * fork()/exit() overhead for people who have cgroups compiled into their
- * kernel but not actually in use.
- */
-static int use_task_css_set_links __read_mostly;
-
-static void __put_css_set(struct css_set *cset, int taskexit)
+static void put_css_set_locked(struct css_set *cset, bool taskexit)
{
struct cgrp_cset_link *link, *tmp_link;
- /*
- * Ensure that the refcount doesn't hit zero while any readers
- * can see it. Similar to atomic_dec_and_lock(), but for an
- * rwlock
- */
- if (atomic_add_unless(&cset->refcount, -1, 1))
- return;
- write_lock(&css_set_lock);
- if (!atomic_dec_and_test(&cset->refcount)) {
- write_unlock(&css_set_lock);
+ lockdep_assert_held(&css_set_rwsem);
+
+ if (!atomic_dec_and_test(&cset->refcount))
return;
- }
/* This css_set is dead. unlink it and release cgroup refcounts */
hash_del(&cset->hlist);
@@ -428,7 +399,7 @@ static void __put_css_set(struct css_set *cset, int taskexit)
list_del(&link->cset_link);
list_del(&link->cgrp_link);
- /* @cgrp can't go away while we're holding css_set_lock */
+ /* @cgrp can't go away while we're holding css_set_rwsem */
if (list_empty(&cgrp->cset_links) && notify_on_release(cgrp)) {
if (taskexit)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
@@ -438,10 +409,24 @@ static void __put_css_set(struct css_set *cset, int taskexit)
kfree(link);
}
- write_unlock(&css_set_lock);
kfree_rcu(cset, rcu_head);
}
+static void put_css_set(struct css_set *cset, bool taskexit)
+{
+ /*
+ * Ensure that the refcount doesn't hit zero while any readers
+ * can see it. Similar to atomic_dec_and_lock(), but for an
+ * rwlock
+ */
+ if (atomic_add_unless(&cset->refcount, -1, 1))
+ return;
+
+ down_write(&css_set_rwsem);
+ put_css_set_locked(cset, taskexit);
+ up_write(&css_set_rwsem);
+}
+
/*
* refcounted get/put for css_set objects
*/
@@ -450,16 +435,6 @@ static inline void get_css_set(struct css_set *cset)
atomic_inc(&cset->refcount);
}
-static inline void put_css_set(struct css_set *cset)
-{
- __put_css_set(cset, 0);
-}
-
-static inline void put_css_set_taskexit(struct css_set *cset)
-{
- __put_css_set(cset, 1);
-}
-
/**
* compare_css_sets - helper function for find_existing_css_set().
* @cset: candidate css_set being tested
@@ -542,7 +517,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
struct cgroup *cgrp,
struct cgroup_subsys_state *template[])
{
- struct cgroupfs_root *root = cgrp->root;
+ struct cgroup_root *root = cgrp->root;
struct cgroup_subsys *ss;
struct css_set *cset;
unsigned long key;
@@ -554,7 +529,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
* won't change, so no need for locking.
*/
for_each_subsys(ss, i) {
- if (root->subsys_mask & (1UL << i)) {
+ if (root->cgrp.subsys_mask & (1UL << i)) {
/* Subsystem is in this hierarchy. So we want
* the subsystem state from the new
* cgroup */
@@ -659,11 +634,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
/* First see if we already have a cgroup group that matches
* the desired set */
- read_lock(&css_set_lock);
+ down_read(&css_set_rwsem);
cset = find_existing_css_set(old_cset, cgrp, template);
if (cset)
get_css_set(cset);
- read_unlock(&css_set_lock);
+ up_read(&css_set_rwsem);
if (cset)
return cset;
@@ -681,13 +656,16 @@ static struct css_set *find_css_set(struct css_set *old_cset,
atomic_set(&cset->refcount, 1);
INIT_LIST_HEAD(&cset->cgrp_links);
INIT_LIST_HEAD(&cset->tasks);
+ INIT_LIST_HEAD(&cset->mg_tasks);
+ INIT_LIST_HEAD(&cset->mg_preload_node);
+ INIT_LIST_HEAD(&cset->mg_node);
INIT_HLIST_NODE(&cset->hlist);
/* Copy the set of subsystem state objects generated in
* find_existing_css_set() */
memcpy(cset->subsys, template, sizeof(cset->subsys));
- write_lock(&css_set_lock);
+ down_write(&css_set_rwsem);
/* Add reference counts and links from the new css_set. */
list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
@@ -705,31 +683,105 @@ static struct css_set *find_css_set(struct css_set *old_cset,
key = css_set_hash(cset->subsys);
hash_add(css_set_table, &cset->hlist, key);
- write_unlock(&css_set_lock);
+ up_write(&css_set_rwsem);
return cset;
}
-/*
- * Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex held.
- */
-static struct cgroup *task_cgroup_from_root(struct task_struct *task,
- struct cgroupfs_root *root)
+static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
{
- struct css_set *cset;
- struct cgroup *res = NULL;
+ struct cgroup *root_cgrp = kf_root->kn->priv;
+
+ return root_cgrp->root;
+}
+
+static int cgroup_init_root_id(struct cgroup_root *root)
+{
+ int id;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL);
+ if (id < 0)
+ return id;
+
+ root->hierarchy_id = id;
+ return 0;
+}
+
+static void cgroup_exit_root_id(struct cgroup_root *root)
+{
+ lockdep_assert_held(&cgroup_mutex);
+
+ if (root->hierarchy_id) {
+ idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
+ root->hierarchy_id = 0;
+ }
+}
+
+static void cgroup_free_root(struct cgroup_root *root)
+{
+ if (root) {
+ /* hierarhcy ID shoulid already have been released */
+ WARN_ON_ONCE(root->hierarchy_id);
+
+ idr_destroy(&root->cgroup_idr);
+ kfree(root);
+ }
+}
+
+static void cgroup_destroy_root(struct cgroup_root *root)
+{
+ struct cgroup *cgrp = &root->cgrp;
+ struct cgrp_cset_link *link, *tmp_link;
+
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
+
+ BUG_ON(atomic_read(&root->nr_cgrps));
+ BUG_ON(!list_empty(&cgrp->children));
+
+ /* Rebind all subsystems back to the default hierarchy */
+ rebind_subsystems(&cgrp_dfl_root, cgrp->subsys_mask);
- BUG_ON(!mutex_is_locked(&cgroup_mutex));
- read_lock(&css_set_lock);
/*
- * No need to lock the task - since we hold cgroup_mutex the
- * task can't change groups, so the only thing that can happen
- * is that it exits and its css is set back to init_css_set.
+ * Release all the links from cset_links to this hierarchy's
+ * root cgroup
*/
- cset = task_css_set(task);
+ down_write(&css_set_rwsem);
+
+ list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
+ list_del(&link->cset_link);
+ list_del(&link->cgrp_link);
+ kfree(link);
+ }
+ up_write(&css_set_rwsem);
+
+ if (!list_empty(&root->root_list)) {
+ list_del(&root->root_list);
+ cgroup_root_count--;
+ }
+
+ cgroup_exit_root_id(root);
+
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+
+ kernfs_destroy_root(root->kf_root);
+ cgroup_free_root(root);
+}
+
+/* look up cgroup associated with given css_set on the specified hierarchy */
+static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
+ struct cgroup_root *root)
+{
+ struct cgroup *res = NULL;
+
+ lockdep_assert_held(&cgroup_mutex);
+ lockdep_assert_held(&css_set_rwsem);
+
if (cset == &init_css_set) {
- res = &root->top_cgroup;
+ res = &root->cgrp;
} else {
struct cgrp_cset_link *link;
@@ -742,16 +794,27 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
}
}
}
- read_unlock(&css_set_lock);
+
BUG_ON(!res);
return res;
}
/*
- * There is one global cgroup mutex. We also require taking
- * task_lock() when dereferencing a task's cgroup subsys pointers.
- * See "The task_lock() exception", at the end of this comment.
- *
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex and css_set_rwsem held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+ struct cgroup_root *root)
+{
+ /*
+ * No need to lock the task - since we hold cgroup_mutex the
+ * task can't change groups, so the only thing that can happen
+ * is that it exits and its css is set back to init_css_set.
+ */
+ return cset_cgroup_from_root(task_css_set(task), root);
+}
+
+/*
* A task must hold cgroup_mutex to modify cgroups.
*
* Any task can increment and decrement the count field without lock.
@@ -777,102 +840,79 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
* A cgroup can only be deleted if both its 'count' of using tasks
* is zero, and its list of 'children' cgroups is empty. Since all
* tasks in the system use _some_ cgroup, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cgroup
+ * least one task in the system (init, pid == 1), therefore, root cgroup
* always has either children cgroups and/or using tasks. So we don't
- * need a special hack to ensure that top_cgroup cannot be deleted.
- *
- * The task_lock() exception
- *
- * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one task's cgroup pointer with
- * another. It does so using cgroup_mutex, however there are
- * several performance critical places that need to reference
- * task->cgroup without the expense of grabbing a system global
- * mutex. Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task's cgroup pointer we use
- * task_lock(), which acts on a spinlock (task->alloc_lock) already in
- * the task_struct routinely used for such matters.
+ * need a special hack to ensure that root cgroup cannot be deleted.
*
* P.S. One more locking exception. RCU is used to guard the
* update of a tasks cgroup pointer by cgroup_attach_task()
*/
-/*
- * A couple of forward declarations required, due to cyclic reference loop:
- * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
- * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
- * -> cgroup_mkdir.
- */
-
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
-static const struct inode_operations cgroup_dir_inode_operations;
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
static const struct file_operations proc_cgroupstats_operations;
-static struct backing_dev_info cgroup_backing_dev_info = {
- .name = "cgroup",
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
-static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
+static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
+ char *buf)
{
- struct inode *inode = new_inode(sb);
-
- if (inode) {
- inode->i_ino = get_next_ino();
- inode->i_mode = mode;
- inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
- }
- return inode;
+ if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
+ !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
+ snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
+ cft->ss->name, cft->name);
+ else
+ strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+ return buf;
}
-static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry)
+/**
+ * cgroup_file_mode - deduce file mode of a control file
+ * @cft: the control file in question
+ *
+ * returns cft->mode if ->mode is not 0
+ * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
+ * returns S_IRUGO if it has only a read handler
+ * returns S_IWUSR if it has only a write hander
+ */
+static umode_t cgroup_file_mode(const struct cftype *cft)
{
- struct cgroup_name *name;
+ umode_t mode = 0;
- name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL);
- if (!name)
- return NULL;
- strcpy(name->name, dentry->d_name.name);
- return name;
+ if (cft->mode)
+ return cft->mode;
+
+ if (cft->read_u64 || cft->read_s64 || cft->seq_show)
+ mode |= S_IRUGO;
+
+ if (cft->write_u64 || cft->write_s64 || cft->write_string ||
+ cft->trigger)
+ mode |= S_IWUSR;
+
+ return mode;
}
static void cgroup_free_fn(struct work_struct *work)
{
struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
- mutex_lock(&cgroup_mutex);
- cgrp->root->number_of_cgroups--;
- mutex_unlock(&cgroup_mutex);
-
- /*
- * We get a ref to the parent's dentry, and put the ref when
- * this cgroup is being freed, so it's guaranteed that the
- * parent won't be destroyed before its children.
- */
- dput(cgrp->parent->dentry);
-
- /*
- * Drop the active superblock reference that we took when we
- * created the cgroup. This will free cgrp->root, if we are
- * holding the last reference to @sb.
- */
- deactivate_super(cgrp->root->sb);
-
- /*
- * if we're getting rid of the cgroup, refcount should ensure
- * that there are no pidlists left.
- */
- BUG_ON(!list_empty(&cgrp->pidlists));
-
- simple_xattrs_free(&cgrp->xattrs);
+ atomic_dec(&cgrp->root->nr_cgrps);
+ cgroup_pidlist_destroy_all(cgrp);
- kfree(rcu_dereference_raw(cgrp->name));
- kfree(cgrp);
+ if (cgrp->parent) {
+ /*
+ * We get a ref to the parent, and put the ref when this
+ * cgroup is being freed, so it's guaranteed that the
+ * parent won't be destroyed before its children.
+ */
+ cgroup_put(cgrp->parent);
+ kernfs_put(cgrp->kn);
+ kfree(cgrp);
+ } else {
+ /*
+ * This is root cgroup's refcnt reaching zero, which
+ * indicates that the root should be released.
+ */
+ cgroup_destroy_root(cgrp->root);
+ }
}
static void cgroup_free_rcu(struct rcu_head *head)
@@ -883,71 +923,40 @@ static void cgroup_free_rcu(struct rcu_head *head)
queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
}
-static void cgroup_diput(struct dentry *dentry, struct inode *inode)
+static void cgroup_get(struct cgroup *cgrp)
{
- /* is dentry a directory ? if so, kfree() associated cgroup */
- if (S_ISDIR(inode->i_mode)) {
- struct cgroup *cgrp = dentry->d_fsdata;
-
- BUG_ON(!(cgroup_is_dead(cgrp)));
-
- /*
- * XXX: cgrp->id is only used to look up css's. As cgroup
- * and css's lifetimes will be decoupled, it should be made
- * per-subsystem and moved to css->id so that lookups are
- * successful until the target css is released.
- */
- idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- cgrp->id = -1;
-
- call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
- } else {
- struct cfent *cfe = __d_cfe(dentry);
- struct cgroup *cgrp = dentry->d_parent->d_fsdata;
-
- WARN_ONCE(!list_empty(&cfe->node) &&
- cgrp != &cgrp->root->top_cgroup,
- "cfe still linked for %s\n", cfe->type->name);
- simple_xattrs_free(&cfe->xattrs);
- kfree(cfe);
- }
- iput(inode);
-}
-
-static void remove_dir(struct dentry *d)
-{
- struct dentry *parent = dget(d->d_parent);
-
- d_delete(d);
- simple_rmdir(parent->d_inode, d);
- dput(parent);
+ WARN_ON_ONCE(cgroup_is_dead(cgrp));
+ WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0);
+ atomic_inc(&cgrp->refcnt);
}
-static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+static void cgroup_put(struct cgroup *cgrp)
{
- struct cfent *cfe;
-
- lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
- lockdep_assert_held(&cgroup_mutex);
+ if (!atomic_dec_and_test(&cgrp->refcnt))
+ return;
+ if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp)))
+ return;
/*
- * If we're doing cleanup due to failure of cgroup_create(),
- * the corresponding @cfe may not exist.
+ * XXX: cgrp->id is only used to look up css's. As cgroup and
+ * css's lifetimes will be decoupled, it should be made
+ * per-subsystem and moved to css->id so that lookups are
+ * successful until the target css is released.
*/
- list_for_each_entry(cfe, &cgrp->files, node) {
- struct dentry *d = cfe->dentry;
+ mutex_lock(&cgroup_mutex);
+ idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ mutex_unlock(&cgroup_mutex);
+ cgrp->id = -1;
- if (cft && cfe->type != cft)
- continue;
+ call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
+}
- dget(d);
- d_delete(d);
- simple_unlink(cgrp->dentry->d_inode, d);
- list_del_init(&cfe->node);
- dput(d);
+static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+{
+ char name[CGROUP_FILE_NAME_MAX];
- break;
- }
+ lockdep_assert_held(&cgroup_tree_mutex);
+ kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
}
/**
@@ -961,158 +970,123 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
int i;
for_each_subsys(ss, i) {
- struct cftype_set *set;
+ struct cftype *cfts;
if (!test_bit(i, &subsys_mask))
continue;
- list_for_each_entry(set, &ss->cftsets, node)
- cgroup_addrm_files(cgrp, set->cfts, false);
+ list_for_each_entry(cfts, &ss->cfts, node)
+ cgroup_addrm_files(cgrp, cfts, false);
}
}
-/*
- * NOTE : the dentry must have been dget()'ed
- */
-static void cgroup_d_remove_dir(struct dentry *dentry)
-{
- struct dentry *parent;
-
- parent = dentry->d_parent;
- spin_lock(&parent->d_lock);
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- list_del_init(&dentry->d_u.d_child);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&parent->d_lock);
- remove_dir(dentry);
-}
-
-/*
- * Call with cgroup_mutex held. Drops reference counts on modules, including
- * any duplicate ones that parse_cgroupfs_options took. If this function
- * returns an error, no reference counts are touched.
- */
-static int rebind_subsystems(struct cgroupfs_root *root,
- unsigned long added_mask, unsigned removed_mask)
+static int rebind_subsystems(struct cgroup_root *dst_root,
+ unsigned long ss_mask)
{
- struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_subsys *ss;
- unsigned long pinned = 0;
- int i, ret;
+ int ssid, ret;
- BUG_ON(!mutex_is_locked(&cgroup_mutex));
- BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
+ lockdep_assert_held(&cgroup_tree_mutex);
+ lockdep_assert_held(&cgroup_mutex);
- /* Check that any added subsystems are currently free */
- for_each_subsys(ss, i) {
- if (!(added_mask & (1 << i)))
+ for_each_subsys(ss, ssid) {
+ if (!(ss_mask & (1 << ssid)))
continue;
- /* is the subsystem mounted elsewhere? */
- if (ss->root != &cgroup_dummy_root) {
- ret = -EBUSY;
- goto out_put;
- }
+ /* if @ss is on the dummy_root, we can always move it */
+ if (ss->root == &cgrp_dfl_root)
+ continue;
- /* pin the module */
- if (!try_module_get(ss->module)) {
- ret = -ENOENT;
- goto out_put;
- }
- pinned |= 1 << i;
- }
+ /* if @ss has non-root cgroups attached to it, can't move */
+ if (!list_empty(&ss->root->cgrp.children))
+ return -EBUSY;
- /* subsys could be missing if unloaded between parsing and here */
- if (added_mask != pinned) {
- ret = -ENOENT;
- goto out_put;
+ /* can't move between two non-dummy roots either */
+ if (dst_root != &cgrp_dfl_root)
+ return -EBUSY;
}
- ret = cgroup_populate_dir(cgrp, added_mask);
- if (ret)
- goto out_put;
+ ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
+ if (ret) {
+ if (dst_root != &cgrp_dfl_root)
+ return ret;
+
+ /*
+ * Rebinding back to the default root is not allowed to
+ * fail. Using both default and non-default roots should
+ * be rare. Moving subsystems back and forth even more so.
+ * Just warn about it and continue.
+ */
+ if (cgrp_dfl_root_visible) {
+ pr_warning("cgroup: failed to create files (%d) while rebinding 0x%lx to default root\n",
+ ret, ss_mask);
+ pr_warning("cgroup: you may retry by moving them to a different hierarchy and unbinding\n");
+ }
+ }
/*
* Nothing can fail from this point on. Remove files for the
* removed subsystems and rebind each subsystem.
*/
- cgroup_clear_dir(cgrp, removed_mask);
+ mutex_unlock(&cgroup_mutex);
+ for_each_subsys(ss, ssid)
+ if (ss_mask & (1 << ssid))
+ cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
+ mutex_lock(&cgroup_mutex);
- for_each_subsys(ss, i) {
- unsigned long bit = 1UL << i;
-
- if (bit & added_mask) {
- /* We're binding this subsystem to this hierarchy */
- BUG_ON(cgroup_css(cgrp, ss));
- BUG_ON(!cgroup_css(cgroup_dummy_top, ss));
- BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top);
-
- rcu_assign_pointer(cgrp->subsys[i],
- cgroup_css(cgroup_dummy_top, ss));
- cgroup_css(cgrp, ss)->cgroup = cgrp;
-
- list_move(&ss->sibling, &root->subsys_list);
- ss->root = root;
- if (ss->bind)
- ss->bind(cgroup_css(cgrp, ss));
-
- /* refcount was already taken, and we're keeping it */
- root->subsys_mask |= bit;
- } else if (bit & removed_mask) {
- /* We're removing this subsystem */
- BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss));
- BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp);
-
- if (ss->bind)
- ss->bind(cgroup_css(cgroup_dummy_top, ss));
-
- cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top;
- RCU_INIT_POINTER(cgrp->subsys[i], NULL);
-
- cgroup_subsys[i]->root = &cgroup_dummy_root;
- list_move(&ss->sibling, &cgroup_dummy_root.subsys_list);
-
- /* subsystem is now free - drop reference on module */
- module_put(ss->module);
- root->subsys_mask &= ~bit;
- }
- }
+ for_each_subsys(ss, ssid) {
+ struct cgroup_root *src_root;
+ struct cgroup_subsys_state *css;
- /*
- * Mark @root has finished binding subsystems. @root->subsys_mask
- * now matches the bound subsystems.
- */
- root->flags |= CGRP_ROOT_SUBSYS_BOUND;
+ if (!(ss_mask & (1 << ssid)))
+ continue;
- return 0;
+ src_root = ss->root;
+ css = cgroup_css(&src_root->cgrp, ss);
-out_put:
- for_each_subsys(ss, i)
- if (pinned & (1 << i))
- module_put(ss->module);
- return ret;
+ WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss));
+
+ RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL);
+ rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css);
+ ss->root = dst_root;
+ css->cgroup = &dst_root->cgrp;
+
+ src_root->cgrp.subsys_mask &= ~(1 << ssid);
+ dst_root->cgrp.subsys_mask |= 1 << ssid;
+
+ if (ss->bind)
+ ss->bind(css);
+ }
+
+ kernfs_activate(dst_root->cgrp.kn);
+ return 0;
}
-static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
+static int cgroup_show_options(struct seq_file *seq,
+ struct kernfs_root *kf_root)
{
- struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_subsys *ss;
+ int ssid;
- mutex_lock(&cgroup_root_mutex);
- for_each_root_subsys(root, ss)
- seq_printf(seq, ",%s", ss->name);
+ for_each_subsys(ss, ssid)
+ if (root->cgrp.subsys_mask & (1 << ssid))
+ seq_printf(seq, ",%s", ss->name);
if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
seq_puts(seq, ",sane_behavior");
if (root->flags & CGRP_ROOT_NOPREFIX)
seq_puts(seq, ",noprefix");
if (root->flags & CGRP_ROOT_XATTR)
seq_puts(seq, ",xattr");
+
+ spin_lock(&release_agent_path_lock);
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
- if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
+ spin_unlock(&release_agent_path_lock);
+
+ if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
- mutex_unlock(&cgroup_root_mutex);
return 0;
}
@@ -1124,9 +1098,6 @@ struct cgroup_sb_opts {
char *name;
/* User explicitly requested empty subsystem */
bool none;
-
- struct cgroupfs_root *new_root;
-
};
/*
@@ -1146,7 +1117,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
BUG_ON(!mutex_is_locked(&cgroup_mutex));
#ifdef CONFIG_CPUSETS
- mask = ~(1UL << cpuset_subsys_id);
+ mask = ~(1UL << cpuset_cgrp_id);
#endif
memset(opts, 0, sizeof(*opts));
@@ -1236,30 +1207,34 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
return -ENOENT;
}
- /*
- * If the 'all' option was specified select all the subsystems,
- * otherwise if 'none', 'name=' and a subsystem name options
- * were not specified, let's default to 'all'
- */
- if (all_ss || (!one_ss && !opts->none && !opts->name))
- for_each_subsys(ss, i)
- if (!ss->disabled)
- set_bit(i, &opts->subsys_mask);
-
/* Consistency checks */
if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
- if (opts->flags & CGRP_ROOT_NOPREFIX) {
- pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
+ if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) ||
+ opts->cpuset_clone_children || opts->release_agent ||
+ opts->name) {
+ pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
return -EINVAL;
}
+ } else {
+ /*
+ * If the 'all' option was specified select all the
+ * subsystems, otherwise if 'none', 'name=' and a subsystem
+ * name options were not specified, let's default to 'all'
+ */
+ if (all_ss || (!one_ss && !opts->none && !opts->name))
+ for_each_subsys(ss, i)
+ if (!ss->disabled)
+ set_bit(i, &opts->subsys_mask);
- if (opts->cpuset_clone_children) {
- pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
+ /*
+ * We either have to specify by name or by subsystems. (So
+ * all empty hierarchies must have a name).
+ */
+ if (!opts->subsys_mask && !opts->name)
return -EINVAL;
- }
}
/*
@@ -1275,21 +1250,13 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
if (opts->subsys_mask && opts->none)
return -EINVAL;
- /*
- * We either have to specify by name or by subsystems. (So all
- * empty hierarchies must have a name).
- */
- if (!opts->subsys_mask && !opts->name)
- return -EINVAL;
-
return 0;
}
-static int cgroup_remount(struct super_block *sb, int *flags, char *data)
+static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
{
int ret = 0;
- struct cgroupfs_root *root = sb->s_fs_info;
- struct cgroup *cgrp = &root->top_cgroup;
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
struct cgroup_sb_opts opts;
unsigned long added_mask, removed_mask;
@@ -1298,21 +1265,20 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
return -EINVAL;
}
- mutex_lock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
/* See what subsystems are wanted */
ret = parse_cgroupfs_options(data, &opts);
if (ret)
goto out_unlock;
- if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+ if (opts.subsys_mask != root->cgrp.subsys_mask || opts.release_agent)
pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
task_tgid_nr(current), current->comm);
- added_mask = opts.subsys_mask & ~root->subsys_mask;
- removed_mask = root->subsys_mask & ~opts.subsys_mask;
+ added_mask = opts.subsys_mask & ~root->cgrp.subsys_mask;
+ removed_mask = root->cgrp.subsys_mask & ~opts.subsys_mask;
/* Don't allow flags or name to change at remount */
if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
@@ -1325,424 +1291,332 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
}
/* remounting is not allowed for populated hierarchies */
- if (root->number_of_cgroups > 1) {
+ if (!list_empty(&root->cgrp.children)) {
ret = -EBUSY;
goto out_unlock;
}
- ret = rebind_subsystems(root, added_mask, removed_mask);
+ ret = rebind_subsystems(root, added_mask);
if (ret)
goto out_unlock;
- if (opts.release_agent)
+ rebind_subsystems(&cgrp_dfl_root, removed_mask);
+
+ if (opts.release_agent) {
+ spin_lock(&release_agent_path_lock);
strcpy(root->release_agent_path, opts.release_agent);
+ spin_unlock(&release_agent_path_lock);
+ }
out_unlock:
kfree(opts.release_agent);
kfree(opts.name);
- mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
return ret;
}
-static const struct super_operations cgroup_ops = {
- .statfs = simple_statfs,
- .drop_inode = generic_delete_inode,
- .show_options = cgroup_show_options,
- .remount_fs = cgroup_remount,
-};
+/*
+ * To reduce the fork() overhead for systems that are not actually using
+ * their cgroups capability, we don't maintain the lists running through
+ * each css_set to its tasks until we see the list actually used - in other
+ * words after the first mount.
+ */
+static bool use_task_css_set_links __read_mostly;
+
+static void cgroup_enable_task_cg_lists(void)
+{
+ struct task_struct *p, *g;
+
+ down_write(&css_set_rwsem);
+
+ if (use_task_css_set_links)
+ goto out_unlock;
+
+ use_task_css_set_links = true;
+
+ /*
+ * We need tasklist_lock because RCU is not safe against
+ * while_each_thread(). Besides, a forking task that has passed
+ * cgroup_post_fork() without seeing use_task_css_set_links = 1
+ * is not guaranteed to have its child immediately visible in the
+ * tasklist if we walk through it with RCU.
+ */
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ WARN_ON_ONCE(!list_empty(&p->cg_list) ||
+ task_css_set(p) != &init_css_set);
+
+ /*
+ * We should check if the process is exiting, otherwise
+ * it will race with cgroup_exit() in that the list
+ * entry won't be deleted though the process has exited.
+ * Do it while holding siglock so that we don't end up
+ * racing against cgroup_exit().
+ */
+ spin_lock_irq(&p->sighand->siglock);
+ if (!(p->flags & PF_EXITING)) {
+ struct css_set *cset = task_css_set(p);
+
+ list_add(&p->cg_list, &cset->tasks);
+ get_css_set(cset);
+ }
+ spin_unlock_irq(&p->sighand->siglock);
+ } while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
+out_unlock:
+ up_write(&css_set_rwsem);
+}
static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
+ atomic_set(&cgrp->refcnt, 1);
INIT_LIST_HEAD(&cgrp->sibling);
INIT_LIST_HEAD(&cgrp->children);
- INIT_LIST_HEAD(&cgrp->files);
INIT_LIST_HEAD(&cgrp->cset_links);
INIT_LIST_HEAD(&cgrp->release_list);
INIT_LIST_HEAD(&cgrp->pidlists);
mutex_init(&cgrp->pidlist_mutex);
cgrp->dummy_css.cgroup = cgrp;
- INIT_LIST_HEAD(&cgrp->event_list);
- spin_lock_init(&cgrp->event_list_lock);
- simple_xattrs_init(&cgrp->xattrs);
}
-static void init_cgroup_root(struct cgroupfs_root *root)
+static void init_cgroup_root(struct cgroup_root *root,
+ struct cgroup_sb_opts *opts)
{
- struct cgroup *cgrp = &root->top_cgroup;
+ struct cgroup *cgrp = &root->cgrp;
- INIT_LIST_HEAD(&root->subsys_list);
INIT_LIST_HEAD(&root->root_list);
- root->number_of_cgroups = 1;
+ atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
- RCU_INIT_POINTER(cgrp->name, &root_cgroup_name);
init_cgroup_housekeeping(cgrp);
idr_init(&root->cgroup_idr);
-}
-static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end)
-{
- int id;
-
- lockdep_assert_held(&cgroup_mutex);
- lockdep_assert_held(&cgroup_root_mutex);
-
- id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, start, end,
- GFP_KERNEL);
- if (id < 0)
- return id;
-
- root->hierarchy_id = id;
- return 0;
-}
-
-static void cgroup_exit_root_id(struct cgroupfs_root *root)
-{
- lockdep_assert_held(&cgroup_mutex);
- lockdep_assert_held(&cgroup_root_mutex);
-
- if (root->hierarchy_id) {
- idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
- root->hierarchy_id = 0;
- }
-}
-
-static int cgroup_test_super(struct super_block *sb, void *data)
-{
- struct cgroup_sb_opts *opts = data;
- struct cgroupfs_root *root = sb->s_fs_info;
-
- /* If we asked for a name then it must match */
- if (opts->name && strcmp(opts->name, root->name))
- return 0;
-
- /*
- * If we asked for subsystems (or explicitly for no
- * subsystems) then they must match
- */
- if ((opts->subsys_mask || opts->none)
- && (opts->subsys_mask != root->subsys_mask))
- return 0;
-
- return 1;
-}
-
-static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
-{
- struct cgroupfs_root *root;
-
- if (!opts->subsys_mask && !opts->none)
- return NULL;
-
- root = kzalloc(sizeof(*root), GFP_KERNEL);
- if (!root)
- return ERR_PTR(-ENOMEM);
-
- init_cgroup_root(root);
-
- /*
- * We need to set @root->subsys_mask now so that @root can be
- * matched by cgroup_test_super() before it finishes
- * initialization; otherwise, competing mounts with the same
- * options may try to bind the same subsystems instead of waiting
- * for the first one leading to unexpected mount errors.
- * SUBSYS_BOUND will be set once actual binding is complete.
- */
- root->subsys_mask = opts->subsys_mask;
root->flags = opts->flags;
if (opts->release_agent)
strcpy(root->release_agent_path, opts->release_agent);
if (opts->name)
strcpy(root->name, opts->name);
if (opts->cpuset_clone_children)
- set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
- return root;
+ set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
-static void cgroup_free_root(struct cgroupfs_root *root)
+static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
{
- if (root) {
- /* hierarhcy ID shoulid already have been released */
- WARN_ON_ONCE(root->hierarchy_id);
-
- idr_destroy(&root->cgroup_idr);
- kfree(root);
- }
-}
+ LIST_HEAD(tmp_links);
+ struct cgroup *root_cgrp = &root->cgrp;
+ struct css_set *cset;
+ int i, ret;
-static int cgroup_set_super(struct super_block *sb, void *data)
-{
- int ret;
- struct cgroup_sb_opts *opts = data;
+ lockdep_assert_held(&cgroup_tree_mutex);
+ lockdep_assert_held(&cgroup_mutex);
- /* If we don't have a new root, we can't set up a new sb */
- if (!opts->new_root)
- return -EINVAL;
+ ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+ if (ret < 0)
+ goto out;
+ root_cgrp->id = ret;
- BUG_ON(!opts->subsys_mask && !opts->none);
+ /*
+ * We're accessing css_set_count without locking css_set_rwsem here,
+ * but that's OK - it can only be increased by someone holding
+ * cgroup_lock, and that's us. The worst that can happen is that we
+ * have some link structures left over
+ */
+ ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
+ if (ret)
+ goto out;
- ret = set_anon_super(sb, NULL);
+ ret = cgroup_init_root_id(root);
if (ret)
- return ret;
+ goto out;
- sb->s_fs_info = opts->new_root;
- opts->new_root->sb = sb;
+ root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
+ KERNFS_ROOT_CREATE_DEACTIVATED,
+ root_cgrp);
+ if (IS_ERR(root->kf_root)) {
+ ret = PTR_ERR(root->kf_root);
+ goto exit_root_id;
+ }
+ root_cgrp->kn = root->kf_root->kn;
- sb->s_blocksize = PAGE_CACHE_SIZE;
- sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
- sb->s_magic = CGROUP_SUPER_MAGIC;
- sb->s_op = &cgroup_ops;
+ ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
+ if (ret)
+ goto destroy_root;
- return 0;
-}
+ ret = rebind_subsystems(root, ss_mask);
+ if (ret)
+ goto destroy_root;
-static int cgroup_get_rootdir(struct super_block *sb)
-{
- static const struct dentry_operations cgroup_dops = {
- .d_iput = cgroup_diput,
- .d_delete = always_delete_dentry,
- };
+ /*
+ * There must be no failure case after here, since rebinding takes
+ * care of subsystems' refcounts, which are explicitly dropped in
+ * the failure exit path.
+ */
+ list_add(&root->root_list, &cgroup_roots);
+ cgroup_root_count++;
- struct inode *inode =
- cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
+ /*
+ * Link the root cgroup in this hierarchy into all the css_set
+ * objects.
+ */
+ down_write(&css_set_rwsem);
+ hash_for_each(css_set_table, i, cset, hlist)
+ link_css_set(&tmp_links, cset, root_cgrp);
+ up_write(&css_set_rwsem);
- if (!inode)
- return -ENOMEM;
+ BUG_ON(!list_empty(&root_cgrp->children));
+ BUG_ON(atomic_read(&root->nr_cgrps) != 1);
- inode->i_fop = &simple_dir_operations;
- inode->i_op = &cgroup_dir_inode_operations;
- /* directories start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
- sb->s_root = d_make_root(inode);
- if (!sb->s_root)
- return -ENOMEM;
- /* for everything else we want ->d_op set */
- sb->s_d_op = &cgroup_dops;
- return 0;
+ kernfs_activate(root_cgrp->kn);
+ ret = 0;
+ goto out;
+
+destroy_root:
+ kernfs_destroy_root(root->kf_root);
+ root->kf_root = NULL;
+exit_root_id:
+ cgroup_exit_root_id(root);
+out:
+ free_cgrp_cset_links(&tmp_links);
+ return ret;
}
static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data)
{
+ struct cgroup_root *root;
struct cgroup_sb_opts opts;
- struct cgroupfs_root *root;
- int ret = 0;
- struct super_block *sb;
- struct cgroupfs_root *new_root;
- struct list_head tmp_links;
- struct inode *inode;
- const struct cred *cred;
+ struct dentry *dentry;
+ int ret;
+ bool new_sb;
- /* First find the desired set of subsystems */
+ /*
+ * The first time anyone tries to mount a cgroup, enable the list
+ * linking each css_set to its tasks and fix up all existing tasks.
+ */
+ if (!use_task_css_set_links)
+ cgroup_enable_task_cg_lists();
+retry:
+ mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
+
+ /* First find the desired set of subsystems */
ret = parse_cgroupfs_options(data, &opts);
- mutex_unlock(&cgroup_mutex);
if (ret)
- goto out_err;
-
- /*
- * Allocate a new cgroup root. We may not need it if we're
- * reusing an existing hierarchy.
- */
- new_root = cgroup_root_from_opts(&opts);
- if (IS_ERR(new_root)) {
- ret = PTR_ERR(new_root);
- goto out_err;
- }
- opts.new_root = new_root;
+ goto out_unlock;
- /* Locate an existing or new sb for this hierarchy */
- sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
- if (IS_ERR(sb)) {
- ret = PTR_ERR(sb);
- cgroup_free_root(opts.new_root);
- goto out_err;
+ /* look for a matching existing root */
+ if (!opts.subsys_mask && !opts.none && !opts.name) {
+ cgrp_dfl_root_visible = true;
+ root = &cgrp_dfl_root;
+ cgroup_get(&root->cgrp);
+ ret = 0;
+ goto out_unlock;
}
- root = sb->s_fs_info;
- BUG_ON(!root);
- if (root == opts.new_root) {
- /* We used the new root structure, so this is a new hierarchy */
- struct cgroup *root_cgrp = &root->top_cgroup;
- struct cgroupfs_root *existing_root;
- int i;
- struct css_set *cset;
-
- BUG_ON(sb->s_root != NULL);
-
- ret = cgroup_get_rootdir(sb);
- if (ret)
- goto drop_new_super;
- inode = sb->s_root->d_inode;
-
- mutex_lock(&inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
-
- root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
- 0, 1, GFP_KERNEL);
- if (root_cgrp->id < 0)
- goto unlock_drop;
-
- /* Check for name clashes with existing mounts */
- ret = -EBUSY;
- if (strlen(root->name))
- for_each_active_root(existing_root)
- if (!strcmp(existing_root->name, root->name))
- goto unlock_drop;
-
- /*
- * We're accessing css_set_count without locking
- * css_set_lock here, but that's OK - it can only be
- * increased by someone holding cgroup_lock, and
- * that's us. The worst that can happen is that we
- * have some link structures left over
- */
- ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
- if (ret)
- goto unlock_drop;
-
- /* ID 0 is reserved for dummy root, 1 for unified hierarchy */
- ret = cgroup_init_root_id(root, 2, 0);
- if (ret)
- goto unlock_drop;
+ for_each_root(root) {
+ bool name_match = false;
- sb->s_root->d_fsdata = root_cgrp;
- root_cgrp->dentry = sb->s_root;
-
- /*
- * We're inside get_sb() and will call lookup_one_len() to
- * create the root files, which doesn't work if SELinux is
- * in use. The following cred dancing somehow works around
- * it. See 2ce9738ba ("cgroupfs: use init_cred when
- * populating new cgroupfs mount") for more details.
- */
- cred = override_creds(&init_cred);
-
- ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
- if (ret)
- goto rm_base_files;
-
- ret = rebind_subsystems(root, root->subsys_mask, 0);
- if (ret)
- goto rm_base_files;
-
- revert_creds(cred);
+ if (root == &cgrp_dfl_root)
+ continue;
/*
- * There must be no failure case after here, since rebinding
- * takes care of subsystems' refcounts, which are explicitly
- * dropped in the failure exit path.
+ * If we asked for a name then it must match. Also, if
+ * name matches but sybsys_mask doesn't, we should fail.
+ * Remember whether name matched.
*/
+ if (opts.name) {
+ if (strcmp(opts.name, root->name))
+ continue;
+ name_match = true;
+ }
- list_add(&root->root_list, &cgroup_roots);
- cgroup_root_count++;
-
- /* Link the top cgroup in this hierarchy into all
- * the css_set objects */
- write_lock(&css_set_lock);
- hash_for_each(css_set_table, i, cset, hlist)
- link_css_set(&tmp_links, cset, root_cgrp);
- write_unlock(&css_set_lock);
-
- free_cgrp_cset_links(&tmp_links);
-
- BUG_ON(!list_empty(&root_cgrp->children));
- BUG_ON(root->number_of_cgroups != 1);
-
- mutex_unlock(&cgroup_root_mutex);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- } else {
/*
- * We re-used an existing hierarchy - the new root (if
- * any) is not needed
+ * If we asked for subsystems (or explicitly for no
+ * subsystems) then they must match.
*/
- cgroup_free_root(opts.new_root);
+ if ((opts.subsys_mask || opts.none) &&
+ (opts.subsys_mask != root->cgrp.subsys_mask)) {
+ if (!name_match)
+ continue;
+ ret = -EBUSY;
+ goto out_unlock;
+ }
if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) {
if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
ret = -EINVAL;
- goto drop_new_super;
+ goto out_unlock;
} else {
pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
}
}
- }
-
- kfree(opts.release_agent);
- kfree(opts.name);
- return dget(sb->s_root);
-
- rm_base_files:
- free_cgrp_cset_links(&tmp_links);
- cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false);
- revert_creds(cred);
- unlock_drop:
- cgroup_exit_root_id(root);
- mutex_unlock(&cgroup_root_mutex);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
- drop_new_super:
- deactivate_locked_super(sb);
- out_err:
- kfree(opts.release_agent);
- kfree(opts.name);
- return ERR_PTR(ret);
-}
-static void cgroup_kill_sb(struct super_block *sb) {
- struct cgroupfs_root *root = sb->s_fs_info;
- struct cgroup *cgrp = &root->top_cgroup;
- struct cgrp_cset_link *link, *tmp_link;
- int ret;
-
- BUG_ON(!root);
-
- BUG_ON(root->number_of_cgroups != 1);
- BUG_ON(!list_empty(&cgrp->children));
-
- mutex_lock(&cgrp->dentry->d_inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
+ /*
+ * A root's lifetime is governed by its root cgroup. Zero
+ * ref indicate that the root is being destroyed. Wait for
+ * destruction to complete so that the subsystems are free.
+ * We can use wait_queue for the wait but this path is
+ * super cold. Let's just sleep for a bit and retry.
+ */
+ if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+ kfree(opts.release_agent);
+ kfree(opts.name);
+ msleep(10);
+ goto retry;
+ }
- /* Rebind all subsystems back to the default hierarchy */
- if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
- ret = rebind_subsystems(root, 0, root->subsys_mask);
- /* Shouldn't be able to fail ... */
- BUG_ON(ret);
+ ret = 0;
+ goto out_unlock;
}
/*
- * Release all the links from cset_links to this hierarchy's
- * root cgroup
+ * No such thing, create a new one. name= matching without subsys
+ * specification is allowed for already existing hierarchies but we
+ * can't create new one without subsys specification.
*/
- write_lock(&css_set_lock);
-
- list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
- list_del(&link->cset_link);
- list_del(&link->cgrp_link);
- kfree(link);
+ if (!opts.subsys_mask && !opts.none) {
+ ret = -EINVAL;
+ goto out_unlock;
}
- write_unlock(&css_set_lock);
- if (!list_empty(&root->root_list)) {
- list_del(&root->root_list);
- cgroup_root_count--;
+ root = kzalloc(sizeof(*root), GFP_KERNEL);
+ if (!root) {
+ ret = -ENOMEM;
+ goto out_unlock;
}
- cgroup_exit_root_id(root);
+ init_cgroup_root(root, &opts);
+
+ ret = cgroup_setup_root(root, opts.subsys_mask);
+ if (ret)
+ cgroup_free_root(root);
- mutex_unlock(&cgroup_root_mutex);
+out_unlock:
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
+
+ kfree(opts.release_agent);
+ kfree(opts.name);
- simple_xattrs_free(&cgrp->xattrs);
+ if (ret)
+ return ERR_PTR(ret);
- kill_litter_super(sb);
- cgroup_free_root(root);
+ dentry = kernfs_mount(fs_type, flags, root->kf_root, &new_sb);
+ if (IS_ERR(dentry) || !new_sb)
+ cgroup_put(&root->cgrp);
+ return dentry;
+}
+
+static void cgroup_kill_sb(struct super_block *sb)
+{
+ struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
+
+ cgroup_put(&root->cgrp);
+ kernfs_kill_sb(sb);
}
static struct file_system_type cgroup_fs_type = {
@@ -1754,57 +1628,6 @@ static struct file_system_type cgroup_fs_type = {
static struct kobject *cgroup_kobj;
/**
- * cgroup_path - generate the path of a cgroup
- * @cgrp: the cgroup in question
- * @buf: the buffer to write the path into
- * @buflen: the length of the buffer
- *
- * Writes path of cgroup into buf. Returns 0 on success, -errno on error.
- *
- * We can't generate cgroup path using dentry->d_name, as accessing
- * dentry->name must be protected by irq-unsafe dentry->d_lock or parent
- * inode's i_mutex, while on the other hand cgroup_path() can be called
- * with some irq-safe spinlocks held.
- */
-int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
-{
- int ret = -ENAMETOOLONG;
- char *start;
-
- if (!cgrp->parent) {
- if (strlcpy(buf, "/", buflen) >= buflen)
- return -ENAMETOOLONG;
- return 0;
- }
-
- start = buf + buflen - 1;
- *start = '\0';
-
- rcu_read_lock();
- do {
- const char *name = cgroup_name(cgrp);
- int len;
-
- len = strlen(name);
- if ((start -= len) < buf)
- goto out;
- memcpy(start, name, len);
-
- if (--start < buf)
- goto out;
- *start = '/';
-
- cgrp = cgrp->parent;
- } while (cgrp->parent);
- ret = 0;
- memmove(buf, start, buf + buflen - start);
-out:
- rcu_read_unlock();
- return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_path);
-
-/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
* @buf: the buffer to write the path into
@@ -1815,49 +1638,55 @@ EXPORT_SYMBOL_GPL(cgroup_path);
* function grabs cgroup_mutex and shouldn't be used inside locks used by
* cgroup controller callbacks.
*
- * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short.
+ * Return value is the same as kernfs_path().
*/
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
+char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
struct cgroup *cgrp;
- int hierarchy_id = 1, ret = 0;
-
- if (buflen < 2)
- return -ENAMETOOLONG;
+ int hierarchy_id = 1;
+ char *path = NULL;
mutex_lock(&cgroup_mutex);
+ down_read(&css_set_rwsem);
root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
if (root) {
cgrp = task_cgroup_from_root(task, root);
- ret = cgroup_path(cgrp, buf, buflen);
+ path = cgroup_path(cgrp, buf, buflen);
} else {
/* if no hierarchy exists, everyone is in "/" */
- memcpy(buf, "/", 2);
+ if (strlcpy(buf, "/", buflen) < buflen)
+ path = buf;
}
+ up_read(&css_set_rwsem);
mutex_unlock(&cgroup_mutex);
- return ret;
+ return path;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
-/*
- * Control Group taskset
- */
-struct task_and_cgroup {
- struct task_struct *task;
- struct cgroup *cgrp;
- struct css_set *cset;
-};
-
+/* used to track tasks and other necessary states during migration */
struct cgroup_taskset {
- struct task_and_cgroup single;
- struct flex_array *tc_array;
- int tc_array_len;
- int idx;
- struct cgroup *cur_cgrp;
+ /* the src and dst cset list running through cset->mg_node */
+ struct list_head src_csets;
+ struct list_head dst_csets;
+
+ /*
+ * Fields for cgroup_taskset_*() iteration.
+ *
+ * Before migration is committed, the target migration tasks are on
+ * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of
+ * the csets on ->dst_csets. ->csets point to either ->src_csets
+ * or ->dst_csets depending on whether migration is committed.
+ *
+ * ->cur_csets and ->cur_task point to the current task position
+ * during iteration.
+ */
+ struct list_head *csets;
+ struct css_set *cur_cset;
+ struct task_struct *cur_task;
};
/**
@@ -1868,15 +1697,11 @@ struct cgroup_taskset {
*/
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
{
- if (tset->tc_array) {
- tset->idx = 0;
- return cgroup_taskset_next(tset);
- } else {
- tset->cur_cgrp = tset->single.cgrp;
- return tset->single.task;
- }
+ tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
+ tset->cur_task = NULL;
+
+ return cgroup_taskset_next(tset);
}
-EXPORT_SYMBOL_GPL(cgroup_taskset_first);
/**
* cgroup_taskset_next - iterate to the next task in taskset
@@ -1887,48 +1712,36 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_first);
*/
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
{
- struct task_and_cgroup *tc;
+ struct css_set *cset = tset->cur_cset;
+ struct task_struct *task = tset->cur_task;
- if (!tset->tc_array || tset->idx >= tset->tc_array_len)
- return NULL;
+ while (&cset->mg_node != tset->csets) {
+ if (!task)
+ task = list_first_entry(&cset->mg_tasks,
+ struct task_struct, cg_list);
+ else
+ task = list_next_entry(task, cg_list);
- tc = flex_array_get(tset->tc_array, tset->idx++);
- tset->cur_cgrp = tc->cgrp;
- return tc->task;
-}
-EXPORT_SYMBOL_GPL(cgroup_taskset_next);
+ if (&task->cg_list != &cset->mg_tasks) {
+ tset->cur_cset = cset;
+ tset->cur_task = task;
+ return task;
+ }
-/**
- * cgroup_taskset_cur_css - return the matching css for the current task
- * @tset: taskset of interest
- * @subsys_id: the ID of the target subsystem
- *
- * Return the css for the current (last returned) task of @tset for
- * subsystem specified by @subsys_id. This function must be preceded by
- * either cgroup_taskset_first() or cgroup_taskset_next().
- */
-struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset,
- int subsys_id)
-{
- return cgroup_css(tset->cur_cgrp, cgroup_subsys[subsys_id]);
-}
-EXPORT_SYMBOL_GPL(cgroup_taskset_cur_css);
+ cset = list_next_entry(cset, mg_node);
+ task = NULL;
+ }
-/**
- * cgroup_taskset_size - return the number of tasks in taskset
- * @tset: taskset of interest
- */
-int cgroup_taskset_size(struct cgroup_taskset *tset)
-{
- return tset->tc_array ? tset->tc_array_len : 1;
+ return NULL;
}
-EXPORT_SYMBOL_GPL(cgroup_taskset_size);
-
-/*
+/**
* cgroup_task_migrate - move a task from one cgroup to another.
+ * @old_cgrp; the cgroup @tsk is being migrated from
+ * @tsk: the task being migrated
+ * @new_cset: the new css_set @tsk is being attached to
*
- * Must be called with cgroup_mutex and threadgroup locked.
+ * Must be called with cgroup_mutex, threadgroup and css_set_rwsem locked.
*/
static void cgroup_task_migrate(struct cgroup *old_cgrp,
struct task_struct *tsk,
@@ -1936,6 +1749,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
{
struct css_set *old_cset;
+ lockdep_assert_held(&cgroup_mutex);
+ lockdep_assert_held(&css_set_rwsem);
+
/*
* We are synchronized through threadgroup_lock() against PF_EXITING
* setting such that we can't race against cgroup_exit() changing the
@@ -1944,15 +1760,16 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
WARN_ON_ONCE(tsk->flags & PF_EXITING);
old_cset = task_css_set(tsk);
- task_lock(tsk);
+ get_css_set(new_cset);
rcu_assign_pointer(tsk->cgroups, new_cset);
- task_unlock(tsk);
- /* Update the css_set linked lists if we're using them */
- write_lock(&css_set_lock);
- if (!list_empty(&tsk->cg_list))
- list_move(&tsk->cg_list, &new_cset->tasks);
- write_unlock(&css_set_lock);
+ /*
+ * Use move_tail so that cgroup_taskset_first() still returns the
+ * leader after migration. This works because cgroup_migrate()
+ * ensures that the dst_cset of the leader is the first on the
+ * tset's dst_csets list.
+ */
+ list_move_tail(&tsk->cg_list, &new_cset->mg_tasks);
/*
* We just gained a reference on old_cset by taking it from the
@@ -1960,178 +1777,291 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
* we're safe to drop it here; it will be freed under RCU.
*/
set_bit(CGRP_RELEASABLE, &old_cgrp->flags);
- put_css_set(old_cset);
+ put_css_set_locked(old_cset, false);
}
/**
- * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
- * @cgrp: the cgroup to attach to
- * @tsk: the task or the leader of the threadgroup to be attached
- * @threadgroup: attach the whole threadgroup?
+ * cgroup_migrate_finish - cleanup after attach
+ * @preloaded_csets: list of preloaded css_sets
*
- * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of @tsk or each thread in the threadgroup individually in turn.
+ * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See
+ * those functions for details.
*/
-static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
- bool threadgroup)
-{
- int retval, i, group_size;
- struct cgroup_subsys *ss, *failed_ss = NULL;
- struct cgroupfs_root *root = cgrp->root;
- /* threadgroup list cursor and array */
- struct task_struct *leader = tsk;
- struct task_and_cgroup *tc;
- struct flex_array *group;
- struct cgroup_taskset tset = { };
+static void cgroup_migrate_finish(struct list_head *preloaded_csets)
+{
+ struct css_set *cset, *tmp_cset;
- /*
- * step 0: in order to do expensive, possibly blocking operations for
- * every thread, we cannot iterate the thread group list, since it needs
- * rcu or tasklist locked. instead, build an array of all threads in the
- * group - group_rwsem prevents new threads from appearing, and if
- * threads exit, this will just be an over-estimate.
- */
- if (threadgroup)
- group_size = get_nr_threads(tsk);
- else
- group_size = 1;
- /* flex_array supports very large thread-groups better than kmalloc. */
- group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
- if (!group)
- return -ENOMEM;
- /* pre-allocate to guarantee space while iterating in rcu read-side. */
- retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
- if (retval)
- goto out_free_group_list;
+ lockdep_assert_held(&cgroup_mutex);
+
+ down_write(&css_set_rwsem);
+ list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
+ cset->mg_src_cgrp = NULL;
+ cset->mg_dst_cset = NULL;
+ list_del_init(&cset->mg_preload_node);
+ put_css_set_locked(cset, false);
+ }
+ up_write(&css_set_rwsem);
+}
+
+/**
+ * cgroup_migrate_add_src - add a migration source css_set
+ * @src_cset: the source css_set to add
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded css_sets
+ *
+ * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin
+ * @src_cset and add it to @preloaded_csets, which should later be cleaned
+ * up by cgroup_migrate_finish().
+ *
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process. Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
+ */
+static void cgroup_migrate_add_src(struct css_set *src_cset,
+ struct cgroup *dst_cgrp,
+ struct list_head *preloaded_csets)
+{
+ struct cgroup *src_cgrp;
+
+ lockdep_assert_held(&cgroup_mutex);
+ lockdep_assert_held(&css_set_rwsem);
+
+ src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
+
+ /* nothing to do if this cset already belongs to the cgroup */
+ if (src_cgrp == dst_cgrp)
+ return;
+
+ if (!list_empty(&src_cset->mg_preload_node))
+ return;
+
+ WARN_ON(src_cset->mg_src_cgrp);
+ WARN_ON(!list_empty(&src_cset->mg_tasks));
+ WARN_ON(!list_empty(&src_cset->mg_node));
+
+ src_cset->mg_src_cgrp = src_cgrp;
+ get_css_set(src_cset);
+ list_add(&src_cset->mg_preload_node, preloaded_csets);
+}
+
+/**
+ * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded source css_sets
+ *
+ * Tasks are about to be moved to @dst_cgrp and all the source css_sets
+ * have been preloaded to @preloaded_csets. This function looks up and
+ * pins all destination css_sets, links each to its source, and put them on
+ * @preloaded_csets.
+ *
+ * This function must be called after cgroup_migrate_add_src() has been
+ * called on each migration source css_set. After migration is performed
+ * using cgroup_migrate(), cgroup_migrate_finish() must be called on
+ * @preloaded_csets.
+ */
+static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
+ struct list_head *preloaded_csets)
+{
+ LIST_HEAD(csets);
+ struct css_set *src_cset;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ /* look up the dst cset for each src cset and link it to src */
+ list_for_each_entry(src_cset, preloaded_csets, mg_preload_node) {
+ struct css_set *dst_cset;
+
+ dst_cset = find_css_set(src_cset, dst_cgrp);
+ if (!dst_cset)
+ goto err;
+
+ WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
+ src_cset->mg_dst_cset = dst_cset;
+
+ if (list_empty(&dst_cset->mg_preload_node))
+ list_add(&dst_cset->mg_preload_node, &csets);
+ else
+ put_css_set(dst_cset, false);
+ }
+
+ list_splice(&csets, preloaded_csets);
+ return 0;
+err:
+ cgroup_migrate_finish(&csets);
+ return -ENOMEM;
+}
+
+/**
+ * cgroup_migrate - migrate a process or task to a cgroup
+ * @cgrp: the destination cgroup
+ * @leader: the leader of the process or the task to migrate
+ * @threadgroup: whether @leader points to the whole process or a single task
+ *
+ * Migrate a process or task denoted by @leader to @cgrp. If migrating a
+ * process, the caller must be holding threadgroup_lock of @leader. The
+ * caller is also responsible for invoking cgroup_migrate_add_src() and
+ * cgroup_migrate_prepare_dst() on the targets before invoking this
+ * function and following up with cgroup_migrate_finish().
+ *
+ * As long as a controller's ->can_attach() doesn't fail, this function is
+ * guaranteed to succeed. This means that, excluding ->can_attach()
+ * failure, when migrating multiple targets, the success or failure can be
+ * decided for all targets by invoking group_migrate_prepare_dst() before
+ * actually starting migrating.
+ */
+static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
+ bool threadgroup)
+{
+ struct cgroup_taskset tset = {
+ .src_csets = LIST_HEAD_INIT(tset.src_csets),
+ .dst_csets = LIST_HEAD_INIT(tset.dst_csets),
+ .csets = &tset.src_csets,
+ };
+ struct cgroup_subsys_state *css, *failed_css = NULL;
+ struct css_set *cset, *tmp_cset;
+ struct task_struct *task, *tmp_task;
+ int i, ret;
- i = 0;
/*
* Prevent freeing of tasks while we take a snapshot. Tasks that are
* already PF_EXITING could be freed from underneath us unless we
* take an rcu_read_lock.
*/
+ down_write(&css_set_rwsem);
rcu_read_lock();
+ task = leader;
do {
- struct task_and_cgroup ent;
+ /* @task either already exited or can't exit until the end */
+ if (task->flags & PF_EXITING)
+ goto next;
- /* @tsk either already exited or can't exit until the end */
- if (tsk->flags & PF_EXITING)
+ /* leave @task alone if post_fork() hasn't linked it yet */
+ if (list_empty(&task->cg_list))
goto next;
- /* as per above, nr_threads may decrease, but not increase. */
- BUG_ON(i >= group_size);
- ent.task = tsk;
- ent.cgrp = task_cgroup_from_root(tsk, root);
- /* nothing to do if this task is already in the cgroup */
- if (ent.cgrp == cgrp)
+ cset = task_css_set(task);
+ if (!cset->mg_src_cgrp)
goto next;
+
/*
- * saying GFP_ATOMIC has no effect here because we did prealloc
- * earlier, but it's good form to communicate our expectations.
+ * cgroup_taskset_first() must always return the leader.
+ * Take care to avoid disturbing the ordering.
*/
- retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
- BUG_ON(retval != 0);
- i++;
+ list_move_tail(&task->cg_list, &cset->mg_tasks);
+ if (list_empty(&cset->mg_node))
+ list_add_tail(&cset->mg_node, &tset.src_csets);
+ if (list_empty(&cset->mg_dst_cset->mg_node))
+ list_move_tail(&cset->mg_dst_cset->mg_node,
+ &tset.dst_csets);
next:
if (!threadgroup)
break;
- } while_each_thread(leader, tsk);
+ } while_each_thread(leader, task);
rcu_read_unlock();
- /* remember the number of threads in the array for later. */
- group_size = i;
- tset.tc_array = group;
- tset.tc_array_len = group_size;
+ up_write(&css_set_rwsem);
/* methods shouldn't be called if no task is actually migrating */
- retval = 0;
- if (!group_size)
- goto out_free_group_list;
-
- /*
- * step 1: check that we can legitimately attach to the cgroup.
- */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
+ if (list_empty(&tset.src_csets))
+ return 0;
- if (ss->can_attach) {
- retval = ss->can_attach(css, &tset);
- if (retval) {
- failed_ss = ss;
+ /* check that we can legitimately attach to the cgroup */
+ for_each_css(css, i, cgrp) {
+ if (css->ss->can_attach) {
+ ret = css->ss->can_attach(css, &tset);
+ if (ret) {
+ failed_css = css;
goto out_cancel_attach;
}
}
}
/*
- * step 2: make sure css_sets exist for all threads to be migrated.
- * we use find_css_set, which allocates a new one if necessary.
+ * Now that we're guaranteed success, proceed to move all tasks to
+ * the new cgroup. There are no failure cases after here, so this
+ * is the commit point.
*/
- for (i = 0; i < group_size; i++) {
- struct css_set *old_cset;
-
- tc = flex_array_get(group, i);
- old_cset = task_css_set(tc->task);
- tc->cset = find_css_set(old_cset, cgrp);
- if (!tc->cset) {
- retval = -ENOMEM;
- goto out_put_css_set_refs;
- }
+ down_write(&css_set_rwsem);
+ list_for_each_entry(cset, &tset.src_csets, mg_node) {
+ list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list)
+ cgroup_task_migrate(cset->mg_src_cgrp, task,
+ cset->mg_dst_cset);
}
+ up_write(&css_set_rwsem);
/*
- * step 3: now that we're guaranteed success wrt the css_sets,
- * proceed to move all tasks to the new cgroup. There are no
- * failure cases after here, so this is the commit point.
+ * Migration is committed, all target tasks are now on dst_csets.
+ * Nothing is sensitive to fork() after this point. Notify
+ * controllers that migration is complete.
*/
- for (i = 0; i < group_size; i++) {
- tc = flex_array_get(group, i);
- cgroup_task_migrate(tc->cgrp, tc->task, tc->cset);
- }
- /* nothing is sensitive to fork() after this point. */
+ tset.csets = &tset.dst_csets;
- /*
- * step 4: do subsystem attach callbacks.
- */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
+ for_each_css(css, i, cgrp)
+ if (css->ss->attach)
+ css->ss->attach(css, &tset);
- if (ss->attach)
- ss->attach(css, &tset);
- }
+ ret = 0;
+ goto out_release_tset;
- /*
- * step 5: success! and cleanup
- */
- retval = 0;
-out_put_css_set_refs:
- if (retval) {
- for (i = 0; i < group_size; i++) {
- tc = flex_array_get(group, i);
- if (!tc->cset)
- break;
- put_css_set(tc->cset);
- }
- }
out_cancel_attach:
- if (retval) {
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (ss == failed_ss)
- break;
- if (ss->cancel_attach)
- ss->cancel_attach(css, &tset);
- }
+ for_each_css(css, i, cgrp) {
+ if (css == failed_css)
+ break;
+ if (css->ss->cancel_attach)
+ css->ss->cancel_attach(css, &tset);
}
-out_free_group_list:
- flex_array_free(group);
- return retval;
+out_release_tset:
+ down_write(&css_set_rwsem);
+ list_splice_init(&tset.dst_csets, &tset.src_csets);
+ list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) {
+ list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
+ list_del_init(&cset->mg_node);
+ }
+ up_write(&css_set_rwsem);
+ return ret;
+}
+
+/**
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
+ * @dst_cgrp: the cgroup to attach to
+ * @leader: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
+ *
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
+ */
+static int cgroup_attach_task(struct cgroup *dst_cgrp,
+ struct task_struct *leader, bool threadgroup)
+{
+ LIST_HEAD(preloaded_csets);
+ struct task_struct *task;
+ int ret;
+
+ /* look up all src csets */
+ down_read(&css_set_rwsem);
+ rcu_read_lock();
+ task = leader;
+ do {
+ cgroup_migrate_add_src(task_css_set(task), dst_cgrp,
+ &preloaded_csets);
+ if (!threadgroup)
+ break;
+ } while_each_thread(leader, task);
+ rcu_read_unlock();
+ up_read(&css_set_rwsem);
+
+ /* prepare dst csets and commit */
+ ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
+ if (!ret)
+ ret = cgroup_migrate(dst_cgrp, leader, threadgroup);
+
+ cgroup_migrate_finish(&preloaded_csets);
+ return ret;
}
/*
* Find the task_struct of the task to attach by vpid and pass it along to the
* function to attach either it or all tasks in its threadgroup. Will lock
- * cgroup_mutex and threadgroup; may take task_lock of task.
+ * cgroup_mutex and threadgroup.
*/
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
{
@@ -2148,7 +2078,7 @@ retry_find_task:
tsk = find_task_by_vpid(pid);
if (!tsk) {
rcu_read_unlock();
- ret= -ESRCH;
+ ret = -ESRCH;
goto out_unlock_cgroup;
}
/*
@@ -2216,12 +2146,19 @@ out_unlock_cgroup:
*/
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
{
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
int retval = 0;
mutex_lock(&cgroup_mutex);
- for_each_active_root(root) {
- struct cgroup *from_cgrp = task_cgroup_from_root(from, root);
+ for_each_root(root) {
+ struct cgroup *from_cgrp;
+
+ if (root == &cgrp_dfl_root)
+ continue;
+
+ down_read(&css_set_rwsem);
+ from_cgrp = task_cgroup_from_root(from, root);
+ up_read(&css_set_rwsem);
retval = cgroup_attach_task(from_cgrp, tsk, false);
if (retval)
@@ -2246,24 +2183,24 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
}
static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
- struct cftype *cft, const char *buffer)
+ struct cftype *cft, char *buffer)
{
- BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX);
- if (strlen(buffer) >= PATH_MAX)
- return -EINVAL;
+ struct cgroup_root *root = css->cgroup->root;
+
+ BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
if (!cgroup_lock_live_group(css->cgroup))
return -ENODEV;
- mutex_lock(&cgroup_root_mutex);
- strcpy(css->cgroup->root->release_agent_path, buffer);
- mutex_unlock(&cgroup_root_mutex);
+ spin_lock(&release_agent_path_lock);
+ strlcpy(root->release_agent_path, buffer,
+ sizeof(root->release_agent_path));
+ spin_unlock(&release_agent_path_lock);
mutex_unlock(&cgroup_mutex);
return 0;
}
-static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_release_agent_show(struct seq_file *seq, void *v)
{
- struct cgroup *cgrp = css->cgroup;
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
@@ -2273,264 +2210,114 @@ static int cgroup_release_agent_show(struct cgroup_subsys_state *css,
return 0;
}
-static int cgroup_sane_behavior_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
{
- seq_printf(seq, "%d\n", cgroup_sane_behavior(css->cgroup));
- return 0;
-}
-
-/* A buffer size big enough for numbers or short strings */
-#define CGROUP_LOCAL_BUFFER_SIZE 64
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
-static ssize_t cgroup_write_X64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- const char __user *userbuf, size_t nbytes,
- loff_t *unused_ppos)
-{
- char buffer[CGROUP_LOCAL_BUFFER_SIZE];
- int retval = 0;
- char *end;
-
- if (!nbytes)
- return -EINVAL;
- if (nbytes >= sizeof(buffer))
- return -E2BIG;
- if (copy_from_user(buffer, userbuf, nbytes))
- return -EFAULT;
-
- buffer[nbytes] = 0; /* nul-terminate */
- if (cft->write_u64) {
- u64 val = simple_strtoull(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
- retval = cft->write_u64(css, cft, val);
- } else {
- s64 val = simple_strtoll(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
- retval = cft->write_s64(css, cft, val);
- }
- if (!retval)
- retval = nbytes;
- return retval;
+ seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
+ return 0;
}
-static ssize_t cgroup_write_string(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- const char __user *userbuf, size_t nbytes,
- loff_t *unused_ppos)
+static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off)
{
- char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
- int retval = 0;
- size_t max_bytes = cft->max_write_len;
- char *buffer = local_buffer;
-
- if (!max_bytes)
- max_bytes = sizeof(local_buffer) - 1;
- if (nbytes >= max_bytes)
- return -E2BIG;
- /* Allocate a dynamic buffer if we need one */
- if (nbytes >= sizeof(local_buffer)) {
- buffer = kmalloc(nbytes + 1, GFP_KERNEL);
- if (buffer == NULL)
- return -ENOMEM;
- }
- if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
- retval = -EFAULT;
- goto out;
- }
-
- buffer[nbytes] = 0; /* nul-terminate */
- retval = cft->write_string(css, cft, strstrip(buffer));
- if (!retval)
- retval = nbytes;
-out:
- if (buffer != local_buffer)
- kfree(buffer);
- return retval;
-}
+ struct cgroup *cgrp = of->kn->parent->priv;
+ struct cftype *cft = of->kn->priv;
+ struct cgroup_subsys_state *css;
+ int ret;
-static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
- size_t nbytes, loff_t *ppos)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
+ /*
+ * kernfs guarantees that a file isn't deleted with operations in
+ * flight, which means that the matching css is and stays alive and
+ * doesn't need to be pinned. The RCU locking is not necessary
+ * either. It's just for the convenience of using cgroup_css().
+ */
+ rcu_read_lock();
+ css = cgroup_css(cgrp, cft->ss);
+ rcu_read_unlock();
- if (cft->write)
- return cft->write(css, cft, file, buf, nbytes, ppos);
- if (cft->write_u64 || cft->write_s64)
- return cgroup_write_X64(css, cft, file, buf, nbytes, ppos);
- if (cft->write_string)
- return cgroup_write_string(css, cft, file, buf, nbytes, ppos);
- if (cft->trigger) {
- int ret = cft->trigger(css, (unsigned int)cft->private);
- return ret ? ret : nbytes;
+ if (cft->write_string) {
+ ret = cft->write_string(css, cft, strstrip(buf));
+ } else if (cft->write_u64) {
+ unsigned long long v;
+ ret = kstrtoull(buf, 0, &v);
+ if (!ret)
+ ret = cft->write_u64(css, cft, v);
+ } else if (cft->write_s64) {
+ long long v;
+ ret = kstrtoll(buf, 0, &v);
+ if (!ret)
+ ret = cft->write_s64(css, cft, v);
+ } else if (cft->trigger) {
+ ret = cft->trigger(css, (unsigned int)cft->private);
+ } else {
+ ret = -EINVAL;
}
- return -EINVAL;
-}
-static ssize_t cgroup_read_u64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes, loff_t *ppos)
-{
- char tmp[CGROUP_LOCAL_BUFFER_SIZE];
- u64 val = cft->read_u64(css, cft);
- int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
-
- return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+ return ret ?: nbytes;
}
-static ssize_t cgroup_read_s64(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes, loff_t *ppos)
+static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
{
- char tmp[CGROUP_LOCAL_BUFFER_SIZE];
- s64 val = cft->read_s64(css, cft);
- int len = sprintf(tmp, "%lld\n", (long long) val);
-
- return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+ return seq_cft(seq)->seq_start(seq, ppos);
}
-static ssize_t cgroup_file_read(struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
+static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
-
- if (cft->read)
- return cft->read(css, cft, file, buf, nbytes, ppos);
- if (cft->read_u64)
- return cgroup_read_u64(css, cft, file, buf, nbytes, ppos);
- if (cft->read_s64)
- return cgroup_read_s64(css, cft, file, buf, nbytes, ppos);
- return -EINVAL;
+ return seq_cft(seq)->seq_next(seq, v, ppos);
}
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
-static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
+static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
{
- struct seq_file *sf = cb->state;
- return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
+ seq_cft(seq)->seq_stop(seq, v);
}
static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
- struct cfent *cfe = m->private;
- struct cftype *cft = cfe->type;
- struct cgroup_subsys_state *css = cfe->css;
-
- if (cft->read_map) {
- struct cgroup_map_cb cb = {
- .fill = cgroup_map_add,
- .state = m,
- };
- return cft->read_map(css, cft, &cb);
- }
- return cft->read_seq_string(css, cft, m);
-}
-
-static const struct file_operations cgroup_seqfile_operations = {
- .read = seq_read,
- .write = cgroup_file_write,
- .llseek = seq_lseek,
- .release = cgroup_file_release,
-};
-
-static int cgroup_file_open(struct inode *inode, struct file *file)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent);
- struct cgroup_subsys_state *css;
- int err;
+ struct cftype *cft = seq_cft(m);
+ struct cgroup_subsys_state *css = seq_css(m);
- err = generic_file_open(inode, file);
- if (err)
- return err;
+ if (cft->seq_show)
+ return cft->seq_show(m, arg);
- /*
- * If the file belongs to a subsystem, pin the css. Will be
- * unpinned either on open failure or release. This ensures that
- * @css stays alive for all file operations.
- */
- rcu_read_lock();
- css = cgroup_css(cgrp, cft->ss);
- if (cft->ss && !css_tryget(css))
- css = NULL;
- rcu_read_unlock();
-
- if (!css)
- return -ENODEV;
-
- /*
- * @cfe->css is used by read/write/close to determine the
- * associated css. @file->private_data would be a better place but
- * that's already used by seqfile. Multiple accessors may use it
- * simultaneously which is okay as the association never changes.
- */
- WARN_ON_ONCE(cfe->css && cfe->css != css);
- cfe->css = css;
-
- if (cft->read_map || cft->read_seq_string) {
- file->f_op = &cgroup_seqfile_operations;
- err = single_open(file, cgroup_seqfile_show, cfe);
- } else if (cft->open) {
- err = cft->open(inode, file);
- }
-
- if (css->ss && err)
- css_put(css);
- return err;
+ if (cft->read_u64)
+ seq_printf(m, "%llu\n", cft->read_u64(css, cft));
+ else if (cft->read_s64)
+ seq_printf(m, "%lld\n", cft->read_s64(css, cft));
+ else
+ return -EINVAL;
+ return 0;
}
-static int cgroup_file_release(struct inode *inode, struct file *file)
-{
- struct cfent *cfe = __d_cfe(file->f_dentry);
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cgroup_subsys_state *css = cfe->css;
- int ret = 0;
+static struct kernfs_ops cgroup_kf_single_ops = {
+ .atomic_write_len = PAGE_SIZE,
+ .write = cgroup_file_write,
+ .seq_show = cgroup_seqfile_show,
+};
- if (cft->release)
- ret = cft->release(inode, file);
- if (css->ss)
- css_put(css);
- if (file->f_op == &cgroup_seqfile_operations)
- single_release(inode, file);
- return ret;
-}
+static struct kernfs_ops cgroup_kf_ops = {
+ .atomic_write_len = PAGE_SIZE,
+ .write = cgroup_file_write,
+ .seq_start = cgroup_seqfile_start,
+ .seq_next = cgroup_seqfile_next,
+ .seq_stop = cgroup_seqfile_stop,
+ .seq_show = cgroup_seqfile_show,
+};
/*
* cgroup_rename - Only allow simple rename of directories in place.
*/
-static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+ const char *new_name_str)
{
+ struct cgroup *cgrp = kn->priv;
int ret;
- struct cgroup_name *name, *old_name;
- struct cgroup *cgrp;
-
- /*
- * It's convinient to use parent dir's i_mutex to protected
- * cgrp->name.
- */
- lockdep_assert_held(&old_dir->i_mutex);
- if (!S_ISDIR(old_dentry->d_inode->i_mode))
+ if (kernfs_type(kn) != KERNFS_DIR)
return -ENOTDIR;
- if (new_dentry->d_inode)
- return -EEXIST;
- if (old_dir != new_dir)
+ if (kn->parent != new_parent)
return -EIO;
- cgrp = __d_cgrp(old_dentry);
-
/*
* This isn't a proper migration and its usefulness is very
* limited. Disallow if sane_behavior.
@@ -2538,229 +2325,61 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
if (cgroup_sane_behavior(cgrp))
return -EPERM;
- name = cgroup_alloc_name(new_dentry);
- if (!name)
- return -ENOMEM;
-
- ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry);
- if (ret) {
- kfree(name);
- return ret;
- }
-
- old_name = rcu_dereference_protected(cgrp->name, true);
- rcu_assign_pointer(cgrp->name, name);
-
- kfree_rcu(old_name, rcu_head);
- return 0;
-}
-
-static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
-{
- if (S_ISDIR(dentry->d_inode->i_mode))
- return &__d_cgrp(dentry)->xattrs;
- else
- return &__d_cfe(dentry)->xattrs;
-}
-
-static inline int xattr_enabled(struct dentry *dentry)
-{
- struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
- return root->flags & CGRP_ROOT_XATTR;
-}
-
-static bool is_valid_xattr(const char *name)
-{
- if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
- !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
- return true;
- return false;
-}
-
-static int cgroup_setxattr(struct dentry *dentry, const char *name,
- const void *val, size_t size, int flags)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- if (!is_valid_xattr(name))
- return -EINVAL;
- return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags);
-}
-
-static int cgroup_removexattr(struct dentry *dentry, const char *name)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- if (!is_valid_xattr(name))
- return -EINVAL;
- return simple_xattr_remove(__d_xattrs(dentry), name);
-}
-
-static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name,
- void *buf, size_t size)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- if (!is_valid_xattr(name))
- return -EINVAL;
- return simple_xattr_get(__d_xattrs(dentry), name, buf, size);
-}
-
-static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
-{
- if (!xattr_enabled(dentry))
- return -EOPNOTSUPP;
- return simple_xattr_list(__d_xattrs(dentry), buf, size);
-}
-
-static const struct file_operations cgroup_file_operations = {
- .read = cgroup_file_read,
- .write = cgroup_file_write,
- .llseek = generic_file_llseek,
- .open = cgroup_file_open,
- .release = cgroup_file_release,
-};
-
-static const struct inode_operations cgroup_file_inode_operations = {
- .setxattr = cgroup_setxattr,
- .getxattr = cgroup_getxattr,
- .listxattr = cgroup_listxattr,
- .removexattr = cgroup_removexattr,
-};
-
-static const struct inode_operations cgroup_dir_inode_operations = {
- .lookup = simple_lookup,
- .mkdir = cgroup_mkdir,
- .rmdir = cgroup_rmdir,
- .rename = cgroup_rename,
- .setxattr = cgroup_setxattr,
- .getxattr = cgroup_getxattr,
- .listxattr = cgroup_listxattr,
- .removexattr = cgroup_removexattr,
-};
-
-/*
- * Check if a file is a control file
- */
-static inline struct cftype *__file_cft(struct file *file)
-{
- if (file_inode(file)->i_fop != &cgroup_file_operations)
- return ERR_PTR(-EINVAL);
- return __d_cft(file->f_dentry);
-}
-
-static int cgroup_create_file(struct dentry *dentry, umode_t mode,
- struct super_block *sb)
-{
- struct inode *inode;
-
- if (!dentry)
- return -ENOENT;
- if (dentry->d_inode)
- return -EEXIST;
+ /*
+ * We're gonna grab cgroup_tree_mutex which nests outside kernfs
+ * active_ref. kernfs_rename() doesn't require active_ref
+ * protection. Break them before grabbing cgroup_tree_mutex.
+ */
+ kernfs_break_active_protection(new_parent);
+ kernfs_break_active_protection(kn);
- inode = cgroup_new_inode(mode, sb);
- if (!inode)
- return -ENOMEM;
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
- if (S_ISDIR(mode)) {
- inode->i_op = &cgroup_dir_inode_operations;
- inode->i_fop = &simple_dir_operations;
+ ret = kernfs_rename(kn, new_parent, new_name_str);
- /* start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
- inc_nlink(dentry->d_parent->d_inode);
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
- /*
- * Control reaches here with cgroup_mutex held.
- * @inode->i_mutex should nest outside cgroup_mutex but we
- * want to populate it immediately without releasing
- * cgroup_mutex. As @inode isn't visible to anyone else
- * yet, trylock will always succeed without affecting
- * lockdep checks.
- */
- WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex));
- } else if (S_ISREG(mode)) {
- inode->i_size = 0;
- inode->i_fop = &cgroup_file_operations;
- inode->i_op = &cgroup_file_inode_operations;
- }
- d_instantiate(dentry, inode);
- dget(dentry); /* Extra count - pin the dentry in core */
- return 0;
+ kernfs_unbreak_active_protection(kn);
+ kernfs_unbreak_active_protection(new_parent);
+ return ret;
}
-/**
- * cgroup_file_mode - deduce file mode of a control file
- * @cft: the control file in question
- *
- * returns cft->mode if ->mode is not 0
- * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
- * returns S_IRUGO if it has only a read handler
- * returns S_IWUSR if it has only a write hander
- */
-static umode_t cgroup_file_mode(const struct cftype *cft)
+/* set uid and gid of cgroup dirs and files to that of the creator */
+static int cgroup_kn_set_ugid(struct kernfs_node *kn)
{
- umode_t mode = 0;
-
- if (cft->mode)
- return cft->mode;
-
- if (cft->read || cft->read_u64 || cft->read_s64 ||
- cft->read_map || cft->read_seq_string)
- mode |= S_IRUGO;
+ struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
+ .ia_uid = current_fsuid(),
+ .ia_gid = current_fsgid(), };
- if (cft->write || cft->write_u64 || cft->write_s64 ||
- cft->write_string || cft->trigger)
- mode |= S_IWUSR;
+ if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
+ gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
+ return 0;
- return mode;
+ return kernfs_setattr(kn, &iattr);
}
static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
{
- struct dentry *dir = cgrp->dentry;
- struct cgroup *parent = __d_cgrp(dir);
- struct dentry *dentry;
- struct cfent *cfe;
- int error;
- umode_t mode;
- char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
-
- if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
- !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
- strcpy(name, cft->ss->name);
- strcat(name, ".");
- }
- strcat(name, cft->name);
-
- BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
-
- cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
- if (!cfe)
- return -ENOMEM;
-
- dentry = lookup_one_len(name, dir, strlen(name));
- if (IS_ERR(dentry)) {
- error = PTR_ERR(dentry);
- goto out;
- }
+ char name[CGROUP_FILE_NAME_MAX];
+ struct kernfs_node *kn;
+ struct lock_class_key *key = NULL;
+ int ret;
- cfe->type = (void *)cft;
- cfe->dentry = dentry;
- dentry->d_fsdata = cfe;
- simple_xattrs_init(&cfe->xattrs);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ key = &cft->lockdep_key;
+#endif
+ kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
+ cgroup_file_mode(cft), 0, cft->kf_ops, cft,
+ NULL, false, key);
+ if (IS_ERR(kn))
+ return PTR_ERR(kn);
- mode = cgroup_file_mode(cft);
- error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
- if (!error) {
- list_add_tail(&cfe->node, &parent->files);
- cfe = NULL;
- }
- dput(dentry);
-out:
- kfree(cfe);
- return error;
+ ret = cgroup_kn_set_ugid(kn);
+ if (ret)
+ kernfs_remove(kn);
+ return ret;
}
/**
@@ -2780,11 +2399,12 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
struct cftype *cft;
int ret;
- lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
- lockdep_assert_held(&cgroup_mutex);
+ lockdep_assert_held(&cgroup_tree_mutex);
for (cft = cfts; cft->name[0] != '\0'; cft++) {
/* does cft->flags tell us to skip this file on @cgrp? */
+ if ((cft->flags & CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
+ continue;
if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
continue;
if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
@@ -2806,115 +2426,96 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
return 0;
}
-static void cgroup_cfts_prepare(void)
- __acquires(&cgroup_mutex)
-{
- /*
- * Thanks to the entanglement with vfs inode locking, we can't walk
- * the existing cgroups under cgroup_mutex and create files.
- * Instead, we use css_for_each_descendant_pre() and drop RCU read
- * lock before calling cgroup_addrm_files().
- */
- mutex_lock(&cgroup_mutex);
-}
-
-static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
- __releases(&cgroup_mutex)
+static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
{
LIST_HEAD(pending);
struct cgroup_subsys *ss = cfts[0].ss;
- struct cgroup *root = &ss->root->top_cgroup;
- struct super_block *sb = ss->root->sb;
- struct dentry *prev = NULL;
- struct inode *inode;
+ struct cgroup *root = &ss->root->cgrp;
struct cgroup_subsys_state *css;
- u64 update_before;
int ret = 0;
- /* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
- if (!cfts || ss->root == &cgroup_dummy_root ||
- !atomic_inc_not_zero(&sb->s_active)) {
- mutex_unlock(&cgroup_mutex);
- return 0;
- }
-
- /*
- * All cgroups which are created after we drop cgroup_mutex will
- * have the updated set of files, so we only need to update the
- * cgroups created before the current @cgroup_serial_nr_next.
- */
- update_before = cgroup_serial_nr_next;
+ lockdep_assert_held(&cgroup_tree_mutex);
- mutex_unlock(&cgroup_mutex);
+ /* don't bother if @ss isn't attached */
+ if (ss->root == &cgrp_dfl_root)
+ return 0;
/* add/rm files for all cgroups created before */
- rcu_read_lock();
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
if (cgroup_is_dead(cgrp))
continue;
- inode = cgrp->dentry->d_inode;
- dget(cgrp->dentry);
- rcu_read_unlock();
-
- dput(prev);
- prev = cgrp->dentry;
-
- mutex_lock(&inode->i_mutex);
- mutex_lock(&cgroup_mutex);
- if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
- ret = cgroup_addrm_files(cgrp, cfts, is_add);
- mutex_unlock(&cgroup_mutex);
- mutex_unlock(&inode->i_mutex);
-
- rcu_read_lock();
+ ret = cgroup_addrm_files(cgrp, cfts, is_add);
if (ret)
break;
}
- rcu_read_unlock();
- dput(prev);
- deactivate_super(sb);
+
+ if (is_add && !ret)
+ kernfs_activate(root->kn);
return ret;
}
-/**
- * cgroup_add_cftypes - add an array of cftypes to a subsystem
- * @ss: target cgroup subsystem
- * @cfts: zero-length name terminated array of cftypes
- *
- * Register @cfts to @ss. Files described by @cfts are created for all
- * existing cgroups to which @ss is attached and all future cgroups will
- * have them too. This function can be called anytime whether @ss is
- * attached or not.
- *
- * Returns 0 on successful registration, -errno on failure. Note that this
- * function currently returns 0 as long as @cfts registration is successful
- * even if some file creation attempts on existing cgroups fail.
- */
-int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+static void cgroup_exit_cftypes(struct cftype *cfts)
{
- struct cftype_set *set;
struct cftype *cft;
- int ret;
- set = kzalloc(sizeof(*set), GFP_KERNEL);
- if (!set)
- return -ENOMEM;
+ for (cft = cfts; cft->name[0] != '\0'; cft++) {
+ /* free copy for custom atomic_write_len, see init_cftypes() */
+ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
+ kfree(cft->kf_ops);
+ cft->kf_ops = NULL;
+ cft->ss = NULL;
+ }
+}
+
+static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+ struct cftype *cft;
+
+ for (cft = cfts; cft->name[0] != '\0'; cft++) {
+ struct kernfs_ops *kf_ops;
+
+ WARN_ON(cft->ss || cft->kf_ops);
+
+ if (cft->seq_start)
+ kf_ops = &cgroup_kf_ops;
+ else
+ kf_ops = &cgroup_kf_single_ops;
+
+ /*
+ * Ugh... if @cft wants a custom max_write_len, we need to
+ * make a copy of kf_ops to set its atomic_write_len.
+ */
+ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
+ kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
+ if (!kf_ops) {
+ cgroup_exit_cftypes(cfts);
+ return -ENOMEM;
+ }
+ kf_ops->atomic_write_len = cft->max_write_len;
+ }
- for (cft = cfts; cft->name[0] != '\0'; cft++)
+ cft->kf_ops = kf_ops;
cft->ss = ss;
+ }
- cgroup_cfts_prepare();
- set->cfts = cfts;
- list_add_tail(&set->node, &ss->cftsets);
- ret = cgroup_cfts_commit(cfts, true);
- if (ret)
- cgroup_rm_cftypes(cfts);
- return ret;
+ return 0;
+}
+
+static int cgroup_rm_cftypes_locked(struct cftype *cfts)
+{
+ lockdep_assert_held(&cgroup_tree_mutex);
+
+ if (!cfts || !cfts[0].ss)
+ return -ENOENT;
+
+ list_del(&cfts->node);
+ cgroup_apply_cftypes(cfts, false);
+ cgroup_exit_cftypes(cfts);
+ return 0;
}
-EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
/**
* cgroup_rm_cftypes - remove an array of cftypes from a subsystem
@@ -2929,24 +2530,48 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
*/
int cgroup_rm_cftypes(struct cftype *cfts)
{
- struct cftype_set *set;
+ int ret;
- if (!cfts || !cfts[0].ss)
- return -ENOENT;
+ mutex_lock(&cgroup_tree_mutex);
+ ret = cgroup_rm_cftypes_locked(cfts);
+ mutex_unlock(&cgroup_tree_mutex);
+ return ret;
+}
- cgroup_cfts_prepare();
+/**
+ * cgroup_add_cftypes - add an array of cftypes to a subsystem
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Register @cfts to @ss. Files described by @cfts are created for all
+ * existing cgroups to which @ss is attached and all future cgroups will
+ * have them too. This function can be called anytime whether @ss is
+ * attached or not.
+ *
+ * Returns 0 on successful registration, -errno on failure. Note that this
+ * function currently returns 0 as long as @cfts registration is successful
+ * even if some file creation attempts on existing cgroups fail.
+ */
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+ int ret;
- list_for_each_entry(set, &cfts[0].ss->cftsets, node) {
- if (set->cfts == cfts) {
- list_del(&set->node);
- kfree(set);
- cgroup_cfts_commit(cfts, false);
- return 0;
- }
- }
+ if (!cfts || cfts[0].name[0] == '\0')
+ return 0;
+
+ ret = cgroup_init_cftypes(ss, cfts);
+ if (ret)
+ return ret;
+
+ mutex_lock(&cgroup_tree_mutex);
+
+ list_add_tail(&cfts->node, &ss->cfts);
+ ret = cgroup_apply_cftypes(cfts, true);
+ if (ret)
+ cgroup_rm_cftypes_locked(cfts);
- cgroup_cfts_commit(NULL, false);
- return -ENOENT;
+ mutex_unlock(&cgroup_tree_mutex);
+ return ret;
}
/**
@@ -2955,61 +2580,27 @@ int cgroup_rm_cftypes(struct cftype *cfts)
*
* Return the number of tasks in the cgroup.
*/
-int cgroup_task_count(const struct cgroup *cgrp)
+static int cgroup_task_count(const struct cgroup *cgrp)
{
int count = 0;
struct cgrp_cset_link *link;
- read_lock(&css_set_lock);
+ down_read(&css_set_rwsem);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
count += atomic_read(&link->cset->refcount);
- read_unlock(&css_set_lock);
+ up_read(&css_set_rwsem);
return count;
}
-/*
- * To reduce the fork() overhead for systems that are not actually using
- * their cgroups capability, we don't maintain the lists running through
- * each css_set to its tasks until we see the list actually used - in other
- * words after the first call to css_task_iter_start().
- */
-static void cgroup_enable_task_cg_lists(void)
-{
- struct task_struct *p, *g;
- write_lock(&css_set_lock);
- use_task_css_set_links = 1;
- /*
- * We need tasklist_lock because RCU is not safe against
- * while_each_thread(). Besides, a forking task that has passed
- * cgroup_post_fork() without seeing use_task_css_set_links = 1
- * is not guaranteed to have its child immediately visible in the
- * tasklist if we walk through it with RCU.
- */
- read_lock(&tasklist_lock);
- do_each_thread(g, p) {
- task_lock(p);
- /*
- * We should check if the process is exiting, otherwise
- * it will race with cgroup_exit() in that the list
- * entry won't be deleted though the process has exited.
- */
- if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
- list_add(&p->cg_list, &task_css_set(p)->tasks);
- task_unlock(p);
- } while_each_thread(g, p);
- read_unlock(&tasklist_lock);
- write_unlock(&css_set_lock);
-}
-
/**
* css_next_child - find the next child of a given css
* @pos_css: the current position (%NULL to initiate traversal)
* @parent_css: css whose children to walk
*
* This function returns the next child of @parent_css and should be called
- * under RCU read lock. The only requirement is that @parent_css and
- * @pos_css are accessible. The next sibling is guaranteed to be returned
- * regardless of their states.
+ * under either cgroup_mutex or RCU read lock. The only requirement is
+ * that @parent_css and @pos_css are accessible. The next sibling is
+ * guaranteed to be returned regardless of their states.
*/
struct cgroup_subsys_state *
css_next_child(struct cgroup_subsys_state *pos_css,
@@ -3019,7 +2610,7 @@ css_next_child(struct cgroup_subsys_state *pos_css,
struct cgroup *cgrp = parent_css->cgroup;
struct cgroup *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
/*
* @pos could already have been removed. Once a cgroup is removed,
@@ -3055,7 +2646,6 @@ css_next_child(struct cgroup_subsys_state *pos_css,
return cgroup_css(next, parent_css->ss);
}
-EXPORT_SYMBOL_GPL(css_next_child);
/**
* css_next_descendant_pre - find the next descendant for pre-order walk
@@ -3066,10 +2656,10 @@ EXPORT_SYMBOL_GPL(css_next_child);
* to visit for pre-order traversal of @root's descendants. @root is
* included in the iteration and the first node to be visited.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct next descendant as long as both @pos
- * and @root are accessible and @pos is a descendant of @root.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct next descendant as long
+ * as both @pos and @root are accessible and @pos is a descendant of @root.
*/
struct cgroup_subsys_state *
css_next_descendant_pre(struct cgroup_subsys_state *pos,
@@ -3077,7 +2667,7 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
{
struct cgroup_subsys_state *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
/* if first iteration, visit @root */
if (!pos)
@@ -3098,7 +2688,6 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
return NULL;
}
-EXPORT_SYMBOL_GPL(css_next_descendant_pre);
/**
* css_rightmost_descendant - return the rightmost descendant of a css
@@ -3108,17 +2697,17 @@ EXPORT_SYMBOL_GPL(css_next_descendant_pre);
* is returned. This can be used during pre-order traversal to skip
* subtree of @pos.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct rightmost descendant as long as @pos is
- * accessible.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct rightmost descendant as
+ * long as @pos is accessible.
*/
struct cgroup_subsys_state *
css_rightmost_descendant(struct cgroup_subsys_state *pos)
{
struct cgroup_subsys_state *last, *tmp;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
do {
last = pos;
@@ -3130,7 +2719,6 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos)
return last;
}
-EXPORT_SYMBOL_GPL(css_rightmost_descendant);
static struct cgroup_subsys_state *
css_leftmost_descendant(struct cgroup_subsys_state *pos)
@@ -3154,10 +2742,11 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos)
* to visit for post-order traversal of @root's descendants. @root is
* included in the iteration and the last node to be visited.
*
- * While this function requires RCU read locking, it doesn't require the
- * whole traversal to be contained in a single RCU critical section. This
- * function will return the correct next descendant as long as both @pos
- * and @cgroup are accessible and @pos is a descendant of @cgroup.
+ * While this function requires cgroup_mutex or RCU read locking, it
+ * doesn't require the whole traversal to be contained in a single critical
+ * section. This function will return the correct next descendant as long
+ * as both @pos and @cgroup are accessible and @pos is a descendant of
+ * @cgroup.
*/
struct cgroup_subsys_state *
css_next_descendant_post(struct cgroup_subsys_state *pos,
@@ -3165,7 +2754,7 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
{
struct cgroup_subsys_state *next;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ cgroup_assert_mutexes_or_rcu_locked();
/* if first iteration, visit leftmost descendant which may be @root */
if (!pos)
@@ -3183,7 +2772,6 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
/* no sibling left, visit parent */
return css_parent(pos);
}
-EXPORT_SYMBOL_GPL(css_next_descendant_post);
/**
* css_advance_task_iter - advance a task itererator to the next css_set
@@ -3206,9 +2794,14 @@ static void css_advance_task_iter(struct css_task_iter *it)
}
link = list_entry(l, struct cgrp_cset_link, cset_link);
cset = link->cset;
- } while (list_empty(&cset->tasks));
+ } while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));
+
it->cset_link = l;
- it->task = cset->tasks.next;
+
+ if (!list_empty(&cset->tasks))
+ it->task = cset->tasks.next;
+ else
+ it->task = cset->mg_tasks.next;
}
/**
@@ -3227,17 +2820,12 @@ static void css_advance_task_iter(struct css_task_iter *it)
*/
void css_task_iter_start(struct cgroup_subsys_state *css,
struct css_task_iter *it)
- __acquires(css_set_lock)
+ __acquires(css_set_rwsem)
{
- /*
- * The first time anyone tries to iterate across a css, we need to
- * enable the list linking each css_set to its tasks, and fix up
- * all existing tasks.
- */
- if (!use_task_css_set_links)
- cgroup_enable_task_cg_lists();
+ /* no one should try to iterate before mounting cgroups */
+ WARN_ON_ONCE(!use_task_css_set_links);
- read_lock(&css_set_lock);
+ down_read(&css_set_rwsem);
it->origin_css = css;
it->cset_link = &css->cgroup->cset_links;
@@ -3257,24 +2845,29 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
{
struct task_struct *res;
struct list_head *l = it->task;
- struct cgrp_cset_link *link;
+ struct cgrp_cset_link *link = list_entry(it->cset_link,
+ struct cgrp_cset_link, cset_link);
/* If the iterator cg is NULL, we have no tasks */
if (!it->cset_link)
return NULL;
res = list_entry(l, struct task_struct, cg_list);
- /* Advance iterator to find next entry */
+
+ /*
+ * Advance iterator to find next entry. cset->tasks is consumed
+ * first and then ->mg_tasks. After ->mg_tasks, we move onto the
+ * next cset.
+ */
l = l->next;
- link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link);
- if (l == &link->cset->tasks) {
- /*
- * We reached the end of this task list - move on to the
- * next cgrp_cset_link.
- */
+
+ if (l == &link->cset->tasks)
+ l = link->cset->mg_tasks.next;
+
+ if (l == &link->cset->mg_tasks)
css_advance_task_iter(it);
- } else {
+ else
it->task = l;
- }
+
return res;
}
@@ -3285,191 +2878,62 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
* Finish task iteration started by css_task_iter_start().
*/
void css_task_iter_end(struct css_task_iter *it)
- __releases(css_set_lock)
-{
- read_unlock(&css_set_lock);
-}
-
-static inline int started_after_time(struct task_struct *t1,
- struct timespec *time,
- struct task_struct *t2)
+ __releases(css_set_rwsem)
{
- int start_diff = timespec_compare(&t1->start_time, time);
- if (start_diff > 0) {
- return 1;
- } else if (start_diff < 0) {
- return 0;
- } else {
- /*
- * Arbitrarily, if two processes started at the same
- * time, we'll say that the lower pointer value
- * started first. Note that t2 may have exited by now
- * so this may not be a valid pointer any longer, but
- * that's fine - it still serves to distinguish
- * between two tasks started (effectively) simultaneously.
- */
- return t1 > t2;
- }
-}
-
-/*
- * This function is a callback from heap_insert() and is used to order
- * the heap.
- * In this case we order the heap in descending task start time.
- */
-static inline int started_after(void *p1, void *p2)
-{
- struct task_struct *t1 = p1;
- struct task_struct *t2 = p2;
- return started_after_time(t1, &t2->start_time, t2);
+ up_read(&css_set_rwsem);
}
/**
- * css_scan_tasks - iterate though all the tasks in a css
- * @css: the css to iterate tasks of
- * @test: optional test callback
- * @process: process callback
- * @data: data passed to @test and @process
- * @heap: optional pre-allocated heap used for task iteration
- *
- * Iterate through all the tasks in @css, calling @test for each, and if it
- * returns %true, call @process for it also.
- *
- * @test may be NULL, meaning always true (select all tasks), which
- * effectively duplicates css_task_iter_{start,next,end}() but does not
- * lock css_set_lock for the call to @process.
- *
- * It is guaranteed that @process will act on every task that is a member
- * of @css for the duration of this call. This function may or may not
- * call @process for tasks that exit or move to a different css during the
- * call, or are forked or move into the css during the call.
- *
- * Note that @test may be called with locks held, and may in some
- * situations be called multiple times for the same task, so it should be
- * cheap.
+ * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
+ * @to: cgroup to which the tasks will be moved
+ * @from: cgroup in which the tasks currently reside
*
- * If @heap is non-NULL, a heap has been pre-allocated and will be used for
- * heap operations (and its "gt" member will be overwritten), else a
- * temporary heap will be used (allocation of which may cause this function
- * to fail).
+ * Locking rules between cgroup_post_fork() and the migration path
+ * guarantee that, if a task is forking while being migrated, the new child
+ * is guaranteed to be either visible in the source cgroup after the
+ * parent's migration is complete or put into the target cgroup. No task
+ * can slip out of migration through forking.
*/
-int css_scan_tasks(struct cgroup_subsys_state *css,
- bool (*test)(struct task_struct *, void *),
- void (*process)(struct task_struct *, void *),
- void *data, struct ptr_heap *heap)
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
{
- int retval, i;
+ LIST_HEAD(preloaded_csets);
+ struct cgrp_cset_link *link;
struct css_task_iter it;
- struct task_struct *p, *dropped;
- /* Never dereference latest_task, since it's not refcounted */
- struct task_struct *latest_task = NULL;
- struct ptr_heap tmp_heap;
- struct timespec latest_time = { 0, 0 };
-
- if (heap) {
- /* The caller supplied our heap and pre-allocated its memory */
- heap->gt = &started_after;
- } else {
- /* We need to allocate our own heap memory */
- heap = &tmp_heap;
- retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
- if (retval)
- /* cannot allocate the heap */
- return retval;
- }
+ struct task_struct *task;
+ int ret;
- again:
- /*
- * Scan tasks in the css, using the @test callback to determine
- * which are of interest, and invoking @process callback on the
- * ones which need an update. Since we don't want to hold any
- * locks during the task updates, gather tasks to be processed in a
- * heap structure. The heap is sorted by descending task start
- * time. If the statically-sized heap fills up, we overflow tasks
- * that started later, and in future iterations only consider tasks
- * that started after the latest task in the previous pass. This
- * guarantees forward progress and that we don't miss any tasks.
- */
- heap->size = 0;
- css_task_iter_start(css, &it);
- while ((p = css_task_iter_next(&it))) {
- /*
- * Only affect tasks that qualify per the caller's callback,
- * if he provided one
- */
- if (test && !test(p, data))
- continue;
- /*
- * Only process tasks that started after the last task
- * we processed
- */
- if (!started_after_time(p, &latest_time, latest_task))
- continue;
- dropped = heap_insert(heap, p);
- if (dropped == NULL) {
- /*
- * The new task was inserted; the heap wasn't
- * previously full
- */
- get_task_struct(p);
- } else if (dropped != p) {
- /*
- * The new task was inserted, and pushed out a
- * different task
- */
- get_task_struct(p);
- put_task_struct(dropped);
- }
- /*
- * Else the new task was newer than anything already in
- * the heap and wasn't inserted
- */
- }
- css_task_iter_end(&it);
+ mutex_lock(&cgroup_mutex);
- if (heap->size) {
- for (i = 0; i < heap->size; i++) {
- struct task_struct *q = heap->ptrs[i];
- if (i == 0) {
- latest_time = q->start_time;
- latest_task = q;
- }
- /* Process the task per the caller's callback */
- process(q, data);
- put_task_struct(q);
- }
- /*
- * If we had to process any tasks at all, scan again
- * in case some of them were in the middle of forking
- * children that didn't get processed.
- * Not the most efficient way to do it, but it avoids
- * having to take callback_mutex in the fork path
- */
- goto again;
- }
- if (heap == &tmp_heap)
- heap_free(&tmp_heap);
- return 0;
-}
+ /* all tasks in @from are being moved, all csets are source */
+ down_read(&css_set_rwsem);
+ list_for_each_entry(link, &from->cset_links, cset_link)
+ cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
+ up_read(&css_set_rwsem);
-static void cgroup_transfer_one_task(struct task_struct *task, void *data)
-{
- struct cgroup *new_cgroup = data;
+ ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
+ if (ret)
+ goto out_err;
- mutex_lock(&cgroup_mutex);
- cgroup_attach_task(new_cgroup, task, false);
+ /*
+ * Migrate tasks one-by-one until @form is empty. This fails iff
+ * ->can_attach() fails.
+ */
+ do {
+ css_task_iter_start(&from->dummy_css, &it);
+ task = css_task_iter_next(&it);
+ if (task)
+ get_task_struct(task);
+ css_task_iter_end(&it);
+
+ if (task) {
+ ret = cgroup_migrate(to, task, false);
+ put_task_struct(task);
+ }
+ } while (task && !ret);
+out_err:
+ cgroup_migrate_finish(&preloaded_csets);
mutex_unlock(&cgroup_mutex);
-}
-
-/**
- * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
- * @to: cgroup to which the tasks will be moved
- * @from: cgroup in which the tasks currently reside
- */
-int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
-{
- return css_scan_tasks(&from->dummy_css, NULL, cgroup_transfer_one_task,
- to, NULL);
+ return ret;
}
/*
@@ -3504,14 +2968,12 @@ struct cgroup_pidlist {
pid_t *list;
/* how many elements the above list has */
int length;
- /* how many files are using the current array */
- int use_count;
/* each of these stored in a list by its cgroup */
struct list_head links;
/* pointer to the cgroup we belong to, for list removal purposes */
struct cgroup *owner;
- /* protects the other fields */
- struct rw_semaphore rwsem;
+ /* for delayed destruction */
+ struct delayed_work destroy_dwork;
};
/*
@@ -3527,6 +2989,7 @@ static void *pidlist_allocate(int count)
else
return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
+
static void pidlist_free(void *p)
{
if (is_vmalloc_addr(p))
@@ -3536,6 +2999,47 @@ static void pidlist_free(void *p)
}
/*
+ * Used to destroy all pidlists lingering waiting for destroy timer. None
+ * should be left afterwards.
+ */
+static void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
+{
+ struct cgroup_pidlist *l, *tmp_l;
+
+ mutex_lock(&cgrp->pidlist_mutex);
+ list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links)
+ mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0);
+ mutex_unlock(&cgrp->pidlist_mutex);
+
+ flush_workqueue(cgroup_pidlist_destroy_wq);
+ BUG_ON(!list_empty(&cgrp->pidlists));
+}
+
+static void cgroup_pidlist_destroy_work_fn(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist,
+ destroy_dwork);
+ struct cgroup_pidlist *tofree = NULL;
+
+ mutex_lock(&l->owner->pidlist_mutex);
+
+ /*
+ * Destroy iff we didn't get queued again. The state won't change
+ * as destroy_dwork can only be queued while locked.
+ */
+ if (!delayed_work_pending(dwork)) {
+ list_del(&l->links);
+ pidlist_free(l->list);
+ put_pid_ns(l->key.ns);
+ tofree = l;
+ }
+
+ mutex_unlock(&l->owner->pidlist_mutex);
+ kfree(tofree);
+}
+
+/*
* pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
* Returns the number of unique elements.
*/
@@ -3565,52 +3069,92 @@ after:
return dest;
}
+/*
+ * The two pid files - task and cgroup.procs - guaranteed that the result
+ * is sorted, which forced this whole pidlist fiasco. As pid order is
+ * different per namespace, each namespace needs differently sorted list,
+ * making it impossible to use, for example, single rbtree of member tasks
+ * sorted by task pointer. As pidlists can be fairly large, allocating one
+ * per open file is dangerous, so cgroup had to implement shared pool of
+ * pidlists keyed by cgroup and namespace.
+ *
+ * All this extra complexity was caused by the original implementation
+ * committing to an entirely unnecessary property. In the long term, we
+ * want to do away with it. Explicitly scramble sort order if
+ * sane_behavior so that no such expectation exists in the new interface.
+ *
+ * Scrambling is done by swapping every two consecutive bits, which is
+ * non-identity one-to-one mapping which disturbs sort order sufficiently.
+ */
+static pid_t pid_fry(pid_t pid)
+{
+ unsigned a = pid & 0x55555555;
+ unsigned b = pid & 0xAAAAAAAA;
+
+ return (a << 1) | (b >> 1);
+}
+
+static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
+{
+ if (cgroup_sane_behavior(cgrp))
+ return pid_fry(pid);
+ else
+ return pid;
+}
+
static int cmppid(const void *a, const void *b)
{
return *(pid_t *)a - *(pid_t *)b;
}
+static int fried_cmppid(const void *a, const void *b)
+{
+ return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b);
+}
+
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+ enum cgroup_filetype type)
+{
+ struct cgroup_pidlist *l;
+ /* don't need task_nsproxy() if we're looking at ourself */
+ struct pid_namespace *ns = task_active_pid_ns(current);
+
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
+ list_for_each_entry(l, &cgrp->pidlists, links)
+ if (l->key.type == type && l->key.ns == ns)
+ return l;
+ return NULL;
+}
+
/*
* find the appropriate pidlist for our purpose (given procs vs tasks)
* returns with the lock on that pidlist already held, and takes care
* of the use count, or returns NULL with no locks held if we're out of
* memory.
*/
-static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
- enum cgroup_filetype type)
+static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
+ enum cgroup_filetype type)
{
struct cgroup_pidlist *l;
- /* don't need task_nsproxy() if we're looking at ourself */
- struct pid_namespace *ns = task_active_pid_ns(current);
- /*
- * We can't drop the pidlist_mutex before taking the l->rwsem in case
- * the last ref-holder is trying to remove l from the list at the same
- * time. Holding the pidlist_mutex precludes somebody taking whichever
- * list we find out from under us - compare release_pid_array().
- */
- mutex_lock(&cgrp->pidlist_mutex);
- list_for_each_entry(l, &cgrp->pidlists, links) {
- if (l->key.type == type && l->key.ns == ns) {
- /* make sure l doesn't vanish out from under us */
- down_write(&l->rwsem);
- mutex_unlock(&cgrp->pidlist_mutex);
- return l;
- }
- }
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
+ l = cgroup_pidlist_find(cgrp, type);
+ if (l)
+ return l;
+
/* entry not found; create a new one */
l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
- if (!l) {
- mutex_unlock(&cgrp->pidlist_mutex);
+ if (!l)
return l;
- }
- init_rwsem(&l->rwsem);
- down_write(&l->rwsem);
+
+ INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn);
l->key.type = type;
- l->key.ns = get_pid_ns(ns);
+ /* don't need task_nsproxy() if we're looking at ourself */
+ l->key.ns = get_pid_ns(task_active_pid_ns(current));
l->owner = cgrp;
list_add(&l->links, &cgrp->pidlists);
- mutex_unlock(&cgrp->pidlist_mutex);
return l;
}
@@ -3627,6 +3171,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
struct task_struct *tsk;
struct cgroup_pidlist *l;
+ lockdep_assert_held(&cgrp->pidlist_mutex);
+
/*
* If cgroup gets more users after we read count, we won't have
* enough space - tough. This race is indistinguishable to the
@@ -3653,20 +3199,24 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
css_task_iter_end(&it);
length = n;
/* now sort & (if procs) strip out duplicates */
- sort(array, length, sizeof(pid_t), cmppid, NULL);
+ if (cgroup_sane_behavior(cgrp))
+ sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
+ else
+ sort(array, length, sizeof(pid_t), cmppid, NULL);
if (type == CGROUP_FILE_PROCS)
length = pidlist_uniq(array, length);
- l = cgroup_pidlist_find(cgrp, type);
+
+ l = cgroup_pidlist_find_create(cgrp, type);
if (!l) {
+ mutex_unlock(&cgrp->pidlist_mutex);
pidlist_free(array);
return -ENOMEM;
}
- /* store array, freeing old if necessary - lock already held */
+
+ /* store array, freeing old if necessary */
pidlist_free(l->list);
l->list = array;
l->length = length;
- l->use_count++;
- up_write(&l->rwsem);
*lp = l;
return 0;
}
@@ -3682,21 +3232,31 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
*/
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
- int ret = -EINVAL;
+ struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
struct cgroup *cgrp;
struct css_task_iter it;
struct task_struct *tsk;
+ /* it should be kernfs_node belonging to cgroupfs and is a directory */
+ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+ kernfs_type(kn) != KERNFS_DIR)
+ return -EINVAL;
+
+ mutex_lock(&cgroup_mutex);
+
/*
- * Validate dentry by checking the superblock operations,
- * and make sure it's a directory.
+ * We aren't being called from kernfs and there's no guarantee on
+ * @kn->priv's validity. For this and css_tryget_from_dir(),
+ * @kn->priv is RCU safe. Let's do the RCU dancing.
*/
- if (dentry->d_sb->s_op != &cgroup_ops ||
- !S_ISDIR(dentry->d_inode->i_mode))
- goto err;
-
- ret = 0;
- cgrp = dentry->d_fsdata;
+ rcu_read_lock();
+ cgrp = rcu_dereference(kn->priv);
+ if (!cgrp || cgroup_is_dead(cgrp)) {
+ rcu_read_unlock();
+ mutex_unlock(&cgroup_mutex);
+ return -ENOENT;
+ }
+ rcu_read_unlock();
css_task_iter_start(&cgrp->dummy_css, &it);
while ((tsk = css_task_iter_next(&it))) {
@@ -3721,8 +3281,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
}
css_task_iter_end(&it);
-err:
- return ret;
+ mutex_unlock(&cgroup_mutex);
+ return 0;
}
@@ -3740,20 +3300,45 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
- struct cgroup_pidlist *l = s->private;
+ struct kernfs_open_file *of = s->private;
+ struct cgroup *cgrp = seq_css(s)->cgroup;
+ struct cgroup_pidlist *l;
+ enum cgroup_filetype type = seq_cft(s)->private;
int index = 0, pid = *pos;
- int *iter;
+ int *iter, ret;
+
+ mutex_lock(&cgrp->pidlist_mutex);
+
+ /*
+ * !NULL @of->priv indicates that this isn't the first start()
+ * after open. If the matching pidlist is around, we can use that.
+ * Look for it. Note that @of->priv can't be used directly. It
+ * could already have been destroyed.
+ */
+ if (of->priv)
+ of->priv = cgroup_pidlist_find(cgrp, type);
+
+ /*
+ * Either this is the first start() after open or the matching
+ * pidlist has been destroyed inbetween. Create a new one.
+ */
+ if (!of->priv) {
+ ret = pidlist_array_load(cgrp, type,
+ (struct cgroup_pidlist **)&of->priv);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+ l = of->priv;
- down_read(&l->rwsem);
if (pid) {
int end = l->length;
while (index < end) {
int mid = (index + end) / 2;
- if (l->list[mid] == pid) {
+ if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) {
index = mid;
break;
- } else if (l->list[mid] <= pid)
+ } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid)
index = mid + 1;
else
end = mid;
@@ -3764,19 +3349,25 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
return NULL;
/* Update the abstract position to be the actual pid that we found */
iter = l->list + index;
- *pos = *iter;
+ *pos = cgroup_pid_fry(cgrp, *iter);
return iter;
}
static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
- struct cgroup_pidlist *l = s->private;
- up_read(&l->rwsem);
+ struct kernfs_open_file *of = s->private;
+ struct cgroup_pidlist *l = of->priv;
+
+ if (l)
+ mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
+ CGROUP_PIDLIST_DESTROY_DELAY);
+ mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex);
}
static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup_pidlist *l = s->private;
+ struct kernfs_open_file *of = s->private;
+ struct cgroup_pidlist *l = of->priv;
pid_t *p = v;
pid_t *end = l->list + l->length;
/*
@@ -3787,7 +3378,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
if (p >= end) {
return NULL;
} else {
- *pos = *p;
+ *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p);
return p;
}
}
@@ -3808,92 +3399,6 @@ static const struct seq_operations cgroup_pidlist_seq_operations = {
.show = cgroup_pidlist_show,
};
-static void cgroup_release_pid_array(struct cgroup_pidlist *l)
-{
- /*
- * the case where we're the last user of this particular pidlist will
- * have us remove it from the cgroup's list, which entails taking the
- * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
- * pidlist_mutex, we have to take pidlist_mutex first.
- */
- mutex_lock(&l->owner->pidlist_mutex);
- down_write(&l->rwsem);
- BUG_ON(!l->use_count);
- if (!--l->use_count) {
- /* we're the last user if refcount is 0; remove and free */
- list_del(&l->links);
- mutex_unlock(&l->owner->pidlist_mutex);
- pidlist_free(l->list);
- put_pid_ns(l->key.ns);
- up_write(&l->rwsem);
- kfree(l);
- return;
- }
- mutex_unlock(&l->owner->pidlist_mutex);
- up_write(&l->rwsem);
-}
-
-static int cgroup_pidlist_release(struct inode *inode, struct file *file)
-{
- struct cgroup_pidlist *l;
- if (!(file->f_mode & FMODE_READ))
- return 0;
- /*
- * the seq_file will only be initialized if the file was opened for
- * reading; hence we check if it's not null only in that case.
- */
- l = ((struct seq_file *)file->private_data)->private;
- cgroup_release_pid_array(l);
- return seq_release(inode, file);
-}
-
-static const struct file_operations cgroup_pidlist_operations = {
- .read = seq_read,
- .llseek = seq_lseek,
- .write = cgroup_file_write,
- .release = cgroup_pidlist_release,
-};
-
-/*
- * The following functions handle opens on a file that displays a pidlist
- * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
- * in the cgroup.
- */
-/* helper function for the two below it */
-static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
-{
- struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
- struct cgroup_pidlist *l;
- int retval;
-
- /* Nothing to do for write-only files */
- if (!(file->f_mode & FMODE_READ))
- return 0;
-
- /* have the array populated */
- retval = pidlist_array_load(cgrp, type, &l);
- if (retval)
- return retval;
- /* configure file information */
- file->f_op = &cgroup_pidlist_operations;
-
- retval = seq_open(file, &cgroup_pidlist_seq_operations);
- if (retval) {
- cgroup_release_pid_array(l);
- return retval;
- }
- ((struct seq_file *)file->private_data)->private = l;
- return 0;
-}
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
-{
- return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
-}
-static int cgroup_procs_open(struct inode *unused, struct file *file)
-{
- return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
-}
-
static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -3911,219 +3416,6 @@ static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
return 0;
}
-/*
- * When dput() is called asynchronously, if umount has been done and
- * then deactivate_super() in cgroup_free_fn() kills the superblock,
- * there's a small window that vfs will see the root dentry with non-zero
- * refcnt and trigger BUG().
- *
- * That's why we hold a reference before dput() and drop it right after.
- */
-static void cgroup_dput(struct cgroup *cgrp)
-{
- struct super_block *sb = cgrp->root->sb;
-
- atomic_inc(&sb->s_active);
- dput(cgrp->dentry);
- deactivate_super(sb);
-}
-
-/*
- * Unregister event and free resources.
- *
- * Gets called from workqueue.
- */
-static void cgroup_event_remove(struct work_struct *work)
-{
- struct cgroup_event *event = container_of(work, struct cgroup_event,
- remove);
- struct cgroup_subsys_state *css = event->css;
-
- remove_wait_queue(event->wqh, &event->wait);
-
- event->cft->unregister_event(css, event->cft, event->eventfd);
-
- /* Notify userspace the event is going away. */
- eventfd_signal(event->eventfd, 1);
-
- eventfd_ctx_put(event->eventfd);
- kfree(event);
- css_put(css);
-}
-
-/*
- * Gets called on POLLHUP on eventfd when user closes it.
- *
- * Called with wqh->lock held and interrupts disabled.
- */
-static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
- int sync, void *key)
-{
- struct cgroup_event *event = container_of(wait,
- struct cgroup_event, wait);
- struct cgroup *cgrp = event->css->cgroup;
- unsigned long flags = (unsigned long)key;
-
- if (flags & POLLHUP) {
- /*
- * If the event has been detached at cgroup removal, we
- * can simply return knowing the other side will cleanup
- * for us.
- *
- * We can't race against event freeing since the other
- * side will require wqh->lock via remove_wait_queue(),
- * which we hold.
- */
- spin_lock(&cgrp->event_list_lock);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- /*
- * We are in atomic context, but cgroup_event_remove()
- * may sleep, so we have to call it in workqueue.
- */
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
- }
-
- return 0;
-}
-
-static void cgroup_event_ptable_queue_proc(struct file *file,
- wait_queue_head_t *wqh, poll_table *pt)
-{
- struct cgroup_event *event = container_of(pt,
- struct cgroup_event, pt);
-
- event->wqh = wqh;
- add_wait_queue(wqh, &event->wait);
-}
-
-/*
- * Parse input and register new cgroup event handler.
- *
- * Input must be in format '<event_fd> <control_fd> <args>'.
- * Interpretation of args is defined by control file implementation.
- */
-static int cgroup_write_event_control(struct cgroup_subsys_state *dummy_css,
- struct cftype *cft, const char *buffer)
-{
- struct cgroup *cgrp = dummy_css->cgroup;
- struct cgroup_event *event;
- struct cgroup_subsys_state *cfile_css;
- unsigned int efd, cfd;
- struct fd efile;
- struct fd cfile;
- char *endp;
- int ret;
-
- efd = simple_strtoul(buffer, &endp, 10);
- if (*endp != ' ')
- return -EINVAL;
- buffer = endp + 1;
-
- cfd = simple_strtoul(buffer, &endp, 10);
- if ((*endp != ' ') && (*endp != '\0'))
- return -EINVAL;
- buffer = endp + 1;
-
- event = kzalloc(sizeof(*event), GFP_KERNEL);
- if (!event)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&event->list);
- init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
- init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
- INIT_WORK(&event->remove, cgroup_event_remove);
-
- efile = fdget(efd);
- if (!efile.file) {
- ret = -EBADF;
- goto out_kfree;
- }
-
- event->eventfd = eventfd_ctx_fileget(efile.file);
- if (IS_ERR(event->eventfd)) {
- ret = PTR_ERR(event->eventfd);
- goto out_put_efile;
- }
-
- cfile = fdget(cfd);
- if (!cfile.file) {
- ret = -EBADF;
- goto out_put_eventfd;
- }
-
- /* the process need read permission on control file */
- /* AV: shouldn't we check that it's been opened for read instead? */
- ret = inode_permission(file_inode(cfile.file), MAY_READ);
- if (ret < 0)
- goto out_put_cfile;
-
- event->cft = __file_cft(cfile.file);
- if (IS_ERR(event->cft)) {
- ret = PTR_ERR(event->cft);
- goto out_put_cfile;
- }
-
- if (!event->cft->ss) {
- ret = -EBADF;
- goto out_put_cfile;
- }
-
- /*
- * Determine the css of @cfile, verify it belongs to the same
- * cgroup as cgroup.event_control, and associate @event with it.
- * Remaining events are automatically removed on cgroup destruction
- * but the removal is asynchronous, so take an extra ref.
- */
- rcu_read_lock();
-
- ret = -EINVAL;
- event->css = cgroup_css(cgrp, event->cft->ss);
- cfile_css = css_from_dir(cfile.file->f_dentry->d_parent, event->cft->ss);
- if (event->css && event->css == cfile_css && css_tryget(event->css))
- ret = 0;
-
- rcu_read_unlock();
- if (ret)
- goto out_put_cfile;
-
- if (!event->cft->register_event || !event->cft->unregister_event) {
- ret = -EINVAL;
- goto out_put_css;
- }
-
- ret = event->cft->register_event(event->css, event->cft,
- event->eventfd, buffer);
- if (ret)
- goto out_put_css;
-
- efile.file->f_op->poll(efile.file, &event->pt);
-
- spin_lock(&cgrp->event_list_lock);
- list_add(&event->list, &cgrp->event_list);
- spin_unlock(&cgrp->event_list_lock);
-
- fdput(cfile);
- fdput(efile);
-
- return 0;
-
-out_put_css:
- css_put(event->css);
-out_put_cfile:
- fdput(cfile);
-out_put_eventfd:
- eventfd_ctx_put(event->eventfd);
-out_put_efile:
- fdput(efile);
-out_kfree:
- kfree(event);
-
- return ret;
-}
-
static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -4143,17 +3435,15 @@ static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.procs",
- .open = cgroup_procs_open,
+ .seq_start = cgroup_pidlist_start,
+ .seq_next = cgroup_pidlist_next,
+ .seq_stop = cgroup_pidlist_stop,
+ .seq_show = cgroup_pidlist_show,
+ .private = CGROUP_FILE_PROCS,
.write_u64 = cgroup_procs_write,
- .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
{
- .name = "cgroup.event_control",
- .write_string = cgroup_write_event_control,
- .mode = S_IWUGO,
- },
- {
.name = "cgroup.clone_children",
.flags = CFTYPE_INSANE,
.read_u64 = cgroup_clone_children_read,
@@ -4162,7 +3452,7 @@ static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.sane_behavior",
.flags = CFTYPE_ONLY_ON_ROOT,
- .read_seq_string = cgroup_sane_behavior_show,
+ .seq_show = cgroup_sane_behavior_show,
},
/*
@@ -4173,9 +3463,12 @@ static struct cftype cgroup_base_files[] = {
{
.name = "tasks",
.flags = CFTYPE_INSANE, /* use "procs" instead */
- .open = cgroup_tasks_open,
+ .seq_start = cgroup_pidlist_start,
+ .seq_next = cgroup_pidlist_next,
+ .seq_stop = cgroup_pidlist_stop,
+ .seq_show = cgroup_pidlist_show,
+ .private = CGROUP_FILE_TASKS,
.write_u64 = cgroup_tasks_write,
- .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
{
@@ -4187,9 +3480,9 @@ static struct cftype cgroup_base_files[] = {
{
.name = "release_agent",
.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
- .read_seq_string = cgroup_release_agent_show,
+ .seq_show = cgroup_release_agent_show,
.write_string = cgroup_release_agent_write,
- .max_write_len = PATH_MAX,
+ .max_write_len = PATH_MAX - 1,
},
{ } /* terminate */
};
@@ -4208,13 +3501,13 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
/* process cftsets of each subsystem */
for_each_subsys(ss, i) {
- struct cftype_set *set;
+ struct cftype *cfts;
if (!test_bit(i, &subsys_mask))
continue;
- list_for_each_entry(set, &ss->cftsets, node) {
- ret = cgroup_addrm_files(cgrp, set->cfts, true);
+ list_for_each_entry(cfts, &ss->cfts, node) {
+ ret = cgroup_addrm_files(cgrp, cfts, true);
if (ret < 0)
goto err;
}
@@ -4257,7 +3550,7 @@ static void css_free_work_fn(struct work_struct *work)
css_put(css->parent);
css->ss->css_free(css);
- cgroup_dput(cgrp);
+ cgroup_put(cgrp);
}
static void css_free_rcu_fn(struct rcu_head *rcu_head)
@@ -4265,10 +3558,6 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
struct cgroup_subsys_state *css =
container_of(rcu_head, struct cgroup_subsys_state, rcu_head);
- /*
- * css holds an extra ref to @cgrp->dentry which is put on the last
- * css_put(). dput() requires process context which we don't have.
- */
INIT_WORK(&css->destroy_work, css_free_work_fn);
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
@@ -4278,7 +3567,7 @@ static void css_release(struct percpu_ref *ref)
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
- rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
+ RCU_INIT_POINTER(css->cgroup->subsys[css->ss->id], NULL);
call_rcu(&css->rcu_head, css_free_rcu_fn);
}
@@ -4303,6 +3592,7 @@ static int online_css(struct cgroup_subsys_state *css)
struct cgroup_subsys *ss = css->ss;
int ret = 0;
+ lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
if (ss->css_online)
@@ -4310,7 +3600,7 @@ static int online_css(struct cgroup_subsys_state *css)
if (!ret) {
css->flags |= CSS_ONLINE;
css->cgroup->nr_css++;
- rcu_assign_pointer(css->cgroup->subsys[ss->subsys_id], css);
+ rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
}
return ret;
}
@@ -4320,6 +3610,7 @@ static void offline_css(struct cgroup_subsys_state *css)
{
struct cgroup_subsys *ss = css->ss;
+ lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
if (!(css->flags & CSS_ONLINE))
@@ -4330,45 +3621,97 @@ static void offline_css(struct cgroup_subsys_state *css)
css->flags &= ~CSS_ONLINE;
css->cgroup->nr_css--;
- RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css);
+ RCU_INIT_POINTER(css->cgroup->subsys[ss->id], css);
}
-/*
+/**
+ * create_css - create a cgroup_subsys_state
+ * @cgrp: the cgroup new css will be associated with
+ * @ss: the subsys of new css
+ *
+ * Create a new css associated with @cgrp - @ss pair. On success, the new
+ * css is online and installed in @cgrp with all interface files created.
+ * Returns 0 on success, -errno on failure.
+ */
+static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+ struct cgroup *parent = cgrp->parent;
+ struct cgroup_subsys_state *css;
+ int err;
+
+ lockdep_assert_held(&cgroup_mutex);
+
+ css = ss->css_alloc(cgroup_css(parent, ss));
+ if (IS_ERR(css))
+ return PTR_ERR(css);
+
+ err = percpu_ref_init(&css->refcnt, css_release);
+ if (err)
+ goto err_free_css;
+
+ init_css(css, ss, cgrp);
+
+ err = cgroup_populate_dir(cgrp, 1 << ss->id);
+ if (err)
+ goto err_free_percpu_ref;
+
+ err = online_css(css);
+ if (err)
+ goto err_clear_dir;
+
+ cgroup_get(cgrp);
+ css_get(css->parent);
+
+ cgrp->subsys_mask |= 1 << ss->id;
+
+ if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
+ parent->parent) {
+ pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
+ current->comm, current->pid, ss->name);
+ if (!strcmp(ss->name, "memory"))
+ pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
+ ss->warned_broken_hierarchy = true;
+ }
+
+ return 0;
+
+err_clear_dir:
+ cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
+err_free_percpu_ref:
+ percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
+ ss->css_free(css);
+ return err;
+}
+
+/**
* cgroup_create - create a cgroup
* @parent: cgroup that will be parent of the new cgroup
- * @dentry: dentry of the new cgroup
- * @mode: mode to set on new inode
- *
- * Must be called with the mutex on the parent inode held
+ * @name: name of the new cgroup
+ * @mode: mode to set on new cgroup
*/
-static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
- umode_t mode)
+static long cgroup_create(struct cgroup *parent, const char *name,
+ umode_t mode)
{
- struct cgroup_subsys_state *css_ar[CGROUP_SUBSYS_COUNT] = { };
struct cgroup *cgrp;
- struct cgroup_name *name;
- struct cgroupfs_root *root = parent->root;
- int err = 0;
+ struct cgroup_root *root = parent->root;
+ int ssid, err;
struct cgroup_subsys *ss;
- struct super_block *sb = root->sb;
+ struct kernfs_node *kn;
+
+ /*
+ * XXX: The default hierarchy isn't fully implemented yet. Block
+ * !root cgroup creation on it for now.
+ */
+ if (root == &cgrp_dfl_root)
+ return -EINVAL;
/* allocate the cgroup and its ID, 0 is reserved for the root */
cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
if (!cgrp)
return -ENOMEM;
- name = cgroup_alloc_name(dentry);
- if (!name)
- goto err_free_cgrp;
- rcu_assign_pointer(cgrp->name, name);
-
- /*
- * Temporarily set the pointer to NULL, so idr_find() won't return
- * a half-baked cgroup.
- */
- cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
- if (cgrp->id < 0)
- goto err_free_name;
+ mutex_lock(&cgroup_tree_mutex);
/*
* Only live parents can have children. Note that the liveliness
@@ -4379,21 +3722,21 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
*/
if (!cgroup_lock_live_group(parent)) {
err = -ENODEV;
- goto err_free_id;
+ goto err_unlock_tree;
}
- /* Grab a reference on the superblock so the hierarchy doesn't
- * get deleted on unmount if there are child cgroups. This
- * can be done outside cgroup_mutex, since the sb can't
- * disappear while someone has an open control file on the
- * fs */
- atomic_inc(&sb->s_active);
+ /*
+ * Temporarily set the pointer to NULL, so idr_find() won't return
+ * a half-baked cgroup.
+ */
+ cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+ if (cgrp->id < 0) {
+ err = -ENOMEM;
+ goto err_unlock;
+ }
init_cgroup_housekeeping(cgrp);
- dentry->d_fsdata = cgrp;
- cgrp->dentry = dentry;
-
cgrp->parent = parent;
cgrp->dummy_css.parent = &parent->dummy_css;
cgrp->root = parent->root;
@@ -4404,123 +3747,93 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css;
-
- css = ss->css_alloc(cgroup_css(parent, ss));
- if (IS_ERR(css)) {
- err = PTR_ERR(css);
- goto err_free_all;
- }
- css_ar[ss->subsys_id] = css;
-
- err = percpu_ref_init(&css->refcnt, css_release);
- if (err)
- goto err_free_all;
-
- init_css(css, ss, cgrp);
+ /* create the directory */
+ kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+ if (IS_ERR(kn)) {
+ err = PTR_ERR(kn);
+ goto err_free_id;
}
+ cgrp->kn = kn;
/*
- * Create directory. cgroup_create_file() returns with the new
- * directory locked on success so that it can be populated without
- * dropping cgroup_mutex.
+ * This extra ref will be put in cgroup_free_fn() and guarantees
+ * that @cgrp->kn is always accessible.
*/
- err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
- if (err < 0)
- goto err_free_all;
- lockdep_assert_held(&dentry->d_inode->i_mutex);
+ kernfs_get(kn);
cgrp->serial_nr = cgroup_serial_nr_next++;
/* allocation complete, commit to creation */
list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
- root->number_of_cgroups++;
-
- /* hold a ref to the parent's dentry */
- dget(parent->dentry);
-
- /* creation succeeded, notify subsystems */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- err = online_css(css);
- if (err)
- goto err_destroy;
-
- /* each css holds a ref to the cgroup's dentry and parent css */
- dget(dentry);
- css_get(css->parent);
-
- /* mark it consumed for error path */
- css_ar[ss->subsys_id] = NULL;
-
- if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
- parent->parent) {
- pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
- current->comm, current->pid, ss->name);
- if (!strcmp(ss->name, "memory"))
- pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
- ss->warned_broken_hierarchy = true;
- }
- }
+ atomic_inc(&root->nr_cgrps);
+ cgroup_get(parent);
+ /*
+ * @cgrp is now fully operational. If something fails after this
+ * point, it'll be released via the normal destruction path.
+ */
idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
- err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
+ err = cgroup_kn_set_ugid(kn);
if (err)
goto err_destroy;
- err = cgroup_populate_dir(cgrp, root->subsys_mask);
+ err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
if (err)
goto err_destroy;
+ /* let's create and online css's */
+ for_each_subsys(ss, ssid) {
+ if (root->cgrp.subsys_mask & (1 << ssid)) {
+ err = create_css(cgrp, ss);
+ if (err)
+ goto err_destroy;
+ }
+ }
+
+ kernfs_activate(kn);
+
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
return 0;
-err_free_all:
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- if (css) {
- percpu_ref_cancel_init(&css->refcnt);
- ss->css_free(css);
- }
- }
- mutex_unlock(&cgroup_mutex);
- /* Release the reference count that we took on the superblock */
- deactivate_super(sb);
err_free_id:
idr_remove(&root->cgroup_idr, cgrp->id);
-err_free_name:
- kfree(rcu_dereference_raw(cgrp->name));
-err_free_cgrp:
+err_unlock:
+ mutex_unlock(&cgroup_mutex);
+err_unlock_tree:
+ mutex_unlock(&cgroup_tree_mutex);
kfree(cgrp);
return err;
err_destroy:
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- if (css) {
- percpu_ref_cancel_init(&css->refcnt);
- ss->css_free(css);
- }
- }
cgroup_destroy_locked(cgrp);
mutex_unlock(&cgroup_mutex);
- mutex_unlock(&dentry->d_inode->i_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
return err;
}
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+ umode_t mode)
{
- struct cgroup *c_parent = dentry->d_parent->d_fsdata;
+ struct cgroup *parent = parent_kn->priv;
+ int ret;
+
+ /*
+ * cgroup_create() grabs cgroup_tree_mutex which nests outside
+ * kernfs active_ref and cgroup_create() already synchronizes
+ * properly against removal through cgroup_lock_live_group().
+ * Break it before calling cgroup_create().
+ */
+ cgroup_get(parent);
+ kernfs_break_active_protection(parent_kn);
+
+ ret = cgroup_create(parent, name, mode);
- /* the vfs holds inode->i_mutex already */
- return cgroup_create(c_parent, dentry, mode | S_IFDIR);
+ kernfs_unbreak_active_protection(parent_kn);
+ cgroup_put(parent);
+ return ret;
}
/*
@@ -4533,6 +3846,7 @@ static void css_killed_work_fn(struct work_struct *work)
container_of(work, struct cgroup_subsys_state, destroy_work);
struct cgroup *cgrp = css->cgroup;
+ mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
/*
@@ -4550,6 +3864,7 @@ static void css_killed_work_fn(struct work_struct *work)
cgroup_destroy_css_killed(cgrp);
mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
/*
* Put the css refs from kill_css(). Each css holds an extra
@@ -4571,18 +3886,15 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
queue_work(cgroup_destroy_wq, &css->destroy_work);
}
-/**
- * kill_css - destroy a css
- * @css: css to destroy
- *
- * This function initiates destruction of @css by removing cgroup interface
- * files and putting its base reference. ->css_offline() will be invoked
- * asynchronously once css_tryget() is guaranteed to fail and when the
- * reference count reaches zero, @css will be released.
- */
-static void kill_css(struct cgroup_subsys_state *css)
+static void __kill_css(struct cgroup_subsys_state *css)
{
- cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+ lockdep_assert_held(&cgroup_tree_mutex);
+
+ /*
+ * This must happen before css is disassociated with its cgroup.
+ * See seq_css() for details.
+ */
+ cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
/*
* Killing would put the base ref, but we need to keep it alive
@@ -4604,6 +3916,28 @@ static void kill_css(struct cgroup_subsys_state *css)
}
/**
+ * kill_css - destroy a css
+ * @css: css to destroy
+ *
+ * This function initiates destruction of @css by removing cgroup interface
+ * files and putting its base reference. ->css_offline() will be invoked
+ * asynchronously once css_tryget() is guaranteed to fail and when the
+ * reference count reaches zero, @css will be released.
+ */
+static void kill_css(struct cgroup_subsys_state *css)
+{
+ struct cgroup *cgrp = css->cgroup;
+
+ lockdep_assert_held(&cgroup_tree_mutex);
+
+ /* if already killed, noop */
+ if (cgrp->subsys_mask & (1 << css->ss->id)) {
+ cgrp->subsys_mask &= ~(1 << css->ss->id);
+ __kill_css(css);
+ }
+}
+
+/**
* cgroup_destroy_locked - the first stage of cgroup destruction
* @cgrp: cgroup to be destroyed
*
@@ -4630,22 +3964,21 @@ static void kill_css(struct cgroup_subsys_state *css)
static int cgroup_destroy_locked(struct cgroup *cgrp)
__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
{
- struct dentry *d = cgrp->dentry;
- struct cgroup_event *event, *tmp;
- struct cgroup_subsys *ss;
struct cgroup *child;
+ struct cgroup_subsys_state *css;
bool empty;
+ int ssid;
- lockdep_assert_held(&d->d_inode->i_mutex);
+ lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
/*
- * css_set_lock synchronizes access to ->cset_links and prevents
- * @cgrp from being removed while __put_css_set() is in progress.
+ * css_set_rwsem synchronizes access to ->cset_links and prevents
+ * @cgrp from being removed while put_css_set() is in progress.
*/
- read_lock(&css_set_lock);
+ down_read(&css_set_rwsem);
empty = list_empty(&cgrp->cset_links);
- read_unlock(&css_set_lock);
+ up_read(&css_set_rwsem);
if (!empty)
return -EBUSY;
@@ -4666,18 +3999,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
return -EBUSY;
/*
- * Initiate massacre of all css's. cgroup_destroy_css_killed()
- * will be invoked to perform the rest of destruction once the
- * percpu refs of all css's are confirmed to be killed.
- */
- for_each_root_subsys(cgrp->root, ss) {
- struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-
- if (css)
- kill_css(css);
- }
-
- /*
* Mark @cgrp dead. This prevents further task migration and child
* creation by disabling cgroup_lock_live_group(). Note that
* CGRP_DEAD assertion is depended upon by css_next_child() to
@@ -4686,6 +4007,17 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
*/
set_bit(CGRP_DEAD, &cgrp->flags);
+ /*
+ * Initiate massacre of all css's. cgroup_destroy_css_killed()
+ * will be invoked to perform the rest of destruction once the
+ * percpu refs of all css's are confirmed to be killed. This
+ * involves removing the subsystem's files, drop cgroup_mutex.
+ */
+ mutex_unlock(&cgroup_mutex);
+ for_each_css(css, ssid, cgrp)
+ kill_css(css);
+ mutex_lock(&cgroup_mutex);
+
/* CGRP_DEAD is set, remove from ->release_list for the last time */
raw_spin_lock(&release_list_lock);
if (!list_empty(&cgrp->release_list))
@@ -4701,26 +4033,20 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
if (!cgrp->nr_css)
cgroup_destroy_css_killed(cgrp);
- /*
- * Clear the base files and remove @cgrp directory. The removal
- * puts the base ref but we aren't quite done with @cgrp yet, so
- * hold onto it.
- */
- cgroup_addrm_files(cgrp, cgroup_base_files, false);
- dget(d);
- cgroup_d_remove_dir(d);
+ /* remove @cgrp directory along with the base files */
+ mutex_unlock(&cgroup_mutex);
/*
- * Unregister events and notify userspace.
- * Notify userspace about cgroup removing only after rmdir of cgroup
- * directory to avoid race between userspace and kernelspace.
+ * There are two control paths which try to determine cgroup from
+ * dentry without going through kernfs - cgroupstats_build() and
+ * css_tryget_from_dir(). Those are supported by RCU protecting
+ * clearing of cgrp->kn->priv backpointer, which should happen
+ * after all files under it have been removed.
*/
- spin_lock(&cgrp->event_list_lock);
- list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
- list_del_init(&event->list);
- schedule_work(&event->remove);
- }
- spin_unlock(&cgrp->event_list_lock);
+ kernfs_remove(cgrp->kn); /* @cgrp has an extra ref on its kn */
+ RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
+
+ mutex_lock(&cgroup_mutex);
return 0;
};
@@ -4737,73 +4063,82 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
static void cgroup_destroy_css_killed(struct cgroup *cgrp)
{
struct cgroup *parent = cgrp->parent;
- struct dentry *d = cgrp->dentry;
+ lockdep_assert_held(&cgroup_tree_mutex);
lockdep_assert_held(&cgroup_mutex);
/* delete this cgroup from parent->children */
list_del_rcu(&cgrp->sibling);
- dput(d);
+ cgroup_put(cgrp);
set_bit(CGRP_RELEASABLE, &parent->flags);
check_for_release(parent);
}
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
+static int cgroup_rmdir(struct kernfs_node *kn)
{
- int ret;
-
- mutex_lock(&cgroup_mutex);
- ret = cgroup_destroy_locked(dentry->d_fsdata);
- mutex_unlock(&cgroup_mutex);
+ struct cgroup *cgrp = kn->priv;
+ int ret = 0;
- return ret;
-}
+ /*
+ * This is self-destruction but @kn can't be removed while this
+ * callback is in progress. Let's break active protection. Once
+ * the protection is broken, @cgrp can be destroyed at any point.
+ * Pin it so that it stays accessible.
+ */
+ cgroup_get(cgrp);
+ kernfs_break_active_protection(kn);
-static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
-{
- INIT_LIST_HEAD(&ss->cftsets);
+ mutex_lock(&cgroup_tree_mutex);
+ mutex_lock(&cgroup_mutex);
/*
- * base_cftset is embedded in subsys itself, no need to worry about
- * deregistration.
+ * @cgrp might already have been destroyed while we're trying to
+ * grab the mutexes.
*/
- if (ss->base_cftypes) {
- struct cftype *cft;
+ if (!cgroup_is_dead(cgrp))
+ ret = cgroup_destroy_locked(cgrp);
- for (cft = ss->base_cftypes; cft->name[0] != '\0'; cft++)
- cft->ss = ss;
+ mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
- ss->base_cftset.cfts = ss->base_cftypes;
- list_add_tail(&ss->base_cftset.node, &ss->cftsets);
- }
+ kernfs_unbreak_active_protection(kn);
+ cgroup_put(cgrp);
+ return ret;
}
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
+ .remount_fs = cgroup_remount,
+ .show_options = cgroup_show_options,
+ .mkdir = cgroup_mkdir,
+ .rmdir = cgroup_rmdir,
+ .rename = cgroup_rename,
+};
+
static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
{
struct cgroup_subsys_state *css;
printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
+ mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
- /* init base cftset */
- cgroup_init_cftsets(ss);
+ INIT_LIST_HEAD(&ss->cfts);
- /* Create the top cgroup state for this subsystem */
- list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
- ss->root = &cgroup_dummy_root;
- css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
+ /* Create the root cgroup state for this subsystem */
+ ss->root = &cgrp_dfl_root;
+ css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
/* We don't handle early failures gracefully */
BUG_ON(IS_ERR(css));
- init_css(css, ss, cgroup_dummy_top);
+ init_css(css, ss, &cgrp_dfl_root.cgrp);
/* Update the init_css_set to contain a subsys
* pointer to this state - since the subsystem is
* newly registered, all tasks and hence the
- * init_css_set is in the subsystem's top cgroup. */
- init_css_set.subsys[ss->subsys_id] = css;
+ * init_css_set is in the subsystem's root cgroup. */
+ init_css_set.subsys[ss->id] = css;
need_forkexit_callback |= ss->fork || ss->exit;
@@ -4814,177 +4149,11 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
BUG_ON(online_css(css));
- mutex_unlock(&cgroup_mutex);
-
- /* this function shouldn't be used with modular subsystems, since they
- * need to register a subsys_id, among other things */
- BUG_ON(ss->module);
-}
-
-/**
- * cgroup_load_subsys: load and register a modular subsystem at runtime
- * @ss: the subsystem to load
- *
- * This function should be called in a modular subsystem's initcall. If the
- * subsystem is built as a module, it will be assigned a new subsys_id and set
- * up for use. If the subsystem is built-in anyway, work is delegated to the
- * simpler cgroup_init_subsys.
- */
-int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
-{
- struct cgroup_subsys_state *css;
- int i, ret;
- struct hlist_node *tmp;
- struct css_set *cset;
- unsigned long key;
-
- /* check name and function validity */
- if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
- ss->css_alloc == NULL || ss->css_free == NULL)
- return -EINVAL;
-
- /*
- * we don't support callbacks in modular subsystems. this check is
- * before the ss->module check for consistency; a subsystem that could
- * be a module should still have no callbacks even if the user isn't
- * compiling it as one.
- */
- if (ss->fork || ss->exit)
- return -EINVAL;
-
- /*
- * an optionally modular subsystem is built-in: we want to do nothing,
- * since cgroup_init_subsys will have already taken care of it.
- */
- if (ss->module == NULL) {
- /* a sanity check */
- BUG_ON(cgroup_subsys[ss->subsys_id] != ss);
- return 0;
- }
-
- /* init base cftset */
- cgroup_init_cftsets(ss);
-
- mutex_lock(&cgroup_mutex);
- cgroup_subsys[ss->subsys_id] = ss;
-
- /*
- * no ss->css_alloc seems to need anything important in the ss
- * struct, so this can happen first (i.e. before the dummy root
- * attachment).
- */
- css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
- if (IS_ERR(css)) {
- /* failure case - need to deassign the cgroup_subsys[] slot. */
- cgroup_subsys[ss->subsys_id] = NULL;
- mutex_unlock(&cgroup_mutex);
- return PTR_ERR(css);
- }
-
- list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
- ss->root = &cgroup_dummy_root;
-
- /* our new subsystem will be attached to the dummy hierarchy. */
- init_css(css, ss, cgroup_dummy_top);
-
- /*
- * Now we need to entangle the css into the existing css_sets. unlike
- * in cgroup_init_subsys, there are now multiple css_sets, so each one
- * will need a new pointer to it; done by iterating the css_set_table.
- * furthermore, modifying the existing css_sets will corrupt the hash
- * table state, so each changed css_set will need its hash recomputed.
- * this is all done under the css_set_lock.
- */
- write_lock(&css_set_lock);
- hash_for_each_safe(css_set_table, i, tmp, cset, hlist) {
- /* skip entries that we already rehashed */
- if (cset->subsys[ss->subsys_id])
- continue;
- /* remove existing entry */
- hash_del(&cset->hlist);
- /* set new value */
- cset->subsys[ss->subsys_id] = css;
- /* recompute hash and restore entry */
- key = css_set_hash(cset->subsys);
- hash_add(css_set_table, &cset->hlist, key);
- }
- write_unlock(&css_set_lock);
-
- ret = online_css(css);
- if (ret)
- goto err_unload;
-
- /* success! */
- mutex_unlock(&cgroup_mutex);
- return 0;
-
-err_unload:
- mutex_unlock(&cgroup_mutex);
- /* @ss can't be mounted here as try_module_get() would fail */
- cgroup_unload_subsys(ss);
- return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_load_subsys);
-
-/**
- * cgroup_unload_subsys: unload a modular subsystem
- * @ss: the subsystem to unload
- *
- * This function should be called in a modular subsystem's exitcall. When this
- * function is invoked, the refcount on the subsystem's module will be 0, so
- * the subsystem will not be attached to any hierarchy.
- */
-void cgroup_unload_subsys(struct cgroup_subsys *ss)
-{
- struct cgrp_cset_link *link;
-
- BUG_ON(ss->module == NULL);
-
- /*
- * we shouldn't be called if the subsystem is in use, and the use of
- * try_module_get() in rebind_subsystems() should ensure that it
- * doesn't start being used while we're killing it off.
- */
- BUG_ON(ss->root != &cgroup_dummy_root);
-
- mutex_lock(&cgroup_mutex);
-
- offline_css(cgroup_css(cgroup_dummy_top, ss));
-
- /* deassign the subsys_id */
- cgroup_subsys[ss->subsys_id] = NULL;
-
- /* remove subsystem from the dummy root's list of subsystems */
- list_del_init(&ss->sibling);
-
- /*
- * disentangle the css from all css_sets attached to the dummy
- * top. as in loading, we need to pay our respects to the hashtable
- * gods.
- */
- write_lock(&css_set_lock);
- list_for_each_entry(link, &cgroup_dummy_top->cset_links, cset_link) {
- struct css_set *cset = link->cset;
- unsigned long key;
-
- hash_del(&cset->hlist);
- cset->subsys[ss->subsys_id] = NULL;
- key = css_set_hash(cset->subsys);
- hash_add(css_set_table, &cset->hlist, key);
- }
- write_unlock(&css_set_lock);
-
- /*
- * remove subsystem's css from the cgroup_dummy_top and free it -
- * need to free before marking as null because ss->css_free needs
- * the cgrp->subsys pointer to find their state.
- */
- ss->css_free(cgroup_css(cgroup_dummy_top, ss));
- RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
+ cgrp_dfl_root.cgrp.subsys_mask |= 1 << ss->id;
mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
}
-EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
/**
* cgroup_init_early - cgroup initialization at system boot
@@ -4994,34 +4163,24 @@ EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
*/
int __init cgroup_init_early(void)
{
+ static struct cgroup_sb_opts __initdata opts =
+ { .flags = CGRP_ROOT_SANE_BEHAVIOR };
struct cgroup_subsys *ss;
int i;
- atomic_set(&init_css_set.refcount, 1);
- INIT_LIST_HEAD(&init_css_set.cgrp_links);
- INIT_LIST_HEAD(&init_css_set.tasks);
- INIT_HLIST_NODE(&init_css_set.hlist);
- css_set_count = 1;
- init_cgroup_root(&cgroup_dummy_root);
- cgroup_root_count = 1;
+ init_cgroup_root(&cgrp_dfl_root, &opts);
RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
- init_cgrp_cset_link.cset = &init_css_set;
- init_cgrp_cset_link.cgrp = cgroup_dummy_top;
- list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links);
- list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
-
- /* at bootup time, we don't worry about modular subsystems */
- for_each_builtin_subsys(ss, i) {
- BUG_ON(!ss->name);
- BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
- BUG_ON(!ss->css_alloc);
- BUG_ON(!ss->css_free);
- if (ss->subsys_id != i) {
- printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
- ss->name, ss->subsys_id);
- BUG();
- }
+ for_each_subsys(ss, i) {
+ WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
+ "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
+ i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
+ ss->id, ss->name);
+ WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
+ "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
+
+ ss->id = i;
+ ss->name = cgroup_subsys_name[i];
if (ss->early_init)
cgroup_init_subsys(ss);
@@ -5039,53 +4198,46 @@ int __init cgroup_init(void)
{
struct cgroup_subsys *ss;
unsigned long key;
- int i, err;
+ int ssid, err;
- err = bdi_init(&cgroup_backing_dev_info);
- if (err)
- return err;
+ BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
- for_each_builtin_subsys(ss, i) {
- if (!ss->early_init)
- cgroup_init_subsys(ss);
- }
-
- /* allocate id for the dummy hierarchy */
+ mutex_lock(&cgroup_tree_mutex);
mutex_lock(&cgroup_mutex);
- mutex_lock(&cgroup_root_mutex);
/* Add init_css_set to the hash table */
key = css_set_hash(init_css_set.subsys);
hash_add(css_set_table, &init_css_set.hlist, key);
- BUG_ON(cgroup_init_root_id(&cgroup_dummy_root, 0, 1));
-
- err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top,
- 0, 1, GFP_KERNEL);
- BUG_ON(err < 0);
+ BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
- mutex_unlock(&cgroup_root_mutex);
mutex_unlock(&cgroup_mutex);
+ mutex_unlock(&cgroup_tree_mutex);
- cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
- if (!cgroup_kobj) {
- err = -ENOMEM;
- goto out;
+ for_each_subsys(ss, ssid) {
+ if (!ss->early_init)
+ cgroup_init_subsys(ss);
+
+ /*
+ * cftype registration needs kmalloc and can't be done
+ * during early_init. Register base cftypes separately.
+ */
+ if (ss->base_cftypes)
+ WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
}
+ cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
+ if (!cgroup_kobj)
+ return -ENOMEM;
+
err = register_filesystem(&cgroup_fs_type);
if (err < 0) {
kobject_put(cgroup_kobj);
- goto out;
+ return err;
}
proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
-
-out:
- if (err)
- bdi_destroy(&cgroup_backing_dev_info);
-
- return err;
+ return 0;
}
static int __init cgroup_wq_init(void)
@@ -5100,6 +4252,15 @@ static int __init cgroup_wq_init(void)
*/
cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
BUG_ON(!cgroup_destroy_wq);
+
+ /*
+ * Used to destroy pidlists and separate to serve as flush domain.
+ * Cap @max_active to 1 too.
+ */
+ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy",
+ 0, 1);
+ BUG_ON(!cgroup_pidlist_destroy_wq);
+
return 0;
}
core_initcall(cgroup_wq_init);
@@ -5108,12 +4269,6 @@ core_initcall(cgroup_wq_init);
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
* - Used for /proc/<pid>/cgroup.
- * - No need to task_lock(tsk) on this tsk->cgroup reference, as it
- * doesn't really matter if tsk->cgroup changes after we read it,
- * and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
- * anyway. No need to check that tsk->cgroup != NULL, thanks to
- * the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
- * cgroup to top_cgroup.
*/
/* TODO: Use a proper seq_file iterator */
@@ -5121,12 +4276,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
{
struct pid *pid;
struct task_struct *tsk;
- char *buf;
+ char *buf, *path;
int retval;
- struct cgroupfs_root *root;
+ struct cgroup_root *root;
retval = -ENOMEM;
- buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf)
goto out;
@@ -5139,28 +4294,36 @@ int proc_cgroup_show(struct seq_file *m, void *v)
retval = 0;
mutex_lock(&cgroup_mutex);
+ down_read(&css_set_rwsem);
- for_each_active_root(root) {
+ for_each_root(root) {
struct cgroup_subsys *ss;
struct cgroup *cgrp;
- int count = 0;
+ int ssid, count = 0;
+
+ if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible)
+ continue;
seq_printf(m, "%d:", root->hierarchy_id);
- for_each_root_subsys(root, ss)
- seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+ for_each_subsys(ss, ssid)
+ if (root->cgrp.subsys_mask & (1 << ssid))
+ seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
if (strlen(root->name))
seq_printf(m, "%sname=%s", count ? "," : "",
root->name);
seq_putc(m, ':');
cgrp = task_cgroup_from_root(tsk, root);
- retval = cgroup_path(cgrp, buf, PAGE_SIZE);
- if (retval < 0)
+ path = cgroup_path(cgrp, buf, PATH_MAX);
+ if (!path) {
+ retval = -ENAMETOOLONG;
goto out_unlock;
- seq_puts(m, buf);
+ }
+ seq_puts(m, path);
seq_putc(m, '\n');
}
out_unlock:
+ up_read(&css_set_rwsem);
mutex_unlock(&cgroup_mutex);
put_task_struct(tsk);
out_free:
@@ -5186,7 +4349,7 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
for_each_subsys(ss, i)
seq_printf(m, "%s\t%d\t%d\t%d\n",
ss->name, ss->root->hierarchy_id,
- ss->root->number_of_cgroups, !ss->disabled);
+ atomic_read(&ss->root->nr_cgrps), !ss->disabled);
mutex_unlock(&cgroup_mutex);
return 0;
@@ -5205,27 +4368,16 @@ static const struct file_operations proc_cgroupstats_operations = {
};
/**
- * cgroup_fork - attach newly forked task to its parents cgroup.
+ * cgroup_fork - initialize cgroup related fields during copy_process()
* @child: pointer to task_struct of forking parent process.
*
- * Description: A task inherits its parent's cgroup at fork().
- *
- * A pointer to the shared css_set was automatically copied in
- * fork.c by dup_task_struct(). However, we ignore that copy, since
- * it was not made under the protection of RCU or cgroup_mutex, so
- * might no longer be a valid cgroup pointer. cgroup_attach_task() might
- * have already changed current->cgroups, allowing the previously
- * referenced cgroup group to be removed and freed.
- *
- * At the point that cgroup_fork() is called, 'current' is the parent
- * task, and the passed argument 'child' points to the child task.
+ * A task is associated with the init_css_set until cgroup_post_fork()
+ * attaches it to the parent's css_set. Empty cg_list indicates that
+ * @child isn't holding reference to its css_set.
*/
void cgroup_fork(struct task_struct *child)
{
- task_lock(current);
- get_css_set(task_css_set(current));
- child->cgroups = current->cgroups;
- task_unlock(current);
+ RCU_INIT_POINTER(child->cgroups, &init_css_set);
INIT_LIST_HEAD(&child->cg_list);
}
@@ -5245,23 +4397,37 @@ void cgroup_post_fork(struct task_struct *child)
int i;
/*
- * use_task_css_set_links is set to 1 before we walk the tasklist
- * under the tasklist_lock and we read it here after we added the child
- * to the tasklist under the tasklist_lock as well. If the child wasn't
- * yet in the tasklist when we walked through it from
- * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
- * should be visible now due to the paired locking and barriers implied
- * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
- * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
- * lock on fork.
+ * This may race against cgroup_enable_task_cg_links(). As that
+ * function sets use_task_css_set_links before grabbing
+ * tasklist_lock and we just went through tasklist_lock to add
+ * @child, it's guaranteed that either we see the set
+ * use_task_css_set_links or cgroup_enable_task_cg_lists() sees
+ * @child during its iteration.
+ *
+ * If we won the race, @child is associated with %current's
+ * css_set. Grabbing css_set_rwsem guarantees both that the
+ * association is stable, and, on completion of the parent's
+ * migration, @child is visible in the source of migration or
+ * already in the destination cgroup. This guarantee is necessary
+ * when implementing operations which need to migrate all tasks of
+ * a cgroup to another.
+ *
+ * Note that if we lose to cgroup_enable_task_cg_links(), @child
+ * will remain in init_css_set. This is safe because all tasks are
+ * in the init_css_set before cg_links is enabled and there's no
+ * operation which transfers all tasks out of init_css_set.
*/
if (use_task_css_set_links) {
- write_lock(&css_set_lock);
- task_lock(child);
- if (list_empty(&child->cg_list))
- list_add(&child->cg_list, &task_css_set(child)->tasks);
- task_unlock(child);
- write_unlock(&css_set_lock);
+ struct css_set *cset;
+
+ down_write(&css_set_rwsem);
+ cset = task_css_set(current);
+ if (list_empty(&child->cg_list)) {
+ rcu_assign_pointer(child->cgroups, cset);
+ list_add(&child->cg_list, &cset->tasks);
+ get_css_set(cset);
+ }
+ up_write(&css_set_rwsem);
}
/*
@@ -5270,15 +4436,7 @@ void cgroup_post_fork(struct task_struct *child)
* and addition to css_set.
*/
if (need_forkexit_callback) {
- /*
- * fork/exit callbacks are supported only for builtin
- * subsystems, and the builtin section of the subsys
- * array is immutable, so we don't need to lock the
- * subsys array here. On the other hand, modular section
- * of the array can be freed at module unload, so we
- * can't touch that.
- */
- for_each_builtin_subsys(ss, i)
+ for_each_subsys(ss, i)
if (ss->fork)
ss->fork(child);
}
@@ -5287,7 +4445,6 @@ void cgroup_post_fork(struct task_struct *child)
/**
* cgroup_exit - detach cgroup from exiting task
* @tsk: pointer to task_struct of exiting process
- * @run_callback: run exit callbacks?
*
* Description: Detach cgroup from @tsk and release it.
*
@@ -5297,57 +4454,38 @@ void cgroup_post_fork(struct task_struct *child)
* use notify_on_release cgroups where very high task exit scaling
* is required on large systems.
*
- * the_top_cgroup_hack:
- *
- * Set the exiting tasks cgroup to the root cgroup (top_cgroup).
- *
- * We call cgroup_exit() while the task is still competent to
- * handle notify_on_release(), then leave the task attached to the
- * root cgroup in each hierarchy for the remainder of its exit.
- *
- * To do this properly, we would increment the reference count on
- * top_cgroup, and near the very end of the kernel/exit.c do_exit()
- * code we would add a second cgroup function call, to drop that
- * reference. This would just create an unnecessary hot spot on
- * the top_cgroup reference count, to no avail.
- *
- * Normally, holding a reference to a cgroup without bumping its
- * count is unsafe. The cgroup could go away, or someone could
- * attach us to a different cgroup, decrementing the count on
- * the first cgroup that we never incremented. But in this case,
- * top_cgroup isn't going away, and either task has PF_EXITING set,
- * which wards off any cgroup_attach_task() attempts, or task is a failed
- * fork, never visible to cgroup_attach_task.
+ * We set the exiting tasks cgroup to the root cgroup (top_cgroup). We
+ * call cgroup_exit() while the task is still competent to handle
+ * notify_on_release(), then leave the task attached to the root cgroup in
+ * each hierarchy for the remainder of its exit. No need to bother with
+ * init_css_set refcnting. init_css_set never goes away and we can't race
+ * with migration path - PF_EXITING is visible to migration path.
*/
-void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+void cgroup_exit(struct task_struct *tsk)
{
struct cgroup_subsys *ss;
struct css_set *cset;
+ bool put_cset = false;
int i;
/*
- * Unlink from the css_set task list if necessary.
- * Optimistically check cg_list before taking
- * css_set_lock
+ * Unlink from @tsk from its css_set. As migration path can't race
+ * with us, we can check cg_list without grabbing css_set_rwsem.
*/
if (!list_empty(&tsk->cg_list)) {
- write_lock(&css_set_lock);
- if (!list_empty(&tsk->cg_list))
- list_del_init(&tsk->cg_list);
- write_unlock(&css_set_lock);
+ down_write(&css_set_rwsem);
+ list_del_init(&tsk->cg_list);
+ up_write(&css_set_rwsem);
+ put_cset = true;
}
/* Reassign the task to the init_css_set. */
- task_lock(tsk);
cset = task_css_set(tsk);
RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
- if (run_callbacks && need_forkexit_callback) {
- /*
- * fork/exit callbacks are supported only for builtin
- * subsystems, see cgroup_post_fork() for details.
- */
- for_each_builtin_subsys(ss, i) {
+ if (need_forkexit_callback) {
+ /* see cgroup_post_fork() for details */
+ for_each_subsys(ss, i) {
if (ss->exit) {
struct cgroup_subsys_state *old_css = cset->subsys[i];
struct cgroup_subsys_state *css = task_css(tsk, i);
@@ -5356,9 +4494,9 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
}
}
}
- task_unlock(tsk);
- put_css_set_taskexit(cset);
+ if (put_cset)
+ put_css_set(cset, true);
}
static void check_for_release(struct cgroup *cgrp)
@@ -5415,16 +4553,17 @@ static void cgroup_release_agent(struct work_struct *work)
while (!list_empty(&release_list)) {
char *argv[3], *envp[3];
int i;
- char *pathbuf = NULL, *agentbuf = NULL;
+ char *pathbuf = NULL, *agentbuf = NULL, *path;
struct cgroup *cgrp = list_entry(release_list.next,
struct cgroup,
release_list);
list_del_init(&cgrp->release_list);
raw_spin_unlock(&release_list_lock);
- pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!pathbuf)
goto continue_free;
- if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
+ path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+ if (!path)
goto continue_free;
agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
if (!agentbuf)
@@ -5432,7 +4571,7 @@ static void cgroup_release_agent(struct work_struct *work)
i = 0;
argv[i++] = agentbuf;
- argv[i++] = pathbuf;
+ argv[i++] = path;
argv[i] = NULL;
i = 0;
@@ -5466,11 +4605,7 @@ static int __init cgroup_disable(char *str)
if (!*token)
continue;
- /*
- * cgroup_disable, being at boot time, can't know about
- * module subsystems, so we don't worry about them.
- */
- for_each_builtin_subsys(ss, i) {
+ for_each_subsys(ss, i) {
if (!strcmp(token, ss->name)) {
ss->disabled = 1;
printk(KERN_INFO "Disabling %s control group"
@@ -5484,28 +4619,42 @@ static int __init cgroup_disable(char *str)
__setup("cgroup_disable=", cgroup_disable);
/**
- * css_from_dir - get corresponding css from the dentry of a cgroup dir
+ * css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir
* @dentry: directory dentry of interest
* @ss: subsystem of interest
*
- * Must be called under RCU read lock. The caller is responsible for
- * pinning the returned css if it needs to be accessed outside the RCU
- * critical section.
+ * If @dentry is a directory for a cgroup which has @ss enabled on it, try
+ * to get the corresponding css and return it. If such css doesn't exist
+ * or can't be pinned, an ERR_PTR value is returned.
*/
-struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
- struct cgroup_subsys *ss)
+struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
+ struct cgroup_subsys *ss)
{
+ struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
+ struct cgroup_subsys_state *css = NULL;
struct cgroup *cgrp;
- WARN_ON_ONCE(!rcu_read_lock_held());
-
/* is @dentry a cgroup dir? */
- if (!dentry->d_inode ||
- dentry->d_inode->i_op != &cgroup_dir_inode_operations)
+ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+ kernfs_type(kn) != KERNFS_DIR)
return ERR_PTR(-EBADF);
- cgrp = __d_cgrp(dentry);
- return cgroup_css(cgrp, ss) ?: ERR_PTR(-ENOENT);
+ rcu_read_lock();
+
+ /*
+ * This path doesn't originate from kernfs and @kn could already
+ * have been or be removed at any point. @kn->priv is RCU
+ * protected for this access. See destroy_locked() for details.
+ */
+ cgrp = rcu_dereference(kn->priv);
+ if (cgrp)
+ css = cgroup_css(cgrp, ss);
+
+ if (!css || !css_tryget(css))
+ css = ERR_PTR(-ENOENT);
+
+ rcu_read_unlock();
+ return css;
}
/**
@@ -5520,9 +4669,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
{
struct cgroup *cgrp;
- rcu_lockdep_assert(rcu_read_lock_held() ||
- lockdep_is_held(&cgroup_mutex),
- "css_from_id() needs proper protection");
+ cgroup_assert_mutexes_or_rcu_locked();
cgrp = idr_find(&ss->root->cgroup_idr, id);
if (cgrp)
@@ -5570,55 +4717,62 @@ static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
return count;
}
-static int current_css_set_cg_links_read(struct cgroup_subsys_state *css,
- struct cftype *cft,
- struct seq_file *seq)
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
{
struct cgrp_cset_link *link;
struct css_set *cset;
+ char *name_buf;
+
+ name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+ if (!name_buf)
+ return -ENOMEM;
- read_lock(&css_set_lock);
+ down_read(&css_set_rwsem);
rcu_read_lock();
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
- const char *name;
- if (c->dentry)
- name = c->dentry->d_name.name;
- else
- name = "?";
+ cgroup_name(c, name_buf, NAME_MAX + 1);
seq_printf(seq, "Root %d group %s\n",
- c->root->hierarchy_id, name);
+ c->root->hierarchy_id, name_buf);
}
rcu_read_unlock();
- read_unlock(&css_set_lock);
+ up_read(&css_set_rwsem);
+ kfree(name_buf);
return 0;
}
#define MAX_TASKS_SHOWN_PER_CSS 25
-static int cgroup_css_links_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *seq)
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
{
+ struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
- read_lock(&css_set_lock);
+ down_read(&css_set_rwsem);
list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
struct css_set *cset = link->cset;
struct task_struct *task;
int count = 0;
+
seq_printf(seq, "css_set %p\n", cset);
+
list_for_each_entry(task, &cset->tasks, cg_list) {
- if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
- seq_puts(seq, " ...\n");
- break;
- } else {
- seq_printf(seq, " task %d\n",
- task_pid_vnr(task));
- }
+ if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+ goto overflow;
+ seq_printf(seq, " task %d\n", task_pid_vnr(task));
+ }
+
+ list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+ if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+ goto overflow;
+ seq_printf(seq, " task %d\n", task_pid_vnr(task));
}
+ continue;
+ overflow:
+ seq_puts(seq, " ...\n");
}
- read_unlock(&css_set_lock);
+ up_read(&css_set_rwsem);
return 0;
}
@@ -5645,12 +4799,12 @@ static struct cftype debug_files[] = {
{
.name = "current_css_set_cg_links",
- .read_seq_string = current_css_set_cg_links_read,
+ .seq_show = current_css_set_cg_links_read,
},
{
.name = "cgroup_css_links",
- .read_seq_string = cgroup_css_links_read,
+ .seq_show = cgroup_css_links_read,
},
{
@@ -5661,11 +4815,9 @@ static struct cftype debug_files[] = {
{ } /* terminate */
};
-struct cgroup_subsys debug_subsys = {
- .name = "debug",
+struct cgroup_subsys debug_cgrp_subsys = {
.css_alloc = debug_css_alloc,
.css_free = debug_css_free,
- .subsys_id = debug_subsys_id,
.base_cftypes = debug_files,
};
#endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index f0ff64d0ebaa..2bc4a2256444 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -52,7 +52,7 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
static inline struct freezer *task_freezer(struct task_struct *task)
{
- return css_freezer(task_css(task, freezer_subsys_id));
+ return css_freezer(task_css(task, freezer_cgrp_id));
}
static struct freezer *parent_freezer(struct freezer *freezer)
@@ -84,8 +84,6 @@ static const char *freezer_state_strs(unsigned int state)
return "THAWED";
};
-struct cgroup_subsys freezer_subsys;
-
static struct cgroup_subsys_state *
freezer_css_alloc(struct cgroup_subsys_state *parent_css)
{
@@ -189,7 +187,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
* current state before executing the following - !frozen tasks may
* be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
*/
- cgroup_taskset_for_each(task, new_css, tset) {
+ cgroup_taskset_for_each(task, tset) {
if (!(freezer->state & CGROUP_FREEZING)) {
__thaw_task(task);
} else {
@@ -216,6 +214,16 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
}
}
+/**
+ * freezer_fork - cgroup post fork callback
+ * @task: a task which has just been forked
+ *
+ * @task has just been created and should conform to the current state of
+ * the cgroup_freezer it belongs to. This function may race against
+ * freezer_attach(). Losing to freezer_attach() means that we don't have
+ * to do anything as freezer_attach() will put @task into the appropriate
+ * state.
+ */
static void freezer_fork(struct task_struct *task)
{
struct freezer *freezer;
@@ -224,14 +232,26 @@ static void freezer_fork(struct task_struct *task)
freezer = task_freezer(task);
/*
- * The root cgroup is non-freezable, so we can skip the
- * following check.
+ * The root cgroup is non-freezable, so we can skip locking the
+ * freezer. This is safe regardless of race with task migration.
+ * If we didn't race or won, skipping is obviously the right thing
+ * to do. If we lost and root is the new cgroup, noop is still the
+ * right thing to do.
*/
if (!parent_freezer(freezer))
goto out;
+ /*
+ * Grab @freezer->lock and freeze @task after verifying @task still
+ * belongs to @freezer and it's freezing. The former is for the
+ * case where we have raced against task migration and lost and
+ * @task is already in a different cgroup which may not be frozen.
+ * This isn't strictly necessary as freeze_task() is allowed to be
+ * called spuriously but let's do it anyway for, if nothing else,
+ * documentation.
+ */
spin_lock_irq(&freezer->lock);
- if (freezer->state & CGROUP_FREEZING)
+ if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING))
freeze_task(task);
spin_unlock_irq(&freezer->lock);
out:
@@ -301,10 +321,9 @@ out_unlock:
spin_unlock_irq(&freezer->lock);
}
-static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
- struct seq_file *m)
+static int freezer_read(struct seq_file *m, void *v)
{
- struct cgroup_subsys_state *pos;
+ struct cgroup_subsys_state *css = seq_css(m), *pos;
rcu_read_lock();
@@ -423,7 +442,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
}
static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
- const char *buffer)
+ char *buffer)
{
bool freeze;
@@ -458,7 +477,7 @@ static struct cftype files[] = {
{
.name = "state",
.flags = CFTYPE_NOT_ON_ROOT,
- .read_seq_string = freezer_read,
+ .seq_show = freezer_read,
.write_string = freezer_write,
},
{
@@ -474,13 +493,11 @@ static struct cftype files[] = {
{ } /* terminate */
};
-struct cgroup_subsys freezer_subsys = {
- .name = "freezer",
+struct cgroup_subsys freezer_cgrp_subsys = {
.css_alloc = freezer_css_alloc,
.css_online = freezer_css_online,
.css_offline = freezer_css_offline,
.css_free = freezer_css_free,
- .subsys_id = freezer_subsys_id,
.attach = freezer_attach,
.fork = freezer_fork,
.base_cftypes = files,
diff --git a/kernel/compat.c b/kernel/compat.c
index 0a09e481b70b..e40b0430b562 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -30,28 +30,6 @@
#include <asm/uaccess.h>
-/*
- * Get/set struct timeval with struct timespec on the native side
- */
-static int compat_get_timeval_convert(struct timespec *o,
- struct compat_timeval __user *i)
-{
- long usec;
-
- if (get_user(o->tv_sec, &i->tv_sec) ||
- get_user(usec, &i->tv_usec))
- return -EFAULT;
- o->tv_nsec = usec * 1000;
- return 0;
-}
-
-static int compat_put_timeval_convert(struct compat_timeval __user *o,
- struct timeval *i)
-{
- return (put_user(i->tv_sec, &o->tv_sec) ||
- put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
-}
-
static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
{
memset(txc, 0, sizeof(struct timex));
@@ -110,13 +88,13 @@ static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc)
return 0;
}
-asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
- struct timezone __user *tz)
+COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv,
+ struct timezone __user *, tz)
{
if (tv) {
struct timeval ktv;
do_gettimeofday(&ktv);
- if (compat_put_timeval_convert(tv, &ktv))
+ if (compat_put_timeval(&ktv, tv))
return -EFAULT;
}
if (tz) {
@@ -127,62 +105,61 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
return 0;
}
-asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
- struct timezone __user *tz)
+COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv,
+ struct timezone __user *, tz)
{
- struct timespec kts;
- struct timezone ktz;
+ struct timeval user_tv;
+ struct timespec new_ts;
+ struct timezone new_tz;
if (tv) {
- if (compat_get_timeval_convert(&kts, tv))
+ if (compat_get_timeval(&user_tv, tv))
return -EFAULT;
+ new_ts.tv_sec = user_tv.tv_sec;
+ new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
}
if (tz) {
- if (copy_from_user(&ktz, tz, sizeof(ktz)))
+ if (copy_from_user(&new_tz, tz, sizeof(*tz)))
return -EFAULT;
}
- return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+ return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
-int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
+static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
{
return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) ||
__get_user(tv->tv_sec, &ctv->tv_sec) ||
__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
}
-EXPORT_SYMBOL_GPL(get_compat_timeval);
-int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
+static int __compat_put_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
{
return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) ||
__put_user(tv->tv_sec, &ctv->tv_sec) ||
__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
}
-EXPORT_SYMBOL_GPL(put_compat_timeval);
-int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
+static int __compat_get_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
{
return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
__get_user(ts->tv_sec, &cts->tv_sec) ||
__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
}
-EXPORT_SYMBOL_GPL(get_compat_timespec);
-int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
+static int __compat_put_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
{
return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) ||
__put_user(ts->tv_sec, &cts->tv_sec) ||
__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
}
-EXPORT_SYMBOL_GPL(put_compat_timespec);
int compat_get_timeval(struct timeval *tv, const void __user *utv)
{
if (COMPAT_USE_64BIT_TIME)
return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0;
else
- return get_compat_timeval(tv, utv);
+ return __compat_get_timeval(tv, utv);
}
EXPORT_SYMBOL_GPL(compat_get_timeval);
@@ -191,7 +168,7 @@ int compat_put_timeval(const struct timeval *tv, void __user *utv)
if (COMPAT_USE_64BIT_TIME)
return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0;
else
- return put_compat_timeval(tv, utv);
+ return __compat_put_timeval(tv, utv);
}
EXPORT_SYMBOL_GPL(compat_put_timeval);
@@ -200,7 +177,7 @@ int compat_get_timespec(struct timespec *ts, const void __user *uts)
if (COMPAT_USE_64BIT_TIME)
return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0;
else
- return get_compat_timespec(ts, uts);
+ return __compat_get_timespec(ts, uts);
}
EXPORT_SYMBOL_GPL(compat_get_timespec);
@@ -209,10 +186,33 @@ int compat_put_timespec(const struct timespec *ts, void __user *uts)
if (COMPAT_USE_64BIT_TIME)
return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0;
else
- return put_compat_timespec(ts, uts);
+ return __compat_put_timespec(ts, uts);
}
EXPORT_SYMBOL_GPL(compat_put_timespec);
+int compat_convert_timespec(struct timespec __user **kts,
+ const void __user *cts)
+{
+ struct timespec ts;
+ struct timespec __user *uts;
+
+ if (!cts || COMPAT_USE_64BIT_TIME) {
+ *kts = (struct timespec __user *)cts;
+ return 0;
+ }
+
+ uts = compat_alloc_user_space(sizeof(ts));
+ if (!uts)
+ return -EFAULT;
+ if (compat_get_timespec(&ts, cts))
+ return -EFAULT;
+ if (copy_to_user(uts, &ts, sizeof(ts)))
+ return -EFAULT;
+
+ *kts = uts;
+ return 0;
+}
+
static long compat_nanosleep_restart(struct restart_block *restart)
{
struct compat_timespec __user *rmtp;
@@ -229,21 +229,21 @@ static long compat_nanosleep_restart(struct restart_block *restart)
if (ret) {
rmtp = restart->nanosleep.compat_rmtp;
- if (rmtp && put_compat_timespec(&rmt, rmtp))
+ if (rmtp && compat_put_timespec(&rmt, rmtp))
return -EFAULT;
}
return ret;
}
-asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
- struct compat_timespec __user *rmtp)
+COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
+ struct compat_timespec __user *, rmtp)
{
struct timespec tu, rmt;
mm_segment_t oldfs;
long ret;
- if (get_compat_timespec(&tu, rqtp))
+ if (compat_get_timespec(&tu, rqtp))
return -EFAULT;
if (!timespec_valid(&tu))
@@ -263,7 +263,7 @@ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
restart->fn = compat_nanosleep_restart;
restart->nanosleep.compat_rmtp = rmtp;
- if (rmtp && put_compat_timespec(&rmt, rmtp))
+ if (rmtp && compat_put_timespec(&rmt, rmtp))
return -EFAULT;
}
@@ -328,7 +328,7 @@ static compat_clock_t clock_t_to_compat_clock_t(clock_t x)
return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
}
-asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
+COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf)
{
if (tbuf) {
struct tms tms;
@@ -354,7 +354,7 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
* types that can be passed to put_user()/get_user().
*/
-asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set)
+COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set)
{
old_sigset_t s;
long ret;
@@ -424,8 +424,8 @@ COMPAT_SYSCALL_DEFINE3(sigprocmask, int, how,
#endif
-asmlinkage long compat_sys_setrlimit(unsigned int resource,
- struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource,
+ struct compat_rlimit __user *, rlim)
{
struct rlimit r;
@@ -443,15 +443,15 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource,
#ifdef COMPAT_RLIM_OLD_INFINITY
-asmlinkage long compat_sys_old_getrlimit(unsigned int resource,
- struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+ struct compat_rlimit __user *, rlim)
{
struct rlimit r;
int ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
- ret = sys_old_getrlimit(resource, &r);
+ ret = sys_old_getrlimit(resource, (struct rlimit __user *)&r);
set_fs(old_fs);
if (!ret) {
@@ -470,8 +470,8 @@ asmlinkage long compat_sys_old_getrlimit(unsigned int resource,
#endif
-asmlinkage long compat_sys_getrlimit(unsigned int resource,
- struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource,
+ struct compat_rlimit __user *, rlim)
{
struct rlimit r;
int ret;
@@ -596,9 +596,9 @@ static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr,
return compat_get_bitmap(k, user_mask_ptr, len * 8);
}
-asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
- unsigned int len,
- compat_ulong_t __user *user_mask_ptr)
+COMPAT_SYSCALL_DEFINE3(sched_setaffinity, compat_pid_t, pid,
+ unsigned int, len,
+ compat_ulong_t __user *, user_mask_ptr)
{
cpumask_var_t new_mask;
int retval;
@@ -616,8 +616,8 @@ out:
return retval;
}
-asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
- compat_ulong_t __user *user_mask_ptr)
+COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len,
+ compat_ulong_t __user *, user_mask_ptr)
{
int ret;
cpumask_var_t mask;
@@ -647,8 +647,8 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
int get_compat_itimerspec(struct itimerspec *dst,
const struct compat_itimerspec __user *src)
{
- if (get_compat_timespec(&dst->it_interval, &src->it_interval) ||
- get_compat_timespec(&dst->it_value, &src->it_value))
+ if (__compat_get_timespec(&dst->it_interval, &src->it_interval) ||
+ __compat_get_timespec(&dst->it_value, &src->it_value))
return -EFAULT;
return 0;
}
@@ -656,15 +656,15 @@ int get_compat_itimerspec(struct itimerspec *dst,
int put_compat_itimerspec(struct compat_itimerspec __user *dst,
const struct itimerspec *src)
{
- if (put_compat_timespec(&src->it_interval, &dst->it_interval) ||
- put_compat_timespec(&src->it_value, &dst->it_value))
+ if (__compat_put_timespec(&src->it_interval, &dst->it_interval) ||
+ __compat_put_timespec(&src->it_value, &dst->it_value))
return -EFAULT;
return 0;
}
-long compat_sys_timer_create(clockid_t which_clock,
- struct compat_sigevent __user *timer_event_spec,
- timer_t __user *created_timer_id)
+COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock,
+ struct compat_sigevent __user *, timer_event_spec,
+ timer_t __user *, created_timer_id)
{
struct sigevent __user *event = NULL;
@@ -680,9 +680,9 @@ long compat_sys_timer_create(clockid_t which_clock,
return sys_timer_create(which_clock, event, created_timer_id);
}
-long compat_sys_timer_settime(timer_t timer_id, int flags,
- struct compat_itimerspec __user *new,
- struct compat_itimerspec __user *old)
+COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
+ struct compat_itimerspec __user *, new,
+ struct compat_itimerspec __user *, old)
{
long err;
mm_segment_t oldfs;
@@ -703,8 +703,8 @@ long compat_sys_timer_settime(timer_t timer_id, int flags,
return err;
}
-long compat_sys_timer_gettime(timer_t timer_id,
- struct compat_itimerspec __user *setting)
+COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
+ struct compat_itimerspec __user *, setting)
{
long err;
mm_segment_t oldfs;
@@ -720,14 +720,14 @@ long compat_sys_timer_gettime(timer_t timer_id,
return err;
}
-long compat_sys_clock_settime(clockid_t which_clock,
- struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
+ struct compat_timespec __user *, tp)
{
long err;
mm_segment_t oldfs;
struct timespec ts;
- if (get_compat_timespec(&ts, tp))
+ if (compat_get_timespec(&ts, tp))
return -EFAULT;
oldfs = get_fs();
set_fs(KERNEL_DS);
@@ -737,8 +737,8 @@ long compat_sys_clock_settime(clockid_t which_clock,
return err;
}
-long compat_sys_clock_gettime(clockid_t which_clock,
- struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
+ struct compat_timespec __user *, tp)
{
long err;
mm_segment_t oldfs;
@@ -749,13 +749,13 @@ long compat_sys_clock_gettime(clockid_t which_clock,
err = sys_clock_gettime(which_clock,
(struct timespec __user *) &ts);
set_fs(oldfs);
- if (!err && put_compat_timespec(&ts, tp))
+ if (!err && compat_put_timespec(&ts, tp))
return -EFAULT;
return err;
}
-long compat_sys_clock_adjtime(clockid_t which_clock,
- struct compat_timex __user *utp)
+COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
+ struct compat_timex __user *, utp)
{
struct timex txc;
mm_segment_t oldfs;
@@ -777,8 +777,8 @@ long compat_sys_clock_adjtime(clockid_t which_clock,
return ret;
}
-long compat_sys_clock_getres(clockid_t which_clock,
- struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
+ struct compat_timespec __user *, tp)
{
long err;
mm_segment_t oldfs;
@@ -789,7 +789,7 @@ long compat_sys_clock_getres(clockid_t which_clock,
err = sys_clock_getres(which_clock,
(struct timespec __user *) &ts);
set_fs(oldfs);
- if (!err && tp && put_compat_timespec(&ts, tp))
+ if (!err && tp && compat_put_timespec(&ts, tp))
return -EFAULT;
return err;
}
@@ -799,7 +799,7 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
long err;
mm_segment_t oldfs;
struct timespec tu;
- struct compat_timespec *rmtp = restart->nanosleep.compat_rmtp;
+ struct compat_timespec __user *rmtp = restart->nanosleep.compat_rmtp;
restart->nanosleep.rmtp = (struct timespec __user *) &tu;
oldfs = get_fs();
@@ -808,7 +808,7 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
set_fs(oldfs);
if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
- put_compat_timespec(&tu, rmtp))
+ compat_put_timespec(&tu, rmtp))
return -EFAULT;
if (err == -ERESTART_RESTARTBLOCK) {
@@ -818,16 +818,16 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
return err;
}
-long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
- struct compat_timespec __user *rqtp,
- struct compat_timespec __user *rmtp)
+COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
+ struct compat_timespec __user *, rqtp,
+ struct compat_timespec __user *, rmtp)
{
long err;
mm_segment_t oldfs;
struct timespec in, out;
struct restart_block *restart;
- if (get_compat_timespec(&in, rqtp))
+ if (compat_get_timespec(&in, rqtp))
return -EFAULT;
oldfs = get_fs();
@@ -838,7 +838,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
set_fs(oldfs);
if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
- put_compat_timespec(&out, rmtp))
+ compat_put_timespec(&out, rmtp))
return -EFAULT;
if (err == -ERESTART_RESTARTBLOCK) {
@@ -1010,7 +1010,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese,
/* compat_time_t is a 32 bit "long" and needs to get converted. */
-asmlinkage long compat_sys_time(compat_time_t __user * tloc)
+COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
{
compat_time_t i;
struct timeval tv;
@@ -1026,7 +1026,7 @@ asmlinkage long compat_sys_time(compat_time_t __user * tloc)
return i;
}
-asmlinkage long compat_sys_stime(compat_time_t __user *tptr)
+COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr)
{
struct timespec tv;
int err;
@@ -1046,7 +1046,7 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr)
#endif /* __ARCH_WANT_COMPAT_SYS_TIME */
-asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
+COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp)
{
struct timex txc;
int err, ret;
@@ -1065,11 +1065,11 @@ asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
}
#ifdef CONFIG_NUMA
-asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages,
- compat_uptr_t __user *pages32,
- const int __user *nodes,
- int __user *status,
- int flags)
+COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
+ compat_uptr_t __user *, pages32,
+ const int __user *, nodes,
+ int __user *, status,
+ int, flags)
{
const void __user * __user *pages;
int i;
@@ -1085,10 +1085,10 @@ asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages,
return sys_move_pages(pid, nr_pages, pages, nodes, status, flags);
}
-asmlinkage long compat_sys_migrate_pages(compat_pid_t pid,
- compat_ulong_t maxnode,
- const compat_ulong_t __user *old_nodes,
- const compat_ulong_t __user *new_nodes)
+COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
+ compat_ulong_t, maxnode,
+ const compat_ulong_t __user *, old_nodes,
+ const compat_ulong_t __user *, new_nodes)
{
unsigned long __user *old = NULL;
unsigned long __user *new = NULL;
@@ -1130,7 +1130,7 @@ COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
set_fs(KERNEL_DS);
ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
set_fs(old_fs);
- if (put_compat_timespec(&t, interval))
+ if (compat_put_timespec(&t, interval))
return -EFAULT;
return ret;
}
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index e5f3917aa05b..6cb20d2e7ee0 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -53,10 +53,10 @@ void context_tracking_user_enter(void)
/*
* Repeat the user_enter() check here because some archs may be calling
* this from asm and if no CPU needs context tracking, they shouldn't
- * go further. Repeat the check here until they support the static key
- * check.
+ * go further. Repeat the check here until they support the inline static
+ * key check.
*/
- if (!static_key_false(&context_tracking_enabled))
+ if (!context_tracking_is_enabled())
return;
/*
@@ -160,7 +160,7 @@ void context_tracking_user_exit(void)
{
unsigned long flags;
- if (!static_key_false(&context_tracking_enabled))
+ if (!context_tracking_is_enabled())
return;
if (in_interrupt())
diff --git a/kernel/cpu.c b/kernel/cpu.c
index deff2e693766..a9e710eef0e2 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -19,6 +19,7 @@
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/suspend.h>
+#include <linux/lockdep.h>
#include "smpboot.h"
@@ -27,18 +28,23 @@
static DEFINE_MUTEX(cpu_add_remove_lock);
/*
- * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_mask, cpu_present_mask.
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
*/
void cpu_maps_update_begin(void)
{
mutex_lock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL(cpu_notifier_register_begin);
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL(cpu_notifier_register_done);
static RAW_NOTIFIER_HEAD(cpu_chain);
@@ -57,17 +63,30 @@ static struct {
* an ongoing cpu hotplug operation.
*/
int refcount;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif
} cpu_hotplug = {
.active_writer = NULL,
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
.refcount = 0,
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ .dep_map = {.name = "cpu_hotplug.lock" },
+#endif
};
+/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
+#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
+#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map)
+#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map)
+
void get_online_cpus(void)
{
might_sleep();
if (cpu_hotplug.active_writer == current)
return;
+ cpuhp_lock_acquire_read();
mutex_lock(&cpu_hotplug.lock);
cpu_hotplug.refcount++;
mutex_unlock(&cpu_hotplug.lock);
@@ -87,6 +106,7 @@ void put_online_cpus(void)
if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
wake_up_process(cpu_hotplug.active_writer);
mutex_unlock(&cpu_hotplug.lock);
+ cpuhp_lock_release();
}
EXPORT_SYMBOL_GPL(put_online_cpus);
@@ -117,6 +137,7 @@ void cpu_hotplug_begin(void)
{
cpu_hotplug.active_writer = current;
+ cpuhp_lock_acquire();
for (;;) {
mutex_lock(&cpu_hotplug.lock);
if (likely(!cpu_hotplug.refcount))
@@ -131,6 +152,7 @@ void cpu_hotplug_done(void)
{
cpu_hotplug.active_writer = NULL;
mutex_unlock(&cpu_hotplug.lock);
+ cpuhp_lock_release();
}
/*
@@ -166,6 +188,11 @@ int __ref register_cpu_notifier(struct notifier_block *nb)
return ret;
}
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+ return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
int *nr_calls)
{
@@ -189,6 +216,7 @@ static void cpu_notify_nofail(unsigned long val, void *v)
BUG_ON(cpu_notify(val, v));
}
EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
void __ref unregister_cpu_notifier(struct notifier_block *nb)
{
@@ -198,6 +226,12 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_cpu_notifier);
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+ raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
diff --git a/kernel/cpu/Makefile b/kernel/cpu/Makefile
deleted file mode 100644
index 59ab052ef7a0..000000000000
--- a/kernel/cpu/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y = idle.o
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
deleted file mode 100644
index 988573a9a387..000000000000
--- a/kernel/cpu/idle.c
+++ /dev/null
@@ -1,141 +0,0 @@
-/*
- * Generic entry point for the idle threads
- */
-#include <linux/sched.h>
-#include <linux/cpu.h>
-#include <linux/tick.h>
-#include <linux/mm.h>
-#include <linux/stackprotector.h>
-
-#include <asm/tlb.h>
-
-#include <trace/events/power.h>
-
-static int __read_mostly cpu_idle_force_poll;
-
-void cpu_idle_poll_ctrl(bool enable)
-{
- if (enable) {
- cpu_idle_force_poll++;
- } else {
- cpu_idle_force_poll--;
- WARN_ON_ONCE(cpu_idle_force_poll < 0);
- }
-}
-
-#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
-static int __init cpu_idle_poll_setup(char *__unused)
-{
- cpu_idle_force_poll = 1;
- return 1;
-}
-__setup("nohlt", cpu_idle_poll_setup);
-
-static int __init cpu_idle_nopoll_setup(char *__unused)
-{
- cpu_idle_force_poll = 0;
- return 1;
-}
-__setup("hlt", cpu_idle_nopoll_setup);
-#endif
-
-static inline int cpu_idle_poll(void)
-{
- rcu_idle_enter();
- trace_cpu_idle_rcuidle(0, smp_processor_id());
- local_irq_enable();
- while (!tif_need_resched())
- cpu_relax();
- trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
- rcu_idle_exit();
- return 1;
-}
-
-/* Weak implementations for optional arch specific functions */
-void __weak arch_cpu_idle_prepare(void) { }
-void __weak arch_cpu_idle_enter(void) { }
-void __weak arch_cpu_idle_exit(void) { }
-void __weak arch_cpu_idle_dead(void) { }
-void __weak arch_cpu_idle(void)
-{
- cpu_idle_force_poll = 1;
- local_irq_enable();
-}
-
-/*
- * Generic idle loop implementation
- */
-static void cpu_idle_loop(void)
-{
- while (1) {
- tick_nohz_idle_enter();
-
- while (!need_resched()) {
- check_pgt_cache();
- rmb();
-
- if (cpu_is_offline(smp_processor_id()))
- arch_cpu_idle_dead();
-
- local_irq_disable();
- arch_cpu_idle_enter();
-
- /*
- * In poll mode we reenable interrupts and spin.
- *
- * Also if we detected in the wakeup from idle
- * path that the tick broadcast device expired
- * for us, we don't want to go deep idle as we
- * know that the IPI is going to arrive right
- * away
- */
- if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
- cpu_idle_poll();
- } else {
- if (!current_clr_polling_and_test()) {
- stop_critical_timings();
- rcu_idle_enter();
- arch_cpu_idle();
- WARN_ON_ONCE(irqs_disabled());
- rcu_idle_exit();
- start_critical_timings();
- } else {
- local_irq_enable();
- }
- __current_set_polling();
- }
- arch_cpu_idle_exit();
- /*
- * We need to test and propagate the TIF_NEED_RESCHED
- * bit here because we might not have send the
- * reschedule IPI to idle tasks.
- */
- if (tif_need_resched())
- set_preempt_need_resched();
- }
- tick_nohz_idle_exit();
- schedule_preempt_disabled();
- }
-}
-
-void cpu_startup_entry(enum cpuhp_state state)
-{
- /*
- * This #ifdef needs to die, but it's too late in the cycle to
- * make this generic (arm and sh have never invoked the canary
- * init for the non boot cpus!). Will be fixed in 3.11
- */
-#ifdef CONFIG_X86
- /*
- * If we're the non-boot CPU, nothing set the stack canary up
- * for us. The boot CPU already has it initialized but no harm
- * in doing it again. This is a good place for updating it, as
- * we wont ever return from this function (so the invalid
- * canaries already on the stack wont ever trigger).
- */
- boot_init_stack_canary();
-#endif
- __current_set_polling();
- arch_cpu_idle_prepare();
- cpu_idle_loop();
-}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4772034b4b17..3d54c418bd06 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -119,7 +119,7 @@ static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
/* Retrieve the cpuset for a task */
static inline struct cpuset *task_cs(struct task_struct *task)
{
- return css_cs(task_css(task, cpuset_subsys_id));
+ return css_cs(task_css(task, cpuset_cgrp_id));
}
static inline struct cpuset *parent_cs(struct cpuset *cs)
@@ -467,7 +467,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
* be changed to have empty cpus_allowed or mems_allowed.
*/
ret = -ENOSPC;
- if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress)) {
+ if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) {
if (!cpumask_empty(cur->cpus_allowed) &&
cpumask_empty(trial->cpus_allowed))
goto out;
@@ -829,55 +829,36 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
}
/**
- * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's
- * @tsk: task to test
- * @data: cpuset to @tsk belongs to
- *
- * Called by css_scan_tasks() for each task in a cgroup whose cpus_allowed
- * mask needs to be changed.
- *
- * We don't need to re-check for the cgroup/cpuset membership, since we're
- * holding cpuset_mutex at this point.
- */
-static void cpuset_change_cpumask(struct task_struct *tsk, void *data)
-{
- struct cpuset *cs = data;
- struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
-
- set_cpus_allowed_ptr(tsk, cpus_cs->cpus_allowed);
-}
-
-/**
* update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
* @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
- * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
- *
- * Called with cpuset_mutex held
- *
- * The css_scan_tasks() function will scan all the tasks in a cgroup,
- * calling callback functions for each.
*
- * No return value. It's guaranteed that css_scan_tasks() always returns 0
- * if @heap != NULL.
+ * Iterate through each task of @cs updating its cpus_allowed to the
+ * effective cpuset's. As this function is called with cpuset_mutex held,
+ * cpuset membership stays stable.
*/
-static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
+static void update_tasks_cpumask(struct cpuset *cs)
{
- css_scan_tasks(&cs->css, NULL, cpuset_change_cpumask, cs, heap);
+ struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
+ struct css_task_iter it;
+ struct task_struct *task;
+
+ css_task_iter_start(&cs->css, &it);
+ while ((task = css_task_iter_next(&it)))
+ set_cpus_allowed_ptr(task, cpus_cs->cpus_allowed);
+ css_task_iter_end(&it);
}
/*
* update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy.
* @root_cs: the root cpuset of the hierarchy
* @update_root: update root cpuset or not?
- * @heap: the heap used by css_scan_tasks()
*
* This will update cpumasks of tasks in @root_cs and all other empty cpusets
* which take on cpumask of @root_cs.
*
* Called with cpuset_mutex held
*/
-static void update_tasks_cpumask_hier(struct cpuset *root_cs,
- bool update_root, struct ptr_heap *heap)
+static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
@@ -898,7 +879,7 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs,
continue;
rcu_read_unlock();
- update_tasks_cpumask(cp, heap);
+ update_tasks_cpumask(cp);
rcu_read_lock();
css_put(&cp->css);
@@ -914,7 +895,6 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs,
static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
const char *buf)
{
- struct ptr_heap heap;
int retval;
int is_load_balanced;
@@ -947,19 +927,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (retval < 0)
return retval;
- retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
- if (retval)
- return retval;
-
is_load_balanced = is_sched_load_balance(trialcs);
mutex_lock(&callback_mutex);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
mutex_unlock(&callback_mutex);
- update_tasks_cpumask_hier(cs, true, &heap);
-
- heap_free(&heap);
+ update_tasks_cpumask_hier(cs, true);
if (is_load_balanced)
rebuild_sched_domains_locked();
@@ -974,12 +948,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* Temporarilly set tasks mems_allowed to target nodes of migration,
* so that the migration code can allocate pages on these nodes.
*
- * Call holding cpuset_mutex, so current's cpuset won't change
- * during this call, as manage_mutex holds off any cpuset_attach()
- * calls. Therefore we don't need to take task_lock around the
- * call to guarantee_online_mems(), as we know no one is changing
- * our task's cpuset.
- *
* While the mm_struct we are migrating is typically from some
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
@@ -996,8 +964,10 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+ rcu_read_lock();
mems_cs = effective_nodemask_cpuset(task_cs(tsk));
guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+ rcu_read_unlock();
}
/*
@@ -1026,7 +996,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
task_lock(tsk);
/*
* Determine if a loop is necessary if another thread is doing
- * get_mems_allowed(). If at least one node remains unchanged and
+ * read_mems_allowed_begin(). If at least one node remains unchanged and
* tsk does not have a mempolicy, then an empty nodemask will not be
* possible when mems_allowed is larger than a word.
*/
@@ -1052,53 +1022,22 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
task_unlock(tsk);
}
-struct cpuset_change_nodemask_arg {
- struct cpuset *cs;
- nodemask_t *newmems;
-};
-
-/*
- * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy
- * of it to cpuset's new mems_allowed, and migrate pages to new nodes if
- * memory_migrate flag is set. Called with cpuset_mutex held.
- */
-static void cpuset_change_nodemask(struct task_struct *p, void *data)
-{
- struct cpuset_change_nodemask_arg *arg = data;
- struct cpuset *cs = arg->cs;
- struct mm_struct *mm;
- int migrate;
-
- cpuset_change_task_nodemask(p, arg->newmems);
-
- mm = get_task_mm(p);
- if (!mm)
- return;
-
- migrate = is_memory_migrate(cs);
-
- mpol_rebind_mm(mm, &cs->mems_allowed);
- if (migrate)
- cpuset_migrate_mm(mm, &cs->old_mems_allowed, arg->newmems);
- mmput(mm);
-}
-
static void *cpuset_being_rebound;
/**
* update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
* @cs: the cpuset in which each task's mems_allowed mask needs to be changed
- * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
*
- * Called with cpuset_mutex held. No return value. It's guaranteed that
- * css_scan_tasks() always returns 0 if @heap != NULL.
+ * Iterate through each task of @cs updating its mems_allowed to the
+ * effective cpuset's. As this function is called with cpuset_mutex held,
+ * cpuset membership stays stable.
*/
-static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
+static void update_tasks_nodemask(struct cpuset *cs)
{
static nodemask_t newmems; /* protected by cpuset_mutex */
struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
- struct cpuset_change_nodemask_arg arg = { .cs = cs,
- .newmems = &newmems };
+ struct css_task_iter it;
+ struct task_struct *task;
cpuset_being_rebound = cs; /* causes mpol_dup() rebind */
@@ -1114,7 +1053,25 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
* It's ok if we rebind the same mm twice; mpol_rebind_mm()
* is idempotent. Also migrate pages in each mm to new nodes.
*/
- css_scan_tasks(&cs->css, NULL, cpuset_change_nodemask, &arg, heap);
+ css_task_iter_start(&cs->css, &it);
+ while ((task = css_task_iter_next(&it))) {
+ struct mm_struct *mm;
+ bool migrate;
+
+ cpuset_change_task_nodemask(task, &newmems);
+
+ mm = get_task_mm(task);
+ if (!mm)
+ continue;
+
+ migrate = is_memory_migrate(cs);
+
+ mpol_rebind_mm(mm, &cs->mems_allowed);
+ if (migrate)
+ cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
+ mmput(mm);
+ }
+ css_task_iter_end(&it);
/*
* All the tasks' nodemasks have been updated, update
@@ -1130,15 +1087,13 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
* update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy.
* @cs: the root cpuset of the hierarchy
* @update_root: update the root cpuset or not?
- * @heap: the heap used by css_scan_tasks()
*
* This will update nodemasks of tasks in @root_cs and all other empty cpusets
* which take on nodemask of @root_cs.
*
* Called with cpuset_mutex held
*/
-static void update_tasks_nodemask_hier(struct cpuset *root_cs,
- bool update_root, struct ptr_heap *heap)
+static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
@@ -1159,7 +1114,7 @@ static void update_tasks_nodemask_hier(struct cpuset *root_cs,
continue;
rcu_read_unlock();
- update_tasks_nodemask(cp, heap);
+ update_tasks_nodemask(cp);
rcu_read_lock();
css_put(&cp->css);
@@ -1184,7 +1139,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
const char *buf)
{
int retval;
- struct ptr_heap heap;
/*
* top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
@@ -1223,17 +1177,11 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
if (retval < 0)
goto done;
- retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
- if (retval < 0)
- goto done;
-
mutex_lock(&callback_mutex);
cs->mems_allowed = trialcs->mems_allowed;
mutex_unlock(&callback_mutex);
- update_tasks_nodemask_hier(cs, true, &heap);
-
- heap_free(&heap);
+ update_tasks_nodemask_hier(cs, true);
done:
return retval;
}
@@ -1261,38 +1209,22 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
}
/**
- * cpuset_change_flag - make a task's spread flags the same as its cpuset's
- * @tsk: task to be updated
- * @data: cpuset to @tsk belongs to
- *
- * Called by css_scan_tasks() for each task in a cgroup.
- *
- * We don't need to re-check for the cgroup/cpuset membership, since we're
- * holding cpuset_mutex at this point.
- */
-static void cpuset_change_flag(struct task_struct *tsk, void *data)
-{
- struct cpuset *cs = data;
-
- cpuset_update_task_spread_flag(cs, tsk);
-}
-
-/**
* update_tasks_flags - update the spread flags of tasks in the cpuset.
* @cs: the cpuset in which each task's spread flags needs to be changed
- * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
*
- * Called with cpuset_mutex held
- *
- * The css_scan_tasks() function will scan all the tasks in a cgroup,
- * calling callback functions for each.
- *
- * No return value. It's guaranteed that css_scan_tasks() always returns 0
- * if @heap != NULL.
+ * Iterate through each task of @cs updating its spread flags. As this
+ * function is called with cpuset_mutex held, cpuset membership stays
+ * stable.
*/
-static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap)
+static void update_tasks_flags(struct cpuset *cs)
{
- css_scan_tasks(&cs->css, NULL, cpuset_change_flag, cs, heap);
+ struct css_task_iter it;
+ struct task_struct *task;
+
+ css_task_iter_start(&cs->css, &it);
+ while ((task = css_task_iter_next(&it)))
+ cpuset_update_task_spread_flag(cs, task);
+ css_task_iter_end(&it);
}
/*
@@ -1310,7 +1242,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
struct cpuset *trialcs;
int balance_flag_changed;
int spread_flag_changed;
- struct ptr_heap heap;
int err;
trialcs = alloc_trial_cpuset(cs);
@@ -1326,10 +1257,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
if (err < 0)
goto out;
- err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
- if (err < 0)
- goto out;
-
balance_flag_changed = (is_sched_load_balance(cs) !=
is_sched_load_balance(trialcs));
@@ -1344,8 +1271,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
rebuild_sched_domains_locked();
if (spread_flag_changed)
- update_tasks_flags(cs, &heap);
- heap_free(&heap);
+ update_tasks_flags(cs);
out:
free_trial_cpuset(trialcs);
return err;
@@ -1449,6 +1375,8 @@ static int fmeter_getrate(struct fmeter *fmp)
return val;
}
+static struct cpuset *cpuset_attach_old_cs;
+
/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
static int cpuset_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
@@ -1457,6 +1385,9 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
struct task_struct *task;
int ret;
+ /* used later by cpuset_attach() */
+ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+
mutex_lock(&cpuset_mutex);
/*
@@ -1468,7 +1399,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
(cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
goto out_unlock;
- cgroup_taskset_for_each(task, css, tset) {
+ cgroup_taskset_for_each(task, tset) {
/*
* Kthreads which disallow setaffinity shouldn't be moved
* to a new cpuset; we don't want to change their cpu
@@ -1520,10 +1451,8 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
struct mm_struct *mm;
struct task_struct *task;
struct task_struct *leader = cgroup_taskset_first(tset);
- struct cgroup_subsys_state *oldcss = cgroup_taskset_cur_css(tset,
- cpuset_subsys_id);
struct cpuset *cs = css_cs(css);
- struct cpuset *oldcs = css_cs(oldcss);
+ struct cpuset *oldcs = cpuset_attach_old_cs;
struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
@@ -1537,7 +1466,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to);
- cgroup_taskset_for_each(task, css, tset) {
+ cgroup_taskset_for_each(task, tset) {
/*
* can_attach beforehand should guarantee that this doesn't
* fail. TODO: have a better way to handle failure here
@@ -1677,7 +1606,7 @@ out_unlock:
* Common handling for a write to a "cpus" or "mems" file.
*/
static int cpuset_write_resmask(struct cgroup_subsys_state *css,
- struct cftype *cft, const char *buf)
+ struct cftype *cft, char *buf)
{
struct cpuset *cs = css_cs(css);
struct cpuset *trialcs;
@@ -1731,66 +1660,41 @@ out_unlock:
* used, list of ranges of sequential numbers, is variable length,
* and since these maps can change value dynamically, one could read
* gibberish by doing partial reads while a list was changing.
- * A single large read to a buffer that crosses a page boundary is
- * ok, because the result being copied to user land is not recomputed
- * across a page fault.
*/
-
-static size_t cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
+static int cpuset_common_seq_show(struct seq_file *sf, void *v)
{
- size_t count;
+ struct cpuset *cs = css_cs(seq_css(sf));
+ cpuset_filetype_t type = seq_cft(sf)->private;
+ ssize_t count;
+ char *buf, *s;
+ int ret = 0;
- mutex_lock(&callback_mutex);
- count = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
- mutex_unlock(&callback_mutex);
-
- return count;
-}
-
-static size_t cpuset_sprintf_memlist(char *page, struct cpuset *cs)
-{
- size_t count;
+ count = seq_get_buf(sf, &buf);
+ s = buf;
mutex_lock(&callback_mutex);
- count = nodelist_scnprintf(page, PAGE_SIZE, cs->mems_allowed);
- mutex_unlock(&callback_mutex);
-
- return count;
-}
-
-static ssize_t cpuset_common_file_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct file *file,
- char __user *buf, size_t nbytes,
- loff_t *ppos)
-{
- struct cpuset *cs = css_cs(css);
- cpuset_filetype_t type = cft->private;
- char *page;
- ssize_t retval = 0;
- char *s;
-
- if (!(page = (char *)__get_free_page(GFP_TEMPORARY)))
- return -ENOMEM;
-
- s = page;
switch (type) {
case FILE_CPULIST:
- s += cpuset_sprintf_cpulist(s, cs);
+ s += cpulist_scnprintf(s, count, cs->cpus_allowed);
break;
case FILE_MEMLIST:
- s += cpuset_sprintf_memlist(s, cs);
+ s += nodelist_scnprintf(s, count, cs->mems_allowed);
break;
default:
- retval = -EINVAL;
- goto out;
+ ret = -EINVAL;
+ goto out_unlock;
}
- *s++ = '\n';
- retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
-out:
- free_page((unsigned long)page);
- return retval;
+ if (s < buf + count - 1) {
+ *s++ = '\n';
+ seq_commit(sf, s - buf);
+ } else {
+ seq_commit(sf, -1);
+ }
+out_unlock:
+ mutex_unlock(&callback_mutex);
+ return ret;
}
static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -1847,7 +1751,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
static struct cftype files[] = {
{
.name = "cpus",
- .read = cpuset_common_file_read,
+ .seq_show = cpuset_common_seq_show,
.write_string = cpuset_write_resmask,
.max_write_len = (100U + 6 * NR_CPUS),
.private = FILE_CPULIST,
@@ -1855,7 +1759,7 @@ static struct cftype files[] = {
{
.name = "mems",
- .read = cpuset_common_file_read,
+ .seq_show = cpuset_common_seq_show,
.write_string = cpuset_write_resmask,
.max_write_len = (100U + 6 * MAX_NUMNODES),
.private = FILE_MEMLIST,
@@ -2049,8 +1953,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
kfree(cs);
}
-struct cgroup_subsys cpuset_subsys = {
- .name = "cpuset",
+struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
.css_offline = cpuset_css_offline,
@@ -2058,7 +1961,6 @@ struct cgroup_subsys cpuset_subsys = {
.can_attach = cpuset_can_attach,
.cancel_attach = cpuset_cancel_attach,
.attach = cpuset_attach,
- .subsys_id = cpuset_subsys_id,
.base_cftypes = files,
.early_init = 1,
};
@@ -2115,10 +2017,9 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
parent = parent_cs(parent);
if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
- rcu_read_lock();
- printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset %s\n",
- cgroup_name(cs->css.cgroup));
- rcu_read_unlock();
+ printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset ");
+ pr_cont_cgroup_name(cs->css.cgroup);
+ pr_cont("\n");
}
}
@@ -2166,7 +2067,7 @@ retry:
*/
if ((sane && cpumask_empty(cs->cpus_allowed)) ||
(!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
- update_tasks_cpumask(cs, NULL);
+ update_tasks_cpumask(cs);
mutex_lock(&callback_mutex);
nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);
@@ -2180,7 +2081,7 @@ retry:
*/
if ((sane && nodes_empty(cs->mems_allowed)) ||
(!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
- update_tasks_nodemask(cs, NULL);
+ update_tasks_nodemask(cs);
is_empty = cpumask_empty(cs->cpus_allowed) ||
nodes_empty(cs->mems_allowed);
@@ -2242,7 +2143,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
mutex_lock(&callback_mutex);
top_cpuset.mems_allowed = new_mems;
mutex_unlock(&callback_mutex);
- update_tasks_nodemask(&top_cpuset, NULL);
+ update_tasks_nodemask(&top_cpuset);
}
mutex_unlock(&cpuset_mutex);
@@ -2334,10 +2235,10 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
struct cpuset *cpus_cs;
mutex_lock(&callback_mutex);
- task_lock(tsk);
+ rcu_read_lock();
cpus_cs = effective_cpumask_cpuset(task_cs(tsk));
guarantee_online_cpus(cpus_cs, pmask);
- task_unlock(tsk);
+ rcu_read_unlock();
mutex_unlock(&callback_mutex);
}
@@ -2390,10 +2291,10 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
nodemask_t mask;
mutex_lock(&callback_mutex);
- task_lock(tsk);
+ rcu_read_lock();
mems_cs = effective_nodemask_cpuset(task_cs(tsk));
guarantee_online_mems(mems_cs, &mask);
- task_unlock(tsk);
+ rcu_read_unlock();
mutex_unlock(&callback_mutex);
return mask;
@@ -2509,11 +2410,11 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
/* Not hardwall and node outside mems_allowed: scan up cpusets */
mutex_lock(&callback_mutex);
- task_lock(current);
+ rcu_read_lock();
cs = nearest_hardwall_ancestor(task_cs(current));
- task_unlock(current);
-
allowed = node_isset(node, cs->mems_allowed);
+ rcu_read_unlock();
+
mutex_unlock(&callback_mutex);
return allowed;
}
@@ -2638,27 +2539,27 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
* @task: pointer to task_struct of some task.
*
* Description: Prints @task's name, cpuset name, and cached copy of its
- * mems_allowed to the kernel log. Must hold task_lock(task) to allow
- * dereferencing task_cs(task).
+ * mems_allowed to the kernel log.
*/
void cpuset_print_task_mems_allowed(struct task_struct *tsk)
{
/* Statically allocated to prevent using excess stack. */
static char cpuset_nodelist[CPUSET_NODELIST_LEN];
static DEFINE_SPINLOCK(cpuset_buffer_lock);
+ struct cgroup *cgrp;
- struct cgroup *cgrp = task_cs(tsk)->css.cgroup;
-
- rcu_read_lock();
spin_lock(&cpuset_buffer_lock);
+ rcu_read_lock();
+ cgrp = task_cs(tsk)->css.cgroup;
nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
tsk->mems_allowed);
- printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n",
- tsk->comm, cgroup_name(cgrp), cpuset_nodelist);
+ printk(KERN_INFO "%s cpuset=", tsk->comm);
+ pr_cont_cgroup_name(cgrp);
+ pr_cont(" mems_allowed=%s\n", cpuset_nodelist);
- spin_unlock(&cpuset_buffer_lock);
rcu_read_unlock();
+ spin_unlock(&cpuset_buffer_lock);
}
/*
@@ -2689,9 +2590,9 @@ int cpuset_memory_pressure_enabled __read_mostly;
void __cpuset_memory_pressure_bump(void)
{
- task_lock(current);
+ rcu_read_lock();
fmeter_markevent(&task_cs(current)->fmeter);
- task_unlock(current);
+ rcu_read_unlock();
}
#ifdef CONFIG_PROC_PID_CPUSET
@@ -2708,12 +2609,12 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
{
struct pid *pid;
struct task_struct *tsk;
- char *buf;
+ char *buf, *p;
struct cgroup_subsys_state *css;
int retval;
retval = -ENOMEM;
- buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!buf)
goto out;
@@ -2723,14 +2624,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
if (!tsk)
goto out_free;
+ retval = -ENAMETOOLONG;
rcu_read_lock();
- css = task_css(tsk, cpuset_subsys_id);
- retval = cgroup_path(css->cgroup, buf, PAGE_SIZE);
+ css = task_css(tsk, cpuset_cgrp_id);
+ p = cgroup_path(css->cgroup, buf, PATH_MAX);
rcu_read_unlock();
- if (retval < 0)
+ if (!p)
goto out_put_task;
- seq_puts(m, buf);
+ seq_puts(m, p);
seq_putc(m, '\n');
+ retval = 0;
out_put_task:
put_task_struct(tsk);
out_free:
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 7d2f35e5df2f..2956c8da1605 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
#include <linux/pid.h>
#include <linux/smp.h>
#include <linux/mm.h>
+#include <linux/vmacache.h>
#include <linux/rcupdate.h>
#include <asm/cacheflush.h>
@@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
if (!CACHE_FLUSH_IS_SAFE)
return;
- if (current->mm && current->mm->mmap_cache) {
- flush_cache_range(current->mm->mmap_cache,
- addr, addr + BREAK_INSTR_SIZE);
+ if (current->mm) {
+ int i;
+
+ for (i = 0; i < VMACACHE_SIZE; i++) {
+ if (!current->vmacache[i])
+ continue;
+ flush_cache_range(current->vmacache[i],
+ addr, addr + BREAK_INSTR_SIZE);
+ }
}
+
/* Force flush instruction cache if it was outside the mm */
flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
}
@@ -736,7 +744,8 @@ int kgdb_nmicallback(int cpu, void *regs)
return 1;
}
-int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *send_ready)
+int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code,
+ atomic_t *send_ready)
{
#ifdef CONFIG_SMP
if (!kgdb_io_ready(0) || !send_ready)
@@ -750,7 +759,7 @@ int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *send_ready)
ks->cpu = cpu;
ks->ex_vector = trapnr;
ks->signo = SIGTRAP;
- ks->err_code = KGDB_KDB_REASON_SYSTEM_NMI;
+ ks->err_code = err_code;
ks->linux_regs = regs;
ks->send_ready = send_ready;
kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
@@ -1034,7 +1043,7 @@ int dbg_io_get_char(void)
* otherwise as a quick means to stop program execution and "break" into
* the debugger.
*/
-void kgdb_breakpoint(void)
+noinline void kgdb_breakpoint(void)
{
atomic_inc(&kgdb_setting_breakpoint);
wmb(); /* Sync point before breakpoint */
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index 572aa4f5677c..127d9bc49fb4 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -75,13 +75,11 @@ extern int kdb_stub(struct kgdb_state *ks);
extern int kdb_parse(const char *cmdstr);
extern int kdb_common_init_state(struct kgdb_state *ks);
extern int kdb_common_deinit_state(void);
-#define KGDB_KDB_REASON_SYSTEM_NMI KDB_REASON_SYSTEM_NMI
#else /* ! CONFIG_KGDB_KDB */
static inline int kdb_stub(struct kgdb_state *ks)
{
return DBG_PASS_EVENT;
}
-#define KGDB_KDB_REASON_SYSTEM_NMI 0
#endif /* CONFIG_KGDB_KDB */
#endif /* _DEBUG_CORE_H_ */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f5744010a8d2..f83a71a3e46d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
- PERF_FLAG_PID_CGROUP)
+ PERF_FLAG_PID_CGROUP |\
+ PERF_FLAG_FD_CLOEXEC)
/*
* branch priv levels that need permission checks
@@ -230,11 +231,29 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
#define NR_ACCUMULATED_SAMPLES 128
static DEFINE_PER_CPU(u64, running_sample_length);
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
{
+ u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
u64 avg_local_sample_len;
u64 local_samples_len;
+
+ local_samples_len = __get_cpu_var(running_sample_length);
+ avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+ printk_ratelimited(KERN_WARNING
+ "perf interrupt took too long (%lld > %lld), lowering "
+ "kernel.perf_event_max_sample_rate to %d\n",
+ avg_local_sample_len, allowed_ns >> 1,
+ sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+ u64 avg_local_sample_len;
+ u64 local_samples_len;
if (allowed_ns == 0)
return;
@@ -262,13 +281,14 @@ void perf_sample_event_took(u64 sample_len_ns)
sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
- printk_ratelimited(KERN_WARNING
- "perf samples too long (%lld > %lld), lowering "
- "kernel.perf_event_max_sample_rate to %d\n",
- avg_local_sample_len, allowed_ns,
- sysctl_perf_event_sample_rate);
-
update_perf_cpu_limits();
+
+ if (!irq_work_queue(&perf_duration_work)) {
+ early_printk("perf interrupt took too long (%lld > %lld), lowering "
+ "kernel.perf_event_max_sample_rate to %d\n",
+ avg_local_sample_len, allowed_ns >> 1,
+ sysctl_perf_event_sample_rate);
+ }
}
static atomic64_t perf_event_id;
@@ -341,7 +361,7 @@ struct perf_cgroup {
static inline struct perf_cgroup *
perf_cgroup_from_task(struct task_struct *task)
{
- return container_of(task_css(task, perf_subsys_id),
+ return container_of(task_css(task, perf_event_cgrp_id),
struct perf_cgroup, css);
}
@@ -369,11 +389,6 @@ perf_cgroup_match(struct perf_event *event)
event->cgrp->css.cgroup);
}
-static inline bool perf_tryget_cgroup(struct perf_event *event)
-{
- return css_tryget(&event->cgrp->css);
-}
-
static inline void perf_put_cgroup(struct perf_event *event)
{
css_put(&event->cgrp->css);
@@ -592,9 +607,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
if (!f.file)
return -EBADF;
- rcu_read_lock();
-
- css = css_from_dir(f.file->f_dentry, &perf_subsys);
+ css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
if (IS_ERR(css)) {
ret = PTR_ERR(css);
goto out;
@@ -603,13 +616,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
cgrp = container_of(css, struct perf_cgroup, css);
event->cgrp = cgrp;
- /* must be done before we fput() the file */
- if (!perf_tryget_cgroup(event)) {
- event->cgrp = NULL;
- ret = -ENOENT;
- goto out;
- }
-
/*
* all events in a group must monitor
* the same cgroup because a task belongs
@@ -620,7 +626,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
ret = -EINVAL;
}
out:
- rcu_read_unlock();
fdput(f);
return ret;
}
@@ -1713,7 +1718,7 @@ group_sched_in(struct perf_event *group_event,
struct perf_event_context *ctx)
{
struct perf_event *event, *partial_group = NULL;
- struct pmu *pmu = group_event->pmu;
+ struct pmu *pmu = ctx->pmu;
u64 now = ctx->time;
bool simulate = false;
@@ -2562,8 +2567,6 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
if (cpuctx->ctx.nr_branch_stack > 0
&& pmu->flush_branch_stack) {
- pmu = cpuctx->ctx.pmu;
-
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(pmu);
@@ -3542,7 +3545,7 @@ static void perf_event_for_each(struct perf_event *event,
static int perf_event_period(struct perf_event *event, u64 __user *arg)
{
struct perf_event_context *ctx = event->ctx;
- int ret = 0;
+ int ret = 0, active;
u64 value;
if (!is_sampling_event(event))
@@ -3566,6 +3569,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
event->attr.sample_period = value;
event->hw.sample_period = value;
}
+
+ active = (event->state == PERF_EVENT_STATE_ACTIVE);
+ if (active) {
+ perf_pmu_disable(ctx->pmu);
+ event->pmu->stop(event, PERF_EF_UPDATE);
+ }
+
+ local64_set(&event->hw.period_left, 0);
+
+ if (active) {
+ event->pmu->start(event, PERF_EF_RELOAD);
+ perf_pmu_enable(ctx->pmu);
+ }
+
unlock:
raw_spin_unlock_irq(&ctx->lock);
@@ -6279,7 +6296,7 @@ static int perf_event_idx_default(struct perf_event *event)
* Ensures all contexts with the same task_ctx_nr have the same
* pmu_cpu_context too.
*/
-static void *find_pmu_context(int ctxn)
+static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
{
struct pmu *pmu;
@@ -6670,6 +6687,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
INIT_LIST_HEAD(&event->event_entry);
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
+ INIT_LIST_HEAD(&event->active_entry);
+ INIT_HLIST_NODE(&event->hlist_entry);
+
init_waitqueue_head(&event->waitq);
init_irq_work(&event->pending, perf_pending_event);
@@ -6980,6 +7000,7 @@ SYSCALL_DEFINE5(perf_event_open,
int event_fd;
int move_group = 0;
int err;
+ int f_flags = O_RDWR;
/* for future expandability... */
if (flags & ~PERF_FLAG_ALL)
@@ -7008,7 +7029,10 @@ SYSCALL_DEFINE5(perf_event_open,
if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
return -EINVAL;
- event_fd = get_unused_fd();
+ if (flags & PERF_FLAG_FD_CLOEXEC)
+ f_flags |= O_CLOEXEC;
+
+ event_fd = get_unused_fd_flags(f_flags);
if (event_fd < 0)
return event_fd;
@@ -7130,7 +7154,8 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_context;
}
- event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+ event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+ f_flags);
if (IS_ERR(event_file)) {
err = PTR_ERR(event_file);
goto err_context;
@@ -7833,14 +7858,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
static void __perf_event_exit_context(void *__info)
{
struct perf_event_context *ctx = __info;
- struct perf_event *event, *tmp;
+ struct perf_event *event;
perf_pmu_rotate_stop(ctx->pmu);
- list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
- __perf_remove_from_context(event);
- list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
+ rcu_read_lock();
+ list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
__perf_remove_from_context(event);
+ rcu_read_unlock();
}
static void perf_event_exit_cpu_context(int cpu)
@@ -7864,11 +7889,11 @@ static void perf_event_exit_cpu(int cpu)
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
+ perf_event_exit_cpu_context(cpu);
+
mutex_lock(&swhash->hlist_mutex);
swevent_hlist_release(swhash);
mutex_unlock(&swhash->hlist_mutex);
-
- perf_event_exit_cpu_context(cpu);
}
#else
static inline void perf_event_exit_cpu(int cpu) { }
@@ -8013,7 +8038,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css,
{
struct task_struct *task;
- cgroup_taskset_for_each(task, css, tset)
+ cgroup_taskset_for_each(task, tset)
task_function_call(task, __perf_cgroup_move, task);
}
@@ -8032,9 +8057,7 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css,
task_function_call(task, __perf_cgroup_move, task);
}
-struct cgroup_subsys perf_subsys = {
- .name = "perf_event",
- .subsys_id = perf_subsys_id,
+struct cgroup_subsys perf_event_cgrp_subsys = {
.css_alloc = perf_cgroup_css_alloc,
.css_free = perf_cgroup_css_free,
.exit = perf_cgroup_exit,
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8b168af135b..146a5792b1d2 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -61,19 +61,20 @@ again:
*
* kernel user
*
- * READ ->data_tail READ ->data_head
- * smp_mb() (A) smp_rmb() (C)
- * WRITE $data READ $data
- * smp_wmb() (B) smp_mb() (D)
- * STORE ->data_head WRITE ->data_tail
+ * if (LOAD ->data_tail) { LOAD ->data_head
+ * (A) smp_rmb() (C)
+ * STORE $data LOAD $data
+ * smp_wmb() (B) smp_mb() (D)
+ * STORE ->data_head STORE ->data_tail
+ * }
*
* Where A pairs with D, and B pairs with C.
*
- * I don't think A needs to be a full barrier because we won't in fact
- * write data until we see the store from userspace. So we simply don't
- * issue the data WRITE until we observe it. Be conservative for now.
+ * In our case (A) is a control dependency that separates the load of
+ * the ->data_tail and the stores of $data. In case ->data_tail
+ * indicates there is no room in the buffer to store $data we do not.
*
- * OTOH, D needs to be a full barrier since it separates the data READ
+ * D needs to be a full barrier since it separates the data READ
* from the tail WRITE.
*
* For B a WMB is sufficient since it separates two WRITEs, and for C
@@ -81,7 +82,7 @@ again:
*
* See perf_output_begin().
*/
- smp_wmb();
+ smp_wmb(); /* B, matches C */
rb->user_page->data_head = head;
/*
@@ -144,17 +145,26 @@ int perf_output_begin(struct perf_output_handle *handle,
if (!rb->overwrite &&
unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
goto fail;
+
+ /*
+ * The above forms a control dependency barrier separating the
+ * @tail load above from the data stores below. Since the @tail
+ * load is required to compute the branch to fail below.
+ *
+ * A, matches D; the full memory barrier userspace SHOULD issue
+ * after reading the data and before storing the new tail
+ * position.
+ *
+ * See perf_output_put_handle().
+ */
+
head += size;
} while (local_cmpxchg(&rb->head, offset, head) != offset);
/*
- * Separate the userpage->tail read from the data stores below.
- * Matches the MB userspace SHOULD issue after reading the data
- * and before storing the new tail position.
- *
- * See perf_output_put_handle().
+ * We rely on the implied barrier() by local_cmpxchg() to ensure
+ * none of the data stores below can be lifted up by the compiler.
*/
- smp_mb();
if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
local_add(rb->watermark, &rb->wakeup);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 24b7d6ca871b..04709b66369d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -73,6 +73,17 @@ struct uprobe {
struct inode *inode; /* Also hold a ref to inode */
loff_t offset;
unsigned long flags;
+
+ /*
+ * The generic code assumes that it has two members of unknown type
+ * owned by the arch-specific code:
+ *
+ * insn - copy_insn() saves the original instruction here for
+ * arch_uprobe_analyze_insn().
+ *
+ * ixol - potentially modified instruction to execute out of
+ * line, copied to xol_area by xol_get_insn_slot().
+ */
struct arch_uprobe arch;
};
@@ -86,6 +97,29 @@ struct return_instance {
};
/*
+ * Execute out of line area: anonymous executable mapping installed
+ * by the probed task to execute the copy of the original instruction
+ * mangled by set_swbp().
+ *
+ * On a breakpoint hit, thread contests for a slot. It frees the
+ * slot after singlestep. Currently a fixed number of slots are
+ * allocated.
+ */
+struct xol_area {
+ wait_queue_head_t wq; /* if all slots are busy */
+ atomic_t slot_count; /* number of in-use slots */
+ unsigned long *bitmap; /* 0 = free slot */
+ struct page *page;
+
+ /*
+ * We keep the vma's vm_start rather than a pointer to the vma
+ * itself. The probed process or a naughty kernel module could make
+ * the vma go away, and we must handle that reasonably gracefully.
+ */
+ unsigned long vaddr; /* Page(s) of instruction slots */
+};
+
+/*
* valid_vma: Verify if the specified vma is an executable vma
* Relax restrictions while unregistering: vm_flags might have
* changed after breakpoint was inserted.
@@ -330,7 +364,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
int __weak
set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+ return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
}
static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -529,8 +563,8 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp)
{
struct address_space *mapping = uprobe->inode->i_mapping;
loff_t offs = uprobe->offset;
- void *insn = uprobe->arch.insn;
- int size = MAX_UINSN_BYTES;
+ void *insn = &uprobe->arch.insn;
+ int size = sizeof(uprobe->arch.insn);
int len, err = -EIO;
/* Copy only available bytes, -EIO if nothing was read */
@@ -569,7 +603,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
goto out;
ret = -ENOTSUPP;
- if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
+ if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
goto out;
ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
@@ -1264,7 +1298,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
/* Initialize the slot */
copy_to_page(area->page, xol_vaddr,
- uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
+ &uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
/*
* We probably need flush_icache_user_range() but it needs vma.
* This should work on supported architectures too.
@@ -1403,12 +1437,10 @@ static void uprobe_warn(struct task_struct *t, const char *msg)
static void dup_xol_work(struct callback_head *work)
{
- kfree(work);
-
if (current->flags & PF_EXITING)
return;
- if (!__create_xol_area(current->utask->vaddr))
+ if (!__create_xol_area(current->utask->dup_xol_addr))
uprobe_warn(current, "dup xol area");
}
@@ -1419,7 +1451,6 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
{
struct uprobe_task *utask = current->utask;
struct mm_struct *mm = current->mm;
- struct callback_head *work;
struct xol_area *area;
t->utask = NULL;
@@ -1441,14 +1472,9 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
if (mm == t->mm)
return;
- /* TODO: move it into the union in uprobe_task */
- work = kmalloc(sizeof(*work), GFP_KERNEL);
- if (!work)
- return uprobe_warn(t, "dup xol area");
-
- t->utask->vaddr = area->vaddr;
- init_task_work(work, dup_xol_work);
- task_work_add(t, work, true);
+ t->utask->dup_xol_addr = area->vaddr;
+ init_task_work(&t->utask->dup_xol_work, dup_xol_work);
+ task_work_add(t, &t->utask->dup_xol_work, true);
}
/*
@@ -1778,6 +1804,11 @@ static bool handle_trampoline(struct pt_regs *regs)
return true;
}
+bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs)
+{
+ return false;
+}
+
/*
* Run handler and ask thread to singlestep.
* Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1828,7 +1859,15 @@ static void handle_swbp(struct pt_regs *regs)
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
+ /* Tracing handlers use ->utask to communicate with fetch methods */
+ if (!get_utask())
+ goto out;
+
+ if (arch_uprobe_ignore(&uprobe->arch, regs))
+ goto out;
+
handler_chain(uprobe, regs);
+
if (can_skip_sstep(uprobe, regs))
goto out;
diff --git a/kernel/exit.c b/kernel/exit.c
index a949819055d5..6ed6a1d552b5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
__this_cpu_dec(process_counts);
}
list_del_rcu(&p->thread_group);
+ list_del_rcu(&p->thread_node);
}
/*
@@ -569,7 +570,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
if (same_thread_group(p->real_parent, father))
return;
- /* We don't want people slaying init. */
+ /* We don't want people slaying init. */
p->exit_signal = SIGCHLD;
/* If it has exited notify the new parent about this child's death. */
@@ -783,9 +784,10 @@ void do_exit(long code)
exit_shm(tsk);
exit_files(tsk);
exit_fs(tsk);
+ if (group_dead)
+ disassociate_ctty(1);
exit_task_namespaces(tsk);
exit_task_work(tsk);
- check_stack_usage();
exit_thread();
/*
@@ -796,21 +798,17 @@ void do_exit(long code)
*/
perf_event_exit_task(tsk);
- cgroup_exit(tsk, 1);
-
- if (group_dead)
- disassociate_ctty(1);
+ cgroup_exit(tsk);
module_put(task_thread_info(tsk)->exec_domain->module);
- proc_exit_connector(tsk);
-
/*
* FIXME: do that only when needed, using sched_exit tracepoint
*/
flush_ptrace_hw_breakpoint(tsk);
exit_notify(tsk, group_dead);
+ proc_exit_connector(tsk);
#ifdef CONFIG_NUMA
task_lock(tsk);
mpol_put(tsk->mempolicy);
@@ -843,6 +841,7 @@ void do_exit(long code)
validate_creds_for_do_exit(tsk);
+ check_stack_usage();
preempt_disable();
if (tsk->nr_dirtied)
__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
@@ -1037,17 +1036,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
return wait_noreap_copyout(wo, p, pid, uid, why, status);
}
+ traced = ptrace_reparented(p);
/*
- * Try to move the task's state to DEAD
- * only one thread is allowed to do this:
+ * Move the task's state to DEAD/TRACE, only one thread can do this.
*/
- state = xchg(&p->exit_state, EXIT_DEAD);
- if (state != EXIT_ZOMBIE) {
- BUG_ON(state != EXIT_DEAD);
+ state = traced && thread_group_leader(p) ? EXIT_TRACE : EXIT_DEAD;
+ if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
return 0;
- }
-
- traced = ptrace_reparented(p);
/*
* It can be ptraced but not reparented, check
* thread_group_leader() to filter out sub-threads.
@@ -1108,7 +1103,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
/*
* Now we are sure this task is interesting, and no other
- * thread can reap it because we set its state to EXIT_DEAD.
+ * thread can reap it because we its state == DEAD/TRACE.
*/
read_unlock(&tasklist_lock);
@@ -1145,22 +1140,19 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
if (!retval)
retval = pid;
- if (traced) {
+ if (state == EXIT_TRACE) {
write_lock_irq(&tasklist_lock);
/* We dropped tasklist, ptracer could die and untrace */
ptrace_unlink(p);
- /*
- * If this is not a sub-thread, notify the parent.
- * If parent wants a zombie, don't release it now.
- */
- if (thread_group_leader(p) &&
- !do_notify_parent(p, p->exit_signal)) {
- p->exit_state = EXIT_ZOMBIE;
- p = NULL;
- }
+
+ /* If parent wants a zombie, don't release it now */
+ state = EXIT_ZOMBIE;
+ if (do_notify_parent(p, p->exit_signal))
+ state = EXIT_DEAD;
+ p->exit_state = state;
write_unlock_irq(&tasklist_lock);
}
- if (p != NULL)
+ if (state == EXIT_DEAD)
release_task(p);
return retval;
@@ -1337,7 +1329,12 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
static int wait_consider_task(struct wait_opts *wo, int ptrace,
struct task_struct *p)
{
- int ret = eligible_child(wo, p);
+ int ret;
+
+ if (unlikely(p->exit_state == EXIT_DEAD))
+ return 0;
+
+ ret = eligible_child(wo, p);
if (!ret)
return ret;
@@ -1355,33 +1352,44 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
return 0;
}
- /* dead body doesn't have much to contribute */
- if (unlikely(p->exit_state == EXIT_DEAD)) {
+ if (unlikely(p->exit_state == EXIT_TRACE)) {
/*
- * But do not ignore this task until the tracer does
- * wait_task_zombie()->do_notify_parent().
+ * ptrace == 0 means we are the natural parent. In this case
+ * we should clear notask_error, debugger will notify us.
*/
- if (likely(!ptrace) && unlikely(ptrace_reparented(p)))
+ if (likely(!ptrace))
wo->notask_error = 0;
return 0;
}
- /* slay zombie? */
- if (p->exit_state == EXIT_ZOMBIE) {
+ if (likely(!ptrace) && unlikely(p->ptrace)) {
/*
- * A zombie ptracee is only visible to its ptracer.
- * Notification and reaping will be cascaded to the real
- * parent when the ptracer detaches.
+ * If it is traced by its real parent's group, just pretend
+ * the caller is ptrace_do_wait() and reap this child if it
+ * is zombie.
+ *
+ * This also hides group stop state from real parent; otherwise
+ * a single stop can be reported twice as group and ptrace stop.
+ * If a ptracer wants to distinguish these two events for its
+ * own children it should create a separate process which takes
+ * the role of real parent.
*/
- if (likely(!ptrace) && unlikely(p->ptrace)) {
- /* it will become visible, clear notask_error */
- wo->notask_error = 0;
- return 0;
- }
+ if (!ptrace_reparented(p))
+ ptrace = 1;
+ }
+ /* slay zombie? */
+ if (p->exit_state == EXIT_ZOMBIE) {
/* we don't reap group leaders with subthreads */
- if (!delay_group_leader(p))
- return wait_task_zombie(wo, p);
+ if (!delay_group_leader(p)) {
+ /*
+ * A zombie ptracee is only visible to its ptracer.
+ * Notification and reaping will be cascaded to the
+ * real parent when the ptracer detaches.
+ */
+ if (unlikely(ptrace) || likely(!p->ptrace))
+ return wait_task_zombie(wo, p);
+ }
/*
* Allow access to stopped/continued state via zombie by
@@ -1407,19 +1415,6 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
wo->notask_error = 0;
} else {
/*
- * If @p is ptraced by a task in its real parent's group,
- * hide group stop/continued state when looking at @p as
- * the real parent; otherwise, a single stop can be
- * reported twice as group and ptrace stops.
- *
- * If a ptracer wants to distinguish the two events for its
- * own children, it should create a separate process which
- * takes the role of real parent.
- */
- if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
- return 0;
-
- /*
* @p is alive and it's gonna stop, continue or exit, so
* there always is something to wait for.
*/
diff --git a/kernel/extable.c b/kernel/extable.c
index 763faf037ec1..d8a6446adbcb 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -36,7 +36,7 @@ extern struct exception_table_entry __start___ex_table[];
extern struct exception_table_entry __stop___ex_table[];
/* Cleared by build time tools if the table is already sorted. */
-u32 __initdata main_extable_sort_needed = 1;
+u32 __initdata __visible main_extable_sort_needed = 1;
/* Sort the kernel's built-in exception table */
void __init sort_main_extable(void)
diff --git a/kernel/fork.c b/kernel/fork.c
index dfa736c98d17..54a8d26f612f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
@@ -71,6 +73,7 @@
#include <linux/signalfd.h>
#include <linux/uprobes.h>
#include <linux/aio.h>
+#include <linux/compiler.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -237,6 +240,7 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
+ task_numa_free(tsk);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
@@ -283,7 +287,7 @@ void __init fork_init(unsigned long mempages)
init_task.signal->rlim[RLIMIT_NPROC];
}
-int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst,
+int __weak arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
@@ -363,7 +367,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
mm->locked_vm = 0;
mm->mmap = NULL;
- mm->mmap_cache = NULL;
+ mm->vmacache_seqnum = 0;
mm->map_count = 0;
cpumask_clear(mm_cpumask(mm));
mm->mm_rb = RB_ROOT;
@@ -529,8 +533,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
- mm->flags = (current->mm) ?
- (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
atomic_long_set(&mm->nr_ptes, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
@@ -539,8 +541,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
mm_init_owner(mm, p);
clear_tlb_flush_pending(mm);
- if (likely(!mm_alloc_pgd(mm))) {
+ if (current->mm) {
+ mm->flags = current->mm->flags & MMF_INIT_MASK;
+ mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+ } else {
+ mm->flags = default_dump_filter;
mm->def_flags = 0;
+ }
+
+ if (likely(!mm_alloc_pgd(mm))) {
mmu_notifier_mm_init(mm);
return mm;
}
@@ -800,14 +809,11 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
* Allocate a new mm structure and copy contents from the
* mm structure of the passed in task structure.
*/
-struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
- if (!oldmm)
- return NULL;
-
mm = allocate_mm();
if (!mm)
goto fail_nomem;
@@ -879,6 +885,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
if (!oldmm)
return 0;
+ /* initialize the new vmacache entries */
+ vmacache_flush(tsk);
+
if (clone_flags & CLONE_VM) {
atomic_inc(&oldmm->mm_users);
mm = oldmm;
@@ -1035,6 +1044,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
atomic_set(&sig->sigcnt, 1);
+
+ /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+ tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
@@ -1067,15 +1081,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
return 0;
}
-static void copy_flags(unsigned long clone_flags, struct task_struct *p)
-{
- unsigned long new_flags = p->flags;
-
- new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
- new_flags |= PF_FORKNOEXEC;
- p->flags = new_flags;
-}
-
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
@@ -1087,8 +1092,10 @@ static void rt_mutex_init_task(struct task_struct *p)
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&p->pi_waiters);
+ p->pi_waiters = RB_ROOT;
+ p->pi_waiters_leftmost = NULL;
p->pi_blocked_on = NULL;
+ p->pi_top_task = NULL;
#endif
}
@@ -1222,9 +1229,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
- p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
- copy_flags(clone_flags, p);
+ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
+ p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
rcu_copy_process(p);
@@ -1268,9 +1275,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
- goto bad_fork_cleanup_cgroup;
+ goto bad_fork_cleanup_threadgroup_lock;
}
- mpol_fix_fork_child_flag(p);
#endif
#ifdef CONFIG_CPUSETS
p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
@@ -1311,7 +1317,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
- sched_fork(clone_flags, p);
+ retval = sched_fork(clone_flags, p);
+ if (retval)
+ goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
@@ -1403,13 +1411,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->tgid = p->pid;
}
- p->pdeath_signal = 0;
- p->exit_state = 0;
-
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
+ p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
@@ -1472,6 +1478,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
atomic_inc(&current->signal->sigcnt);
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
+ list_add_tail_rcu(&p->thread_node,
+ &p->signal->thread_head);
}
attach_pid(p, PIDTYPE_PID);
nr_threads++;
@@ -1519,11 +1527,10 @@ bad_fork_cleanup_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
-bad_fork_cleanup_cgroup:
+bad_fork_cleanup_threadgroup_lock:
#endif
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
- cgroup_exit(p, 0);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
@@ -1645,7 +1652,7 @@ SYSCALL_DEFINE0(fork)
return do_fork(SIGCHLD, 0, 0, NULL, NULL);
#else
/* can not support in nommu mode */
- return(-EINVAL);
+ return -EINVAL;
#endif
}
#endif
@@ -1653,7 +1660,7 @@ SYSCALL_DEFINE0(fork)
#ifdef __ARCH_WANT_SYS_VFORK
SYSCALL_DEFINE0(vfork)
{
- return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
0, NULL, NULL);
}
#endif
diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff0191ecf7..6801b3751a95 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,14 +63,103 @@
#include <linux/sched/rt.h>
#include <linux/hugetlb.h>
#include <linux/freezer.h>
+#include <linux/bootmem.h>
#include <asm/futex.h>
#include "locking/rtmutex_common.h"
-int __read_mostly futex_cmpxchg_enabled;
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ * futex_wait(futex, val);
+ * uval = *futex;
+ * *futex = newval;
+ * sys_futex(WAKE, futex);
+ * futex_wake(futex);
+ * if (queue_empty())
+ * return;
+ * if (uval == val)
+ * lock(hash_bucket(futex));
+ * queue();
+ * unlock(hash_bucket(futex));
+ * schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ * futex_wait(futex, val);
+ *
+ * waiters++;
+ * mb(); (A) <-- paired with -.
+ * |
+ * lock(hash_bucket(futex)); |
+ * |
+ * uval = *futex; |
+ * | *futex = newval;
+ * | sys_futex(WAKE, futex);
+ * | futex_wake(futex);
+ * |
+ * `-------> mb(); (B)
+ * if (uval == val)
+ * queue();
+ * unlock(hash_bucket(futex));
+ * schedule(); if (waiters)
+ * lock(hash_bucket(futex));
+ * wake_waiters(futex);
+ * unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ * X = Y = 0
+ *
+ * w[X]=1 w[Y]=1
+ * MB MB
+ * r[Y]=y r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ */
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
+int __read_mostly futex_cmpxchg_enabled;
+#endif
/*
* Futex flags used to encode options to functions and preserve them across
@@ -147,11 +236,59 @@ static const struct futex_q futex_q_init = {
* waiting on a futex.
*/
struct futex_hash_bucket {
+ atomic_t waiters;
spinlock_t lock;
struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
+
+static unsigned long __read_mostly futex_hashsize;
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+static struct futex_hash_bucket *futex_queues;
+
+static inline void futex_get_mm(union futex_key *key)
+{
+ atomic_inc(&key->private.mm->mm_count);
+ /*
+ * Ensure futex_get_mm() implies a full barrier such that
+ * get_futex_key() implies a full barrier. This is relied upon
+ * as full barrier (B), see the ordering comment above.
+ */
+ smp_mb__after_atomic_inc();
+}
+
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ atomic_inc(&hb->waiters);
+ /*
+ * Full barrier (A), see the ordering comment above.
+ */
+ smp_mb__after_atomic_inc();
+#endif
+}
+
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ atomic_dec(&hb->waiters);
+#endif
+}
+
+static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ return atomic_read(&hb->waiters);
+#else
+ return 1;
+#endif
+}
/*
* We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +298,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
u32 hash = jhash2((u32*)&key->both.word,
(sizeof(key->both.word)+sizeof(key->both.ptr))/4,
key->both.offset);
- return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+ return &futex_queues[hash & (futex_hashsize - 1)];
}
/*
@@ -187,10 +324,10 @@ static void get_futex_key_refs(union futex_key *key)
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- ihold(key->shared.inode);
+ ihold(key->shared.inode); /* implies MB (B) */
break;
case FUT_OFF_MMSHARED:
- atomic_inc(&key->private.mm->mm_count);
+ futex_get_mm(key); /* implies MB (B) */
break;
}
}
@@ -264,7 +401,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
if (!fshared) {
key->private.mm = mm;
key->private.address = address;
- get_futex_key_refs(key);
+ get_futex_key_refs(key); /* implies MB (B) */
return 0;
}
@@ -371,7 +508,7 @@ again:
key->shared.pgoff = basepage_index(page);
}
- get_futex_key_refs(key);
+ get_futex_key_refs(key); /* implies MB (B) */
out:
unlock_page(page_head);
@@ -598,13 +735,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
{
struct futex_pi_state *pi_state = NULL;
struct futex_q *this, *next;
- struct plist_head *head;
struct task_struct *p;
pid_t pid = uval & FUTEX_TID_MASK;
- head = &hb->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (match_futex(&this->key, key)) {
/*
* Another waiter already exists - bump up
@@ -838,6 +972,7 @@ static void __unqueue_futex(struct futex_q *q)
hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
plist_del(&q->list, &hb->chain);
+ hb_waiters_dec(hb);
}
/*
@@ -986,7 +1121,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
int ret;
@@ -998,10 +1132,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
goto out;
hb = hash_futex(&key);
+
+ /* Make sure we really have tasks to wakeup */
+ if (!hb_waiters_pending(hb))
+ goto out_put_key;
+
spin_lock(&hb->lock);
- head = &hb->chain;
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (match_futex (&this->key, &key)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1019,6 +1157,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
}
spin_unlock(&hb->lock);
+out_put_key:
put_futex_key(&key);
out:
return ret;
@@ -1034,7 +1173,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
struct futex_hash_bucket *hb1, *hb2;
- struct plist_head *head;
struct futex_q *this, *next;
int ret, op_ret;
@@ -1082,9 +1220,7 @@ retry_private:
goto retry;
}
- head = &hb1->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (match_futex (&this->key, &key1)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1097,10 +1233,8 @@ retry_private:
}
if (op_ret > 0) {
- head = &hb2->chain;
-
op_ret = 0;
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb2->chain, list) {
if (match_futex (&this->key, &key2)) {
if (this->pi_state || this->rt_waiter) {
ret = -EINVAL;
@@ -1142,7 +1276,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
*/
if (likely(&hb1->chain != &hb2->chain)) {
plist_del(&q->list, &hb1->chain);
+ hb_waiters_dec(hb1);
plist_add(&q->list, &hb2->chain);
+ hb_waiters_inc(hb2);
q->lock_ptr = &hb2->lock;
}
get_futex_key_refs(key2);
@@ -1270,7 +1406,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
int drop_count = 0, task_count = 0, ret;
struct futex_pi_state *pi_state = NULL;
struct futex_hash_bucket *hb1, *hb2;
- struct plist_head *head1;
struct futex_q *this, *next;
u32 curval2;
@@ -1317,6 +1452,7 @@ retry:
hb2 = hash_futex(&key2);
retry_private:
+ hb_waiters_inc(hb2);
double_lock_hb(hb1, hb2);
if (likely(cmpval != NULL)) {
@@ -1326,6 +1462,7 @@ retry_private:
if (unlikely(ret)) {
double_unlock_hb(hb1, hb2);
+ hb_waiters_dec(hb2);
ret = get_user(curval, uaddr1);
if (ret)
@@ -1375,6 +1512,7 @@ retry_private:
break;
case -EFAULT:
double_unlock_hb(hb1, hb2);
+ hb_waiters_dec(hb2);
put_futex_key(&key2);
put_futex_key(&key1);
ret = fault_in_user_writeable(uaddr2);
@@ -1384,6 +1522,7 @@ retry_private:
case -EAGAIN:
/* The owner was exiting, try again. */
double_unlock_hb(hb1, hb2);
+ hb_waiters_dec(hb2);
put_futex_key(&key2);
put_futex_key(&key1);
cond_resched();
@@ -1393,8 +1532,7 @@ retry_private:
}
}
- head1 = &hb1->chain;
- plist_for_each_entry_safe(this, next, head1, list) {
+ plist_for_each_entry_safe(this, next, &hb1->chain, list) {
if (task_count - nr_wake >= nr_requeue)
break;
@@ -1460,6 +1598,7 @@ retry_private:
out_unlock:
double_unlock_hb(hb1, hb2);
+ hb_waiters_dec(hb2);
/*
* drop_futex_key_refs() must be called outside the spinlocks. During
@@ -1487,17 +1626,29 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
struct futex_hash_bucket *hb;
hb = hash_futex(&q->key);
+
+ /*
+ * Increment the counter before taking the lock so that
+ * a potential waker won't miss a to-be-slept task that is
+ * waiting for the spinlock. This is safe as all queue_lock()
+ * users end up calling queue_me(). Similarly, for housekeeping,
+ * decrement the counter at queue_unlock() when some error has
+ * occurred and we don't end up adding the task to the list.
+ */
+ hb_waiters_inc(hb);
+
q->lock_ptr = &hb->lock;
- spin_lock(&hb->lock);
+ spin_lock(&hb->lock); /* implies MB (A) */
return hb;
}
static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
__releases(&hb->lock)
{
spin_unlock(&hb->lock);
+ hb_waiters_dec(hb);
}
/**
@@ -1867,7 +2018,7 @@ retry_private:
ret = get_futex_value_locked(&uval, uaddr);
if (ret) {
- queue_unlock(q, *hb);
+ queue_unlock(*hb);
ret = get_user(uval, uaddr);
if (ret)
@@ -1881,7 +2032,7 @@ retry_private:
}
if (uval != val) {
- queue_unlock(q, *hb);
+ queue_unlock(*hb);
ret = -EWOULDBLOCK;
}
@@ -2029,7 +2180,7 @@ retry_private:
* Task is exiting and we just wait for the
* exit to complete.
*/
- queue_unlock(&q, hb);
+ queue_unlock(hb);
put_futex_key(&q.key);
cond_resched();
goto retry;
@@ -2081,7 +2232,7 @@ retry_private:
goto out_put_key;
out_unlock_put_key:
- queue_unlock(&q, hb);
+ queue_unlock(hb);
out_put_key:
put_futex_key(&q.key);
@@ -2091,7 +2242,7 @@ out:
return ret != -EINTR ? ret : -ERESTARTNOINTR;
uaddr_faulted:
- queue_unlock(&q, hb);
+ queue_unlock(hb);
ret = fault_in_user_writeable(uaddr);
if (ret)
@@ -2113,7 +2264,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
- struct plist_head *head;
union futex_key key = FUTEX_KEY_INIT;
u32 uval, vpid = task_pid_vnr(current);
int ret;
@@ -2153,9 +2303,7 @@ retry:
* Ok, other tasks may need to be woken up - check waiters
* and do the wakeup if necessary:
*/
- head = &hb->chain;
-
- plist_for_each_entry_safe(this, next, head, list) {
+ plist_for_each_entry_safe(this, next, &hb->chain, list) {
if (!match_futex (&this->key, &key))
continue;
ret = wake_futex_pi(uaddr, uval, this);
@@ -2232,6 +2380,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* Unqueue the futex_q and determine which it was.
*/
plist_del(&q->list, &hb->chain);
+ hb_waiters_dec(hb);
/* Handle spurious wakeups gracefully */
ret = -EWOULDBLOCK;
@@ -2316,6 +2465,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
* code while we sleep on uaddr.
*/
debug_rt_mutex_init_waiter(&rt_waiter);
+ RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+ RB_CLEAR_NODE(&rt_waiter.tree_entry);
rt_waiter.task = NULL;
ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
@@ -2731,10 +2882,10 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
{
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
u32 curval;
- int i;
/*
* This will fail and we want it. Some arch implementations do
@@ -2748,8 +2899,31 @@ static int __init futex_init(void)
*/
if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
+ unsigned int futex_shift;
+ unsigned long i;
+
+#if CONFIG_BASE_SMALL
+ futex_hashsize = 16;
+#else
+ futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
+
+ futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+ futex_hashsize, 0,
+ futex_hashsize < 256 ? HASH_SMALL : 0,
+ &futex_shift, NULL,
+ futex_hashsize, futex_hashsize);
+ futex_hashsize = 1UL << futex_shift;
+
+ futex_detect_cmpxchg();
- for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+ for (i = 0; i < futex_hashsize; i++) {
+ atomic_set(&futex_queues[i].waiters, 0);
plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f9f44fd4d34d..55c8c9349cfe 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -183,7 +183,7 @@ COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
cmd == FUTEX_WAIT_BITSET ||
cmd == FUTEX_WAIT_REQUEUE_PI)) {
- if (get_compat_timespec(&ts, utime))
+ if (compat_get_timespec(&ts, utime))
return -EFAULT;
if (!timespec_valid(&ts))
return -EINVAL;
diff --git a/kernel/groups.c b/kernel/groups.c
index 90cf1c38c8ea..451698f86cfa 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -157,17 +157,13 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
* set_groups - Change a group subscription in a set of credentials
* @new: The newly prepared set of credentials to alter
* @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
*/
-int set_groups(struct cred *new, struct group_info *group_info)
+void set_groups(struct cred *new, struct group_info *group_info)
{
put_group_info(new->group_info);
groups_sort(group_info);
get_group_info(group_info);
new->group_info = group_info;
- return 0;
}
EXPORT_SYMBOL(set_groups);
@@ -182,18 +178,12 @@ EXPORT_SYMBOL(set_groups);
int set_current_groups(struct group_info *group_info)
{
struct cred *new;
- int ret;
new = prepare_creds();
if (!new)
return -ENOMEM;
- ret = set_groups(new, group_info);
- if (ret < 0) {
- abort_creds(new);
- return ret;
- }
-
+ set_groups(new, group_info);
return commit_creds(new);
}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 383319bae3f7..d55092ceee29 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -46,6 +46,7 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include <linux/freezer.h>
@@ -167,19 +168,6 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
}
}
-
-/*
- * Get the preferred target CPU for NOHZ
- */
-static int hrtimer_get_target(int this_cpu, int pinned)
-{
-#ifdef CONFIG_NO_HZ_COMMON
- if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
- return get_nohz_timer_target();
-#endif
- return this_cpu;
-}
-
/*
* With HIGHRES=y we do not migrate the timer when it is expiring
* before the next event on the target cpu because we cannot reprogram
@@ -213,7 +201,7 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
struct hrtimer_clock_base *new_base;
struct hrtimer_cpu_base *new_cpu_base;
int this_cpu = smp_processor_id();
- int cpu = hrtimer_get_target(this_cpu, pinned);
+ int cpu = get_nohz_timer_target(pinned);
int basenum = base->index;
again:
@@ -1610,7 +1598,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
unsigned long slack;
slack = current->timer_slack_ns;
- if (rt_task(current))
+ if (dl_task(current) || rt_task(current))
slack = 0;
hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 9328b80eaf14..06bb1417b063 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -37,7 +37,7 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
*/
unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
-unsigned long __read_mostly sysctl_hung_task_warnings = 10;
+int __read_mostly sysctl_hung_task_warnings = 10;
static int __read_mostly did_panic;
@@ -98,7 +98,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
if (!sysctl_hung_task_warnings)
return;
- sysctl_hung_task_warnings--;
+
+ if (sysctl_hung_task_warnings > 0)
+ sysctl_hung_task_warnings--;
/*
* Ok, the task did not get scheduled for more than 2 minutes,
@@ -244,5 +246,4 @@ static int __init hung_task_init(void)
return 0;
}
-
-module_init(hung_task_init);
+subsys_initcall(hung_task_init);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 4a1fef09f658..07cbdfea9ae2 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -40,6 +40,7 @@ config IRQ_EDGE_EOI_HANDLER
# Generic configurable interrupt chip implementation
config GENERIC_IRQ_CHIP
bool
+ select IRQ_DOMAIN
# Generic irq_domain hw <--> linux irq number translation
config IRQ_DOMAIN
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index dc04c166c54d..6397df2d6945 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -281,6 +281,19 @@ void unmask_irq(struct irq_desc *desc)
}
}
+void unmask_threaded_irq(struct irq_desc *desc)
+{
+ struct irq_chip *chip = desc->irq_data.chip;
+
+ if (chip->flags & IRQCHIP_EOI_THREADED)
+ chip->irq_eoi(&desc->irq_data);
+
+ if (chip->irq_unmask) {
+ chip->irq_unmask(&desc->irq_data);
+ irq_state_clr_masked(desc);
+ }
+}
+
/*
* handle_nested_irq - Handle a nested irq from a irq thread
* @irq: the interrupt number
@@ -435,6 +448,27 @@ static inline void preflow_handler(struct irq_desc *desc)
static inline void preflow_handler(struct irq_desc *desc) { }
#endif
+static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip)
+{
+ if (!(desc->istate & IRQS_ONESHOT)) {
+ chip->irq_eoi(&desc->irq_data);
+ return;
+ }
+ /*
+ * We need to unmask in the following cases:
+ * - Oneshot irq which did not wake the thread (caused by a
+ * spurious interrupt or a primary handler handling it
+ * completely).
+ */
+ if (!irqd_irq_disabled(&desc->irq_data) &&
+ irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) {
+ chip->irq_eoi(&desc->irq_data);
+ unmask_irq(desc);
+ } else if (!(chip->flags & IRQCHIP_EOI_THREADED)) {
+ chip->irq_eoi(&desc->irq_data);
+ }
+}
+
/**
* handle_fasteoi_irq - irq handler for transparent controllers
* @irq: the interrupt number
@@ -448,6 +482,8 @@ static inline void preflow_handler(struct irq_desc *desc) { }
void
handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
{
+ struct irq_chip *chip = desc->irq_data.chip;
+
raw_spin_lock(&desc->lock);
if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
@@ -473,18 +509,14 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
preflow_handler(desc);
handle_irq_event(desc);
- if (desc->istate & IRQS_ONESHOT)
- cond_unmask_irq(desc);
+ cond_unmask_eoi_irq(desc, chip);
-out_eoi:
- desc->irq_data.chip->irq_eoi(&desc->irq_data);
-out_unlock:
raw_spin_unlock(&desc->lock);
return;
out:
- if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
- goto out_eoi;
- goto out_unlock;
+ if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED))
+ chip->irq_eoi(&desc->irq_data);
+ raw_spin_unlock(&desc->lock);
}
/**
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index bd8e788d71e0..1ef0606797c9 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -73,6 +73,51 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq,
EXPORT_SYMBOL(devm_request_threaded_irq);
/**
+ * devm_request_any_context_irq - allocate an interrupt line for a managed device
+ * @dev: device to request interrupt for
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs
+ * @thread_fn: function to be called in a threaded interrupt context. NULL
+ * for devices which handle everything in @handler
+ * @irqflags: Interrupt type flags
+ * @devname: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * Except for the extra @dev argument, this function takes the
+ * same arguments and performs the same function as
+ * request_any_context_irq(). IRQs requested with this function will be
+ * automatically freed on driver detach.
+ *
+ * If an IRQ allocated with this function needs to be freed
+ * separately, devm_free_irq() must be used.
+ */
+int devm_request_any_context_irq(struct device *dev, unsigned int irq,
+ irq_handler_t handler, unsigned long irqflags,
+ const char *devname, void *dev_id)
+{
+ struct irq_devres *dr;
+ int rc;
+
+ dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres),
+ GFP_KERNEL);
+ if (!dr)
+ return -ENOMEM;
+
+ rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
+ if (rc) {
+ devres_free(dr);
+ return rc;
+ }
+
+ dr->irq = irq;
+ dr->dev_id = dev_id;
+ devres_add(dev, dr);
+
+ return 0;
+}
+EXPORT_SYMBOL(devm_request_any_context_irq);
+
+/**
* devm_free_irq - free an interrupt
* @dev: device to free interrupt for
* @irq: Interrupt line to free
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 131ca176b497..635480270858 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -41,6 +41,7 @@ irqreturn_t no_action(int cpl, void *dev_id)
{
return IRQ_NONE;
}
+EXPORT_SYMBOL_GPL(no_action);
static void warn_no_thread(unsigned int irq, struct irqaction *action)
{
@@ -51,7 +52,7 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
"but no thread function available.", irq, action->name);
}
-static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
{
/*
* In case the thread crashed and was killed we just pretend that
@@ -157,7 +158,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
break;
}
- irq_wake_thread(desc, action);
+ __irq_wake_thread(desc, action);
/* Fall through to add to randomness */
case IRQ_HANDLED:
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 001fa5bab490..ddf1ffeb79f1 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -6,6 +6,7 @@
* of this file for your non core code.
*/
#include <linux/irqdesc.h>
+#include <linux/kernel_stat.h>
#ifdef CONFIG_SPARSE_IRQ
# define IRQ_BITMAP_BITS (NR_IRQS + 8196)
@@ -73,6 +74,7 @@ extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu);
extern void mask_irq(struct irq_desc *desc);
extern void unmask_irq(struct irq_desc *desc);
+extern void unmask_threaded_irq(struct irq_desc *desc);
extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
@@ -82,6 +84,7 @@ irqreturn_t handle_irq_event(struct irq_desc *desc);
/* Resending of interrupts :*/
void check_irq_resend(struct irq_desc *desc, unsigned int irq);
bool irq_wait_for_poll(struct irq_desc *desc);
+void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
#ifdef CONFIG_PROC_FS
extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
@@ -179,3 +182,9 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
{
return d->state_use_accessors & mask;
}
+
+static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc)
+{
+ __this_cpu_inc(*desc->kstat_irqs);
+ __this_cpu_inc(kstat.irqs_sum);
+}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302d6cfd..a7174617616b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -274,6 +274,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
{
return (irq < NR_IRQS) ? irq_desc + irq : NULL;
}
+EXPORT_SYMBOL(irq_to_desc);
static void free_desc(unsigned int irq)
{
@@ -488,6 +489,11 @@ void dynamic_irq_cleanup(unsigned int irq)
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
+void kstat_incr_irq_this_cpu(unsigned int irq)
+{
+ kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+}
+
unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
{
struct irq_desc *desc = irq_to_desc(irq);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf68bb36fe58..f14033700c25 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_irq.h>
#include <linux/topology.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 481a13c43b17..2486a4c1a710 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -32,24 +32,10 @@ static int __init setup_forced_irqthreads(char *arg)
early_param("threadirqs", setup_forced_irqthreads);
#endif
-/**
- * synchronize_irq - wait for pending IRQ handlers (on other CPUs)
- * @irq: interrupt number to wait for
- *
- * This function waits for any pending IRQ handlers for this interrupt
- * to complete before returning. If you use this function while
- * holding a resource the IRQ handler may need you will deadlock.
- *
- * This function may be called - with care - from IRQ context.
- */
-void synchronize_irq(unsigned int irq)
+static void __synchronize_hardirq(struct irq_desc *desc)
{
- struct irq_desc *desc = irq_to_desc(irq);
bool inprogress;
- if (!desc)
- return;
-
do {
unsigned long flags;
@@ -67,12 +53,56 @@ void synchronize_irq(unsigned int irq)
/* Oops, that failed? */
} while (inprogress);
+}
- /*
- * We made sure that no hardirq handler is running. Now verify
- * that no threaded handlers are active.
- */
- wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
+/**
+ * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
+ * @irq: interrupt number to wait for
+ *
+ * This function waits for any pending hard IRQ handlers for this
+ * interrupt to complete before returning. If you use this
+ * function while holding a resource the IRQ handler may need you
+ * will deadlock. It does not take associated threaded handlers
+ * into account.
+ *
+ * Do not use this for shutdown scenarios where you must be sure
+ * that all parts (hardirq and threaded handler) have completed.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+void synchronize_hardirq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ if (desc)
+ __synchronize_hardirq(desc);
+}
+EXPORT_SYMBOL(synchronize_hardirq);
+
+/**
+ * synchronize_irq - wait for pending IRQ handlers (on other CPUs)
+ * @irq: interrupt number to wait for
+ *
+ * This function waits for any pending IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while
+ * holding a resource the IRQ handler may need you will deadlock.
+ *
+ * This function may be called - with care - from IRQ context.
+ */
+void synchronize_irq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ if (desc) {
+ __synchronize_hardirq(desc);
+ /*
+ * We made sure that no hardirq handler is
+ * running. Now verify that no threaded handlers are
+ * active.
+ */
+ wait_event(desc->wait_for_threads,
+ !atomic_read(&desc->threads_active));
+ }
}
EXPORT_SYMBOL(synchronize_irq);
@@ -718,7 +748,7 @@ again:
if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) &&
irqd_irq_masked(&desc->irq_data))
- unmask_irq(desc);
+ unmask_threaded_irq(desc);
out_unlock:
raw_spin_unlock_irq(&desc->lock);
@@ -727,7 +757,7 @@ out_unlock:
#ifdef CONFIG_SMP
/*
- * Check whether we need to chasnge the affinity of the interrupt thread.
+ * Check whether we need to change the affinity of the interrupt thread.
*/
static void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
@@ -802,8 +832,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
static void wake_threads_waitq(struct irq_desc *desc)
{
- if (atomic_dec_and_test(&desc->threads_active) &&
- waitqueue_active(&desc->wait_for_threads))
+ if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
@@ -881,6 +910,33 @@ static int irq_thread(void *data)
return 0;
}
+/**
+ * irq_wake_thread - wake the irq thread for the action identified by dev_id
+ * @irq: Interrupt line
+ * @dev_id: Device identity for which the thread should be woken
+ *
+ */
+void irq_wake_thread(unsigned int irq, void *dev_id)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irqaction *action;
+ unsigned long flags;
+
+ if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+ return;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ for (action = desc->action; action; action = action->next) {
+ if (action->dev_id == dev_id) {
+ if (action->thread)
+ __irq_wake_thread(desc, action);
+ break;
+ }
+ }
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+EXPORT_SYMBOL_GPL(irq_wake_thread);
+
static void irq_setup_forced_threading(struct irqaction *new)
{
if (!force_irqthreads)
@@ -897,6 +953,23 @@ static void irq_setup_forced_threading(struct irqaction *new)
}
}
+static int irq_request_resources(struct irq_desc *desc)
+{
+ struct irq_data *d = &desc->irq_data;
+ struct irq_chip *c = d->chip;
+
+ return c->irq_request_resources ? c->irq_request_resources(d) : 0;
+}
+
+static void irq_release_resources(struct irq_desc *desc)
+{
+ struct irq_data *d = &desc->irq_data;
+ struct irq_chip *c = d->chip;
+
+ if (c->irq_release_resources)
+ c->irq_release_resources(d);
+}
+
/*
* Internal function to register an irqaction - typically used to
* allocate special interrupts that are part of the architecture.
@@ -1092,6 +1165,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
}
if (!shared) {
+ ret = irq_request_resources(desc);
+ if (ret) {
+ pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
+ new->name, irq, desc->irq_data.chip->name);
+ goto out_mask;
+ }
+
init_waitqueue_head(&desc->wait_for_threads);
/* Setup the type (level, edge polarity) if configured: */
@@ -1262,8 +1342,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
*action_ptr = action->next;
/* If this was the last handler, shut down the IRQ line: */
- if (!desc->action)
+ if (!desc->action) {
irq_shutdown(desc);
+ irq_release_resources(desc);
+ }
#ifdef CONFIG_SMP
/* make sure affinity_hint is cleaned up */
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 36f6ee181b0c..ac1ba2f11032 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -324,15 +324,15 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
#ifdef CONFIG_SMP
/* create /proc/irq/<irq>/smp_affinity */
- proc_create_data("smp_affinity", 0600, desc->dir,
+ proc_create_data("smp_affinity", 0644, desc->dir,
&irq_affinity_proc_fops, (void *)(long)irq);
/* create /proc/irq/<irq>/affinity_hint */
- proc_create_data("affinity_hint", 0400, desc->dir,
+ proc_create_data("affinity_hint", 0444, desc->dir,
&irq_affinity_hint_proc_fops, (void *)(long)irq);
/* create /proc/irq/<irq>/smp_affinity_list */
- proc_create_data("smp_affinity_list", 0600, desc->dir,
+ proc_create_data("smp_affinity_list", 0644, desc->dir,
&irq_affinity_list_proc_fops, (void *)(long)irq);
proc_create_data("node", 0444, desc->dir,
@@ -372,7 +372,7 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
static void register_default_affinity_proc(void)
{
#ifdef CONFIG_SMP
- proc_create("irq/default_smp_affinity", 0600, NULL,
+ proc_create("irq/default_smp_affinity", 0644, NULL,
&default_affinity_proc_fops);
#endif
}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 55fcce6065cf..a82170e2fa78 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -61,11 +61,11 @@ void __weak arch_irq_work_raise(void)
*
* Can be re-enqueued while the callback is still in progress.
*/
-void irq_work_queue(struct irq_work *work)
+bool irq_work_queue(struct irq_work *work)
{
/* Only queue if not already pending */
if (!irq_work_claim(work))
- return;
+ return false;
/* Queue the entry and raise the IPI if needed. */
preempt_disable();
@@ -83,6 +83,8 @@ void irq_work_queue(struct irq_work *work)
}
preempt_enable();
+
+ return true;
}
EXPORT_SYMBOL_GPL(irq_work_queue);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 3127ad52cdb2..cb0cf37dac3a 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -23,6 +23,7 @@
#include <linux/mm.h>
#include <linux/ctype.h>
#include <linux/slab.h>
+#include <linux/compiler.h>
#include <asm/sections.h>
@@ -36,8 +37,8 @@
* These will be re-linked against their real values
* during the second link stage.
*/
-extern const unsigned long kallsyms_addresses[] __attribute__((weak));
-extern const u8 kallsyms_names[] __attribute__((weak));
+extern const unsigned long kallsyms_addresses[] __weak;
+extern const u8 kallsyms_names[] __weak;
/*
* Tell the compiler that the count isn't in the small data section if the arch
@@ -46,10 +47,10 @@ extern const u8 kallsyms_names[] __attribute__((weak));
extern const unsigned long kallsyms_num_syms
__attribute__((weak, section(".rodata")));
-extern const u8 kallsyms_token_table[] __attribute__((weak));
-extern const u16 kallsyms_token_index[] __attribute__((weak));
+extern const u8 kallsyms_token_table[] __weak;
+extern const u16 kallsyms_token_index[] __weak;
-extern const unsigned long kallsyms_markers[] __attribute__((weak));
+extern const unsigned long kallsyms_markers[] __weak;
static inline int is_kernel_inittext(unsigned long addr)
{
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 9c970167e402..c8380ad203bc 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -32,6 +32,7 @@
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/syscore_ops.h>
+#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/uaccess.h>
@@ -932,6 +933,7 @@ static int kimage_load_segment(struct kimage *image,
*/
struct kimage *kexec_image;
struct kimage *kexec_crash_image;
+int kexec_load_disabled;
static DEFINE_MUTEX(kexec_mutex);
@@ -942,7 +944,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
int result;
/* We only trust the superuser with rebooting the system. */
- if (!capable(CAP_SYS_BOOT))
+ if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
return -EPERM;
/*
@@ -1038,10 +1040,10 @@ void __weak crash_unmap_reserved_pages(void)
{}
#ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_kexec_load(unsigned long entry,
- unsigned long nr_segments,
- struct compat_kexec_segment __user *segments,
- unsigned long flags)
+COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
+ compat_ulong_t, nr_segments,
+ struct compat_kexec_segment __user *, segments,
+ compat_ulong_t, flags)
{
struct compat_kexec_segment in;
struct kexec_segment out, __user *ksegments;
@@ -1234,7 +1236,7 @@ static int __init crash_notes_memory_init(void)
}
return 0;
}
-module_init(crash_notes_memory_init)
+subsys_initcall(crash_notes_memory_init);
/*
@@ -1536,7 +1538,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
size_t r;
va_start(args, fmt);
- r = vsnprintf(buf, sizeof(buf), fmt, args);
+ r = vscnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
@@ -1550,10 +1552,10 @@ void vmcoreinfo_append_str(const char *fmt, ...)
* provide an empty default implementation here -- architecture
* code may override this
*/
-void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void)
+void __weak arch_crash_save_vmcoreinfo(void)
{}
-unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void)
+unsigned long __weak paddr_vmcoreinfo_note(void)
{
return __pa((unsigned long)(char *)&vmcoreinfo_note);
}
@@ -1628,7 +1630,7 @@ static int __init crash_save_vmcoreinfo_init(void)
return 0;
}
-module_init(crash_save_vmcoreinfo_init)
+subsys_initcall(crash_save_vmcoreinfo_init);
/*
* Move into place and start executing a preloaded standalone
diff --git a/kernel/kmod.c b/kernel/kmod.c
index b086006c59e7..6b375af4958d 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -239,7 +239,7 @@ static int ____call_usermodehelper(void *data)
commit_creds(new);
- retval = do_execve(sub_info->path,
+ retval = do_execve(getname_kernel(sub_info->path),
(const char __user *const __user *)sub_info->argv,
(const char __user *const __user *)sub_info->envp);
if (!retval)
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 9659d38e008f..2495a9b14ac8 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -18,6 +18,9 @@
#include <linux/stat.h>
#include <linux/sched.h>
#include <linux/capability.h>
+#include <linux/compiler.h>
+
+#include <linux/rcupdate.h> /* rcu_expedited */
#define KERNEL_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
@@ -126,7 +129,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
{
return sprintf(buf, "%lx %x\n",
paddr_vmcoreinfo_note(),
- (unsigned int)vmcoreinfo_max_size);
+ (unsigned int)sizeof(vmcoreinfo_note));
}
KERNEL_ATTR_RO(vmcoreinfo);
@@ -160,8 +163,8 @@ KERNEL_ATTR_RW(rcu_expedited);
/*
* Make /sys/kernel/notes give the raw contents of our kernel .notes section.
*/
-extern const void __start_notes __attribute__((weak));
-extern const void __stop_notes __attribute__((weak));
+extern const void __start_notes __weak;
+extern const void __stop_notes __weak;
#define notes_size (&__stop_notes - &__start_notes)
static ssize_t notes_read(struct file *filp, struct kobject *kobj,
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b5ae3ee860a9..9a130ec06f7a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -217,7 +217,7 @@ int tsk_fork_get_node(struct task_struct *tsk)
if (tsk == kthreadd_task)
return tsk->pref_node_fork;
#endif
- return numa_node_id();
+ return NUMA_NO_NODE;
}
static void create_kthread(struct kthread_create_info *create)
@@ -369,7 +369,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
{
struct task_struct *p;
- p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+ p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt,
cpu);
if (IS_ERR(p))
return p;
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index baab8e5e7f66..b8bdcd4785b7 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,5 +1,5 @@
-obj-y += mutex.o semaphore.o rwsem.o lglock.o
+obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_lockdep.o = -pg
@@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y)
obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
endif
obj-$(CONFIG_SMP) += spinlock.o
+obj-$(CONFIG_SMP) += lglock.o
obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
@@ -23,3 +24,4 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
+obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 576ba756a32d..b0e9467922e1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
/*
* Is this the address of a static object:
*/
+#ifdef __KERNEL__
static int static_obj(void *obj)
{
unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
*/
return is_module_address(addr) || is_module_percpu_address(addr);
}
+#endif
/*
* To make lock name printouts unique, we calculate a unique
@@ -1934,12 +1936,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
for (;;) {
int distance = curr->lockdep_depth - depth + 1;
- hlock = curr->held_locks + depth-1;
+ hlock = curr->held_locks + depth - 1;
/*
* Only non-recursive-read entries get new dependencies
* added:
*/
- if (hlock->read != 2) {
+ if (hlock->read != 2 && hlock->check) {
if (!check_prev_add(curr, hlock, next,
distance, trylock_loop))
return 0;
@@ -2096,7 +2098,7 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
* (If lookup_chain_cache() returns with 1 it acquires
* graph_lock for us)
*/
- if (!hlock->trylock && (hlock->check == 2) &&
+ if (!hlock->trylock && hlock->check &&
lookup_chain_cache(curr, hlock, chain_key)) {
/*
* Check whether last held lock:
@@ -2515,7 +2517,7 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark)
BUG_ON(usage_bit >= LOCK_USAGE_STATES);
- if (hlock_class(hlock)->key == __lockdep_no_validate__.subkeys)
+ if (!hlock->check)
continue;
if (!mark_lock(curr, hlock, usage_bit))
@@ -2555,7 +2557,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
debug_atomic_inc(hardirqs_on_events);
}
-void trace_hardirqs_on_caller(unsigned long ip)
+__visible void trace_hardirqs_on_caller(unsigned long ip)
{
time_hardirqs_on(CALLER_ADDR0, ip);
@@ -2608,7 +2610,7 @@ EXPORT_SYMBOL(trace_hardirqs_on);
/*
* Hardirqs were disabled:
*/
-void trace_hardirqs_off_caller(unsigned long ip)
+__visible void trace_hardirqs_off_caller(unsigned long ip)
{
struct task_struct *curr = current;
@@ -3053,9 +3055,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
int class_idx;
u64 chain_key;
- if (!prove_locking)
- check = 1;
-
if (unlikely(!debug_locks))
return 0;
@@ -3067,8 +3066,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
return 0;
- if (lock->key == &__lockdep_no_validate__)
- check = 1;
+ if (!prove_locking || lock->key == &__lockdep_no_validate__)
+ check = 0;
if (subclass < NR_LOCKDEP_CACHING_CLASSES)
class = lock->class_cache[subclass];
@@ -3136,7 +3135,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
hlock->holdtime_stamp = lockstat_clock();
#endif
- if (check == 2 && !mark_irqflags(curr, hlock))
+ if (check && !mark_irqflags(curr, hlock))
return 0;
/* mark it as used: */
@@ -4115,6 +4114,7 @@ void debug_check_no_locks_held(void)
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
+#ifdef __KERNEL__
void debug_show_all_locks(void)
{
struct task_struct *g, *p;
@@ -4172,6 +4172,7 @@ retry:
read_unlock(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
/*
* Careful: only use this function if you are sure that
@@ -4187,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task)
}
EXPORT_SYMBOL_GPL(debug_show_held_locks);
-void lockdep_sys_exit(void)
+asmlinkage void lockdep_sys_exit(void)
{
struct task_struct *curr = current;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
new file mode 100644
index 000000000000..f26b1a18e34e
--- /dev/null
+++ b/kernel/locking/locktorture.c
@@ -0,0 +1,452 @@
+/*
+ * Module-based torture test facility for locking
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ * Based on kernel/rcu/torture.c.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+
+torture_param(int, nwriters_stress, -1,
+ "Number of write-locking stress-test threads");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0,
+ "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shuffle_interval, 3,
+ "Number of jiffies between shuffles, 0=disable");
+torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
+torture_param(int, stat_interval, 60,
+ "Number of seconds between stats printk()s");
+torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
+torture_param(bool, verbose, true,
+ "Enable verbose debugging printk()s");
+
+static char *torture_type = "spin_lock";
+module_param(torture_type, charp, 0444);
+MODULE_PARM_DESC(torture_type,
+ "Type of lock to torture (spin_lock, spin_lock_irq, ...)");
+
+static atomic_t n_lock_torture_errors;
+
+static struct task_struct *stats_task;
+static struct task_struct **writer_tasks;
+
+static int nrealwriters_stress;
+static bool lock_is_write_held;
+
+struct lock_writer_stress_stats {
+ long n_write_lock_fail;
+ long n_write_lock_acquired;
+};
+static struct lock_writer_stress_stats *lwsa;
+
+#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE)
+#define LOCKTORTURE_RUNNABLE_INIT 1
+#else
+#define LOCKTORTURE_RUNNABLE_INIT 0
+#endif
+int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
+module_param(locktorture_runnable, int, 0444);
+MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot");
+
+/* Forward reference. */
+static void lock_torture_cleanup(void);
+
+/*
+ * Operations vector for selecting different types of tests.
+ */
+struct lock_torture_ops {
+ void (*init)(void);
+ int (*writelock)(void);
+ void (*write_delay)(struct torture_random_state *trsp);
+ void (*writeunlock)(void);
+ unsigned long flags;
+ const char *name;
+};
+
+static struct lock_torture_ops *cur_ops;
+
+/*
+ * Definitions for lock torture testing.
+ */
+
+static int torture_lock_busted_write_lock(void)
+{
+ return 0; /* BUGGY, do not use in real life!!! */
+}
+
+static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
+{
+ const unsigned long longdelay_us = 100;
+
+ /* We want a long delay occasionally to force massive contention. */
+ if (!(torture_random(trsp) %
+ (nrealwriters_stress * 2000 * longdelay_us)))
+ mdelay(longdelay_us);
+#ifdef CONFIG_PREEMPT
+ if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+ preempt_schedule(); /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_lock_busted_write_unlock(void)
+{
+ /* BUGGY, do not use in real life!!! */
+}
+
+static struct lock_torture_ops lock_busted_ops = {
+ .writelock = torture_lock_busted_write_lock,
+ .write_delay = torture_lock_busted_write_delay,
+ .writeunlock = torture_lock_busted_write_unlock,
+ .name = "lock_busted"
+};
+
+static DEFINE_SPINLOCK(torture_spinlock);
+
+static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
+{
+ spin_lock(&torture_spinlock);
+ return 0;
+}
+
+static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
+{
+ const unsigned long shortdelay_us = 2;
+ const unsigned long longdelay_us = 100;
+
+ /* We want a short delay mostly to emulate likely code, and
+ * we want a long delay occasionally to force massive contention.
+ */
+ if (!(torture_random(trsp) %
+ (nrealwriters_stress * 2000 * longdelay_us)))
+ mdelay(longdelay_us);
+ if (!(torture_random(trsp) %
+ (nrealwriters_stress * 2 * shortdelay_us)))
+ udelay(shortdelay_us);
+#ifdef CONFIG_PREEMPT
+ if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+ preempt_schedule(); /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
+{
+ spin_unlock(&torture_spinlock);
+}
+
+static struct lock_torture_ops spin_lock_ops = {
+ .writelock = torture_spin_lock_write_lock,
+ .write_delay = torture_spin_lock_write_delay,
+ .writeunlock = torture_spin_lock_write_unlock,
+ .name = "spin_lock"
+};
+
+static int torture_spin_lock_write_lock_irq(void)
+__acquires(torture_spinlock_irq)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&torture_spinlock, flags);
+ cur_ops->flags = flags;
+ return 0;
+}
+
+static void torture_lock_spin_write_unlock_irq(void)
+__releases(torture_spinlock)
+{
+ spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags);
+}
+
+static struct lock_torture_ops spin_lock_irq_ops = {
+ .writelock = torture_spin_lock_write_lock_irq,
+ .write_delay = torture_spin_lock_write_delay,
+ .writeunlock = torture_lock_spin_write_unlock_irq,
+ .name = "spin_lock_irq"
+};
+
+/*
+ * Lock torture writer kthread. Repeatedly acquires and releases
+ * the lock, checking for duplicate acquisitions.
+ */
+static int lock_torture_writer(void *arg)
+{
+ struct lock_writer_stress_stats *lwsp = arg;
+ static DEFINE_TORTURE_RANDOM(rand);
+
+ VERBOSE_TOROUT_STRING("lock_torture_writer task started");
+ set_user_nice(current, 19);
+
+ do {
+ schedule_timeout_uninterruptible(1);
+ cur_ops->writelock();
+ if (WARN_ON_ONCE(lock_is_write_held))
+ lwsp->n_write_lock_fail++;
+ lock_is_write_held = 1;
+ lwsp->n_write_lock_acquired++;
+ cur_ops->write_delay(&rand);
+ lock_is_write_held = 0;
+ cur_ops->writeunlock();
+ stutter_wait("lock_torture_writer");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("lock_torture_writer");
+ return 0;
+}
+
+/*
+ * Create an lock-torture-statistics message in the specified buffer.
+ */
+static void lock_torture_printk(char *page)
+{
+ bool fail = 0;
+ int i;
+ long max = 0;
+ long min = lwsa[0].n_write_lock_acquired;
+ long long sum = 0;
+
+ for (i = 0; i < nrealwriters_stress; i++) {
+ if (lwsa[i].n_write_lock_fail)
+ fail = true;
+ sum += lwsa[i].n_write_lock_acquired;
+ if (max < lwsa[i].n_write_lock_fail)
+ max = lwsa[i].n_write_lock_fail;
+ if (min > lwsa[i].n_write_lock_fail)
+ min = lwsa[i].n_write_lock_fail;
+ }
+ page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page,
+ "Writes: Total: %lld Max/Min: %ld/%ld %s Fail: %d %s\n",
+ sum, max, min, max / 2 > min ? "???" : "",
+ fail, fail ? "!!!" : "");
+ if (fail)
+ atomic_inc(&n_lock_torture_errors);
+}
+
+/*
+ * Print torture statistics. Caller must ensure that there is only one
+ * call to this function at a given time!!! This is normally accomplished
+ * by relying on the module system to only have one copy of the module
+ * loaded, and then by giving the lock_torture_stats kthread full control
+ * (or the init/cleanup functions when lock_torture_stats thread is not
+ * running).
+ */
+static void lock_torture_stats_print(void)
+{
+ int size = nrealwriters_stress * 200 + 8192;
+ char *buf;
+
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf) {
+ pr_err("lock_torture_stats_print: Out of memory, need: %d",
+ size);
+ return;
+ }
+ lock_torture_printk(buf);
+ pr_alert("%s", buf);
+ kfree(buf);
+}
+
+/*
+ * Periodically prints torture statistics, if periodic statistics printing
+ * was specified via the stat_interval module parameter.
+ *
+ * No need to worry about fullstop here, since this one doesn't reference
+ * volatile state or register callbacks.
+ */
+static int lock_torture_stats(void *arg)
+{
+ VERBOSE_TOROUT_STRING("lock_torture_stats task started");
+ do {
+ schedule_timeout_interruptible(stat_interval * HZ);
+ lock_torture_stats_print();
+ torture_shutdown_absorb("lock_torture_stats");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("lock_torture_stats");
+ return 0;
+}
+
+static inline void
+lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
+ const char *tag)
+{
+ pr_alert("%s" TORTURE_FLAG
+ "--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+ torture_type, tag, nrealwriters_stress, stat_interval, verbose,
+ shuffle_interval, stutter, shutdown_secs,
+ onoff_interval, onoff_holdoff);
+}
+
+static void lock_torture_cleanup(void)
+{
+ int i;
+
+ if (torture_cleanup())
+ return;
+
+ if (writer_tasks) {
+ for (i = 0; i < nrealwriters_stress; i++)
+ torture_stop_kthread(lock_torture_writer,
+ writer_tasks[i]);
+ kfree(writer_tasks);
+ writer_tasks = NULL;
+ }
+
+ torture_stop_kthread(lock_torture_stats, stats_task);
+ lock_torture_stats_print(); /* -After- the stats thread is stopped! */
+
+ if (atomic_read(&n_lock_torture_errors))
+ lock_torture_print_module_parms(cur_ops,
+ "End of test: FAILURE");
+ else if (torture_onoff_failures())
+ lock_torture_print_module_parms(cur_ops,
+ "End of test: LOCK_HOTPLUG");
+ else
+ lock_torture_print_module_parms(cur_ops,
+ "End of test: SUCCESS");
+}
+
+static int __init lock_torture_init(void)
+{
+ int i;
+ int firsterr = 0;
+ static struct lock_torture_ops *torture_ops[] = {
+ &lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
+ };
+
+ torture_init_begin(torture_type, verbose, &locktorture_runnable);
+
+ /* Process args and tell the world that the torturer is on the job. */
+ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
+ cur_ops = torture_ops[i];
+ if (strcmp(torture_type, cur_ops->name) == 0)
+ break;
+ }
+ if (i == ARRAY_SIZE(torture_ops)) {
+ pr_alert("lock-torture: invalid torture type: \"%s\"\n",
+ torture_type);
+ pr_alert("lock-torture types:");
+ for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+ pr_alert(" %s", torture_ops[i]->name);
+ pr_alert("\n");
+ torture_init_end();
+ return -EINVAL;
+ }
+ if (cur_ops->init)
+ cur_ops->init(); /* no "goto unwind" prior to this point!!! */
+
+ if (nwriters_stress >= 0)
+ nrealwriters_stress = nwriters_stress;
+ else
+ nrealwriters_stress = 2 * num_online_cpus();
+ lock_torture_print_module_parms(cur_ops, "Start of test");
+
+ /* Initialize the statistics so that each run gets its own numbers. */
+
+ lock_is_write_held = 0;
+ lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL);
+ if (lwsa == NULL) {
+ VERBOSE_TOROUT_STRING("lwsa: Out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ for (i = 0; i < nrealwriters_stress; i++) {
+ lwsa[i].n_write_lock_fail = 0;
+ lwsa[i].n_write_lock_acquired = 0;
+ }
+
+ /* Start up the kthreads. */
+
+ if (onoff_interval > 0) {
+ firsterr = torture_onoff_init(onoff_holdoff * HZ,
+ onoff_interval * HZ);
+ if (firsterr)
+ goto unwind;
+ }
+ if (shuffle_interval > 0) {
+ firsterr = torture_shuffle_init(shuffle_interval);
+ if (firsterr)
+ goto unwind;
+ }
+ if (shutdown_secs > 0) {
+ firsterr = torture_shutdown_init(shutdown_secs,
+ lock_torture_cleanup);
+ if (firsterr)
+ goto unwind;
+ }
+ if (stutter > 0) {
+ firsterr = torture_stutter_init(stutter);
+ if (firsterr)
+ goto unwind;
+ }
+
+ writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]),
+ GFP_KERNEL);
+ if (writer_tasks == NULL) {
+ VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ for (i = 0; i < nrealwriters_stress; i++) {
+ firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i],
+ writer_tasks[i]);
+ if (firsterr)
+ goto unwind;
+ }
+ if (stat_interval > 0) {
+ firsterr = torture_create_kthread(lock_torture_stats, NULL,
+ stats_task);
+ if (firsterr)
+ goto unwind;
+ }
+ torture_init_end();
+ return 0;
+
+unwind:
+ torture_init_end();
+ lock_torture_cleanup();
+ return firsterr;
+}
+
+module_init(lock_torture_init);
+module_exit(lock_torture_cleanup);
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
new file mode 100644
index 000000000000..838dc9e00669
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.c
@@ -0,0 +1,178 @@
+
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_SMP
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ *
+ * Using a single mcs node per CPU is safe because sleeping locks should not be
+ * called from interrupt context and we have preemption disabled while
+ * spinning.
+ */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+
+/*
+ * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
+ * Can return NULL in case we were the last queued and we updated @lock instead.
+ */
+static inline struct optimistic_spin_queue *
+osq_wait_next(struct optimistic_spin_queue **lock,
+ struct optimistic_spin_queue *node,
+ struct optimistic_spin_queue *prev)
+{
+ struct optimistic_spin_queue *next = NULL;
+
+ for (;;) {
+ if (*lock == node && cmpxchg(lock, node, prev) == node) {
+ /*
+ * We were the last queued, we moved @lock back. @prev
+ * will now observe @lock and will complete its
+ * unlock()/unqueue().
+ */
+ break;
+ }
+
+ /*
+ * We must xchg() the @node->next value, because if we were to
+ * leave it in, a concurrent unlock()/unqueue() from
+ * @node->next might complete Step-A and think its @prev is
+ * still valid.
+ *
+ * If the concurrent unlock()/unqueue() wins the race, we'll
+ * wait for either @lock to point to us, through its Step-B, or
+ * wait for a new @node->next from its Step-C.
+ */
+ if (node->next) {
+ next = xchg(&node->next, NULL);
+ if (next)
+ break;
+ }
+
+ arch_mutex_cpu_relax();
+ }
+
+ return next;
+}
+
+bool osq_lock(struct optimistic_spin_queue **lock)
+{
+ struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+ struct optimistic_spin_queue *prev, *next;
+
+ node->locked = 0;
+ node->next = NULL;
+
+ node->prev = prev = xchg(lock, node);
+ if (likely(prev == NULL))
+ return true;
+
+ ACCESS_ONCE(prev->next) = node;
+
+ /*
+ * Normally @prev is untouchable after the above store; because at that
+ * moment unlock can proceed and wipe the node element from stack.
+ *
+ * However, since our nodes are static per-cpu storage, we're
+ * guaranteed their existence -- this allows us to apply
+ * cmpxchg in an attempt to undo our queueing.
+ */
+
+ while (!smp_load_acquire(&node->locked)) {
+ /*
+ * If we need to reschedule bail... so we can block.
+ */
+ if (need_resched())
+ goto unqueue;
+
+ arch_mutex_cpu_relax();
+ }
+ return true;
+
+unqueue:
+ /*
+ * Step - A -- stabilize @prev
+ *
+ * Undo our @prev->next assignment; this will make @prev's
+ * unlock()/unqueue() wait for a next pointer since @lock points to us
+ * (or later).
+ */
+
+ for (;;) {
+ if (prev->next == node &&
+ cmpxchg(&prev->next, node, NULL) == node)
+ break;
+
+ /*
+ * We can only fail the cmpxchg() racing against an unlock(),
+ * in which case we should observe @node->locked becomming
+ * true.
+ */
+ if (smp_load_acquire(&node->locked))
+ return true;
+
+ arch_mutex_cpu_relax();
+
+ /*
+ * Or we race against a concurrent unqueue()'s step-B, in which
+ * case its step-C will write us a new @node->prev pointer.
+ */
+ prev = ACCESS_ONCE(node->prev);
+ }
+
+ /*
+ * Step - B -- stabilize @next
+ *
+ * Similar to unlock(), wait for @node->next or move @lock from @node
+ * back to @prev.
+ */
+
+ next = osq_wait_next(lock, node, prev);
+ if (!next)
+ return false;
+
+ /*
+ * Step - C -- unlink
+ *
+ * @prev is stable because its still waiting for a new @prev->next
+ * pointer, @next is stable because our @node->next pointer is NULL and
+ * it will wait in Step-A.
+ */
+
+ ACCESS_ONCE(next->prev) = prev;
+ ACCESS_ONCE(prev->next) = next;
+
+ return false;
+}
+
+void osq_unlock(struct optimistic_spin_queue **lock)
+{
+ struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+ struct optimistic_spin_queue *next;
+
+ /*
+ * Fast path for the uncontended case.
+ */
+ if (likely(cmpxchg(lock, node, NULL) == node))
+ return;
+
+ /*
+ * Second most likely case.
+ */
+ next = xchg(&node->next, NULL);
+ if (next) {
+ ACCESS_ONCE(next->locked) = 1;
+ return;
+ }
+
+ next = osq_wait_next(lock, node, NULL);
+ if (next)
+ ACCESS_ONCE(next->locked) = 1;
+}
+
+#endif
+
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
new file mode 100644
index 000000000000..a2dbac4aca6b
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.h
@@ -0,0 +1,129 @@
+/*
+ * MCS lock defines
+ *
+ * This file contains the main data structure and API definitions of MCS lock.
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bouncings that common test-and-set spin-lock
+ * implementations incur.
+ */
+#ifndef __LINUX_MCS_SPINLOCK_H
+#define __LINUX_MCS_SPINLOCK_H
+
+#include <asm/mcs_spinlock.h>
+
+struct mcs_spinlock {
+ struct mcs_spinlock *next;
+ int locked; /* 1 if lock acquired */
+};
+
+#ifndef arch_mcs_spin_lock_contended
+/*
+ * Using smp_load_acquire() provides a memory barrier that ensures
+ * subsequent operations happen after the lock is acquired.
+ */
+#define arch_mcs_spin_lock_contended(l) \
+do { \
+ while (!(smp_load_acquire(l))) \
+ arch_mutex_cpu_relax(); \
+} while (0)
+#endif
+
+#ifndef arch_mcs_spin_unlock_contended
+/*
+ * smp_store_release() provides a memory barrier to ensure all
+ * operations in the critical section has been completed before
+ * unlocking.
+ */
+#define arch_mcs_spin_unlock_contended(l) \
+ smp_store_release((l), 1)
+#endif
+
+/*
+ * Note: the smp_load_acquire/smp_store_release pair is not
+ * sufficient to form a full memory barrier across
+ * cpus for many architectures (except x86) for mcs_unlock and mcs_lock.
+ * For applications that need a full barrier across multiple cpus
+ * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be
+ * used after mcs_lock.
+ */
+
+/*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
+ *
+ * We don't inline mcs_spin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+static inline
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+ struct mcs_spinlock *prev;
+
+ /* Init node */
+ node->locked = 0;
+ node->next = NULL;
+
+ prev = xchg(lock, node);
+ if (likely(prev == NULL)) {
+ /*
+ * Lock acquired, don't need to set node->locked to 1. Threads
+ * only spin on its own node->locked value for lock acquisition.
+ * However, since this thread can immediately acquire the lock
+ * and does not proceed to spin on its own node->locked, this
+ * value won't be used. If a debug mode is needed to
+ * audit lock status, then set node->locked value here.
+ */
+ return;
+ }
+ ACCESS_ONCE(prev->next) = node;
+
+ /* Wait until the lock holder passes the lock down. */
+ arch_mcs_spin_lock_contended(&node->locked);
+}
+
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
+static inline
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+ struct mcs_spinlock *next = ACCESS_ONCE(node->next);
+
+ if (likely(!next)) {
+ /*
+ * Release the lock by setting it to NULL
+ */
+ if (likely(cmpxchg(lock, node, NULL) == node))
+ return;
+ /* Wait until the next pointer is set */
+ while (!(next = ACCESS_ONCE(node->next)))
+ arch_mutex_cpu_relax();
+ }
+
+ /* Pass lock to next waiter. */
+ arch_mcs_spin_unlock_contended(&next->locked);
+}
+
+/*
+ * Cancellable version of the MCS lock above.
+ *
+ * Intended for adaptive spinning of sleeping locks:
+ * mutex_lock()/rwsem_down_{read,write}() etc.
+ */
+
+struct optimistic_spin_queue {
+ struct optimistic_spin_queue *next, *prev;
+ int locked; /* 1 if lock acquired */
+};
+
+extern bool osq_lock(struct optimistic_spin_queue **lock);
+extern void osq_unlock(struct optimistic_spin_queue **lock);
+
+#endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443fe1f48..e1191c996c59 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,9 +75,20 @@ void debug_mutex_unlock(struct mutex *lock)
return;
DEBUG_LOCKS_WARN_ON(lock->magic != lock);
- DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+ if (!lock->owner)
+ DEBUG_LOCKS_WARN_ON(!lock->owner);
+ else
+ DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
mutex_clear_owner(lock);
+
+ /*
+ * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
+ * mutexes so that we can do it here after we've verified state.
+ */
+ atomic_set(&lock->count, 1);
}
void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 4dd6e4c219de..bc73d33c6760 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -25,6 +25,7 @@
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
+#include "mcs_spinlock.h"
/*
* In the DEBUG case we are using the "NULL fastpath" for mutexes,
@@ -33,6 +34,13 @@
#ifdef CONFIG_DEBUG_MUTEXES
# include "mutex-debug.h"
# include <asm-generic/mutex-null.h>
+/*
+ * Must be 0 for the debug case so we do not do the unlock outside of the
+ * wait_lock region. debug_mutex_unlock() will do the actual unlock in this
+ * case.
+ */
+# undef __mutex_slowpath_needs_to_unlock
+# define __mutex_slowpath_needs_to_unlock() 0
#else
# include "mutex.h"
# include <asm/mutex.h>
@@ -52,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
INIT_LIST_HEAD(&lock->wait_list);
mutex_clear_owner(lock);
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
- lock->spin_mlock = NULL;
+ lock->osq = NULL;
#endif
debug_mutex_init(lock, name, key);
@@ -67,8 +75,7 @@ EXPORT_SYMBOL(__mutex_init);
* We also put the fastpath first in the kernel image, to make sure the
* branch is predicted by the CPU as default-untaken.
*/
-static __used noinline void __sched
-__mutex_lock_slowpath(atomic_t *lock_count);
+__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
/**
* mutex_lock - acquire the mutex
@@ -111,54 +118,7 @@ EXPORT_SYMBOL(mutex_lock);
* more or less simultaneously, the spinners need to acquire a MCS lock
* first before spinning on the owner field.
*
- * We don't inline mspin_lock() so that perf can correctly account for the
- * time spent in this lock function.
*/
-struct mspin_node {
- struct mspin_node *next ;
- int locked; /* 1 if lock acquired */
-};
-#define MLOCK(mutex) ((struct mspin_node **)&((mutex)->spin_mlock))
-
-static noinline
-void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
-{
- struct mspin_node *prev;
-
- /* Init node */
- node->locked = 0;
- node->next = NULL;
-
- prev = xchg(lock, node);
- if (likely(prev == NULL)) {
- /* Lock acquired */
- node->locked = 1;
- return;
- }
- ACCESS_ONCE(prev->next) = node;
- smp_wmb();
- /* Wait until the lock holder passes the lock down */
- while (!ACCESS_ONCE(node->locked))
- arch_mutex_cpu_relax();
-}
-
-static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
-{
- struct mspin_node *next = ACCESS_ONCE(node->next);
-
- if (likely(!next)) {
- /*
- * Release the lock by setting it to NULL
- */
- if (cmpxchg(lock, node, NULL) == node)
- return;
- /* Wait until the next pointer is set */
- while (!(next = ACCESS_ONCE(node->next)))
- arch_mutex_cpu_relax();
- }
- ACCESS_ONCE(next->locked) = 1;
- smp_wmb();
-}
/*
* Mutex spinning code migrated from kernel/sched/core.c
@@ -212,6 +172,9 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
struct task_struct *owner;
int retval = 1;
+ if (need_resched())
+ return 0;
+
rcu_read_lock();
owner = ACCESS_ONCE(lock->owner);
if (owner)
@@ -225,7 +188,8 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
}
#endif
-static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+__visible __used noinline
+void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
/**
* mutex_unlock - release the mutex
@@ -446,9 +410,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
if (!mutex_can_spin_on_owner(lock))
goto slowpath;
+ if (!osq_lock(&lock->osq))
+ goto slowpath;
+
for (;;) {
struct task_struct *owner;
- struct mspin_node node;
if (use_ww_ctx && ww_ctx->acquired > 0) {
struct ww_mutex *ww;
@@ -463,19 +429,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* performed the optimistic spinning cannot be done.
*/
if (ACCESS_ONCE(ww->ctx))
- goto slowpath;
+ break;
}
/*
* If there's an owner, wait for it to either
* release the lock or go to sleep.
*/
- mspin_lock(MLOCK(lock), &node);
owner = ACCESS_ONCE(lock->owner);
- if (owner && !mutex_spin_on_owner(lock, owner)) {
- mspin_unlock(MLOCK(lock), &node);
- goto slowpath;
- }
+ if (owner && !mutex_spin_on_owner(lock, owner))
+ break;
if ((atomic_read(&lock->count) == 1) &&
(atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
@@ -488,11 +451,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
}
mutex_set_owner(lock);
- mspin_unlock(MLOCK(lock), &node);
+ osq_unlock(&lock->osq);
preempt_enable();
return 0;
}
- mspin_unlock(MLOCK(lock), &node);
/*
* When there's no owner, we might have preempted between the
@@ -501,7 +463,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* the owner complete.
*/
if (!owner && (need_resched() || rt_task(task)))
- goto slowpath;
+ break;
/*
* The cpu_relax() call is a compiler barrier which forces
@@ -511,7 +473,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
*/
arch_mutex_cpu_relax();
}
+ osq_unlock(&lock->osq);
slowpath:
+ /*
+ * If we fell out of the spin path because of need_resched(),
+ * reschedule now, before we try-lock the mutex. This avoids getting
+ * scheduled out right after we obtained the mutex.
+ */
+ if (need_resched())
+ schedule_preempt_disabled();
#endif
spin_lock_mutex(&lock->wait_lock, flags);
@@ -717,10 +687,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
struct mutex *lock = container_of(lock_count, struct mutex, count);
unsigned long flags;
- spin_lock_mutex(&lock->wait_lock, flags);
- mutex_release(&lock->dep_map, nested, _RET_IP_);
- debug_mutex_unlock(lock);
-
/*
* some architectures leave the lock unlocked in the fastpath failure
* case, others need to leave it locked. In the later case we have to
@@ -729,6 +695,10 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
if (__mutex_slowpath_needs_to_unlock())
atomic_set(&lock->count, 1);
+ spin_lock_mutex(&lock->wait_lock, flags);
+ mutex_release(&lock->dep_map, nested, _RET_IP_);
+ debug_mutex_unlock(lock);
+
if (!list_empty(&lock->wait_list)) {
/* get the first entry from the wait-list: */
struct mutex_waiter *waiter =
@@ -746,7 +716,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
/*
* Release the lock, slowpath:
*/
-static __used noinline void
+__visible void
__mutex_unlock_slowpath(atomic_t *lock_count)
{
__mutex_unlock_common_slowpath(lock_count, 1);
@@ -803,7 +773,7 @@ int __sched mutex_lock_killable(struct mutex *lock)
}
EXPORT_SYMBOL(mutex_lock_killable);
-static __used noinline void __sched
+__visible void __sched
__mutex_lock_slowpath(atomic_t *lock_count)
{
struct mutex *lock = container_of(lock_count, struct mutex, count);
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a323fa..49b2ed3dced8 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -24,7 +24,7 @@
#include <linux/kallsyms.h>
#include <linux/syscalls.h>
#include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
#include <linux/fs.h>
#include <linux/debug_locks.h>
@@ -57,7 +57,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
void rt_mutex_debug_task_free(struct task_struct *task)
{
- DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+ DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
}
@@ -154,16 +154,12 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
{
memset(waiter, 0x11, sizeof(*waiter));
- plist_node_init(&waiter->list_entry, MAX_PRIO);
- plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
waiter->deadlock_task_pid = NULL;
}
void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
{
put_pid(waiter->deadlock_task_pid);
- DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
- DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
memset(waiter, 0x22, sizeof(*waiter));
}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec1cb6a..aa4dff04b594 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include "rtmutex_common.h"
@@ -91,10 +92,107 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
}
#endif
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+ struct rt_mutex_waiter *right)
+{
+ if (left->prio < right->prio)
+ return 1;
+
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+ * If left waiter has a dl_prio(), and we didn't return 1 above,
+ * then right waiter has a dl_prio() too.
+ */
+ if (dl_prio(left->prio))
+ return (left->task->dl.deadline < right->task->dl.deadline);
+
+ return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+ struct rb_node **link = &lock->waiters.rb_node;
+ struct rb_node *parent = NULL;
+ struct rt_mutex_waiter *entry;
+ int leftmost = 1;
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+ if (rt_mutex_waiter_less(waiter, entry)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ lock->waiters_leftmost = &waiter->tree_entry;
+
+ rb_link_node(&waiter->tree_entry, parent, link);
+ rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+ if (RB_EMPTY_NODE(&waiter->tree_entry))
+ return;
+
+ if (lock->waiters_leftmost == &waiter->tree_entry)
+ lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+ rb_erase(&waiter->tree_entry, &lock->waiters);
+ RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+ struct rb_node **link = &task->pi_waiters.rb_node;
+ struct rb_node *parent = NULL;
+ struct rt_mutex_waiter *entry;
+ int leftmost = 1;
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+ if (rt_mutex_waiter_less(waiter, entry)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+ rb_link_node(&waiter->pi_tree_entry, parent, link);
+ rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+ if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+ return;
+
+ if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+ task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+ rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+ RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
/*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
*
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
* the waiter is not allowed to do priority boosting
*/
int rt_mutex_getprio(struct task_struct *task)
@@ -102,10 +200,30 @@ int rt_mutex_getprio(struct task_struct *task)
if (likely(!task_has_pi_waiters(task)))
return task->normal_prio;
- return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+ return min(task_top_pi_waiter(task)->prio,
task->normal_prio);
}
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+ if (likely(!task_has_pi_waiters(task)))
+ return NULL;
+
+ return task_top_pi_waiter(task)->task;
+}
+
+/*
+ * Called by sched_setscheduler() to check whether the priority change
+ * is overruled by a possible priority boosting.
+ */
+int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+ if (!task_has_pi_waiters(task))
+ return 0;
+
+ return task_top_pi_waiter(task)->task->prio <= newprio;
+}
+
/*
* Adjust the priority of a task, after its pi_waiters got modified.
*
@@ -115,7 +233,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
{
int prio = rt_mutex_getprio(task);
- if (task->prio != prio)
+ if (task->prio != prio || dl_prio(prio))
rt_mutex_setprio(task, prio);
}
@@ -233,7 +351,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
* When deadlock detection is off then we check, if further
* priority adjustment is necessary.
*/
- if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+ if (!detect_deadlock && waiter->prio == task->prio)
goto out_unlock_pi;
lock = waiter->lock;
@@ -254,9 +372,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
top_waiter = rt_mutex_top_waiter(lock);
/* Requeue the waiter */
- plist_del(&waiter->list_entry, &lock->wait_list);
- waiter->list_entry.prio = task->prio;
- plist_add(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
+ waiter->prio = task->prio;
+ rt_mutex_enqueue(lock, waiter);
/* Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +398,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
if (waiter == rt_mutex_top_waiter(lock)) {
/* Boost the owner */
- plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
- waiter->pi_list_entry.prio = waiter->list_entry.prio;
- plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_dequeue_pi(task, top_waiter);
+ rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
} else if (top_waiter == waiter) {
/* Deboost the owner */
- plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
- waiter->pi_list_entry.prio = waiter->list_entry.prio;
- plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
}
@@ -355,7 +471,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
* 3) it is top waiter
*/
if (rt_mutex_has_waiters(lock)) {
- if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+ if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
if (!waiter || waiter != rt_mutex_top_waiter(lock))
return 0;
}
@@ -369,7 +485,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
/* remove the queued waiter. */
if (waiter) {
- plist_del(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
task->pi_blocked_on = NULL;
}
@@ -379,8 +495,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
*/
if (rt_mutex_has_waiters(lock)) {
top = rt_mutex_top_waiter(lock);
- top->pi_list_entry.prio = top->list_entry.prio;
- plist_add(&top->pi_list_entry, &task->pi_waiters);
+ rt_mutex_enqueue_pi(task, top);
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
@@ -416,13 +531,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
- plist_node_init(&waiter->list_entry, task->prio);
- plist_node_init(&waiter->pi_list_entry, task->prio);
+ waiter->prio = task->prio;
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
top_waiter = rt_mutex_top_waiter(lock);
- plist_add(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_enqueue(lock, waiter);
task->pi_blocked_on = waiter;
@@ -433,8 +547,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
- plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
- plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_dequeue_pi(owner, top_waiter);
+ rt_mutex_enqueue_pi(owner, waiter);
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
@@ -486,7 +600,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
* boosted mode and go back to normal after releasing
* lock->wait_lock.
*/
- plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+ rt_mutex_dequeue_pi(current, waiter);
rt_mutex_set_owner(lock, NULL);
@@ -510,7 +624,7 @@ static void remove_waiter(struct rt_mutex *lock,
int chain_walk = 0;
raw_spin_lock_irqsave(&current->pi_lock, flags);
- plist_del(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
current->pi_blocked_on = NULL;
raw_spin_unlock_irqrestore(&current->pi_lock, flags);
@@ -521,13 +635,13 @@ static void remove_waiter(struct rt_mutex *lock,
raw_spin_lock_irqsave(&owner->pi_lock, flags);
- plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_dequeue_pi(owner, waiter);
if (rt_mutex_has_waiters(lock)) {
struct rt_mutex_waiter *next;
next = rt_mutex_top_waiter(lock);
- plist_add(&next->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_enqueue_pi(owner, next);
}
__rt_mutex_adjust_prio(owner);
@@ -537,8 +651,6 @@ static void remove_waiter(struct rt_mutex *lock,
raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
- WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
if (!chain_walk)
return;
@@ -565,7 +677,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
- if (!waiter || waiter->list_entry.prio == task->prio) {
+ if (!waiter || (waiter->prio == task->prio &&
+ !dl_prio(task->prio))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
@@ -638,6 +751,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
int ret = 0;
debug_rt_mutex_init_waiter(&waiter);
+ RB_CLEAR_NODE(&waiter.pi_tree_entry);
+ RB_CLEAR_NODE(&waiter.tree_entry);
raw_spin_lock(&lock->wait_lock);
@@ -904,7 +1019,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
{
lock->owner = NULL;
raw_spin_lock_init(&lock->wait_lock);
- plist_head_init(&lock->wait_list);
+ lock->waiters = RB_ROOT;
+ lock->waiters_leftmost = NULL;
debug_rt_mutex_init(lock, name);
}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c85261b..7431a9c86f35 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
* This is the control structure for tasks blocked on a rt_mutex,
* which is allocated on the kernel stack on of the blocked task.
*
- * @list_entry: pi node to enqueue into the mutex waiters list
- * @pi_list_entry: pi node to enqueue into the mutex owner waiters list
+ * @tree_entry: pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree
* @task: task reference to the blocked task
*/
struct rt_mutex_waiter {
- struct plist_node list_entry;
- struct plist_node pi_list_entry;
+ struct rb_node tree_entry;
+ struct rb_node pi_tree_entry;
struct task_struct *task;
struct rt_mutex *lock;
#ifdef CONFIG_DEBUG_RT_MUTEXES
@@ -54,14 +54,15 @@ struct rt_mutex_waiter {
struct pid *deadlock_task_pid;
struct rt_mutex *deadlock_lock;
#endif
+ int prio;
};
/*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
*/
static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
{
- return !plist_head_empty(&lock->wait_list);
+ return !RB_EMPTY_ROOT(&lock->waiters);
}
static inline struct rt_mutex_waiter *
@@ -69,8 +70,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
{
struct rt_mutex_waiter *w;
- w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
- list_entry);
+ w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+ tree_entry);
BUG_ON(w->lock != lock);
return w;
@@ -78,14 +79,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
static inline int task_has_pi_waiters(struct task_struct *p)
{
- return !plist_head_empty(&p->pi_waiters);
+ return !RB_EMPTY_ROOT(&p->pi_waiters);
}
static inline struct rt_mutex_waiter *
task_top_pi_waiter(struct task_struct *p)
{
- return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
- pi_list_entry);
+ return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+ pi_tree_entry);
}
/*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 19c5fa95e0b4..1d66e08e897d 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -143,6 +143,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
/*
* wait for the read lock to be granted
*/
+__visible
struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
{
long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
@@ -190,6 +191,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
/*
* wait until we successfully acquire the write lock
*/
+__visible
struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
{
long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
@@ -252,6 +254,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
* handle waking up a waiter on the semaphore
* - up_read/up_write has decremented the active part of count if we come here
*/
+__visible
struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
unsigned long flags;
@@ -272,6 +275,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
* - caller incremented waiting part of count and discovered it still negative
* - just wake up any readers at the front of the queue
*/
+__visible
struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
unsigned long flags;
diff --git a/kernel/module.c b/kernel/module.c
index f5a3b1e8ec51..11869408f79b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -640,7 +640,7 @@ static int module_unload_init(struct module *mod)
INIT_LIST_HEAD(&mod->target_list);
/* Hold reference count during initialization. */
- __this_cpu_write(mod->refptr->incs, 1);
+ raw_cpu_write(mod->refptr->incs, 1);
return 0;
}
@@ -815,10 +815,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
return -EFAULT;
name[MODULE_NAME_LEN-1] = '\0';
- if (!(flags & O_NONBLOCK)) {
- printk(KERN_WARNING
- "waiting module removal not supported: please upgrade");
- }
+ if (!(flags & O_NONBLOCK))
+ pr_warn("waiting module removal not supported: please upgrade\n");
if (mutex_lock_interruptible(&module_mutex) != 0)
return -EINTR;
@@ -1015,9 +1013,11 @@ static size_t module_flags_taint(struct module *mod, char *buf)
buf[l++] = 'F';
if (mod->taints & (1 << TAINT_CRAP))
buf[l++] = 'C';
+ if (mod->taints & (1 << TAINT_UNSIGNED_MODULE))
+ buf[l++] = 'E';
/*
* TAINT_FORCED_RMMOD: could be added.
- * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
+ * TAINT_CPU_OUT_OF_SPEC, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
* apply to modules.
*/
return l;
@@ -1950,6 +1950,10 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
switch (sym[i].st_shndx) {
case SHN_COMMON:
+ /* Ignore common symbols */
+ if (!strncmp(name, "__gnu_lto", 9))
+ break;
+
/* We compiled with -fno-common. These are not
supposed to happen. */
pr_debug("Common symbol: %s\n", name);
@@ -3216,7 +3220,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
pr_notice_once("%s: module verification failed: signature "
"and/or required key missing - tainting "
"kernel\n", mod->name);
- add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_STILL_OK);
+ add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK);
}
#endif
@@ -3811,12 +3815,12 @@ void print_modules(void)
list_for_each_entry_rcu(mod, &modules, list) {
if (mod->state == MODULE_STATE_UNFORMED)
continue;
- printk(" %s%s", mod->name, module_flags(mod, buf));
+ pr_cont(" %s%s", mod->name, module_flags(mod, buf));
}
preempt_enable();
if (last_unloaded_module[0])
- printk(" [last unloaded: %s]", last_unloaded_module);
- printk("\n");
+ pr_cont(" [last unloaded: %s]", last_unloaded_module);
+ pr_cont("\n");
}
#ifdef CONFIG_MODVERSIONS
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 2d5cc4ccff7f..db4c8b08a50c 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -309,7 +309,7 @@ int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
* racy then it does not matter what the result of the test
* is, we re-check the list after having taken the lock anyway:
*/
- if (rcu_dereference_raw(nh->head)) {
+ if (rcu_access_pointer(nh->head)) {
down_read(&nh->rwsem);
ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
nr_calls);
diff --git a/kernel/padata.c b/kernel/padata.c
index 2abd25d79cc8..161402f0b517 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -112,7 +112,7 @@ int padata_do_parallel(struct padata_instance *pinst,
rcu_read_lock_bh();
- pd = rcu_dereference(pinst->pd);
+ pd = rcu_dereference_bh(pinst->pd);
err = -EINVAL;
if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID)
diff --git a/kernel/panic.c b/kernel/panic.c
index c00b4ceb39e8..d02fa9fef46a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,7 +33,7 @@ static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
-int panic_timeout;
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
@@ -100,7 +100,7 @@ void panic(const char *fmt, ...)
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
- printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+ pr_emerg("Kernel panic - not syncing: %s\n", buf);
#ifdef CONFIG_DEBUG_BUGVERBOSE
/*
* Avoid nested stack-dumping if a panic occurs during oops processing
@@ -141,7 +141,7 @@ void panic(const char *fmt, ...)
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
- printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
+ pr_emerg("Rebooting in %d seconds..", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
@@ -165,7 +165,7 @@ void panic(const char *fmt, ...)
extern int stop_a_enabled;
/* Make sure the user can actually press Stop-A (L1-A) */
stop_a_enabled = 1;
- printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
+ pr_emerg("Press Stop-A (L1-A) to return to the boot prom\n");
}
#endif
#if defined(CONFIG_S390)
@@ -176,6 +176,7 @@ void panic(const char *fmt, ...)
disabled_wait(caller);
}
#endif
+ pr_emerg("---[ end Kernel panic - not syncing: %s\n", buf);
local_irq_enable();
for (i = 0; ; i += PANIC_TIMER_STEP) {
touch_softlockup_watchdog();
@@ -199,7 +200,7 @@ struct tnt {
static const struct tnt tnts[] = {
{ TAINT_PROPRIETARY_MODULE, 'P', 'G' },
{ TAINT_FORCED_MODULE, 'F', ' ' },
- { TAINT_UNSAFE_SMP, 'S', ' ' },
+ { TAINT_CPU_OUT_OF_SPEC, 'S', ' ' },
{ TAINT_FORCED_RMMOD, 'R', ' ' },
{ TAINT_MACHINE_CHECK, 'M', ' ' },
{ TAINT_BAD_PAGE, 'B', ' ' },
@@ -210,6 +211,7 @@ static const struct tnt tnts[] = {
{ TAINT_CRAP, 'C', ' ' },
{ TAINT_FIRMWARE_WORKAROUND, 'I', ' ' },
{ TAINT_OOT_MODULE, 'O', ' ' },
+ { TAINT_UNSIGNED_MODULE, 'E', ' ' },
};
/**
@@ -228,6 +230,7 @@ static const struct tnt tnts[] = {
* 'C' - modules from drivers/staging are loaded.
* 'I' - Working around severe firmware bug.
* 'O' - Out-of-tree module has been loaded.
+ * 'E' - Unsigned module has been loaded.
*
* The string is overwritten by the next call to print_tainted().
*/
@@ -274,8 +277,7 @@ unsigned long get_taint(void)
void add_taint(unsigned flag, enum lockdep_ok lockdep_ok)
{
if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off())
- printk(KERN_WARNING
- "Disabling lock debugging due to kernel taint\n");
+ pr_warn("Disabling lock debugging due to kernel taint\n");
set_bit(flag, &tainted_mask);
}
@@ -380,8 +382,7 @@ late_initcall(init_oops_id);
void print_oops_end_marker(void)
{
init_oops_id();
- printk(KERN_WARNING "---[ end trace %016llx ]---\n",
- (unsigned long long)oops_id);
+ pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
}
/*
@@ -459,7 +460,7 @@ EXPORT_SYMBOL(warn_slowpath_null);
* Called when gcc's -fstack-protector feature is used, and
* gcc detects corruption of the on-stack canary value
*/
-void __stack_chk_fail(void)
+__visible void __stack_chk_fail(void)
{
panic("stack-protector: Kernel stack is corrupted in: %p\n",
__builtin_return_address(0));
diff --git a/kernel/params.c b/kernel/params.c
index c00d5b502aa4..b00142e7f3ba 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -227,17 +227,10 @@ int parse_args(const char *doing,
}
/* Lazy bastard, eh? */
-#define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn) \
+#define STANDARD_PARAM_DEF(name, type, format, strtolfn) \
int param_set_##name(const char *val, const struct kernel_param *kp) \
{ \
- tmptype l; \
- int ret; \
- \
- ret = strtolfn(val, 0, &l); \
- if (ret < 0 || ((type)l != l)) \
- return ret < 0 ? ret : -EINVAL; \
- *((type *)kp->arg) = l; \
- return 0; \
+ return strtolfn(val, 0, (type *)kp->arg); \
} \
int param_get_##name(char *buffer, const struct kernel_param *kp) \
{ \
@@ -253,13 +246,13 @@ int parse_args(const char *doing,
EXPORT_SYMBOL(param_ops_##name)
-STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
-STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
-STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
-STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
+STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8);
+STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16);
+STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16);
+STANDARD_PARAM_DEF(int, int, "%i", kstrtoint);
+STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint);
+STANDARD_PARAM_DEF(long, long, "%li", kstrtol);
+STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul);
int param_set_charp(const char *val, const struct kernel_param *kp)
{
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 06c62de9c711..db95d8eb761b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -318,7 +318,9 @@ static void *pidns_get(struct task_struct *task)
struct pid_namespace *ns;
rcu_read_lock();
- ns = get_pid_ns(task_active_pid_ns(task));
+ ns = task_active_pid_ns(task);
+ if (ns)
+ get_pid_ns(ns);
rcu_read_unlock();
return ns;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c7f31aa272f7..3b8946416a5f 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -233,7 +233,8 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
/*
* Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
*/
static int cpu_clock_sample_group(const clockid_t which_clock,
struct task_struct *p,
@@ -260,30 +261,53 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
return 0;
}
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+ const clockid_t which_clock,
+ struct timespec *tp)
+{
+ int err = -EINVAL;
+ unsigned long long rtn;
+
+ if (CPUCLOCK_PERTHREAD(which_clock)) {
+ if (same_thread_group(tsk, current))
+ err = cpu_clock_sample(which_clock, tsk, &rtn);
+ } else {
+ unsigned long flags;
+ struct sighand_struct *sighand;
+
+ /*
+ * while_each_thread() is not yet entirely RCU safe,
+ * keep locking the group while sampling process
+ * clock for now.
+ */
+ sighand = lock_task_sighand(tsk, &flags);
+ if (!sighand)
+ return err;
+
+ if (tsk == current || thread_group_leader(tsk))
+ err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+ unlock_task_sighand(tsk, &flags);
+ }
+
+ if (!err)
+ sample_to_timespec(which_clock, rtn, tp);
+
+ return err;
+}
+
static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
{
const pid_t pid = CPUCLOCK_PID(which_clock);
- int error = -EINVAL;
- unsigned long long rtn;
+ int err = -EINVAL;
if (pid == 0) {
/*
* Special case constant value for our own clocks.
* We don't have to do any lookup to find ourselves.
*/
- if (CPUCLOCK_PERTHREAD(which_clock)) {
- /*
- * Sampling just ourselves we can do with no locking.
- */
- error = cpu_clock_sample(which_clock,
- current, &rtn);
- } else {
- read_lock(&tasklist_lock);
- error = cpu_clock_sample_group(which_clock,
- current, &rtn);
- read_unlock(&tasklist_lock);
- }
+ err = posix_cpu_clock_get_task(current, which_clock, tp);
} else {
/*
* Find the given PID, and validate that the caller
@@ -292,29 +316,12 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
struct task_struct *p;
rcu_read_lock();
p = find_task_by_vpid(pid);
- if (p) {
- if (CPUCLOCK_PERTHREAD(which_clock)) {
- if (same_thread_group(p, current)) {
- error = cpu_clock_sample(which_clock,
- p, &rtn);
- }
- } else {
- read_lock(&tasklist_lock);
- if (thread_group_leader(p) && p->sighand) {
- error =
- cpu_clock_sample_group(which_clock,
- p, &rtn);
- }
- read_unlock(&tasklist_lock);
- }
- }
+ if (p)
+ err = posix_cpu_clock_get_task(p, which_clock, tp);
rcu_read_unlock();
}
- if (error)
- return error;
- sample_to_timespec(which_clock, rtn, tp);
- return 0;
+ return err;
}
@@ -371,36 +378,40 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
*/
static int posix_cpu_timer_del(struct k_itimer *timer)
{
- struct task_struct *p = timer->it.cpu.task;
int ret = 0;
+ unsigned long flags;
+ struct sighand_struct *sighand;
+ struct task_struct *p = timer->it.cpu.task;
- if (likely(p != NULL)) {
- read_lock(&tasklist_lock);
- if (unlikely(p->sighand == NULL)) {
- /*
- * We raced with the reaping of the task.
- * The deletion should have cleared us off the list.
- */
- BUG_ON(!list_empty(&timer->it.cpu.entry));
- } else {
- spin_lock(&p->sighand->siglock);
- if (timer->it.cpu.firing)
- ret = TIMER_RETRY;
- else
- list_del(&timer->it.cpu.entry);
- spin_unlock(&p->sighand->siglock);
- }
- read_unlock(&tasklist_lock);
+ WARN_ON_ONCE(p == NULL);
- if (!ret)
- put_task_struct(p);
+ /*
+ * Protect against sighand release/switch in exit/exec and process/
+ * thread timer list entry concurrent read/writes.
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
+ /*
+ * We raced with the reaping of the task.
+ * The deletion should have cleared us off the list.
+ */
+ WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
+ } else {
+ if (timer->it.cpu.firing)
+ ret = TIMER_RETRY;
+ else
+ list_del(&timer->it.cpu.entry);
+
+ unlock_task_sighand(p, &flags);
}
+ if (!ret)
+ put_task_struct(p);
+
return ret;
}
-static void cleanup_timers_list(struct list_head *head,
- unsigned long long curr)
+static void cleanup_timers_list(struct list_head *head)
{
struct cpu_timer_list *timer, *next;
@@ -414,16 +425,11 @@ static void cleanup_timers_list(struct list_head *head,
* time for later timer_gettime calls to return.
* This must be called with the siglock held.
*/
-static void cleanup_timers(struct list_head *head,
- cputime_t utime, cputime_t stime,
- unsigned long long sum_exec_runtime)
+static void cleanup_timers(struct list_head *head)
{
-
- cputime_t ptime = utime + stime;
-
- cleanup_timers_list(head, cputime_to_expires(ptime));
- cleanup_timers_list(++head, cputime_to_expires(utime));
- cleanup_timers_list(++head, sum_exec_runtime);
+ cleanup_timers_list(head);
+ cleanup_timers_list(++head);
+ cleanup_timers_list(++head);
}
/*
@@ -433,41 +439,14 @@ static void cleanup_timers(struct list_head *head,
*/
void posix_cpu_timers_exit(struct task_struct *tsk)
{
- cputime_t utime, stime;
-
add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
sizeof(unsigned long long));
- task_cputime(tsk, &utime, &stime);
- cleanup_timers(tsk->cpu_timers,
- utime, stime, tsk->se.sum_exec_runtime);
+ cleanup_timers(tsk->cpu_timers);
}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
- struct signal_struct *const sig = tsk->signal;
- cputime_t utime, stime;
-
- task_cputime(tsk, &utime, &stime);
- cleanup_timers(tsk->signal->cpu_timers,
- utime + sig->utime, stime + sig->stime,
- tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
-}
-
-static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
-{
- struct cpu_timer_list *timer = &itimer->it.cpu;
-
- /*
- * That's all for this thread or process.
- * We leave our residual in expires to be reported.
- */
- put_task_struct(timer->task);
- timer->task = NULL;
- if (timer->expires < now) {
- timer->expires = 0;
- } else {
- timer->expires -= now;
- }
+ cleanup_timers(tsk->signal->cpu_timers);
}
static inline int expires_gt(cputime_t expires, cputime_t new_exp)
@@ -477,8 +456,7 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
/*
* Insert the timer on the appropriate list before any timers that
- * expire later. This must be called with the tasklist_lock held
- * for reading, interrupts disabled and p->sighand->siglock taken.
+ * expire later. This must be called with the sighand lock held.
*/
static void arm_timer(struct k_itimer *timer)
{
@@ -569,7 +547,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
/*
* Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
*/
static int cpu_timer_sample_group(const clockid_t which_clock,
struct task_struct *p,
@@ -608,7 +587,8 @@ static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
*/
static void posix_cpu_timer_kick_nohz(void)
{
- schedule_work(&nohz_kick_work);
+ if (context_tracking_is_enabled())
+ schedule_work(&nohz_kick_work);
}
bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
@@ -631,43 +611,39 @@ static inline void posix_cpu_timer_kick_nohz(void) { }
* If we return TIMER_RETRY, it's necessary to release the timer's lock
* and try again. (This happens when the timer is in the middle of firing.)
*/
-static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
struct itimerspec *new, struct itimerspec *old)
{
+ unsigned long flags;
+ struct sighand_struct *sighand;
struct task_struct *p = timer->it.cpu.task;
unsigned long long old_expires, new_expires, old_incr, val;
int ret;
- if (unlikely(p == NULL)) {
- /*
- * Timer refers to a dead task's clock.
- */
- return -ESRCH;
- }
+ WARN_ON_ONCE(p == NULL);
new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
- read_lock(&tasklist_lock);
/*
- * We need the tasklist_lock to protect against reaping that
- * clears p->sighand. If p has just been reaped, we can no
+ * Protect against sighand release/switch in exit/exec and p->cpu_timers
+ * and p->signal->cpu_timers read/write in arm_timer()
+ */
+ sighand = lock_task_sighand(p, &flags);
+ /*
+ * If p has just been reaped, we can no
* longer get any information about it at all.
*/
- if (unlikely(p->sighand == NULL)) {
- read_unlock(&tasklist_lock);
- put_task_struct(p);
- timer->it.cpu.task = NULL;
+ if (unlikely(sighand == NULL)) {
return -ESRCH;
}
/*
* Disarm any old timer after extracting its expiry time.
*/
- BUG_ON(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
ret = 0;
old_incr = timer->it.cpu.incr;
- spin_lock(&p->sighand->siglock);
old_expires = timer->it.cpu.expires;
if (unlikely(timer->it.cpu.firing)) {
timer->it.cpu.firing = -1;
@@ -724,12 +700,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
* disable this firing since we are already reporting
* it as an overrun (thanks to bump_cpu_timer above).
*/
- spin_unlock(&p->sighand->siglock);
- read_unlock(&tasklist_lock);
+ unlock_task_sighand(p, &flags);
goto out;
}
- if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+ if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
new_expires += val;
}
@@ -743,9 +718,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
arm_timer(timer);
}
- spin_unlock(&p->sighand->siglock);
- read_unlock(&tasklist_lock);
-
+ unlock_task_sighand(p, &flags);
/*
* Install the new reload setting, and
* set up the signal and overrun bookkeeping.
@@ -787,7 +760,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
unsigned long long now;
struct task_struct *p = timer->it.cpu.task;
- int clear_dead;
+
+ WARN_ON_ONCE(p == NULL);
/*
* Easy part: convert the reload time.
@@ -800,52 +774,34 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
return;
}
- if (unlikely(p == NULL)) {
- /*
- * This task already died and the timer will never fire.
- * In this case, expires is actually the dead value.
- */
- dead:
- sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
- &itp->it_value);
- return;
- }
-
/*
* Sample the clock to take the difference with the expiry time.
*/
if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
cpu_clock_sample(timer->it_clock, p, &now);
- clear_dead = p->exit_state;
} else {
- read_lock(&tasklist_lock);
- if (unlikely(p->sighand == NULL)) {
+ struct sighand_struct *sighand;
+ unsigned long flags;
+
+ /*
+ * Protect against sighand release/switch in exit/exec and
+ * also make timer sampling safe if it ends up calling
+ * thread_group_cputime().
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
/*
* The process has been reaped.
* We can't even collect a sample any more.
* Call the timer disarmed, nothing else to do.
*/
- put_task_struct(p);
- timer->it.cpu.task = NULL;
timer->it.cpu.expires = 0;
- read_unlock(&tasklist_lock);
- goto dead;
+ sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+ &itp->it_value);
} else {
cpu_timer_sample_group(timer->it_clock, p, &now);
- clear_dead = (unlikely(p->exit_state) &&
- thread_group_empty(p));
+ unlock_task_sighand(p, &flags);
}
- read_unlock(&tasklist_lock);
- }
-
- if (unlikely(clear_dead)) {
- /*
- * We've noticed that the thread is dead, but
- * not yet reaped. Take this opportunity to
- * drop our task ref.
- */
- clear_dead_task(timer, now);
- goto dead;
}
if (now < timer->it.cpu.expires) {
@@ -1059,14 +1015,12 @@ static void check_process_timers(struct task_struct *tsk,
*/
void posix_cpu_timer_schedule(struct k_itimer *timer)
{
+ struct sighand_struct *sighand;
+ unsigned long flags;
struct task_struct *p = timer->it.cpu.task;
unsigned long long now;
- if (unlikely(p == NULL))
- /*
- * The task was cleaned up already, no future firings.
- */
- goto out;
+ WARN_ON_ONCE(p == NULL);
/*
* Fetch the current sample and update the timer's expiry time.
@@ -1074,49 +1028,45 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
cpu_clock_sample(timer->it_clock, p, &now);
bump_cpu_timer(timer, now);
- if (unlikely(p->exit_state)) {
- clear_dead_task(timer, now);
+ if (unlikely(p->exit_state))
+ goto out;
+
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (!sighand)
goto out;
- }
- read_lock(&tasklist_lock); /* arm_timer needs it. */
- spin_lock(&p->sighand->siglock);
} else {
- read_lock(&tasklist_lock);
- if (unlikely(p->sighand == NULL)) {
+ /*
+ * Protect arm_timer() and timer sampling in case of call to
+ * thread_group_cputime().
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
/*
* The process has been reaped.
* We can't even collect a sample any more.
*/
- put_task_struct(p);
- timer->it.cpu.task = p = NULL;
timer->it.cpu.expires = 0;
- goto out_unlock;
+ goto out;
} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
- /*
- * We've noticed that the thread is dead, but
- * not yet reaped. Take this opportunity to
- * drop our task ref.
- */
- cpu_timer_sample_group(timer->it_clock, p, &now);
- clear_dead_task(timer, now);
- goto out_unlock;
+ unlock_task_sighand(p, &flags);
+ /* Optimizations: if the process is dying, no need to rearm */
+ goto out;
}
- spin_lock(&p->sighand->siglock);
cpu_timer_sample_group(timer->it_clock, p, &now);
bump_cpu_timer(timer, now);
- /* Leave the tasklist_lock locked for the call below. */
+ /* Leave the sighand locked for the call below. */
}
/*
* Now re-arm for the new expiry time.
*/
- BUG_ON(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
arm_timer(timer);
- spin_unlock(&p->sighand->siglock);
-
-out_unlock:
- read_unlock(&tasklist_lock);
+ unlock_task_sighand(p, &flags);
+ /* Kick full dynticks CPUs in case they need to tick on the new timer */
+ posix_cpu_timer_kick_nohz();
out:
timer->it_overrun_last = timer->it_overrun;
timer->it_overrun = -1;
@@ -1200,7 +1150,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
struct k_itimer *timer, *next;
unsigned long flags;
- BUG_ON(!irqs_disabled());
+ WARN_ON_ONCE(!irqs_disabled());
/*
* The fast path checks that there are no expired thread or thread
@@ -1256,13 +1206,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
cpu_timer_fire(timer);
spin_unlock(&timer->it_lock);
}
-
- /*
- * In case some timers were rescheduled after the queue got emptied,
- * wake up full dynticks CPUs.
- */
- if (tsk->signal->cputimer.running)
- posix_cpu_timer_kick_nohz();
}
/*
@@ -1274,7 +1217,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
{
unsigned long long now;
- BUG_ON(clock_idx == CPUCLOCK_SCHED);
+ WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
cpu_timer_sample_group(clock_idx, tsk, &now);
if (oldval) {
diff --git a/kernel/power/block_io.c b/kernel/power/block_io.c
index d09dd10c5a5e..9a58bc258810 100644
--- a/kernel/power/block_io.c
+++ b/kernel/power/block_io.c
@@ -32,7 +32,7 @@ static int submit(int rw, struct block_device *bdev, sector_t sector,
struct bio *bio;
bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_end_io = end_swap_bio_read;
diff --git a/kernel/power/console.c b/kernel/power/console.c
index eacb8bd8cab4..aba9c545a0e3 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -9,6 +9,7 @@
#include <linux/kbd_kern.h>
#include <linux/vt.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include "power.h"
#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 0121dab83f43..f4f2073711d3 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -82,6 +82,7 @@ void hibernation_set_ops(const struct platform_hibernation_ops *ops)
unlock_system_sleep();
}
+EXPORT_SYMBOL_GPL(hibernation_set_ops);
static bool entering_platform_hibernation;
@@ -293,10 +294,10 @@ static int create_image(int platform_mode)
error);
/* Restore control flow magically appears here */
restore_processor_state();
- if (!in_suspend) {
+ if (!in_suspend)
events_check_enabled = false;
- platform_leave(platform_mode);
- }
+
+ platform_leave(platform_mode);
Power_up:
syscore_resume();
@@ -972,16 +973,20 @@ static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t n)
{
- unsigned int maj, min;
dev_t res;
- int ret = -EINVAL;
+ int len = n;
+ char *name;
- if (sscanf(buf, "%u:%u", &maj, &min) != 2)
- goto out;
+ if (len && buf[len-1] == '\n')
+ len--;
+ name = kstrndup(buf, len, GFP_KERNEL);
+ if (!name)
+ return -ENOMEM;
- res = MKDEV(maj,min);
- if (maj != MAJOR(res) || min != MINOR(res))
- goto out;
+ res = name_to_dev_t(name);
+ kfree(name);
+ if (!res)
+ return -EINVAL;
lock_system_sleep();
swsusp_resume_device = res;
@@ -989,9 +994,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
printk(KERN_INFO "PM: Starting manual resume from disk\n");
noresume = 0;
software_resume();
- ret = n;
- out:
- return ret;
+ return n;
}
power_attr(resume);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 1d1bf630e6e9..6271bc4073ef 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -282,8 +282,8 @@ struct kobject *power_kobj;
* state - control system power state.
*
* show() returns what states are supported, which is hard-coded to
- * 'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and
- * 'disk' (Suspend-to-Disk).
+ * 'freeze' (Low-Power Idle), 'standby' (Power-On Suspend),
+ * 'mem' (Suspend-to-RAM), and 'disk' (Suspend-to-Disk).
*
* store() accepts one of those strings, translates it into the
* proper enumerated value, and initiates a suspend transition.
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7d4b7ffb3c1d..15f37ea08719 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -2,6 +2,7 @@
#include <linux/suspend_ioctls.h>
#include <linux/utsname.h>
#include <linux/freezer.h>
+#include <linux/compiler.h>
struct swsusp_info {
struct new_utsname uts;
@@ -11,7 +12,7 @@ struct swsusp_info {
unsigned long image_pages;
unsigned long pages;
unsigned long size;
-} __attribute__((aligned(PAGE_SIZE)));
+} __aligned(PAGE_SIZE);
#ifdef CONFIG_HIBERNATION
/* kernel/power/snapshot.c */
@@ -49,6 +50,8 @@ static inline char *check_image_kernel(struct swsusp_info *info)
*/
#define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT)
+asmlinkage int swsusp_save(void);
+
/* kernel/power/hibernate.c */
extern bool freezer_test_done;
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 8dff9b48075a..884b77058864 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -66,6 +66,7 @@ static struct pm_qos_constraints cpu_dma_constraints = {
.list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
.type = PM_QOS_MIN,
.notifiers = &cpu_dma_lat_notifier,
};
@@ -79,6 +80,7 @@ static struct pm_qos_constraints network_lat_constraints = {
.list = PLIST_HEAD_INIT(network_lat_constraints.list),
.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
.type = PM_QOS_MIN,
.notifiers = &network_lat_notifier,
};
@@ -93,6 +95,7 @@ static struct pm_qos_constraints network_tput_constraints = {
.list = PLIST_HEAD_INIT(network_tput_constraints.list),
.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
.type = PM_QOS_MAX,
.notifiers = &network_throughput_notifier,
};
@@ -128,7 +131,7 @@ static const struct file_operations pm_qos_power_fops = {
static inline int pm_qos_get_value(struct pm_qos_constraints *c)
{
if (plist_head_empty(&c->list))
- return c->default_value;
+ return c->no_constraint_value;
switch (c->type) {
case PM_QOS_MIN:
@@ -170,6 +173,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
{
unsigned long flags;
int prev_value, curr_value, new_value;
+ int ret;
spin_lock_irqsave(&pm_qos_lock, flags);
prev_value = pm_qos_get_value(c);
@@ -205,13 +209,15 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
trace_pm_qos_update_target(action, prev_value, curr_value);
if (prev_value != curr_value) {
- blocking_notifier_call_chain(c->notifiers,
- (unsigned long)curr_value,
- NULL);
- return 1;
+ ret = 1;
+ if (c->notifiers)
+ blocking_notifier_call_chain(c->notifiers,
+ (unsigned long)curr_value,
+ NULL);
} else {
- return 0;
+ ret = 0;
}
+ return ret;
}
/**
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b38109e204af..18fb7a2fb14b 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -27,6 +27,7 @@
#include <linux/highmem.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/compiler.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
@@ -155,7 +156,7 @@ static inline void free_image_page(void *addr, int clear_nosave_free)
struct linked_page {
struct linked_page *next;
char data[LINKED_PAGE_DATA_SIZE];
-} __attribute__((packed));
+} __packed;
static inline void
free_list_of_pages(struct linked_page *list, int clear_page_nosave)
@@ -637,7 +638,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
BUG_ON(!region);
} else
/* This allocation cannot fail */
- region = alloc_bootmem(sizeof(struct nosave_region));
+ region = memblock_virt_alloc(sizeof(struct nosave_region), 0);
region->start_pfn = start_pfn;
region->end_pfn = end_pfn;
list_add_tail(&region->list, &nosave_regions);
@@ -1268,7 +1269,7 @@ static void free_unnecessary_pages(void)
* [number of saveable pages] - [number of pages that can be freed in theory]
*
* where the second term is the sum of (1) reclaimable slab pages, (2) active
- * and (3) inactive anonymouns pages, (4) active and (5) inactive file pages,
+ * and (3) inactive anonymous pages, (4) active and (5) inactive file pages,
* minus mapped file pages.
*/
static unsigned long minimum_image_size(unsigned long saveable)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 62ee437b5c7e..c3ad9cafe930 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -26,6 +26,7 @@
#include <linux/syscore_ops.h>
#include <linux/ftrace.h>
#include <trace/events/power.h>
+#include <linux/compiler.h>
#include "power.h"
@@ -39,7 +40,7 @@ static const struct platform_suspend_ops *suspend_ops;
static bool need_suspend_ops(suspend_state_t state)
{
- return !!(state > PM_SUSPEND_FREEZE);
+ return state > PM_SUSPEND_FREEZE;
}
static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
@@ -156,13 +157,13 @@ static int suspend_prepare(suspend_state_t state)
}
/* default implementation */
-void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
+void __weak arch_suspend_disable_irqs(void)
{
local_irq_disable();
}
/* default implementation */
-void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
+void __weak arch_suspend_enable_irqs(void)
{
local_irq_enable();
}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 7c33ed200410..8c9a4819f798 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -101,7 +101,7 @@ struct swsusp_header {
unsigned int flags; /* Flags to pass to the "boot" kernel */
char orig_sig[10];
char sig[10];
-} __attribute__((packed));
+} __packed;
static struct swsusp_header *swsusp_header;
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index 8f50de394d22..019069c84ff6 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -18,6 +18,8 @@
#include <linux/rbtree.h>
#include <linux/slab.h>
+#include "power.h"
+
static DEFINE_MUTEX(wakelocks_lock);
struct wakelock {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index be7c86bae576..a45b50962295 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -319,7 +319,7 @@ static void log_store(int facility, int level,
else
free = log_first_idx - log_next_idx;
- if (free > size + sizeof(struct printk_log))
+ if (free >= size + sizeof(struct printk_log))
break;
/* drop old messages until we have enough contiuous space */
@@ -327,7 +327,7 @@ static void log_store(int facility, int level,
log_first_seq++;
}
- if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) {
+ if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) {
/*
* This message + an additional empty header does not fit
* at the end of the buffer. Add an empty header with len == 0
@@ -351,7 +351,7 @@ static void log_store(int facility, int level,
else
msg->ts_nsec = local_clock();
memset(log_dict(msg) + dict_len, 0, pad_len);
- msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len;
+ msg->len = size;
/* insert message */
log_next_idx += msg->len;
@@ -757,14 +757,10 @@ void __init setup_log_buf(int early)
return;
if (early) {
- unsigned long mem;
-
- mem = memblock_alloc(new_log_buf_len, PAGE_SIZE);
- if (!mem)
- return;
- new_log_buf = __va(mem);
+ new_log_buf =
+ memblock_virt_alloc(new_log_buf_len, PAGE_SIZE);
} else {
- new_log_buf = alloc_bootmem_nopanic(new_log_buf_len);
+ new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, 0);
}
if (unlikely(!new_log_buf)) {
@@ -1080,7 +1076,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
next_seq = log_next_seq;
len = 0;
- prev = 0;
while (len >= 0 && seq < next_seq) {
struct printk_log *msg = log_from_idx(idx);
int textlen;
@@ -1565,9 +1560,12 @@ asmlinkage int vprintk_emit(int facility, int level,
level = kern_level - '0';
case 'd': /* KERN_DEFAULT */
lflags |= LOG_PREFIX;
- case 'c': /* KERN_CONT */
- break;
}
+ /*
+ * No need to check length here because vscnprintf
+ * put '\0' at the end of the string. Only valid and
+ * newly printed level is detected.
+ */
text_len -= end_of_header - text;
text = (char *)end_of_header;
}
@@ -1599,10 +1597,13 @@ asmlinkage int vprintk_emit(int facility, int level,
* either merge it with the current buffer and flush, or if
* there was a race with interrupts (prefix == true) then just
* flush it out and store this line separately.
+ * If the preceding printk was from a different task and missed
+ * a newline, flush and append the newline.
*/
- if (cont.len && cont.owner == current) {
- if (!(lflags & LOG_PREFIX))
- stored = cont_add(facility, level, text, text_len);
+ if (cont.len) {
+ if (cont.owner == current && !(lflags & LOG_PREFIX))
+ stored = cont_add(facility, level, text,
+ text_len);
cont_flush(LOG_NEWLINE);
}
@@ -1882,6 +1883,7 @@ void suspend_console(void)
console_lock();
console_suspended = 1;
up(&console_sem);
+ mutex_release(&console_lock_dep_map, 1, _RET_IP_);
}
void resume_console(void)
@@ -1889,6 +1891,7 @@ void resume_console(void)
if (!console_suspend_enabled)
return;
down(&console_sem);
+ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);
console_suspended = 0;
console_unlock();
}
@@ -2789,7 +2792,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
next_idx = idx;
l = 0;
- prev = 0;
while (seq < dumper->next_seq) {
struct printk_log *msg = log_from_idx(idx);
diff --git a/kernel/profile.c b/kernel/profile.c
index 6631e1ef55ab..cb980f0c731b 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -549,14 +549,14 @@ static int create_hash_tables(void)
struct page *page;
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
@@ -591,18 +591,28 @@ out_cleanup:
int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */
{
struct proc_dir_entry *entry;
+ int err = 0;
if (!prof_on)
return 0;
- if (create_hash_tables())
- return -ENOMEM;
+
+ cpu_notifier_register_begin();
+
+ if (create_hash_tables()) {
+ err = -ENOMEM;
+ goto out;
+ }
+
entry = proc_create("profile", S_IWUSR | S_IRUGO,
NULL, &proc_profile_operations);
if (!entry)
- return 0;
+ goto out;
proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
- hotcpu_notifier(profile_cpu_callback, 0);
- return 0;
+ __hotcpu_notifier(profile_cpu_callback, 0);
+
+out:
+ cpu_notifier_register_done();
+ return err;
}
-module_init(create_proc_profile);
+subsys_initcall(create_proc_profile);
#endif /* CONFIG_PROC_FS */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1f4bcb3cc21c..adf98622cb32 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -1180,8 +1180,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
return ret;
}
-asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
- compat_long_t addr, compat_long_t data)
+COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
+ compat_long_t, addr, compat_long_t, data)
{
struct task_struct *child;
long ret;
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 01e9ec37a3e3..807ccfbf69b3 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,5 +1,5 @@
obj-y += update.o srcu.o
-obj-$(CONFIG_RCU_TORTURE_TEST) += torture.o
+obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_TREE_RCU) += tree.o
obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7859a0a3951e..bfda2726ca45 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2011
*
@@ -23,6 +23,7 @@
#ifndef __LINUX_RCU_H
#define __LINUX_RCU_H
+#include <trace/events/rcu.h>
#ifdef CONFIG_RCU_TRACE
#define RCU_TRACE(stmt) stmt
#else /* #ifdef CONFIG_RCU_TRACE */
@@ -96,25 +97,26 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-extern void kfree(const void *);
+void kfree(const void *);
static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
{
unsigned long offset = (unsigned long)head->func;
+ rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
kfree((void *)head - offset);
+ rcu_lock_release(&rcu_callback_map);
return 1;
} else {
RCU_TRACE(trace_rcu_invoke_callback(rn, head));
head->func(head);
+ rcu_lock_release(&rcu_callback_map);
return 0;
}
}
-extern int rcu_expedited;
-
#ifdef CONFIG_RCU_STALL_COMMON
extern int rcu_cpu_stall_suppress;
diff --git a/kernel/rcu/torture.c b/kernel/rcu/rcutorture.c
index 3929cd451511..bd30bc61bc05 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/rcutorture.c
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2005, 2006
*
@@ -48,112 +48,58 @@
#include <linux/slab.h>
#include <linux/trace_clock.h>
#include <asm/byteorder.h>
+#include <linux/torture.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
-MODULE_ALIAS("rcutorture");
-#ifdef MODULE_PARAM_PREFIX
-#undef MODULE_PARAM_PREFIX
-#endif
-#define MODULE_PARAM_PREFIX "rcutorture."
-
-static int fqs_duration;
-module_param(fqs_duration, int, 0444);
-MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable");
-static int fqs_holdoff;
-module_param(fqs_holdoff, int, 0444);
-MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
-static int fqs_stutter = 3;
-module_param(fqs_stutter, int, 0444);
-MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
-static bool gp_exp;
-module_param(gp_exp, bool, 0444);
-MODULE_PARM_DESC(gp_exp, "Use expedited GP wait primitives");
-static bool gp_normal;
-module_param(gp_normal, bool, 0444);
-MODULE_PARM_DESC(gp_normal, "Use normal (non-expedited) GP wait primitives");
-static int irqreader = 1;
-module_param(irqreader, int, 0444);
-MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
-static int n_barrier_cbs;
-module_param(n_barrier_cbs, int, 0444);
-MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
-static int nfakewriters = 4;
-module_param(nfakewriters, int, 0444);
-MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
-static int nreaders = -1;
-module_param(nreaders, int, 0444);
-MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
-static int object_debug;
-module_param(object_debug, int, 0444);
-MODULE_PARM_DESC(object_debug, "Enable debug-object double call_rcu() testing");
-static int onoff_holdoff;
-module_param(onoff_holdoff, int, 0444);
-MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)");
-static int onoff_interval;
-module_param(onoff_interval, int, 0444);
-MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
-static int shuffle_interval = 3;
-module_param(shuffle_interval, int, 0444);
-MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
-static int shutdown_secs;
-module_param(shutdown_secs, int, 0444);
-MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), <= zero to disable.");
-static int stall_cpu;
-module_param(stall_cpu, int, 0444);
-MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable.");
-static int stall_cpu_holdoff = 10;
-module_param(stall_cpu_holdoff, int, 0444);
-MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s).");
-static int stat_interval = 60;
-module_param(stat_interval, int, 0644);
-MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
-static int stutter = 5;
-module_param(stutter, int, 0444);
-MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
-static int test_boost = 1;
-module_param(test_boost, int, 0444);
-MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
-static int test_boost_duration = 4;
-module_param(test_boost_duration, int, 0444);
-MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
-static int test_boost_interval = 7;
-module_param(test_boost_interval, int, 0444);
-MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
-static bool test_no_idle_hz = true;
-module_param(test_no_idle_hz, bool, 0444);
-MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
+
+torture_param(int, fqs_duration, 0,
+ "Duration of fqs bursts (us), 0 to disable");
+torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
+torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
+torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
+torture_param(bool, gp_normal, false,
+ "Use normal (non-expedited) GP wait primitives");
+torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
+torture_param(int, n_barrier_cbs, 0,
+ "# of callbacks/kthreads for barrier testing");
+torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads");
+torture_param(int, nreaders, -1, "Number of RCU reader threads");
+torture_param(int, object_debug, 0,
+ "Enable debug-object double call_rcu() testing");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0,
+ "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
+torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
+torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
+torture_param(int, stall_cpu_holdoff, 10,
+ "Time to wait before starting stall (s).");
+torture_param(int, stat_interval, 60,
+ "Number of seconds between stats printk()s");
+torture_param(int, stutter, 5, "Number of seconds to run/halt test");
+torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
+torture_param(int, test_boost_duration, 4,
+ "Duration of each boost test, seconds.");
+torture_param(int, test_boost_interval, 7,
+ "Interval between boost tests, seconds.");
+torture_param(bool, test_no_idle_hz, true,
+ "Test support for tickless idle CPUs");
+torture_param(bool, verbose, true,
+ "Enable verbose debugging printk()s");
+
static char *torture_type = "rcu";
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
-static bool verbose;
-module_param(verbose, bool, 0444);
-MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
-
-#define TORTURE_FLAG "-torture:"
-#define PRINTK_STRING(s) \
- do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
-#define VERBOSE_PRINTK_STRING(s) \
- do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
-#define VERBOSE_PRINTK_ERRSTRING(s) \
- do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
-
-static char printk_buf[4096];
static int nrealreaders;
static struct task_struct *writer_task;
static struct task_struct **fakewriter_tasks;
static struct task_struct **reader_tasks;
static struct task_struct *stats_task;
-static struct task_struct *shuffler_task;
-static struct task_struct *stutter_task;
static struct task_struct *fqs_task;
static struct task_struct *boost_tasks[NR_CPUS];
-static struct task_struct *shutdown_task;
-#ifdef CONFIG_HOTPLUG_CPU
-static struct task_struct *onoff_task;
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static struct task_struct *stall_task;
static struct task_struct **barrier_cbs_tasks;
static struct task_struct *barrier_task;
@@ -172,10 +118,10 @@ static struct rcu_torture __rcu *rcu_torture_current;
static unsigned long rcu_torture_current_version;
static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
static DEFINE_SPINLOCK(rcu_torture_lock);
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
- { 0 };
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) =
- { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
+ rcu_torture_count) = { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
+ rcu_torture_batch) = { 0 };
static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
static atomic_t n_rcu_torture_alloc;
static atomic_t n_rcu_torture_alloc_fail;
@@ -188,22 +134,9 @@ static long n_rcu_torture_boost_rterror;
static long n_rcu_torture_boost_failure;
static long n_rcu_torture_boosts;
static long n_rcu_torture_timers;
-static long n_offline_attempts;
-static long n_offline_successes;
-static unsigned long sum_offline;
-static int min_offline = -1;
-static int max_offline;
-static long n_online_attempts;
-static long n_online_successes;
-static unsigned long sum_online;
-static int min_online = -1;
-static int max_online;
static long n_barrier_attempts;
static long n_barrier_successes;
static struct list_head rcu_torture_removed;
-static cpumask_var_t shuffle_tmp_mask;
-
-static int stutter_pause_test;
#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
#define RCUTORTURE_RUNNABLE_INIT 1
@@ -234,7 +167,6 @@ static u64 notrace rcu_trace_clock_local(void)
}
#endif /* #else #ifdef CONFIG_RCU_TRACE */
-static unsigned long shutdown_time; /* jiffies to system shutdown. */
static unsigned long boost_starttime; /* jiffies of next boost test start. */
DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
/* and boost task create/destroy. */
@@ -244,51 +176,6 @@ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */
static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
-/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
-
-#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
-#define FULLSTOP_SHUTDOWN 1 /* System shutdown with rcutorture running. */
-#define FULLSTOP_RMMOD 2 /* Normal rmmod of rcutorture. */
-static int fullstop = FULLSTOP_RMMOD;
-/*
- * Protect fullstop transitions and spawning of kthreads.
- */
-static DEFINE_MUTEX(fullstop_mutex);
-
-/* Forward reference. */
-static void rcu_torture_cleanup(void);
-
-/*
- * Detect and respond to a system shutdown.
- */
-static int
-rcutorture_shutdown_notify(struct notifier_block *unused1,
- unsigned long unused2, void *unused3)
-{
- mutex_lock(&fullstop_mutex);
- if (fullstop == FULLSTOP_DONTSTOP)
- fullstop = FULLSTOP_SHUTDOWN;
- else
- pr_warn(/* but going down anyway, so... */
- "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
- mutex_unlock(&fullstop_mutex);
- return NOTIFY_DONE;
-}
-
-/*
- * Absorb kthreads into a kernel function that won't return, so that
- * they won't ever access module text or data again.
- */
-static void rcutorture_shutdown_absorb(const char *title)
-{
- if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
- pr_notice(
- "rcutorture thread %s parking due to system shutdown\n",
- title);
- schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
- }
-}
-
/*
* Allocate an element from the rcu_tortures pool.
*/
@@ -322,44 +209,6 @@ rcu_torture_free(struct rcu_torture *p)
spin_unlock_bh(&rcu_torture_lock);
}
-struct rcu_random_state {
- unsigned long rrs_state;
- long rrs_count;
-};
-
-#define RCU_RANDOM_MULT 39916801 /* prime */
-#define RCU_RANDOM_ADD 479001701 /* prime */
-#define RCU_RANDOM_REFRESH 10000
-
-#define DEFINE_RCU_RANDOM(name) struct rcu_random_state name = { 0, 0 }
-
-/*
- * Crude but fast random-number generator. Uses a linear congruential
- * generator, with occasional help from cpu_clock().
- */
-static unsigned long
-rcu_random(struct rcu_random_state *rrsp)
-{
- if (--rrsp->rrs_count < 0) {
- rrsp->rrs_state += (unsigned long)local_clock();
- rrsp->rrs_count = RCU_RANDOM_REFRESH;
- }
- rrsp->rrs_state = rrsp->rrs_state * RCU_RANDOM_MULT + RCU_RANDOM_ADD;
- return swahw32(rrsp->rrs_state);
-}
-
-static void
-rcu_stutter_wait(const char *title)
-{
- while (stutter_pause_test || !rcutorture_runnable) {
- if (rcutorture_runnable)
- schedule_timeout_interruptible(1);
- else
- schedule_timeout_interruptible(round_jiffies_relative(HZ));
- rcutorture_shutdown_absorb(title);
- }
-}
-
/*
* Operations vector for selecting different types of tests.
*/
@@ -367,7 +216,7 @@ rcu_stutter_wait(const char *title)
struct rcu_torture_ops {
void (*init)(void);
int (*readlock)(void);
- void (*read_delay)(struct rcu_random_state *rrsp);
+ void (*read_delay)(struct torture_random_state *rrsp);
void (*readunlock)(int idx);
int (*completed)(void);
void (*deferred_free)(struct rcu_torture *p);
@@ -376,7 +225,7 @@ struct rcu_torture_ops {
void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
void (*cb_barrier)(void);
void (*fqs)(void);
- int (*stats)(char *page);
+ void (*stats)(char *page);
int irq_capable;
int can_boost;
const char *name;
@@ -394,7 +243,7 @@ static int rcu_torture_read_lock(void) __acquires(RCU)
return 0;
}
-static void rcu_read_delay(struct rcu_random_state *rrsp)
+static void rcu_read_delay(struct torture_random_state *rrsp)
{
const unsigned long shortdelay_us = 200;
const unsigned long longdelay_ms = 50;
@@ -403,12 +252,13 @@ static void rcu_read_delay(struct rcu_random_state *rrsp)
* period, and we want a long delay occasionally to trigger
* force_quiescent_state. */
- if (!(rcu_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
+ if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
mdelay(longdelay_ms);
- if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
+ if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
udelay(shortdelay_us);
#ifdef CONFIG_PREEMPT
- if (!preempt_count() && !(rcu_random(rrsp) % (nrealreaders * 20000)))
+ if (!preempt_count() &&
+ !(torture_random(rrsp) % (nrealreaders * 20000)))
preempt_schedule(); /* No QS if preempt_disable() in effect */
#endif
}
@@ -429,7 +279,7 @@ rcu_torture_cb(struct rcu_head *p)
int i;
struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
- if (fullstop != FULLSTOP_DONTSTOP) {
+ if (torture_must_stop_irq()) {
/* Test is ending, just drop callbacks on the floor. */
/* The next initialization will pick up the pieces. */
return;
@@ -522,6 +372,48 @@ static struct rcu_torture_ops rcu_bh_ops = {
};
/*
+ * Don't even think about trying any of these in real life!!!
+ * The names includes "busted", and they really means it!
+ * The only purpose of these functions is to provide a buggy RCU
+ * implementation to make sure that rcutorture correctly emits
+ * buggy-RCU error messages.
+ */
+static void rcu_busted_torture_deferred_free(struct rcu_torture *p)
+{
+ /* This is a deliberate bug for testing purposes only! */
+ rcu_torture_cb(&p->rtort_rcu);
+}
+
+static void synchronize_rcu_busted(void)
+{
+ /* This is a deliberate bug for testing purposes only! */
+}
+
+static void
+call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+ /* This is a deliberate bug for testing purposes only! */
+ func(head);
+}
+
+static struct rcu_torture_ops rcu_busted_ops = {
+ .init = rcu_sync_torture_init,
+ .readlock = rcu_torture_read_lock,
+ .read_delay = rcu_read_delay, /* just reuse rcu's version. */
+ .readunlock = rcu_torture_read_unlock,
+ .completed = rcu_no_completed,
+ .deferred_free = rcu_busted_torture_deferred_free,
+ .sync = synchronize_rcu_busted,
+ .exp_sync = synchronize_rcu_busted,
+ .call = call_rcu_busted,
+ .cb_barrier = NULL,
+ .fqs = NULL,
+ .stats = NULL,
+ .irq_capable = 1,
+ .name = "rcu_busted"
+};
+
+/*
* Definitions for srcu torture testing.
*/
@@ -532,7 +424,7 @@ static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
return srcu_read_lock(&srcu_ctl);
}
-static void srcu_read_delay(struct rcu_random_state *rrsp)
+static void srcu_read_delay(struct torture_random_state *rrsp)
{
long delay;
const long uspertick = 1000000 / HZ;
@@ -540,7 +432,8 @@ static void srcu_read_delay(struct rcu_random_state *rrsp)
/* We want there to be long-running readers, but not all the time. */
- delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick);
+ delay = torture_random(rrsp) %
+ (nrealreaders * 2 * longdelay * uspertick);
if (!delay)
schedule_timeout_interruptible(longdelay);
else
@@ -578,21 +471,19 @@ static void srcu_torture_barrier(void)
srcu_barrier(&srcu_ctl);
}
-static int srcu_torture_stats(char *page)
+static void srcu_torture_stats(char *page)
{
- int cnt = 0;
int cpu;
int idx = srcu_ctl.completed & 0x1;
- cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
+ page += sprintf(page, "%s%s per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
- cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
+ page += sprintf(page, " %d(%lu,%lu)", cpu,
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
}
- cnt += sprintf(&page[cnt], "\n");
- return cnt;
+ sprintf(page, "\n");
}
static void srcu_torture_synchronize_expedited(void)
@@ -681,12 +572,12 @@ static int rcu_torture_boost(void *arg)
struct rcu_boost_inflight rbi = { .inflight = 0 };
struct sched_param sp;
- VERBOSE_PRINTK_STRING("rcu_torture_boost started");
+ VERBOSE_TOROUT_STRING("rcu_torture_boost started");
/* Set real-time priority. */
sp.sched_priority = 1;
if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
- VERBOSE_PRINTK_STRING("rcu_torture_boost RT prio failed!");
+ VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!");
n_rcu_torture_boost_rterror++;
}
@@ -697,9 +588,8 @@ static int rcu_torture_boost(void *arg)
oldstarttime = boost_starttime;
while (ULONG_CMP_LT(jiffies, oldstarttime)) {
schedule_timeout_interruptible(oldstarttime - jiffies);
- rcu_stutter_wait("rcu_torture_boost");
- if (kthread_should_stop() ||
- fullstop != FULLSTOP_DONTSTOP)
+ stutter_wait("rcu_torture_boost");
+ if (torture_must_stop())
goto checkwait;
}
@@ -714,15 +604,14 @@ static int rcu_torture_boost(void *arg)
call_rcu(&rbi.rcu, rcu_torture_boost_cb);
if (jiffies - call_rcu_time >
test_boost_duration * HZ - HZ / 2) {
- VERBOSE_PRINTK_STRING("rcu_torture_boost boosting failed");
+ VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
n_rcu_torture_boost_failure++;
}
call_rcu_time = jiffies;
}
cond_resched();
- rcu_stutter_wait("rcu_torture_boost");
- if (kthread_should_stop() ||
- fullstop != FULLSTOP_DONTSTOP)
+ stutter_wait("rcu_torture_boost");
+ if (torture_must_stop())
goto checkwait;
}
@@ -746,16 +635,17 @@ static int rcu_torture_boost(void *arg)
}
/* Go do the stutter. */
-checkwait: rcu_stutter_wait("rcu_torture_boost");
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+checkwait: stutter_wait("rcu_torture_boost");
+ } while (!torture_must_stop());
/* Clean up and exit. */
- VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
- rcutorture_shutdown_absorb("rcu_torture_boost");
- while (!kthread_should_stop() || rbi.inflight)
+ while (!kthread_should_stop() || rbi.inflight) {
+ torture_shutdown_absorb("rcu_torture_boost");
schedule_timeout_uninterruptible(1);
+ }
smp_mb(); /* order accesses to ->inflight before stack-frame death. */
destroy_rcu_head_on_stack(&rbi.rcu);
+ torture_kthread_stopping("rcu_torture_boost");
return 0;
}
@@ -770,7 +660,7 @@ rcu_torture_fqs(void *arg)
unsigned long fqs_resume_time;
int fqs_burst_remaining;
- VERBOSE_PRINTK_STRING("rcu_torture_fqs task started");
+ VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
do {
fqs_resume_time = jiffies + fqs_stutter * HZ;
while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
@@ -784,12 +674,9 @@ rcu_torture_fqs(void *arg)
udelay(fqs_holdoff);
fqs_burst_remaining -= fqs_holdoff;
}
- rcu_stutter_wait("rcu_torture_fqs");
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
- VERBOSE_PRINTK_STRING("rcu_torture_fqs task stopping");
- rcutorture_shutdown_absorb("rcu_torture_fqs");
- while (!kthread_should_stop())
- schedule_timeout_uninterruptible(1);
+ stutter_wait("rcu_torture_fqs");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("rcu_torture_fqs");
return 0;
}
@@ -806,10 +693,10 @@ rcu_torture_writer(void *arg)
struct rcu_torture *rp;
struct rcu_torture *rp1;
struct rcu_torture *old_rp;
- static DEFINE_RCU_RANDOM(rand);
+ static DEFINE_TORTURE_RANDOM(rand);
- VERBOSE_PRINTK_STRING("rcu_torture_writer task started");
- set_user_nice(current, 19);
+ VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
+ set_user_nice(current, MAX_NICE);
do {
schedule_timeout_uninterruptible(1);
@@ -817,7 +704,7 @@ rcu_torture_writer(void *arg)
if (rp == NULL)
continue;
rp->rtort_pipe_count = 0;
- udelay(rcu_random(&rand) & 0x3ff);
+ udelay(torture_random(&rand) & 0x3ff);
old_rp = rcu_dereference_check(rcu_torture_current,
current == writer_task);
rp->rtort_mbtest = 1;
@@ -830,7 +717,7 @@ rcu_torture_writer(void *arg)
atomic_inc(&rcu_torture_wcount[i]);
old_rp->rtort_pipe_count++;
if (gp_normal == gp_exp)
- exp = !!(rcu_random(&rand) & 0x80);
+ exp = !!(torture_random(&rand) & 0x80);
else
exp = gp_exp;
if (!exp) {
@@ -856,12 +743,9 @@ rcu_torture_writer(void *arg)
}
}
rcutorture_record_progress(++rcu_torture_current_version);
- rcu_stutter_wait("rcu_torture_writer");
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
- VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
- rcutorture_shutdown_absorb("rcu_torture_writer");
- while (!kthread_should_stop())
- schedule_timeout_uninterruptible(1);
+ stutter_wait("rcu_torture_writer");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("rcu_torture_writer");
return 0;
}
@@ -872,19 +756,19 @@ rcu_torture_writer(void *arg)
static int
rcu_torture_fakewriter(void *arg)
{
- DEFINE_RCU_RANDOM(rand);
+ DEFINE_TORTURE_RANDOM(rand);
- VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task started");
- set_user_nice(current, 19);
+ VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started");
+ set_user_nice(current, MAX_NICE);
do {
- schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
- udelay(rcu_random(&rand) & 0x3ff);
+ schedule_timeout_uninterruptible(1 + torture_random(&rand)%10);
+ udelay(torture_random(&rand) & 0x3ff);
if (cur_ops->cb_barrier != NULL &&
- rcu_random(&rand) % (nfakewriters * 8) == 0) {
+ torture_random(&rand) % (nfakewriters * 8) == 0) {
cur_ops->cb_barrier();
} else if (gp_normal == gp_exp) {
- if (rcu_random(&rand) & 0x80)
+ if (torture_random(&rand) & 0x80)
cur_ops->sync();
else
cur_ops->exp_sync();
@@ -893,13 +777,10 @@ rcu_torture_fakewriter(void *arg)
} else {
cur_ops->exp_sync();
}
- rcu_stutter_wait("rcu_torture_fakewriter");
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+ stutter_wait("rcu_torture_fakewriter");
+ } while (!torture_must_stop());
- VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
- rcutorture_shutdown_absorb("rcu_torture_fakewriter");
- while (!kthread_should_stop())
- schedule_timeout_uninterruptible(1);
+ torture_kthread_stopping("rcu_torture_fakewriter");
return 0;
}
@@ -925,7 +806,7 @@ static void rcu_torture_timer(unsigned long unused)
int idx;
int completed;
int completed_end;
- static DEFINE_RCU_RANDOM(rand);
+ static DEFINE_TORTURE_RANDOM(rand);
static DEFINE_SPINLOCK(rand_lock);
struct rcu_torture *p;
int pipe_count;
@@ -984,14 +865,14 @@ rcu_torture_reader(void *arg)
int completed;
int completed_end;
int idx;
- DEFINE_RCU_RANDOM(rand);
+ DEFINE_TORTURE_RANDOM(rand);
struct rcu_torture *p;
int pipe_count;
struct timer_list t;
unsigned long long ts;
- VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
- set_user_nice(current, 19);
+ VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
+ set_user_nice(current, MAX_NICE);
if (irqreader && cur_ops->irq_capable)
setup_timer_on_stack(&t, rcu_torture_timer, 0);
@@ -1038,24 +919,20 @@ rcu_torture_reader(void *arg)
preempt_enable();
cur_ops->readunlock(idx);
schedule();
- rcu_stutter_wait("rcu_torture_reader");
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
- VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
- rcutorture_shutdown_absorb("rcu_torture_reader");
+ stutter_wait("rcu_torture_reader");
+ } while (!torture_must_stop());
if (irqreader && cur_ops->irq_capable)
del_timer_sync(&t);
- while (!kthread_should_stop())
- schedule_timeout_uninterruptible(1);
+ torture_kthread_stopping("rcu_torture_reader");
return 0;
}
/*
* Create an RCU-torture statistics message in the specified buffer.
*/
-static int
+static void
rcu_torture_printk(char *page)
{
- int cnt = 0;
int cpu;
int i;
long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
@@ -1071,8 +948,8 @@ rcu_torture_printk(char *page)
if (pipesummary[i] != 0)
break;
}
- cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt],
+ page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page,
"rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
rcu_torture_current,
rcu_torture_current_version,
@@ -1080,53 +957,46 @@ rcu_torture_printk(char *page)
atomic_read(&n_rcu_torture_alloc),
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free));
- cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
+ page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
atomic_read(&n_rcu_torture_mberror),
n_rcu_torture_boost_ktrerror,
n_rcu_torture_boost_rterror);
- cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
+ page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
n_rcu_torture_timers);
- cnt += sprintf(&page[cnt],
- "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
- n_online_successes, n_online_attempts,
- n_offline_successes, n_offline_attempts,
- min_online, max_online,
- min_offline, max_offline,
- sum_online, sum_offline, HZ);
- cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
+ page = torture_onoff_stats(page);
+ page += sprintf(page, "barrier: %ld/%ld:%ld",
n_barrier_successes,
n_barrier_attempts,
n_rcu_torture_barrier_error);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
if (atomic_read(&n_rcu_torture_mberror) != 0 ||
n_rcu_torture_barrier_error != 0 ||
n_rcu_torture_boost_ktrerror != 0 ||
n_rcu_torture_boost_rterror != 0 ||
n_rcu_torture_boost_failure != 0 ||
i > 1) {
- cnt += sprintf(&page[cnt], "!!! ");
+ page += sprintf(page, "!!! ");
atomic_inc(&n_rcu_torture_error);
WARN_ON_ONCE(1);
}
- cnt += sprintf(&page[cnt], "Reader Pipe: ");
+ page += sprintf(page, "Reader Pipe: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
- cnt += sprintf(&page[cnt], " %ld", pipesummary[i]);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt], "Reader Batch: ");
+ page += sprintf(page, " %ld", pipesummary[i]);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "Reader Batch: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
- cnt += sprintf(&page[cnt], " %ld", batchsummary[i]);
- cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
- cnt += sprintf(&page[cnt], "Free-Block Circulation: ");
+ page += sprintf(page, " %ld", batchsummary[i]);
+ page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+ page += sprintf(page, "Free-Block Circulation: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
- cnt += sprintf(&page[cnt], " %d",
+ page += sprintf(page, " %d",
atomic_read(&rcu_torture_wcount[i]));
}
- cnt += sprintf(&page[cnt], "\n");
+ page += sprintf(page, "\n");
if (cur_ops->stats)
- cnt += cur_ops->stats(&page[cnt]);
- return cnt;
+ cur_ops->stats(page);
}
/*
@@ -1140,132 +1010,33 @@ rcu_torture_printk(char *page)
static void
rcu_torture_stats_print(void)
{
- int cnt;
+ int size = nr_cpu_ids * 200 + 8192;
+ char *buf;
- cnt = rcu_torture_printk(printk_buf);
- pr_alert("%s", printk_buf);
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf) {
+ pr_err("rcu-torture: Out of memory, need: %d", size);
+ return;
+ }
+ rcu_torture_printk(buf);
+ pr_alert("%s", buf);
+ kfree(buf);
}
/*
* Periodically prints torture statistics, if periodic statistics printing
* was specified via the stat_interval module parameter.
- *
- * No need to worry about fullstop here, since this one doesn't reference
- * volatile state or register callbacks.
*/
static int
rcu_torture_stats(void *arg)
{
- VERBOSE_PRINTK_STRING("rcu_torture_stats task started");
+ VERBOSE_TOROUT_STRING("rcu_torture_stats task started");
do {
schedule_timeout_interruptible(stat_interval * HZ);
rcu_torture_stats_print();
- rcutorture_shutdown_absorb("rcu_torture_stats");
- } while (!kthread_should_stop());
- VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
- return 0;
-}
-
-static int rcu_idle_cpu; /* Force all torture tasks off this CPU */
-
-/* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case
- * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs.
- */
-static void rcu_torture_shuffle_tasks(void)
-{
- int i;
-
- cpumask_setall(shuffle_tmp_mask);
- get_online_cpus();
-
- /* No point in shuffling if there is only one online CPU (ex: UP) */
- if (num_online_cpus() == 1) {
- put_online_cpus();
- return;
- }
-
- if (rcu_idle_cpu != -1)
- cpumask_clear_cpu(rcu_idle_cpu, shuffle_tmp_mask);
-
- set_cpus_allowed_ptr(current, shuffle_tmp_mask);
-
- if (reader_tasks) {
- for (i = 0; i < nrealreaders; i++)
- if (reader_tasks[i])
- set_cpus_allowed_ptr(reader_tasks[i],
- shuffle_tmp_mask);
- }
- if (fakewriter_tasks) {
- for (i = 0; i < nfakewriters; i++)
- if (fakewriter_tasks[i])
- set_cpus_allowed_ptr(fakewriter_tasks[i],
- shuffle_tmp_mask);
- }
- if (writer_task)
- set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask);
- if (stats_task)
- set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask);
- if (stutter_task)
- set_cpus_allowed_ptr(stutter_task, shuffle_tmp_mask);
- if (fqs_task)
- set_cpus_allowed_ptr(fqs_task, shuffle_tmp_mask);
- if (shutdown_task)
- set_cpus_allowed_ptr(shutdown_task, shuffle_tmp_mask);
-#ifdef CONFIG_HOTPLUG_CPU
- if (onoff_task)
- set_cpus_allowed_ptr(onoff_task, shuffle_tmp_mask);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
- if (stall_task)
- set_cpus_allowed_ptr(stall_task, shuffle_tmp_mask);
- if (barrier_cbs_tasks)
- for (i = 0; i < n_barrier_cbs; i++)
- if (barrier_cbs_tasks[i])
- set_cpus_allowed_ptr(barrier_cbs_tasks[i],
- shuffle_tmp_mask);
- if (barrier_task)
- set_cpus_allowed_ptr(barrier_task, shuffle_tmp_mask);
-
- if (rcu_idle_cpu == -1)
- rcu_idle_cpu = num_online_cpus() - 1;
- else
- rcu_idle_cpu--;
-
- put_online_cpus();
-}
-
-/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
- * system to become idle at a time and cut off its timer ticks. This is meant
- * to test the support for such tickless idle CPU in RCU.
- */
-static int
-rcu_torture_shuffle(void *arg)
-{
- VERBOSE_PRINTK_STRING("rcu_torture_shuffle task started");
- do {
- schedule_timeout_interruptible(shuffle_interval * HZ);
- rcu_torture_shuffle_tasks();
- rcutorture_shutdown_absorb("rcu_torture_shuffle");
- } while (!kthread_should_stop());
- VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
- return 0;
-}
-
-/* Cause the rcutorture test to "stutter", starting and stopping all
- * threads periodically.
- */
-static int
-rcu_torture_stutter(void *arg)
-{
- VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
- do {
- schedule_timeout_interruptible(stutter * HZ);
- stutter_pause_test = 1;
- if (!kthread_should_stop())
- schedule_timeout_interruptible(stutter * HZ);
- stutter_pause_test = 0;
- rcutorture_shutdown_absorb("rcu_torture_stutter");
- } while (!kthread_should_stop());
- VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
+ torture_shutdown_absorb("rcu_torture_stats");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("rcu_torture_stats");
return 0;
}
@@ -1292,10 +1063,6 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
onoff_interval, onoff_holdoff);
}
-static struct notifier_block rcutorture_shutdown_nb = {
- .notifier_call = rcutorture_shutdown_notify,
-};
-
static void rcutorture_booster_cleanup(int cpu)
{
struct task_struct *t;
@@ -1303,14 +1070,12 @@ static void rcutorture_booster_cleanup(int cpu)
if (boost_tasks[cpu] == NULL)
return;
mutex_lock(&boost_mutex);
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_boost task");
t = boost_tasks[cpu];
boost_tasks[cpu] = NULL;
mutex_unlock(&boost_mutex);
/* This must be outside of the mutex, otherwise deadlock! */
- kthread_stop(t);
- boost_tasks[cpu] = NULL;
+ torture_stop_kthread(rcu_torture_boost, t);
}
static int rcutorture_booster_init(int cpu)
@@ -1322,13 +1087,13 @@ static int rcutorture_booster_init(int cpu)
/* Don't allow time recalculation while creating a new task. */
mutex_lock(&boost_mutex);
- VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task");
+ VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
cpu_to_node(cpu),
"rcu_torture_boost");
if (IS_ERR(boost_tasks[cpu])) {
retval = PTR_ERR(boost_tasks[cpu]);
- VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed");
+ VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed");
n_rcu_torture_boost_ktrerror++;
boost_tasks[cpu] = NULL;
mutex_unlock(&boost_mutex);
@@ -1341,175 +1106,6 @@ static int rcutorture_booster_init(int cpu)
}
/*
- * Cause the rcutorture test to shutdown the system after the test has
- * run for the time specified by the shutdown_secs module parameter.
- */
-static int
-rcu_torture_shutdown(void *arg)
-{
- long delta;
- unsigned long jiffies_snap;
-
- VERBOSE_PRINTK_STRING("rcu_torture_shutdown task started");
- jiffies_snap = ACCESS_ONCE(jiffies);
- while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
- !kthread_should_stop()) {
- delta = shutdown_time - jiffies_snap;
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_shutdown task: %lu jiffies remaining\n",
- torture_type, delta);
- schedule_timeout_interruptible(delta);
- jiffies_snap = ACCESS_ONCE(jiffies);
- }
- if (kthread_should_stop()) {
- VERBOSE_PRINTK_STRING("rcu_torture_shutdown task stopping");
- return 0;
- }
-
- /* OK, shut down the system. */
-
- VERBOSE_PRINTK_STRING("rcu_torture_shutdown task shutting down system");
- shutdown_task = NULL; /* Avoid self-kill deadlock. */
- rcu_torture_cleanup(); /* Get the success/failure message. */
- kernel_power_off(); /* Shut down the system. */
- return 0;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Execute random CPU-hotplug operations at the interval specified
- * by the onoff_interval.
- */
-static int
-rcu_torture_onoff(void *arg)
-{
- int cpu;
- unsigned long delta;
- int maxcpu = -1;
- DEFINE_RCU_RANDOM(rand);
- int ret;
- unsigned long starttime;
-
- VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
- for_each_online_cpu(cpu)
- maxcpu = cpu;
- WARN_ON(maxcpu < 0);
- if (onoff_holdoff > 0) {
- VERBOSE_PRINTK_STRING("rcu_torture_onoff begin holdoff");
- schedule_timeout_interruptible(onoff_holdoff * HZ);
- VERBOSE_PRINTK_STRING("rcu_torture_onoff end holdoff");
- }
- while (!kthread_should_stop()) {
- cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1);
- if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_onoff task: offlining %d\n",
- torture_type, cpu);
- starttime = jiffies;
- n_offline_attempts++;
- ret = cpu_down(cpu);
- if (ret) {
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_onoff task: offline %d failed: errno %d\n",
- torture_type, cpu, ret);
- } else {
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_onoff task: offlined %d\n",
- torture_type, cpu);
- n_offline_successes++;
- delta = jiffies - starttime;
- sum_offline += delta;
- if (min_offline < 0) {
- min_offline = delta;
- max_offline = delta;
- }
- if (min_offline > delta)
- min_offline = delta;
- if (max_offline < delta)
- max_offline = delta;
- }
- } else if (cpu_is_hotpluggable(cpu)) {
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_onoff task: onlining %d\n",
- torture_type, cpu);
- starttime = jiffies;
- n_online_attempts++;
- ret = cpu_up(cpu);
- if (ret) {
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_onoff task: online %d failed: errno %d\n",
- torture_type, cpu, ret);
- } else {
- if (verbose)
- pr_alert("%s" TORTURE_FLAG
- "rcu_torture_onoff task: onlined %d\n",
- torture_type, cpu);
- n_online_successes++;
- delta = jiffies - starttime;
- sum_online += delta;
- if (min_online < 0) {
- min_online = delta;
- max_online = delta;
- }
- if (min_online > delta)
- min_online = delta;
- if (max_online < delta)
- max_online = delta;
- }
- }
- schedule_timeout_interruptible(onoff_interval * HZ);
- }
- VERBOSE_PRINTK_STRING("rcu_torture_onoff task stopping");
- return 0;
-}
-
-static int
-rcu_torture_onoff_init(void)
-{
- int ret;
-
- if (onoff_interval <= 0)
- return 0;
- onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff");
- if (IS_ERR(onoff_task)) {
- ret = PTR_ERR(onoff_task);
- onoff_task = NULL;
- return ret;
- }
- return 0;
-}
-
-static void rcu_torture_onoff_cleanup(void)
-{
- if (onoff_task == NULL)
- return;
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task");
- kthread_stop(onoff_task);
- onoff_task = NULL;
-}
-
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static int
-rcu_torture_onoff_init(void)
-{
- return 0;
-}
-
-static void rcu_torture_onoff_cleanup(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
-/*
* CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then
* induces a CPU stall for the time specified by stall_cpu.
*/
@@ -1517,11 +1113,11 @@ static int rcu_torture_stall(void *args)
{
unsigned long stop_at;
- VERBOSE_PRINTK_STRING("rcu_torture_stall task started");
+ VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
if (stall_cpu_holdoff > 0) {
- VERBOSE_PRINTK_STRING("rcu_torture_stall begin holdoff");
+ VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
- VERBOSE_PRINTK_STRING("rcu_torture_stall end holdoff");
+ VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
}
if (!kthread_should_stop()) {
stop_at = get_seconds() + stall_cpu;
@@ -1535,7 +1131,7 @@ static int rcu_torture_stall(void *args)
rcu_read_unlock();
pr_alert("rcu_torture_stall end.\n");
}
- rcutorture_shutdown_absorb("rcu_torture_stall");
+ torture_shutdown_absorb("rcu_torture_stall");
while (!kthread_should_stop())
schedule_timeout_interruptible(10 * HZ);
return 0;
@@ -1544,27 +1140,9 @@ static int rcu_torture_stall(void *args)
/* Spawn CPU-stall kthread, if stall_cpu specified. */
static int __init rcu_torture_stall_init(void)
{
- int ret;
-
if (stall_cpu <= 0)
return 0;
- stall_task = kthread_run(rcu_torture_stall, NULL, "rcu_torture_stall");
- if (IS_ERR(stall_task)) {
- ret = PTR_ERR(stall_task);
- stall_task = NULL;
- return ret;
- }
- return 0;
-}
-
-/* Clean up after the CPU-stall kthread, if one was spawned. */
-static void rcu_torture_stall_cleanup(void)
-{
- if (stall_task == NULL)
- return;
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task.");
- kthread_stop(stall_task);
- stall_task = NULL;
+ return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
}
/* Callback function for RCU barrier testing. */
@@ -1578,30 +1156,28 @@ static int rcu_torture_barrier_cbs(void *arg)
{
long myid = (long)arg;
bool lastphase = 0;
+ bool newphase;
struct rcu_head rcu;
init_rcu_head_on_stack(&rcu);
- VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started");
- set_user_nice(current, 19);
+ VERBOSE_TOROUT_STRING("rcu_torture_barrier_cbs task started");
+ set_user_nice(current, MAX_NICE);
do {
wait_event(barrier_cbs_wq[myid],
- barrier_phase != lastphase ||
- kthread_should_stop() ||
- fullstop != FULLSTOP_DONTSTOP);
- lastphase = barrier_phase;
+ (newphase =
+ ACCESS_ONCE(barrier_phase)) != lastphase ||
+ torture_must_stop());
+ lastphase = newphase;
smp_mb(); /* ensure barrier_phase load before ->call(). */
- if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+ if (torture_must_stop())
break;
cur_ops->call(&rcu, rcu_torture_barrier_cbf);
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
- VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping");
- rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
- while (!kthread_should_stop())
- schedule_timeout_interruptible(1);
+ } while (!torture_must_stop());
cur_ops->cb_barrier();
destroy_rcu_head_on_stack(&rcu);
+ torture_kthread_stopping("rcu_torture_barrier_cbs");
return 0;
}
@@ -1610,7 +1186,7 @@ static int rcu_torture_barrier(void *arg)
{
int i;
- VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting");
+ VERBOSE_TOROUT_STRING("rcu_torture_barrier task starting");
do {
atomic_set(&barrier_cbs_invoked, 0);
atomic_set(&barrier_cbs_count, n_barrier_cbs);
@@ -1620,23 +1196,19 @@ static int rcu_torture_barrier(void *arg)
wake_up(&barrier_cbs_wq[i]);
wait_event(barrier_wq,
atomic_read(&barrier_cbs_count) == 0 ||
- kthread_should_stop() ||
- fullstop != FULLSTOP_DONTSTOP);
- if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+ torture_must_stop());
+ if (torture_must_stop())
break;
n_barrier_attempts++;
- cur_ops->cb_barrier();
+ cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
n_rcu_torture_barrier_error++;
WARN_ON_ONCE(1);
}
n_barrier_successes++;
schedule_timeout_interruptible(HZ / 10);
- } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
- VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping");
- rcutorture_shutdown_absorb("rcu_torture_barrier");
- while (!kthread_should_stop())
- schedule_timeout_interruptible(1);
+ } while (!torture_must_stop());
+ torture_kthread_stopping("rcu_torture_barrier");
return 0;
}
@@ -1669,24 +1241,13 @@ static int rcu_torture_barrier_init(void)
return -ENOMEM;
for (i = 0; i < n_barrier_cbs; i++) {
init_waitqueue_head(&barrier_cbs_wq[i]);
- barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs,
- (void *)(long)i,
- "rcu_torture_barrier_cbs");
- if (IS_ERR(barrier_cbs_tasks[i])) {
- ret = PTR_ERR(barrier_cbs_tasks[i]);
- VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs");
- barrier_cbs_tasks[i] = NULL;
+ ret = torture_create_kthread(rcu_torture_barrier_cbs,
+ (void *)(long)i,
+ barrier_cbs_tasks[i]);
+ if (ret)
return ret;
- }
- }
- barrier_task = kthread_run(rcu_torture_barrier, NULL,
- "rcu_torture_barrier");
- if (IS_ERR(barrier_task)) {
- ret = PTR_ERR(barrier_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier");
- barrier_task = NULL;
}
- return 0;
+ return torture_create_kthread(rcu_torture_barrier, NULL, barrier_task);
}
/* Clean up after RCU barrier testing. */
@@ -1694,19 +1255,11 @@ static void rcu_torture_barrier_cleanup(void)
{
int i;
- if (barrier_task != NULL) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task");
- kthread_stop(barrier_task);
- barrier_task = NULL;
- }
+ torture_stop_kthread(rcu_torture_barrier, barrier_task);
if (barrier_cbs_tasks != NULL) {
- for (i = 0; i < n_barrier_cbs; i++) {
- if (barrier_cbs_tasks[i] != NULL) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task");
- kthread_stop(barrier_cbs_tasks[i]);
- barrier_cbs_tasks[i] = NULL;
- }
- }
+ for (i = 0; i < n_barrier_cbs; i++)
+ torture_stop_kthread(rcu_torture_barrier_cbs,
+ barrier_cbs_tasks[i]);
kfree(barrier_cbs_tasks);
barrier_cbs_tasks = NULL;
}
@@ -1744,90 +1297,42 @@ rcu_torture_cleanup(void)
{
int i;
- mutex_lock(&fullstop_mutex);
rcutorture_record_test_transition();
- if (fullstop == FULLSTOP_SHUTDOWN) {
- pr_warn(/* but going down anyway, so... */
- "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
- mutex_unlock(&fullstop_mutex);
- schedule_timeout_uninterruptible(10);
+ if (torture_cleanup()) {
if (cur_ops->cb_barrier != NULL)
cur_ops->cb_barrier();
return;
}
- fullstop = FULLSTOP_RMMOD;
- mutex_unlock(&fullstop_mutex);
- unregister_reboot_notifier(&rcutorture_shutdown_nb);
- rcu_torture_barrier_cleanup();
- rcu_torture_stall_cleanup();
- if (stutter_task) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
- kthread_stop(stutter_task);
- }
- stutter_task = NULL;
- if (shuffler_task) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
- kthread_stop(shuffler_task);
- free_cpumask_var(shuffle_tmp_mask);
- }
- shuffler_task = NULL;
- if (writer_task) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
- kthread_stop(writer_task);
- }
- writer_task = NULL;
+ rcu_torture_barrier_cleanup();
+ torture_stop_kthread(rcu_torture_stall, stall_task);
+ torture_stop_kthread(rcu_torture_writer, writer_task);
if (reader_tasks) {
- for (i = 0; i < nrealreaders; i++) {
- if (reader_tasks[i]) {
- VERBOSE_PRINTK_STRING(
- "Stopping rcu_torture_reader task");
- kthread_stop(reader_tasks[i]);
- }
- reader_tasks[i] = NULL;
- }
+ for (i = 0; i < nrealreaders; i++)
+ torture_stop_kthread(rcu_torture_reader,
+ reader_tasks[i]);
kfree(reader_tasks);
- reader_tasks = NULL;
}
rcu_torture_current = NULL;
if (fakewriter_tasks) {
for (i = 0; i < nfakewriters; i++) {
- if (fakewriter_tasks[i]) {
- VERBOSE_PRINTK_STRING(
- "Stopping rcu_torture_fakewriter task");
- kthread_stop(fakewriter_tasks[i]);
- }
- fakewriter_tasks[i] = NULL;
+ torture_stop_kthread(rcu_torture_fakewriter,
+ fakewriter_tasks[i]);
}
kfree(fakewriter_tasks);
fakewriter_tasks = NULL;
}
- if (stats_task) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task");
- kthread_stop(stats_task);
- }
- stats_task = NULL;
-
- if (fqs_task) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_fqs task");
- kthread_stop(fqs_task);
- }
- fqs_task = NULL;
+ torture_stop_kthread(rcu_torture_stats, stats_task);
+ torture_stop_kthread(rcu_torture_fqs, fqs_task);
if ((test_boost == 1 && cur_ops->can_boost) ||
test_boost == 2) {
unregister_cpu_notifier(&rcutorture_cpu_nb);
for_each_possible_cpu(i)
rcutorture_booster_cleanup(i);
}
- if (shutdown_task != NULL) {
- VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task");
- kthread_stop(shutdown_task);
- }
- shutdown_task = NULL;
- rcu_torture_onoff_cleanup();
/* Wait for all RCU callbacks to fire. */
@@ -1838,8 +1343,7 @@ rcu_torture_cleanup(void)
if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error)
rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
- else if (n_online_successes != n_online_attempts ||
- n_offline_successes != n_offline_attempts)
+ else if (torture_onoff_failures())
rcu_torture_print_module_parms(cur_ops,
"End of test: RCU_HOTPLUG");
else
@@ -1908,12 +1412,11 @@ rcu_torture_init(void)
int i;
int cpu;
int firsterr = 0;
- int retval;
static struct rcu_torture_ops *torture_ops[] = {
- &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops,
+ &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
};
- mutex_lock(&fullstop_mutex);
+ torture_init_begin(torture_type, verbose, &rcutorture_runnable);
/* Process args and tell the world that the torturer is on the job. */
for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
@@ -1928,7 +1431,7 @@ rcu_torture_init(void)
for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
pr_alert(" %s", torture_ops[i]->name);
pr_alert("\n");
- mutex_unlock(&fullstop_mutex);
+ torture_init_end();
return -EINVAL;
}
if (cur_ops->fqs == NULL && fqs_duration != 0) {
@@ -1943,7 +1446,6 @@ rcu_torture_init(void)
else
nrealreaders = 2 * num_online_cpus();
rcu_torture_print_module_parms(cur_ops, "Start of test");
- fullstop = FULLSTOP_DONTSTOP;
/* Set up the freelist. */
@@ -1979,108 +1481,61 @@ rcu_torture_init(void)
/* Start up the kthreads. */
- VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task");
- writer_task = kthread_create(rcu_torture_writer, NULL,
- "rcu_torture_writer");
- if (IS_ERR(writer_task)) {
- firsterr = PTR_ERR(writer_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create writer");
- writer_task = NULL;
+ firsterr = torture_create_kthread(rcu_torture_writer, NULL,
+ writer_task);
+ if (firsterr)
goto unwind;
- }
- wake_up_process(writer_task);
fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
GFP_KERNEL);
if (fakewriter_tasks == NULL) {
- VERBOSE_PRINTK_ERRSTRING("out of memory");
+ VERBOSE_TOROUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nfakewriters; i++) {
- VERBOSE_PRINTK_STRING("Creating rcu_torture_fakewriter task");
- fakewriter_tasks[i] = kthread_run(rcu_torture_fakewriter, NULL,
- "rcu_torture_fakewriter");
- if (IS_ERR(fakewriter_tasks[i])) {
- firsterr = PTR_ERR(fakewriter_tasks[i]);
- VERBOSE_PRINTK_ERRSTRING("Failed to create fakewriter");
- fakewriter_tasks[i] = NULL;
+ firsterr = torture_create_kthread(rcu_torture_fakewriter,
+ NULL, fakewriter_tasks[i]);
+ if (firsterr)
goto unwind;
- }
}
reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]),
GFP_KERNEL);
if (reader_tasks == NULL) {
- VERBOSE_PRINTK_ERRSTRING("out of memory");
+ VERBOSE_TOROUT_ERRSTRING("out of memory");
firsterr = -ENOMEM;
goto unwind;
}
for (i = 0; i < nrealreaders; i++) {
- VERBOSE_PRINTK_STRING("Creating rcu_torture_reader task");
- reader_tasks[i] = kthread_run(rcu_torture_reader, NULL,
- "rcu_torture_reader");
- if (IS_ERR(reader_tasks[i])) {
- firsterr = PTR_ERR(reader_tasks[i]);
- VERBOSE_PRINTK_ERRSTRING("Failed to create reader");
- reader_tasks[i] = NULL;
+ firsterr = torture_create_kthread(rcu_torture_reader, NULL,
+ reader_tasks[i]);
+ if (firsterr)
goto unwind;
- }
}
if (stat_interval > 0) {
- VERBOSE_PRINTK_STRING("Creating rcu_torture_stats task");
- stats_task = kthread_run(rcu_torture_stats, NULL,
- "rcu_torture_stats");
- if (IS_ERR(stats_task)) {
- firsterr = PTR_ERR(stats_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create stats");
- stats_task = NULL;
+ firsterr = torture_create_kthread(rcu_torture_stats, NULL,
+ stats_task);
+ if (firsterr)
goto unwind;
- }
}
if (test_no_idle_hz) {
- rcu_idle_cpu = num_online_cpus() - 1;
-
- if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
- firsterr = -ENOMEM;
- VERBOSE_PRINTK_ERRSTRING("Failed to alloc mask");
+ firsterr = torture_shuffle_init(shuffle_interval * HZ);
+ if (firsterr)
goto unwind;
- }
-
- /* Create the shuffler thread */
- shuffler_task = kthread_run(rcu_torture_shuffle, NULL,
- "rcu_torture_shuffle");
- if (IS_ERR(shuffler_task)) {
- free_cpumask_var(shuffle_tmp_mask);
- firsterr = PTR_ERR(shuffler_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler");
- shuffler_task = NULL;
- goto unwind;
- }
}
if (stutter < 0)
stutter = 0;
if (stutter) {
- /* Create the stutter thread */
- stutter_task = kthread_run(rcu_torture_stutter, NULL,
- "rcu_torture_stutter");
- if (IS_ERR(stutter_task)) {
- firsterr = PTR_ERR(stutter_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
- stutter_task = NULL;
+ firsterr = torture_stutter_init(stutter * HZ);
+ if (firsterr)
goto unwind;
- }
}
if (fqs_duration < 0)
fqs_duration = 0;
if (fqs_duration) {
- /* Create the stutter thread */
- fqs_task = kthread_run(rcu_torture_fqs, NULL,
- "rcu_torture_fqs");
- if (IS_ERR(fqs_task)) {
- firsterr = PTR_ERR(fqs_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create fqs");
- fqs_task = NULL;
+ /* Create the fqs thread */
+ torture_create_kthread(rcu_torture_fqs, NULL, fqs_task);
+ if (firsterr)
goto unwind;
- }
}
if (test_boost_interval < 1)
test_boost_interval = 1;
@@ -2094,49 +1549,31 @@ rcu_torture_init(void)
for_each_possible_cpu(i) {
if (cpu_is_offline(i))
continue; /* Heuristic: CPU can go offline. */
- retval = rcutorture_booster_init(i);
- if (retval < 0) {
- firsterr = retval;
+ firsterr = rcutorture_booster_init(i);
+ if (firsterr)
goto unwind;
- }
}
}
- if (shutdown_secs > 0) {
- shutdown_time = jiffies + shutdown_secs * HZ;
- shutdown_task = kthread_create(rcu_torture_shutdown, NULL,
- "rcu_torture_shutdown");
- if (IS_ERR(shutdown_task)) {
- firsterr = PTR_ERR(shutdown_task);
- VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown");
- shutdown_task = NULL;
- goto unwind;
- }
- wake_up_process(shutdown_task);
- }
- i = rcu_torture_onoff_init();
- if (i != 0) {
- firsterr = i;
+ firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
+ if (firsterr)
goto unwind;
- }
- register_reboot_notifier(&rcutorture_shutdown_nb);
- i = rcu_torture_stall_init();
- if (i != 0) {
- firsterr = i;
+ firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+ if (firsterr)
goto unwind;
- }
- retval = rcu_torture_barrier_init();
- if (retval != 0) {
- firsterr = retval;
+ firsterr = rcu_torture_stall_init();
+ if (firsterr)
+ goto unwind;
+ firsterr = rcu_torture_barrier_init();
+ if (firsterr)
goto unwind;
- }
if (object_debug)
rcu_test_debug_objects();
rcutorture_record_test_transition();
- mutex_unlock(&fullstop_mutex);
+ torture_init_end();
return 0;
unwind:
- mutex_unlock(&fullstop_mutex);
+ torture_init_end();
rcu_torture_cleanup();
return firsterr;
}
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 01d5ccb8bfe3..c639556f3fa0 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (C) IBM Corporation, 2006
* Copyright (C) Fujitsu, 2012
@@ -36,8 +36,6 @@
#include <linux/delay.h>
#include <linux/srcu.h>
-#include <trace/events/rcu.h>
-
#include "rcu.h"
/*
@@ -363,6 +361,29 @@ static void srcu_flip(struct srcu_struct *sp)
/*
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section. On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu(). It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
*/
void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
void (*func)(struct rcu_head *head))
@@ -375,7 +396,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
rcu_batch_queue(&sp->batch_queue, head);
if (!sp->running) {
sp->running = true;
- schedule_delayed_work(&sp->work, 0);
+ queue_delayed_work(system_power_efficient_wq, &sp->work, 0);
}
spin_unlock_irqrestore(&sp->queue_lock, flags);
}
@@ -459,7 +480,30 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
* Note that it is illegal to call synchronize_srcu() from the corresponding
* SRCU read-side critical section; doing so will result in deadlock.
* However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu(). In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section. Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu(). This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
*/
void synchronize_srcu(struct srcu_struct *sp)
{
@@ -476,12 +520,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
* Wait for an SRCU grace period to elapse, but be more aggressive about
* spinning rather than blocking when waiting.
*
- * Note that it is also illegal to call synchronize_srcu_expedited()
- * from the corresponding SRCU read-side critical section;
- * doing so will result in deadlock. However, it is perfectly legal
- * to call synchronize_srcu_expedited() on one srcu_struct from some
- * other srcu_struct's read-side critical section, as long as
- * the resulting graph of srcu_structs is acyclic.
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
*/
void synchronize_srcu_expedited(struct srcu_struct *sp)
{
@@ -491,6 +531,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
/**
* srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
*/
void srcu_barrier(struct srcu_struct *sp)
{
@@ -631,7 +672,8 @@ static void srcu_reschedule(struct srcu_struct *sp)
}
if (pending)
- schedule_delayed_work(&sp->work, SRCU_INTERVAL);
+ queue_delayed_work(system_power_efficient_wq,
+ &sp->work, SRCU_INTERVAL);
}
/*
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 1254f312d024..d9efcc13008c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
@@ -37,10 +37,6 @@
#include <linux/prefetch.h>
#include <linux/ftrace_event.h>
-#ifdef CONFIG_RCU_TRACE
-#include <trace/events/rcu.h>
-#endif /* #else #ifdef CONFIG_RCU_TRACE */
-
#include "rcu.h"
/* Forward declarations for tiny_plugin.h. */
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 280d06cae352..431528520562 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -14,8 +14,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright (c) 2010 Linaro
*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd081987a8ec..0c47e300210a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
@@ -58,8 +58,6 @@
#include <linux/suspend.h>
#include "tree.h"
-#include <trace/events/rcu.h>
-
#include "rcu.h"
MODULE_ALIAS("rcutree");
@@ -369,6 +367,9 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
bool user)
{
+ struct rcu_state *rsp;
+ struct rcu_data *rdp;
+
trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
if (!user && !is_idle_task(current)) {
struct task_struct *idle __maybe_unused =
@@ -380,6 +381,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
+ for_each_rcu_flavor(rsp) {
+ rdp = this_cpu_ptr(rsp->rda);
+ do_nocb_deferred_wakeup(rdp);
+ }
rcu_prepare_for_idle(smp_processor_id());
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic_inc(); /* See above. */
@@ -411,11 +416,12 @@ static void rcu_eqs_enter(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
- if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+ if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
rdtp->dynticks_nesting = 0;
- else
+ rcu_eqs_enter_common(rdtp, oldval, user);
+ } else {
rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- rcu_eqs_enter_common(rdtp, oldval, user);
+ }
}
/**
@@ -533,11 +539,12 @@ static void rcu_eqs_exit(bool user)
rdtp = this_cpu_ptr(&rcu_dynticks);
oldval = rdtp->dynticks_nesting;
WARN_ON_ONCE(oldval < 0);
- if (oldval & DYNTICK_TASK_NEST_MASK)
+ if (oldval & DYNTICK_TASK_NEST_MASK) {
rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
- else
+ } else {
rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
- rcu_eqs_exit_common(rdtp, oldval, user);
+ rcu_eqs_exit_common(rdtp, oldval, user);
+ }
}
/**
@@ -716,7 +723,7 @@ bool rcu_lockdep_current_cpu_online(void)
bool ret;
if (in_nmi())
- return 1;
+ return true;
preempt_disable();
rdp = this_cpu_ptr(&rcu_sched_data);
rnp = rdp->mynode;
@@ -755,6 +762,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
}
/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
+/*
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
@@ -812,16 +825,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
*/
rcu_kick_nohz_cpu(rdp->cpu);
+ /*
+ * Alternatively, the CPU might be running in the kernel
+ * for an extended period of time without a quiescent state.
+ * Attempt to force the CPU through the scheduler to gain the
+ * needed quiescent state, but only if the grace period has gone
+ * on for an uncommonly long time. If there are many stuck CPUs,
+ * we will beat on the first one until it gets unstuck, then move
+ * to the next. Only do this for the primary flavor of RCU.
+ */
+ if (rdp->rsp == rcu_state &&
+ ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+ rdp->rsp->jiffies_resched += 5;
+ resched_cpu(rdp->cpu);
+ }
+
return 0;
}
static void record_gp_stall_check_time(struct rcu_state *rsp)
{
- unsigned long j = ACCESS_ONCE(jiffies);
+ unsigned long j = jiffies;
+ unsigned long j1;
rsp->gp_start = j;
smp_wmb(); /* Record start time before stall time. */
- rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
+ j1 = rcu_jiffies_till_stall_check();
+ rsp->jiffies_stall = j + j1;
+ rsp->jiffies_resched = j + j1 / 2;
}
/*
@@ -972,7 +1003,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
return;
- j = ACCESS_ONCE(jiffies);
+ j = jiffies;
/*
* Lots of memory barriers to reject false positives.
@@ -1133,8 +1164,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
* hold it, acquire the root rcu_node structure's lock in order to
* start one (if needed).
*/
- if (rnp != rnp_root)
+ if (rnp != rnp_root) {
raw_spin_lock(&rnp_root->lock);
+ smp_mb__after_unlock_lock();
+ }
/*
* Get a new grace-period number. If there really is no grace
@@ -1354,6 +1387,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
local_irq_restore(flags);
return;
}
+ smp_mb__after_unlock_lock();
__note_gp_changes(rsp, rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
@@ -1368,6 +1402,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
rcu_bind_gp_kthread();
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
if (rsp->gp_flags == 0) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq(&rnp->lock);
@@ -1386,13 +1421,14 @@ static int rcu_gp_init(struct rcu_state *rsp)
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time(rsp);
- smp_wmb(); /* Record GP times before starting GP. */
- rsp->gpnum++;
+ /* Record GP times before starting GP, hence smp_store_release(). */
+ smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
raw_spin_unlock_irq(&rnp->lock);
/* Exclude any concurrent CPU-hotplug operations. */
mutex_lock(&rsp->onoff_mutex);
+ smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */
/*
* Set the quiescent-state-needed bits in all the rcu_node
@@ -1409,6 +1445,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rdp = this_cpu_ptr(rsp->rda);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1500,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
/* Clear flag to prevent immediate re-entry. */
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
raw_spin_unlock_irq(&rnp->lock);
}
@@ -1480,6 +1518,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
struct rcu_node *rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
if (gp_duration > rsp->gp_max)
rsp->gp_max = gp_duration;
@@ -1505,19 +1544,23 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
*/
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock();
ACCESS_ONCE(rnp->completed) = rsp->gpnum;
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
__note_gp_changes(rsp, rnp, rdp);
+ /* smp_mb() provided by prior unlock-lock pair. */
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched();
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
+ smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
rcu_nocb_gp_set(rnp, nocb);
- rsp->completed = rsp->gpnum; /* Declare grace period done. */
+ /* Declare grace period done. */
+ ACCESS_ONCE(rsp->completed) = rsp->gpnum;
trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
rsp->fqs_state = RCU_GP_IDLE;
rdp = this_cpu_ptr(rsp->rda);
@@ -1553,6 +1596,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
wait_event_interruptible(rsp->gp_wq,
ACCESS_ONCE(rsp->gp_flags) &
RCU_GP_FLAG_INIT);
+ /* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
cond_resched();
@@ -1582,6 +1626,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
(!ACCESS_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp)),
j);
+ /* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!ACCESS_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
@@ -1749,6 +1794,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
WARN_ON_ONCE(rnp_c->qsmask);
}
@@ -1778,6 +1824,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
rnp->completed == rnp->gpnum) {
@@ -1901,13 +1948,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
* Adopt the RCU callbacks from the specified rcu_state structure's
* orphanage. The caller must hold the ->orphan_lock.
*/
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
{
int i;
struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
- if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+ if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
return;
/* Do the accounting first. */
@@ -1986,12 +2033,13 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
- rcu_adopt_orphan_cbs(rsp);
+ rcu_adopt_orphan_cbs(rsp, flags);
/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
mask = rdp->grpmask; /* rnp->grplo is constant. */
do {
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rnp->qsmaskinit &= ~mask;
if (rnp->qsmaskinit != 0) {
if (rnp != rdp->mynode)
@@ -2202,6 +2250,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
cond_resched();
mask = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (!rcu_gp_in_progress(rsp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
@@ -2231,6 +2280,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
rnp = rcu_get_root(rsp);
if (rnp->qsmask == 0) {
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
}
}
@@ -2254,7 +2304,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
if (ret) {
- rsp->n_force_qs_lh++;
+ ACCESS_ONCE(rsp->n_force_qs_lh)++;
return;
}
rnp_old = rnp;
@@ -2263,9 +2313,10 @@ static void force_quiescent_state(struct rcu_state *rsp)
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave(&rnp_old->lock, flags);
+ smp_mb__after_unlock_lock();
raw_spin_unlock(&rnp_old->fqslock);
if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
- rsp->n_force_qs_lh++;
+ ACCESS_ONCE(rsp->n_force_qs_lh)++;
raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
return; /* Someone beat us to it. */
}
@@ -2303,6 +2354,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
/* If there are callbacks ready, invoke them. */
if (cpu_has_callbacks_ready_to_invoke(rdp))
invoke_rcu_callbacks(rsp, rdp);
+
+ /* Do any needed deferred wakeups of rcuo kthreads. */
+ do_nocb_deferred_wakeup(rdp);
}
/*
@@ -2378,6 +2432,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
struct rcu_node *rnp_root = rcu_get_root(rsp);
raw_spin_lock(&rnp_root->lock);
+ smp_mb__after_unlock_lock();
rcu_start_gp(rsp);
raw_spin_unlock(&rnp_root->lock);
} else {
@@ -2437,7 +2492,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
if (cpu != -1)
rdp = per_cpu_ptr(rsp->rda, cpu);
- offline = !__call_rcu_nocb(rdp, head, lazy);
+ offline = !__call_rcu_nocb(rdp, head, lazy, flags);
WARN_ON_ONCE(offline);
/* _call_rcu() is illegal on offline CPU; leak the callback. */
local_irq_restore(flags);
@@ -2584,6 +2639,58 @@ void synchronize_rcu_bh(void)
}
EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+/**
+ * get_state_synchronize_rcu - Snapshot current RCU state
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * to determine whether or not a full grace period has elapsed in the
+ * meantime.
+ */
+unsigned long get_state_synchronize_rcu(void)
+{
+ /*
+ * Any prior manipulation of RCU-protected data must happen
+ * before the load from ->gpnum.
+ */
+ smp_mb(); /* ^^^ */
+
+ /*
+ * Make sure this load happens before the purportedly
+ * time-consuming work between get_state_synchronize_rcu()
+ * and cond_synchronize_rcu().
+ */
+ return smp_load_acquire(&rcu_state->gpnum);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
+
+/**
+ * cond_synchronize_rcu - Conditionally wait for an RCU grace period
+ *
+ * @oldstate: return value from earlier call to get_state_synchronize_rcu()
+ *
+ * If a full RCU grace period has elapsed since the earlier call to
+ * get_state_synchronize_rcu(), just return. Otherwise, invoke
+ * synchronize_rcu() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account. But
+ * counter wrap is harmless. If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for one additional grace period should be just fine.
+ */
+void cond_synchronize_rcu(unsigned long oldstate)
+{
+ unsigned long newstate;
+
+ /*
+ * Ensure that this load happens before any RCU-destructive
+ * actions the caller might carry out after we return.
+ */
+ newstate = smp_load_acquire(&rcu_state->completed);
+ if (ULONG_CMP_GE(oldstate, newstate))
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
+
static int synchronize_sched_expedited_cpu_stop(void *data)
{
/*
@@ -2757,6 +2864,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rsp, rdp);
+ /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
+ if (rcu_nohz_full_cpu(rsp))
+ return 0;
+
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
rdp->qs_pending && !rdp->passed_quiesce) {
@@ -2790,6 +2901,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
return 1;
}
+ /* Does this CPU need a deferred NOCB wakeup? */
+ if (rcu_nocb_need_deferred_wakeup(rdp)) {
+ rdp->n_rp_nocb_defer_wakeup++;
+ return 1;
+ }
+
/* nothing to do */
rdp->n_rp_need_nothing++;
return 0;
@@ -2815,7 +2932,7 @@ static int rcu_pending(int cpu)
* non-NULL, store an indication of whether all callbacks are lazy.
* (If there are no callbacks, all of them are deemed to be lazy.)
*/
-static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
+static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
{
bool al = true;
bool hc = false;
@@ -3214,9 +3331,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- for (i = rcu_num_lvls - 1; i > 0; i--)
+ rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+ for (i = rcu_num_lvls - 2; i >= 0; i--)
rsp->levelspread[i] = CONFIG_RCU_FANOUT;
- rsp->levelspread[0] = rcu_fanout_leaf;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
@@ -3346,6 +3463,8 @@ static void __init rcu_init_geometry(void)
if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
+ pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
+ rcu_fanout_leaf, nr_cpu_ids);
/*
* Compute number of nodes that can be handled an rcu_node tree
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 52be957c9fe2..75dc3c39a02a 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -13,8 +13,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
@@ -317,6 +317,7 @@ struct rcu_data {
unsigned long n_rp_cpu_needs_gp;
unsigned long n_rp_gp_completed;
unsigned long n_rp_gp_started;
+ unsigned long n_rp_nocb_defer_wakeup;
unsigned long n_rp_need_nothing;
/* 6) _rcu_barrier() and OOM callbacks. */
@@ -335,6 +336,7 @@ struct rcu_data {
int nocb_p_count_lazy; /* (approximate). */
wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */
struct task_struct *nocb_kthread;
+ bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
/* 8) RCU CPU stall data. */
@@ -453,6 +455,8 @@ struct rcu_state {
/* but in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
+ unsigned long jiffies_resched; /* Time at which to resched */
+ /* a reluctant CPU. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
const char *name; /* Name of structure. */
@@ -548,9 +552,12 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy);
+ bool lazy, unsigned long flags);
static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp);
+ struct rcu_data *rdp,
+ unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
static void rcu_kick_nohz_cpu(int cpu);
@@ -564,6 +571,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
unsigned long maxj);
static void rcu_bind_gp_kthread(void);
static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
#endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 08a765232432..962d1d589929 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -14,8 +14,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright Red Hat, 2009
* Copyright IBM Corporation, 2009
@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
t->rcu_blocked_node = rnp;
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
}
@@ -361,10 +363,14 @@ void rcu_read_unlock_special(struct task_struct *t)
special = t->rcu_read_unlock_special;
if (special & RCU_READ_UNLOCK_NEED_QS) {
rcu_preempt_qs(smp_processor_id());
+ if (!t->rcu_read_unlock_special) {
+ local_irq_restore(flags);
+ return;
+ }
}
- /* Hardware IRQ handlers cannot block. */
- if (in_irq() || in_serving_softirq()) {
+ /* Hardware IRQ handlers cannot block, complain if they get here. */
+ if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
local_irq_restore(flags);
return;
}
@@ -381,6 +387,7 @@ void rcu_read_unlock_special(struct task_struct *t)
for (;;) {
rnp = t->rcu_blocked_node;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
if (rnp == t->rcu_blocked_node)
break;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +612,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
while (!list_empty(lp)) {
t = list_entry(lp->next, typeof(*t), rcu_node_entry);
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
list_del(&t->rcu_node_entry);
t->rcu_blocked_node = rnp_root;
list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +637,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
* in this case.
*/
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
if (rnp_root->boost_tasks != NULL &&
rnp_root->boost_tasks != rnp_root->gp_tasks &&
rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +781,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
for (;;) {
if (!sync_rcu_preempt_exp_done(rnp)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -779,14 +789,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- if (wake)
+ if (wake) {
+ smp_mb(); /* EGP done before wake_up(). */
wake_up(&sync_rcu_preempt_exp_wq);
+ }
break;
}
mask = rnp->grpmask;
raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
rnp = rnp->parent;
raw_spin_lock(&rnp->lock); /* irqs already disabled */
+ smp_mb__after_unlock_lock();
rnp->expmask &= ~mask;
}
}
@@ -806,6 +819,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
int must_wait = 0;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
if (list_empty(&rnp->blkd_tasks)) {
raw_spin_unlock_irqrestore(&rnp->lock, flags);
} else {
@@ -886,6 +900,7 @@ void synchronize_rcu_expedited(void)
/* Initialize ->expmask for all non-leaf rcu_node structures. */
rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rnp->expmask = rnp->qsmaskinit;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
@@ -1191,6 +1206,7 @@ static int rcu_boost(struct rcu_node *rnp)
return 0; /* Nothing left to boost. */
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
/*
* Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1393,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
if (IS_ERR(t))
return PTR_ERR(t);
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
rnp->boost_kthread_task = t;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
sp.sched_priority = RCU_BOOST_PRIO;
@@ -1569,11 +1586,13 @@ static void rcu_prepare_kthreads(int cpu)
* Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
* any flavor of RCU.
*/
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
return rcu_cpu_has_callbacks(cpu, NULL);
}
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
@@ -1639,7 +1658,7 @@ extern int tick_nohz_active;
* only if it has been awhile since the last time we did so. Afterwards,
* if there are any callbacks ready for immediate invocation, return true.
*/
-static bool rcu_try_advance_all_cbs(void)
+static bool __maybe_unused rcu_try_advance_all_cbs(void)
{
bool cbs_ready = false;
struct rcu_data *rdp;
@@ -1679,6 +1698,7 @@ static bool rcu_try_advance_all_cbs(void)
*
* The caller must have disabled interrupts.
*/
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
int rcu_needs_cpu(int cpu, unsigned long *dj)
{
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
@@ -1709,6 +1729,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
}
return 0;
}
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Prepare a CPU for idle from an RCU perspective. The first major task
@@ -1722,6 +1743,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
*/
static void rcu_prepare_for_idle(int cpu)
{
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
struct rcu_data *rdp;
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
struct rcu_node *rnp;
@@ -1769,9 +1791,11 @@ static void rcu_prepare_for_idle(int cpu)
continue;
rnp = rdp->mynode;
raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ smp_mb__after_unlock_lock();
rcu_accelerate_cbs(rsp, rnp, rdp);
raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
}
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
@@ -1781,11 +1805,12 @@ static void rcu_prepare_for_idle(int cpu)
*/
static void rcu_cleanup_after_idle(int cpu)
{
-
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
if (rcu_is_nocb_cpu(cpu))
return;
if (rcu_try_advance_all_cbs())
invoke_rcu_core();
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
}
/*
@@ -1852,6 +1877,7 @@ static int rcu_oom_notify(struct notifier_block *self,
/* Wait for callbacks from earlier instance to complete. */
wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+ smp_mb(); /* Ensure callback reuse happens after callback invocation. */
/*
* Prevent premature wakeup: ensure that all increments happen
@@ -2082,6 +2108,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
init_waitqueue_head(&rnp->nocb_gp_wq[1]);
}
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
/* Is the specified CPU a no-CPUs CPU? */
bool rcu_is_nocb_cpu(int cpu)
{
@@ -2089,6 +2116,7 @@ bool rcu_is_nocb_cpu(int cpu)
return cpumask_test_cpu(cpu, rcu_nocb_mask);
return false;
}
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
/*
* Enqueue the specified string of rcu_head structures onto the specified
@@ -2101,7 +2129,8 @@ bool rcu_is_nocb_cpu(int cpu)
static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
struct rcu_head *rhp,
struct rcu_head **rhtp,
- int rhcount, int rhcount_lazy)
+ int rhcount, int rhcount_lazy,
+ unsigned long flags)
{
int len;
struct rcu_head **old_rhpp;
@@ -2122,9 +2151,16 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
}
len = atomic_long_read(&rdp->nocb_q_count);
if (old_rhpp == &rdp->nocb_head) {
- wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+ if (!irqs_disabled_flags(flags)) {
+ wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeEmpty"));
+ } else {
+ rdp->nocb_defer_wakeup = true;
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+ TPS("WakeEmptyIsDeferred"));
+ }
rdp->qlen_last_fqs_check = 0;
- trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
} else if (len > rdp->qlen_last_fqs_check + qhimark) {
wake_up_process(t); /* ... or if many callbacks queued. */
rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2145,12 +2181,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
* "rcuo" kthread can find it.
*/
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy)
+ bool lazy, unsigned long flags)
{
if (!rcu_is_nocb_cpu(rdp->cpu))
return 0;
- __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+ __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
if (__is_kfree_rcu_offset((unsigned long)rhp->func))
trace_rcu_kfree_callback(rdp->rsp->name, rhp,
(unsigned long)rhp->func,
@@ -2168,7 +2204,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
* not a no-CBs CPU.
*/
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp)
+ struct rcu_data *rdp,
+ unsigned long flags)
{
long ql = rsp->qlen;
long qll = rsp->qlen_lazy;
@@ -2182,14 +2219,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
/* First, enqueue the donelist, if any. This preserves CB ordering. */
if (rsp->orphan_donelist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
- rsp->orphan_donetail, ql, qll);
+ rsp->orphan_donetail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_donelist = NULL;
rsp->orphan_donetail = &rsp->orphan_donelist;
}
if (rsp->orphan_nxtlist != NULL) {
__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
- rsp->orphan_nxttail, ql, qll);
+ rsp->orphan_nxttail, ql, qll, flags);
ql = qll = 0;
rsp->orphan_nxtlist = NULL;
rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2209,6 +2246,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
struct rcu_node *rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ smp_mb__after_unlock_lock();
c = rcu_start_future_gp(rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -2250,6 +2288,7 @@ static int rcu_nocb_kthread(void *arg)
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("Sleep"));
wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+ /* Memory barrier provide by xchg() below. */
} else if (firsttime) {
firsttime = 0;
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
@@ -2310,6 +2349,22 @@ static int rcu_nocb_kthread(void *arg)
return 0;
}
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+ return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+ if (!rcu_nocb_need_deferred_wakeup(rdp))
+ return;
+ ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+ wake_up(&rdp->nocb_wq);
+ trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
/* Initialize per-rcu_data variables for no-CBs CPUs. */
static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
@@ -2365,13 +2420,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
}
static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
- bool lazy)
+ bool lazy, unsigned long flags)
{
return 0;
}
static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
- struct rcu_data *rdp)
+ struct rcu_data *rdp,
+ unsigned long flags)
{
return 0;
}
@@ -2380,6 +2436,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
{
}
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+ return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
{
}
@@ -2829,3 +2894,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
}
#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+/*
+ * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
+ * grace-period kthread will do force_quiescent_state() processing?
+ * The idea is to avoid waking up RCU core processing on such a
+ * CPU unless the grace period has extended for too long.
+ *
+ * This code relies on the fact that all NO_HZ_FULL CPUs are also
+ * CONFIG_RCU_NOCB_CPU CPUs.
+ */
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ if (tick_nohz_full_cpu(smp_processor_id()) &&
+ (!rcu_gp_in_progress(rsp) ||
+ ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
+ return 1;
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+ return 0;
+}
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3596797b7e46..5cdc62e1beeb 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2008
*
@@ -273,7 +273,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen);
+ ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
rdp->n_rp_report_qs,
rdp->n_rp_cb_ready,
rdp->n_rp_cpu_needs_gp);
- seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+ seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
rdp->n_rp_gp_completed,
rdp->n_rp_gp_started,
+ rdp->n_rp_nocb_defer_wakeup,
rdp->n_rp_need_nothing);
}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6cb3dff89e2b..4c0a9b0af469 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -12,8 +12,8 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
*
* Copyright IBM Corporation, 2001
*
@@ -49,7 +49,6 @@
#include <linux/module.h>
#define CREATE_TRACE_POINTS
-#include <trace/events/rcu.h>
#include "rcu.h"
@@ -128,6 +127,11 @@ struct lockdep_map rcu_sched_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
+static struct lock_class_key rcu_callback_key;
+struct lockdep_map rcu_callback_map =
+ STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
+EXPORT_SYMBOL_GPL(rcu_callback_map);
+
int notrace debug_lockdep_rcu_enabled(void)
{
return rcu_scheduler_active && debug_locks &&
@@ -195,17 +199,6 @@ void wait_rcu_gp(call_rcu_func_t crf)
}
EXPORT_SYMBOL_GPL(wait_rcu_gp);
-#ifdef CONFIG_PROVE_RCU
-/*
- * wrapper function to avoid #include problems.
- */
-int rcu_my_thread_group_empty(void)
-{
- return thread_group_empty(current);
-}
-EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
-#endif /* #ifdef CONFIG_PROVE_RCU */
-
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
static inline void debug_init_rcu_head(struct rcu_head *head)
{
diff --git a/kernel/relay.c b/kernel/relay.c
index 5001c9887db1..52d6a6f56261 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -227,7 +227,7 @@ static void relay_destroy_buf(struct rchan_buf *buf)
* relay_remove_buf - remove a channel buffer
* @kref: target kernel reference that contains the relay buffer
*
- * Removes the file from the fileystem, which also frees the
+ * Removes the file from the filesystem, which also frees the
* rchan_buf_struct and the channel buffer. Should only be called from
* kref_put().
*/
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 4aa8a305aede..51dbac6a3633 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -22,8 +22,18 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
counter->parent = parent;
}
-int res_counter_charge_locked(struct res_counter *counter, unsigned long val,
- bool force)
+static u64 res_counter_uncharge_locked(struct res_counter *counter,
+ unsigned long val)
+{
+ if (WARN_ON(counter->usage < val))
+ val = counter->usage;
+
+ counter->usage -= val;
+ return counter->usage;
+}
+
+static int res_counter_charge_locked(struct res_counter *counter,
+ unsigned long val, bool force)
{
int ret = 0;
@@ -86,15 +96,6 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
return __res_counter_charge(counter, val, limit_fail_at, true);
}
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
-{
- if (WARN_ON(counter->usage < val))
- val = counter->usage;
-
- counter->usage -= val;
- return counter->usage;
-}
-
u64 res_counter_uncharge_until(struct res_counter *counter,
struct res_counter *top,
unsigned long val)
diff --git a/kernel/resource.c b/kernel/resource.c
index 3f285dce9347..8957d686e29b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -432,11 +432,6 @@ static void resource_clip(struct resource *res, resource_size_t min,
res->end = max;
}
-static bool resource_contains(struct resource *res1, struct resource *res2)
-{
- return res1->start <= res2->start && res1->end >= res2->end;
-}
-
/*
* Find empty slot in the resource tree with the given range and
* alignment constraints
@@ -471,10 +466,11 @@ static int __find_resource(struct resource *root, struct resource *old,
arch_remove_reservations(&tmp);
/* Check for overflow after ALIGN() */
- avail = *new;
avail.start = ALIGN(tmp.start, constraint->align);
avail.end = tmp.end;
+ avail.flags = new->flags & ~IORESOURCE_UNSET;
if (avail.start >= tmp.start) {
+ alloc.flags = avail.flags;
alloc.start = constraint->alignf(constraint->alignf_data, &avail,
size, constraint->align);
alloc.end = alloc.start + size - 1;
@@ -515,7 +511,7 @@ static int find_resource(struct resource *root, struct resource *new,
* @newsize: new size of the resource descriptor
* @constraint: the size and alignment constraints to be met.
*/
-int reallocate_resource(struct resource *root, struct resource *old,
+static int reallocate_resource(struct resource *root, struct resource *old,
resource_size_t newsize,
struct resource_constraint *constraint)
{
@@ -949,8 +945,8 @@ struct resource * __request_region(struct resource *parent,
res->name = name;
res->start = start;
res->end = start + n - 1;
- res->flags = IORESOURCE_BUSY;
- res->flags |= flags;
+ res->flags = resource_type(parent);
+ res->flags |= IORESOURCE_BUSY | flags;
write_lock(&resource_lock);
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7b621409cf15..ab32b7b0db5c 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,9 +11,10 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
-obj-y += wait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
+obj-y += wait.o completion.o idle.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 4a073539c58e..e73efba98301 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -203,7 +203,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
struct autogroup *ag;
int err;
- if (nice < -20 || nice > 19)
+ if (nice < MIN_NICE || nice > MAX_NICE)
return -EINVAL;
err = security_task_setnice(current, nice);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae1446461c..3ef6451e972e 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
* at 0 on boot (but people really shouldn't rely on that).
*
* cpu_clock(i) -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
* local_clock() -- is cpu_clock() on the current cpu.
*
+ * sched_clock_cpu(i)
+ *
* How:
*
* The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
* Furthermore, explicit sleep and wakeup hooks allow us to account for time
* that is otherwise invisible (TSC gets stopped).
*
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
*/
#include <linux/spinlock.h>
#include <linux/hardirq.h>
@@ -66,13 +58,16 @@
#include <linux/percpu.h>
#include <linux/ktime.h>
#include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
+#include <linux/compiler.h>
/*
* Scheduler clock - returns current time in nanosec units.
* This is default implementation.
* Architectures and sub-architectures can override this.
*/
-unsigned long long __attribute__((weak)) sched_clock(void)
+unsigned long long __weak sched_clock(void)
{
return (unsigned long long)(jiffies - INITIAL_JIFFIES)
* (NSEC_PER_SEC / HZ);
@@ -82,7 +77,52 @@ EXPORT_SYMBOL_GPL(sched_clock);
__read_mostly int sched_clock_running;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+static int __sched_clock_stable_early;
+
+int sched_clock_stable(void)
+{
+ return static_key_false(&__sched_clock_stable);
+}
+
+static void __set_sched_clock_stable(void)
+{
+ if (!sched_clock_stable())
+ static_key_slow_inc(&__sched_clock_stable);
+}
+
+void set_sched_clock_stable(void)
+{
+ __sched_clock_stable_early = 1;
+
+ smp_mb(); /* matches sched_clock_init() */
+
+ if (!sched_clock_running)
+ return;
+
+ __set_sched_clock_stable();
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+ /* XXX worry about clock continuity */
+ if (sched_clock_stable())
+ static_key_slow_dec(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+ __sched_clock_stable_early = 0;
+
+ smp_mb(); /* matches sched_clock_init() */
+
+ if (!sched_clock_running)
+ return;
+
+ schedule_work(&sched_clock_work);
+}
struct sched_clock_data {
u64 tick_raw;
@@ -116,6 +156,20 @@ void sched_clock_init(void)
}
sched_clock_running = 1;
+
+ /*
+ * Ensure that it is impossible to not do a static_key update.
+ *
+ * Either {set,clear}_sched_clock_stable() must see sched_clock_running
+ * and do the update, or we must see their __sched_clock_stable_early
+ * and do the update, or both.
+ */
+ smp_mb(); /* matches {set,clear}_sched_clock_stable() */
+
+ if (__sched_clock_stable_early)
+ __set_sched_clock_stable();
+ else
+ __clear_sched_clock_stable(NULL);
}
/*
@@ -242,20 +296,20 @@ u64 sched_clock_cpu(int cpu)
struct sched_clock_data *scd;
u64 clock;
- WARN_ON_ONCE(!irqs_disabled());
-
- if (sched_clock_stable)
+ if (sched_clock_stable())
return sched_clock();
if (unlikely(!sched_clock_running))
return 0ull;
+ preempt_disable_notrace();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
+ preempt_enable_notrace();
return clock;
}
@@ -265,7 +319,7 @@ void sched_clock_tick(void)
struct sched_clock_data *scd;
u64 now, now_gtod;
- if (sched_clock_stable)
+ if (sched_clock_stable())
return;
if (unlikely(!sched_clock_running))
@@ -316,14 +370,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
*/
u64 cpu_clock(int cpu)
{
- u64 clock;
- unsigned long flags;
-
- local_irq_save(flags);
- clock = sched_clock_cpu(cpu);
- local_irq_restore(flags);
+ if (!sched_clock_stable())
+ return sched_clock_cpu(cpu);
- return clock;
+ return sched_clock();
}
/*
@@ -335,14 +385,10 @@ u64 cpu_clock(int cpu)
*/
u64 local_clock(void)
{
- u64 clock;
- unsigned long flags;
+ if (!sched_clock_stable())
+ return sched_clock_cpu(raw_smp_processor_id());
- local_irq_save(flags);
- clock = sched_clock_cpu(smp_processor_id());
- local_irq_restore(flags);
-
- return clock;
+ return sched_clock();
}
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -362,12 +408,12 @@ u64 sched_clock_cpu(int cpu)
u64 cpu_clock(int cpu)
{
- return sched_clock_cpu(cpu);
+ return sched_clock();
}
u64 local_clock(void)
{
- return sched_clock_cpu(0);
+ return sched_clock();
}
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a88f4a485c5e..268a45ea238c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -73,6 +73,7 @@
#include <linux/init_task.h>
#include <linux/binfmts.h>
#include <linux/context_tracking.h>
+#include <linux/compiler.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
@@ -296,8 +297,6 @@ __read_mostly int scheduler_running;
*/
int sysctl_sched_rt_runtime = 950000;
-
-
/*
* __task_rq_lock - lock the rq @p resides on.
*/
@@ -434,7 +433,7 @@ void hrtick_start(struct rq *rq, u64 delay)
if (rq == this_rq()) {
__hrtick_restart(rq);
} else if (!rq->hrtick_csd_pending) {
- __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
+ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
rq->hrtick_csd_pending = 1;
}
}
@@ -557,12 +556,15 @@ void resched_cpu(int cpu)
* selecting an idle cpu will add more delays to the timers than intended
* (as that cpu's timer base may not be uptodate wrt jiffies etc).
*/
-int get_nohz_timer_target(void)
+int get_nohz_timer_target(int pinned)
{
int cpu = smp_processor_id();
int i;
struct sched_domain *sd;
+ if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+ return cpu;
+
rcu_read_lock();
for_each_domain(cpu, sd) {
for_each_cpu(i, sched_domain_span(sd)) {
@@ -825,19 +827,13 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
if (static_key_false((&paravirt_steal_rq_enabled))) {
- u64 st;
-
steal = paravirt_steal_clock(cpu_of(rq));
steal -= rq->prev_steal_time_rq;
if (unlikely(steal > delta))
steal = delta;
- st = steal_ticks(steal);
- steal = st * TICK_NSEC;
-
rq->prev_steal_time_rq += steal;
-
delta -= steal;
}
#endif
@@ -899,7 +895,9 @@ static inline int normal_prio(struct task_struct *p)
{
int prio;
- if (task_has_rt_policy(p))
+ if (task_has_dl_policy(p))
+ prio = MAX_DL_PRIO-1;
+ else if (task_has_rt_policy(p))
prio = MAX_RT_PRIO-1 - p->rt_priority;
else
prio = __normal_prio(p);
@@ -945,7 +943,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
if (prev_class->switched_from)
prev_class->switched_from(rq, p);
p->sched_class->switched_to(rq, p);
- } else if (oldprio != p->prio)
+ } else if (oldprio != p->prio || dl_task(p))
p->sched_class->prio_changed(rq, p, oldprio);
}
@@ -1108,6 +1106,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
goto out;
+ trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
out:
@@ -1499,8 +1498,7 @@ void scheduler_ipi(void)
* TIF_NEED_RESCHED remotely (for the first time) will also send
* this IPI.
*/
- if (tif_need_resched())
- set_preempt_need_resched();
+ preempt_fold_need_resched();
if (llist_empty(&this_rq()->wake_list)
&& !tick_nohz_full_cpu(smp_processor_id())
@@ -1717,6 +1715,13 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
+ RB_CLEAR_NODE(&p->dl.rb_node);
+ hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ p->dl.dl_runtime = p->dl.runtime = 0;
+ p->dl.dl_deadline = p->dl.deadline = 0;
+ p->dl.dl_period = 0;
+ p->dl.flags = 0;
+
INIT_LIST_HEAD(&p->rt.run_list);
#ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -1738,8 +1743,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
p->numa_scan_period = sysctl_numa_balancing_scan_delay;
p->numa_work.next = &p->numa_work;
- p->numa_faults = NULL;
- p->numa_faults_buffer = NULL;
+ p->numa_faults_memory = NULL;
+ p->numa_faults_buffer_memory = NULL;
+ p->last_task_numa_placement = 0;
+ p->last_sum_exec_runtime = 0;
INIT_LIST_HEAD(&p->numa_entry);
p->numa_group = NULL;
@@ -1763,12 +1770,34 @@ void set_numabalancing_state(bool enabled)
numabalancing_enabled = enabled;
}
#endif /* CONFIG_SCHED_DEBUG */
-#endif /* CONFIG_NUMA_BALANCING */
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_numa_balancing(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table t;
+ int err;
+ int state = numabalancing_enabled;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ t = *table;
+ t.data = &state;
+ err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+ if (err < 0)
+ return err;
+ if (write)
+ set_numabalancing_state(state);
+ return err;
+}
+#endif
+#endif
/*
* fork()/clone()-time setup:
*/
-void sched_fork(unsigned long clone_flags, struct task_struct *p)
+int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
int cpu = get_cpu();
@@ -1790,7 +1819,7 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
- if (task_has_rt_policy(p)) {
+ if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->policy = SCHED_NORMAL;
p->static_prio = NICE_TO_PRIO(0);
p->rt_priority = 0;
@@ -1807,8 +1836,14 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
p->sched_reset_on_fork = 0;
}
- if (!rt_prio(p->prio))
+ if (dl_prio(p->prio)) {
+ put_cpu();
+ return -EAGAIN;
+ } else if (rt_prio(p->prio)) {
+ p->sched_class = &rt_sched_class;
+ } else {
p->sched_class = &fair_sched_class;
+ }
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
@@ -1834,12 +1869,125 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
+ RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
put_cpu();
+ return 0;
+}
+
+unsigned long to_ratio(u64 period, u64 runtime)
+{
+ if (runtime == RUNTIME_INF)
+ return 1ULL << 20;
+
+ /*
+ * Doing this here saves a lot of checks in all
+ * the calling paths, and returning zero seems
+ * safe for them anyway.
+ */
+ if (period == 0)
+ return 0;
+
+ return div64_u64(runtime << 20, period);
+}
+
+#ifdef CONFIG_SMP
+inline struct dl_bw *dl_bw_of(int i)
+{
+ return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+ struct root_domain *rd = cpu_rq(i)->rd;
+ int cpus = 0;
+
+ for_each_cpu_and(i, rd->span, cpu_active_mask)
+ cpus++;
+
+ return cpus;
+}
+#else
+inline struct dl_bw *dl_bw_of(int i)
+{
+ return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+ return 1;
+}
+#endif
+
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+ dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+ dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+ return dl_b->bw != -1 &&
+ dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
}
/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+static int dl_overflow(struct task_struct *p, int policy,
+ const struct sched_attr *attr)
+{
+
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+ u64 period = attr->sched_period ?: attr->sched_deadline;
+ u64 runtime = attr->sched_runtime;
+ u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+ int cpus, err = -1;
+
+ if (new_bw == p->dl.dl_bw)
+ return 0;
+
+ /*
+ * Either if a task, enters, leave, or stays -deadline but changes
+ * its parameters, we may need to update accordingly the total
+ * allocated bandwidth of the container.
+ */
+ raw_spin_lock(&dl_b->lock);
+ cpus = dl_bw_cpus(task_cpu(p));
+ if (dl_policy(policy) && !task_has_dl_policy(p) &&
+ !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+ __dl_add(dl_b, new_bw);
+ err = 0;
+ } else if (dl_policy(policy) && task_has_dl_policy(p) &&
+ !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+ __dl_clear(dl_b, p->dl.dl_bw);
+ __dl_add(dl_b, new_bw);
+ err = 0;
+ } else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+ __dl_clear(dl_b, p->dl.dl_bw);
+ err = 0;
+ }
+ raw_spin_unlock(&dl_b->lock);
+
+ return err;
+}
+
+extern void init_dl_bw(struct dl_bw *dl_b);
+
+/*
* wake_up_new_task - wake up a newly created task for the first time.
*
* This function will do some initial scheduler statistics housekeeping
@@ -2001,7 +2149,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
if (mm)
mmdrop(mm);
if (unlikely(prev_state == TASK_DEAD)) {
- task_numa_free(prev);
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
/*
* Remove function-return probe instances associated with this
@@ -2016,13 +2165,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
#ifdef CONFIG_SMP
-/* assumes rq->lock is held */
-static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
-{
- if (prev->sched_class->pre_schedule)
- prev->sched_class->pre_schedule(rq, prev);
-}
-
/* rq->lock is NOT held, but preemption is disabled */
static inline void post_schedule(struct rq *rq)
{
@@ -2040,10 +2182,6 @@ static inline void post_schedule(struct rq *rq)
#else
-static inline void pre_schedule(struct rq *rq, struct task_struct *p)
-{
-}
-
static inline void post_schedule(struct rq *rq)
{
}
@@ -2296,7 +2434,7 @@ void scheduler_tick(void)
#ifdef CONFIG_SMP
rq->idle_balance = idle_cpu(cpu);
- trigger_load_balance(rq, cpu);
+ trigger_load_balance(rq);
#endif
rq_last_tick_reset(rq);
}
@@ -2325,7 +2463,7 @@ u64 scheduler_tick_max_deferment(void)
if (time_before_eq(next, now))
return 0;
- return jiffies_to_usecs(next - now) * NSEC_PER_USEC;
+ return jiffies_to_nsecs(next - now);
}
#endif
@@ -2359,8 +2497,13 @@ void __kprobes preempt_count_add(int val)
DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
PREEMPT_MASK - 10);
#endif
- if (preempt_count() == val)
- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+ if (preempt_count() == val) {
+ unsigned long ip = get_parent_ip(CALLER_ADDR1);
+#ifdef CONFIG_DEBUG_PREEMPT
+ current->preempt_disable_ip = ip;
+#endif
+ trace_preempt_off(CALLER_ADDR0, ip);
+ }
}
EXPORT_SYMBOL(preempt_count_add);
@@ -2403,6 +2546,13 @@ static noinline void __schedule_bug(struct task_struct *prev)
print_modules();
if (irqs_disabled())
print_irqtrace_events(prev);
+#ifdef CONFIG_DEBUG_PREEMPT
+ if (in_atomic_preempt_off()) {
+ pr_err("Preemption disabled at:");
+ print_ip_sym(current->preempt_disable_ip);
+ pr_cont("\n");
+ }
+#endif
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
@@ -2414,10 +2564,10 @@ static inline void schedule_debug(struct task_struct *prev)
{
/*
* Test if we are atomic. Since do_exit() needs to call into
- * schedule() atomically, we ignore that path for now.
- * Otherwise, whine if we are scheduling when we should not be.
+ * schedule() atomically, we ignore that path. Otherwise whine
+ * if we are scheduling when we should not.
*/
- if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+ if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
__schedule_bug(prev);
rcu_sleep_check();
@@ -2426,36 +2576,34 @@ static inline void schedule_debug(struct task_struct *prev)
schedstat_inc(this_rq(), sched_count);
}
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
- if (prev->on_rq || rq->skip_clock_update < 0)
- update_rq_clock(rq);
- prev->sched_class->put_prev_task(rq, prev);
-}
-
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
{
- const struct sched_class *class;
+ const struct sched_class *class = &fair_sched_class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in
* the fair class we can call that function directly:
*/
- if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq);
- if (likely(p))
+ if (likely(prev->sched_class == class &&
+ rq->nr_running == rq->cfs.h_nr_running)) {
+ p = fair_sched_class.pick_next_task(rq, prev);
+ if (likely(p && p != RETRY_TASK))
return p;
}
+again:
for_each_class(class) {
- p = class->pick_next_task(rq);
- if (p)
+ p = class->pick_next_task(rq, prev);
+ if (p) {
+ if (unlikely(p == RETRY_TASK))
+ goto again;
return p;
+ }
}
BUG(); /* the idle class will always have a runnable task */
@@ -2549,13 +2697,10 @@ need_resched:
switch_count = &prev->nvcsw;
}
- pre_schedule(rq, prev);
-
- if (unlikely(!rq->nr_running))
- idle_balance(cpu, rq);
+ if (prev->on_rq || rq->skip_clock_update < 0)
+ update_rq_clock(rq);
- put_prev_task(rq, prev);
- next = pick_next_task(rq);
+ next = pick_next_task(rq, prev);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
rq->skip_clock_update = 0;
@@ -2701,52 +2846,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
}
EXPORT_SYMBOL(default_wake_function);
-static long __sched
-sleep_on_common(wait_queue_head_t *q, int state, long timeout)
-{
- unsigned long flags;
- wait_queue_t wait;
-
- init_waitqueue_entry(&wait, current);
-
- __set_current_state(state);
-
- spin_lock_irqsave(&q->lock, flags);
- __add_wait_queue(q, &wait);
- spin_unlock(&q->lock);
- timeout = schedule_timeout(timeout);
- spin_lock_irq(&q->lock);
- __remove_wait_queue(q, &wait);
- spin_unlock_irqrestore(&q->lock, flags);
-
- return timeout;
-}
-
-void __sched interruptible_sleep_on(wait_queue_head_t *q)
-{
- sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(interruptible_sleep_on);
-
-long __sched
-interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
- return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(interruptible_sleep_on_timeout);
-
-void __sched sleep_on(wait_queue_head_t *q)
-{
- sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(sleep_on);
-
-long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
- return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(sleep_on_timeout);
-
#ifdef CONFIG_RT_MUTEXES
/*
@@ -2757,15 +2856,16 @@ EXPORT_SYMBOL(sleep_on_timeout);
* This function changes the 'effective' priority of a task. It does
* not touch ->normal_prio like __setscheduler().
*
- * Used by the rt_mutex code to implement priority inheritance logic.
+ * Used by the rt_mutex code to implement priority inheritance
+ * logic. Call site only calls if the priority of the task changed.
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
- int oldprio, on_rq, running;
+ int oldprio, on_rq, running, enqueue_flag = 0;
struct rq *rq;
const struct sched_class *prev_class;
- BUG_ON(prio < 0 || prio > MAX_PRIO);
+ BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p);
@@ -2788,6 +2888,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
}
trace_sched_pi_setprio(p, prio);
+ p->pi_top_task = rt_mutex_get_top_task(p);
oldprio = p->prio;
prev_class = p->sched_class;
on_rq = p->on_rq;
@@ -2797,30 +2898,56 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
if (running)
p->sched_class->put_prev_task(rq, p);
- if (rt_prio(prio))
+ /*
+ * Boosting condition are:
+ * 1. -rt task is running and holds mutex A
+ * --> -dl task blocks on mutex A
+ *
+ * 2. -dl task is running and holds mutex A
+ * --> -dl task blocks on mutex A and could preempt the
+ * running task
+ */
+ if (dl_prio(prio)) {
+ if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+ dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+ p->dl.dl_boosted = 1;
+ p->dl.dl_throttled = 0;
+ enqueue_flag = ENQUEUE_REPLENISH;
+ } else
+ p->dl.dl_boosted = 0;
+ p->sched_class = &dl_sched_class;
+ } else if (rt_prio(prio)) {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
+ if (oldprio < prio)
+ enqueue_flag = ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
- else
+ } else {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
p->sched_class = &fair_sched_class;
+ }
p->prio = prio;
if (running)
p->sched_class->set_curr_task(rq);
if (on_rq)
- enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+ enqueue_task(rq, p, enqueue_flag);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
__task_rq_unlock(rq);
}
#endif
+
void set_user_nice(struct task_struct *p, long nice)
{
int old_prio, delta, on_rq;
unsigned long flags;
struct rq *rq;
- if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+ if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
return;
/*
* We have to be careful, if called from sys_setpriority(),
@@ -2831,9 +2958,9 @@ void set_user_nice(struct task_struct *p, long nice)
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
* it wont have any effect on scheduling until the task is
- * SCHED_FIFO/SCHED_RR:
+ * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
*/
- if (task_has_rt_policy(p)) {
+ if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->static_prio = NICE_TO_PRIO(nice);
goto out_unlock;
}
@@ -2898,11 +3025,11 @@ SYSCALL_DEFINE1(nice, int, increment)
if (increment > 40)
increment = 40;
- nice = TASK_NICE(current) + increment;
- if (nice < -20)
- nice = -20;
- if (nice > 19)
- nice = 19;
+ nice = task_nice(current) + increment;
+ if (nice < MIN_NICE)
+ nice = MIN_NICE;
+ if (nice > MAX_NICE)
+ nice = MAX_NICE;
if (increment < 0 && !can_nice(current, nice))
return -EPERM;
@@ -2931,18 +3058,6 @@ int task_prio(const struct task_struct *p)
}
/**
- * task_nice - return the nice value of a given task.
- * @p: the task in question.
- *
- * Return: The nice value [ -20 ... 0 ... 19 ].
- */
-int task_nice(const struct task_struct *p)
-{
- return TASK_NICE(p);
-}
-EXPORT_SYMBOL(task_nice);
-
-/**
* idle_cpu - is a given cpu idle currently?
* @cpu: the processor in question.
*
@@ -2988,20 +3103,102 @@ static struct task_struct *find_process_by_pid(pid_t pid)
return pid ? find_task_by_vpid(pid) : current;
}
-/* Actually do priority change: must hold rq lock. */
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
static void
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ init_dl_task_timer(dl_se);
+ dl_se->dl_runtime = attr->sched_runtime;
+ dl_se->dl_deadline = attr->sched_deadline;
+ dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+ dl_se->flags = attr->sched_flags;
+ dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_throttled = 0;
+ dl_se->dl_new = 1;
+}
+
+static void __setscheduler_params(struct task_struct *p,
+ const struct sched_attr *attr)
{
+ int policy = attr->sched_policy;
+
+ if (policy == -1) /* setparam */
+ policy = p->policy;
+
p->policy = policy;
- p->rt_priority = prio;
+
+ if (dl_policy(policy))
+ __setparam_dl(p, attr);
+ else if (fair_policy(policy))
+ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
+ /*
+ * __sched_setscheduler() ensures attr->sched_priority == 0 when
+ * !rt_policy. Always setting this ensures that things like
+ * getparam()/getattr() don't report silly values for !rt tasks.
+ */
+ p->rt_priority = attr->sched_priority;
p->normal_prio = normal_prio(p);
- /* we are holding p->pi_lock already */
- p->prio = rt_mutex_getprio(p);
- if (rt_prio(p->prio))
+ set_load_weight(p);
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+ const struct sched_attr *attr)
+{
+ __setscheduler_params(p, attr);
+
+ /*
+ * If we get here, there was no pi waiters boosting the
+ * task. It is safe to use the normal prio.
+ */
+ p->prio = normal_prio(p);
+
+ if (dl_prio(p->prio))
+ p->sched_class = &dl_sched_class;
+ else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class;
- set_load_weight(p);
+}
+
+static void
+__getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ attr->sched_priority = p->rt_priority;
+ attr->sched_runtime = dl_se->dl_runtime;
+ attr->sched_deadline = dl_se->dl_deadline;
+ attr->sched_period = dl_se->dl_period;
+ attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution (1us); we
+ * check sched_runtime only since it is always the smaller one.
+ */
+static bool
+__checkparam_dl(const struct sched_attr *attr)
+{
+ return attr && attr->sched_deadline != 0 &&
+ (attr->sched_period == 0 ||
+ (s64)(attr->sched_period - attr->sched_deadline) >= 0) &&
+ (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0 &&
+ attr->sched_runtime >= (2 << (DL_SCALE - 1));
}
/*
@@ -3020,10 +3217,14 @@ static bool check_same_owner(struct task_struct *p)
return match;
}
-static int __sched_setscheduler(struct task_struct *p, int policy,
- const struct sched_param *param, bool user)
+static int __sched_setscheduler(struct task_struct *p,
+ const struct sched_attr *attr,
+ bool user)
{
+ int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
+ MAX_RT_PRIO - 1 - attr->sched_priority;
int retval, oldprio, oldpolicy = -1, on_rq, running;
+ int policy = attr->sched_policy;
unsigned long flags;
const struct sched_class *prev_class;
struct rq *rq;
@@ -3037,31 +3238,40 @@ recheck:
reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
} else {
- reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
- policy &= ~SCHED_RESET_ON_FORK;
+ reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
- if (policy != SCHED_FIFO && policy != SCHED_RR &&
+ if (policy != SCHED_DEADLINE &&
+ policy != SCHED_FIFO && policy != SCHED_RR &&
policy != SCHED_NORMAL && policy != SCHED_BATCH &&
policy != SCHED_IDLE)
return -EINVAL;
}
+ if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
+ return -EINVAL;
+
/*
* Valid priorities for SCHED_FIFO and SCHED_RR are
* 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
* SCHED_BATCH and SCHED_IDLE is 0.
*/
- if (param->sched_priority < 0 ||
- (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
- (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+ if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
+ (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
return -EINVAL;
- if (rt_policy(policy) != (param->sched_priority != 0))
+ if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
+ (rt_policy(policy) != (attr->sched_priority != 0)))
return -EINVAL;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
if (user && !capable(CAP_SYS_NICE)) {
+ if (fair_policy(policy)) {
+ if (attr->sched_nice < task_nice(p) &&
+ !can_nice(p, attr->sched_nice))
+ return -EPERM;
+ }
+
if (rt_policy(policy)) {
unsigned long rlim_rtprio =
task_rlimit(p, RLIMIT_RTPRIO);
@@ -3071,17 +3281,26 @@ recheck:
return -EPERM;
/* can't increase priority */
- if (param->sched_priority > p->rt_priority &&
- param->sched_priority > rlim_rtprio)
+ if (attr->sched_priority > p->rt_priority &&
+ attr->sched_priority > rlim_rtprio)
return -EPERM;
}
+ /*
+ * Can't set/change SCHED_DEADLINE policy at all for now
+ * (safest behavior); in the future we would like to allow
+ * unprivileged DL tasks to increase their relative deadline
+ * or reduce their runtime (both ways reducing utilization)
+ */
+ if (dl_policy(policy))
+ return -EPERM;
+
/*
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
- if (!can_nice(p, TASK_NICE(p)))
+ if (!can_nice(p, task_nice(p)))
return -EPERM;
}
@@ -3118,16 +3337,25 @@ recheck:
}
/*
- * If not changing anything there's no need to proceed further:
+ * If not changing anything there's no need to proceed further,
+ * but store a possible modification of reset_on_fork.
*/
- if (unlikely(policy == p->policy && (!rt_policy(policy) ||
- param->sched_priority == p->rt_priority))) {
+ if (unlikely(policy == p->policy)) {
+ if (fair_policy(policy) && attr->sched_nice != task_nice(p))
+ goto change;
+ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+ goto change;
+ if (dl_policy(policy))
+ goto change;
+
+ p->sched_reset_on_fork = reset_on_fork;
task_rq_unlock(rq, p, &flags);
return 0;
}
+change:
-#ifdef CONFIG_RT_GROUP_SCHED
if (user) {
+#ifdef CONFIG_RT_GROUP_SCHED
/*
* Do not allow realtime tasks into groups that have no runtime
* assigned.
@@ -3138,8 +3366,24 @@ recheck:
task_rq_unlock(rq, p, &flags);
return -EPERM;
}
- }
#endif
+#ifdef CONFIG_SMP
+ if (dl_bandwidth_enabled() && dl_policy(policy)) {
+ cpumask_t *span = rq->rd->span;
+
+ /*
+ * Don't allow tasks with an affinity mask smaller than
+ * the entire root_domain to become SCHED_DEADLINE. We
+ * will also fail if there's no bandwidth available.
+ */
+ if (!cpumask_subset(span, &p->cpus_allowed) ||
+ rq->rd->dl_bw.bw == 0) {
+ task_rq_unlock(rq, p, &flags);
+ return -EPERM;
+ }
+ }
+#endif
+ }
/* recheck policy now with rq lock held */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
@@ -3147,6 +3391,35 @@ recheck:
task_rq_unlock(rq, p, &flags);
goto recheck;
}
+
+ /*
+ * If setscheduling to SCHED_DEADLINE (or changing the parameters
+ * of a SCHED_DEADLINE task) we need to check if enough bandwidth
+ * is available.
+ */
+ if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+ task_rq_unlock(rq, p, &flags);
+ return -EBUSY;
+ }
+
+ p->sched_reset_on_fork = reset_on_fork;
+ oldprio = p->prio;
+
+ /*
+ * Special case for priority boosted tasks.
+ *
+ * If the new priority is lower or equal (user space view)
+ * than the current (boosted) priority, we just store the new
+ * normal parameters and do not touch the scheduler class and
+ * the runqueue. This will be done when the task deboost
+ * itself.
+ */
+ if (rt_mutex_check_prio(p, newprio)) {
+ __setscheduler_params(p, attr);
+ task_rq_unlock(rq, p, &flags);
+ return 0;
+ }
+
on_rq = p->on_rq;
running = task_current(rq, p);
if (on_rq)
@@ -3154,16 +3427,18 @@ recheck:
if (running)
p->sched_class->put_prev_task(rq, p);
- p->sched_reset_on_fork = reset_on_fork;
-
- oldprio = p->prio;
prev_class = p->sched_class;
- __setscheduler(rq, p, policy, param->sched_priority);
+ __setscheduler(rq, p, attr);
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq)
- enqueue_task(rq, p, 0);
+ if (on_rq) {
+ /*
+ * We enqueue to tail when the priority of a task is
+ * increased (user space view).
+ */
+ enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+ }
check_class_changed(rq, p, prev_class, oldprio);
task_rq_unlock(rq, p, &flags);
@@ -3173,6 +3448,26 @@ recheck:
return 0;
}
+static int _sched_setscheduler(struct task_struct *p, int policy,
+ const struct sched_param *param, bool check)
+{
+ struct sched_attr attr = {
+ .sched_policy = policy,
+ .sched_priority = param->sched_priority,
+ .sched_nice = PRIO_TO_NICE(p->static_prio),
+ };
+
+ /*
+ * Fixup the legacy SCHED_RESET_ON_FORK hack
+ */
+ if (policy & SCHED_RESET_ON_FORK) {
+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ policy &= ~SCHED_RESET_ON_FORK;
+ attr.sched_policy = policy;
+ }
+
+ return __sched_setscheduler(p, &attr, check);
+}
/**
* sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
* @p: the task in question.
@@ -3186,10 +3481,16 @@ recheck:
int sched_setscheduler(struct task_struct *p, int policy,
const struct sched_param *param)
{
- return __sched_setscheduler(p, policy, param, true);
+ return _sched_setscheduler(p, policy, param, true);
}
EXPORT_SYMBOL_GPL(sched_setscheduler);
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+ return __sched_setscheduler(p, attr, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
* @p: the task in question.
@@ -3206,7 +3507,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
const struct sched_param *param)
{
- return __sched_setscheduler(p, policy, param, false);
+ return _sched_setscheduler(p, policy, param, false);
}
static int
@@ -3231,6 +3532,79 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
return retval;
}
+/*
+ * Mimics kernel/events/core.c perf_copy_attr().
+ */
+static int sched_copy_attr(struct sched_attr __user *uattr,
+ struct sched_attr *attr)
+{
+ u32 size;
+ int ret;
+
+ if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
+ return -EFAULT;
+
+ /*
+ * zero the full structure, so that a short copy will be nice.
+ */
+ memset(attr, 0, sizeof(*attr));
+
+ ret = get_user(size, &uattr->size);
+ if (ret)
+ return ret;
+
+ if (size > PAGE_SIZE) /* silly large */
+ goto err_size;
+
+ if (!size) /* abi compat */
+ size = SCHED_ATTR_SIZE_VER0;
+
+ if (size < SCHED_ATTR_SIZE_VER0)
+ goto err_size;
+
+ /*
+ * If we're handed a bigger struct than we know of,
+ * ensure all the unknown bits are 0 - i.e. new
+ * user-space does not rely on any kernel feature
+ * extensions we dont know about yet.
+ */
+ if (size > sizeof(*attr)) {
+ unsigned char __user *addr;
+ unsigned char __user *end;
+ unsigned char val;
+
+ addr = (void __user *)uattr + sizeof(*attr);
+ end = (void __user *)uattr + size;
+
+ for (; addr < end; addr++) {
+ ret = get_user(val, addr);
+ if (ret)
+ return ret;
+ if (val)
+ goto err_size;
+ }
+ size = sizeof(*attr);
+ }
+
+ ret = copy_from_user(attr, uattr, size);
+ if (ret)
+ return -EFAULT;
+
+ /*
+ * XXX: do we want to be lenient like existing syscalls; or do we want
+ * to be strict and return an error on out-of-bounds values?
+ */
+ attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
+
+out:
+ return ret;
+
+err_size:
+ put_user(sizeof(*attr), &uattr->size);
+ ret = -E2BIG;
+ goto out;
+}
+
/**
* sys_sched_setscheduler - set/change the scheduler policy and RT priority
* @pid: the pid in question.
@@ -3262,6 +3636,34 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
}
/**
+ * sys_sched_setattr - same as above, but with extended sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ */
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, flags)
+{
+ struct sched_attr attr;
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0 || flags)
+ return -EINVAL;
+
+ if (sched_copy_attr(uattr, &attr))
+ return -EFAULT;
+
+ rcu_read_lock();
+ retval = -ESRCH;
+ p = find_process_by_pid(pid);
+ if (p != NULL)
+ retval = sched_setattr(p, &attr);
+ rcu_read_unlock();
+
+ return retval;
+}
+
+/**
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
*
@@ -3316,6 +3718,10 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
if (retval)
goto out_unlock;
+ if (task_has_dl_policy(p)) {
+ retval = -EINVAL;
+ goto out_unlock;
+ }
lp.sched_priority = p->rt_priority;
rcu_read_unlock();
@@ -3331,6 +3737,96 @@ out_unlock:
return retval;
}
+static int sched_read_attr(struct sched_attr __user *uattr,
+ struct sched_attr *attr,
+ unsigned int usize)
+{
+ int ret;
+
+ if (!access_ok(VERIFY_WRITE, uattr, usize))
+ return -EFAULT;
+
+ /*
+ * If we're handed a smaller struct than we know of,
+ * ensure all the unknown bits are 0 - i.e. old
+ * user-space does not get uncomplete information.
+ */
+ if (usize < sizeof(*attr)) {
+ unsigned char *addr;
+ unsigned char *end;
+
+ addr = (void *)attr + usize;
+ end = (void *)attr + sizeof(*attr);
+
+ for (; addr < end; addr++) {
+ if (*addr)
+ goto err_size;
+ }
+
+ attr->size = usize;
+ }
+
+ ret = copy_to_user(uattr, attr, attr->size);
+ if (ret)
+ return -EFAULT;
+
+out:
+ return ret;
+
+err_size:
+ ret = -E2BIG;
+ goto out;
+}
+
+/**
+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ * @size: sizeof(attr) for fwd/bwd comp.
+ */
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, size, unsigned int, flags)
+{
+ struct sched_attr attr = {
+ .size = sizeof(struct sched_attr),
+ };
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0 || size > PAGE_SIZE ||
+ size < SCHED_ATTR_SIZE_VER0 || flags)
+ return -EINVAL;
+
+ rcu_read_lock();
+ p = find_process_by_pid(pid);
+ retval = -ESRCH;
+ if (!p)
+ goto out_unlock;
+
+ retval = security_task_getscheduler(p);
+ if (retval)
+ goto out_unlock;
+
+ attr.sched_policy = p->policy;
+ if (p->sched_reset_on_fork)
+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ if (task_has_dl_policy(p))
+ __getparam_dl(p, &attr);
+ else if (task_has_rt_policy(p))
+ attr.sched_priority = p->rt_priority;
+ else
+ attr.sched_nice = task_nice(p);
+
+ rcu_read_unlock();
+
+ retval = sched_read_attr(uattr, &attr, size);
+ return retval;
+
+out_unlock:
+ rcu_read_unlock();
+ return retval;
+}
+
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
cpumask_var_t cpus_allowed, new_mask;
@@ -3375,8 +3871,26 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (retval)
goto out_unlock;
+
cpuset_cpus_allowed(p, cpus_allowed);
cpumask_and(new_mask, in_mask, cpus_allowed);
+
+ /*
+ * Since bandwidth control happens on root_domain basis,
+ * if admission test is enabled, we only admit -deadline
+ * tasks allowed to run on all the CPUs in the task's
+ * root_domain.
+ */
+#ifdef CONFIG_SMP
+ if (task_has_dl_policy(p)) {
+ const struct cpumask *span = task_rq(p)->rd->span;
+
+ if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+ retval = -EBUSY;
+ goto out_unlock;
+ }
+ }
+#endif
again:
retval = set_cpus_allowed_ptr(p, new_mask);
@@ -3653,7 +4167,7 @@ again:
}
double_rq_lock(rq, p_rq);
- while (task_rq(p) != p_rq) {
+ if (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
@@ -3742,6 +4256,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
case SCHED_RR:
ret = MAX_USER_RT_PRIO-1;
break;
+ case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
@@ -3768,6 +4283,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
case SCHED_RR:
ret = 1;
break;
+ case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
@@ -3811,7 +4327,9 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
goto out_unlock;
rq = task_rq_lock(p, &flags);
- time_slice = p->sched_class->get_rr_interval(rq, p);
+ time_slice = 0;
+ if (p->sched_class->get_rr_interval)
+ time_slice = p->sched_class->get_rr_interval(rq, p);
task_rq_unlock(rq, p, &flags);
rcu_read_unlock();
@@ -3935,6 +4453,7 @@ void init_idle(struct task_struct *idle, int cpu)
rcu_read_unlock();
rq->curr = rq->idle = idle;
+ idle->on_rq = 1;
#if defined(CONFIG_SMP)
idle->on_cpu = 1;
#endif
@@ -4090,6 +4609,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
/* TODO: This is not properly updating schedstats */
+ trace_sched_move_numa(p, curr_cpu, target_cpu);
return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
}
@@ -4153,8 +4673,10 @@ void idle_task_exit(void)
BUG_ON(cpu_online(smp_processor_id()));
- if (mm != &init_mm)
+ if (mm != &init_mm) {
switch_mm(mm, &init_mm, current);
+ finish_arch_post_lock_switch();
+ }
mmdrop(mm);
}
@@ -4172,6 +4694,22 @@ static void calc_load_migrate(struct rq *rq)
atomic_long_add(delta, &calc_load_tasks);
}
+static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static const struct sched_class fake_sched_class = {
+ .put_prev_task = put_prev_task_fake,
+};
+
+static struct task_struct fake_task = {
+ /*
+ * Avoid pull_{rt,dl}_task()
+ */
+ .prio = MAX_PRIO + 1,
+ .sched_class = &fake_sched_class,
+};
+
/*
* Migrate all tasks from the rq, sleeping tasks will be migrated by
* try_to_wake_up()->select_task_rq().
@@ -4212,7 +4750,7 @@ static void migrate_tasks(unsigned int dead_cpu)
if (rq->nr_running == 1)
break;
- next = pick_next_task(rq);
+ next = pick_next_task(rq, &fake_task);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
@@ -4302,7 +4840,7 @@ set_table_entry(struct ctl_table *entry,
static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
- struct ctl_table *table = sd_alloc_ctl_entry(13);
+ struct ctl_table *table = sd_alloc_ctl_entry(14);
if (table == NULL)
return NULL;
@@ -4330,9 +4868,12 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[10], "flags", &sd->flags,
sizeof(int), 0644, proc_dointvec_minmax, false);
- set_table_entry(&table[11], "name", sd->name,
+ set_table_entry(&table[11], "max_newidle_lb_cost",
+ &sd->max_newidle_lb_cost,
+ sizeof(long), 0644, proc_doulongvec_minmax, false);
+ set_table_entry(&table[12], "name", sd->name,
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
- /* &table[12] is terminator */
+ /* &table[13] is terminator */
return table;
}
@@ -4514,13 +5055,31 @@ static int sched_cpu_active(struct notifier_block *nfb,
static int sched_cpu_inactive(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ unsigned long flags;
+ long cpu = (long)hcpu;
+
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
- set_cpu_active((long)hcpu, false);
+ set_cpu_active(cpu, false);
+
+ /* explicitly allow suspend */
+ if (!(action & CPU_TASKS_FROZEN)) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+ bool overflow;
+ int cpus;
+
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ cpus = dl_bw_cpus(cpu);
+ overflow = __dl_overflow(dl_b, cpus, 0, 0);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+ if (overflow)
+ return notifier_from_errno(-EBUSY);
+ }
return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
}
+
+ return NOTIFY_DONE;
}
static int __init migration_init(void)
@@ -4739,6 +5298,8 @@ static void free_rootdomain(struct rcu_head *rcu)
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
cpupri_cleanup(&rd->cpupri);
+ cpudl_cleanup(&rd->cpudl);
+ free_cpumask_var(rd->dlo_mask);
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
@@ -4790,8 +5351,14 @@ static int init_rootdomain(struct root_domain *rd)
goto out;
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
- if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
goto free_online;
+ if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ goto free_dlo_mask;
+
+ init_dl_bw(&rd->dl_bw);
+ if (cpudl_init(&rd->cpudl) != 0)
+ goto free_dlo_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
@@ -4799,6 +5366,8 @@ static int init_rootdomain(struct root_domain *rd)
free_rto_mask:
free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+ free_cpumask_var(rd->dlo_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
@@ -5884,7 +6453,7 @@ static cpumask_var_t fallback_doms;
* cpu core maps. It is supposed to return 1 if the topology changed
* or 0 if it stayed the same.
*/
-int __attribute__((weak)) arch_update_cpu_topology(void)
+int __weak arch_update_cpu_topology(void)
{
return 0;
}
@@ -6150,6 +6719,7 @@ void __init sched_init_smp(void)
free_cpumask_var(non_isolated_cpus);
init_sched_rt_class();
+ init_sched_dl_class();
}
#else
void __init sched_init_smp(void)
@@ -6219,13 +6789,15 @@ void __init sched_init(void)
#endif /* CONFIG_CPUMASK_OFFSTACK */
}
+ init_rt_bandwidth(&def_rt_bandwidth,
+ global_rt_period(), global_rt_runtime());
+ init_dl_bandwidth(&def_dl_bandwidth,
+ global_rt_period(), global_rt_runtime());
+
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
- init_rt_bandwidth(&def_rt_bandwidth,
- global_rt_period(), global_rt_runtime());
-
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
@@ -6249,6 +6821,7 @@ void __init sched_init(void)
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs);
init_rt_rq(&rq->rt, rq);
+ init_dl_rq(&rq->dl, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -6277,7 +6850,6 @@ void __init sched_init(void)
rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
- INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
@@ -6320,10 +6892,6 @@ void __init sched_init(void)
INIT_HLIST_HEAD(&init_task.preempt_notifiers);
#endif
-#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&init_task.pi_waiters);
-#endif
-
/*
* The boot idle thread does lazy MMU switching as well:
*/
@@ -6370,7 +6938,8 @@ void __might_sleep(const char *file, int line, int preempt_offset)
static unsigned long prev_jiffy; /* ratelimiting */
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
- if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+ if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+ !is_idle_task(current)) ||
system_state != SYSTEM_RUNNING || oops_in_progress)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
@@ -6388,6 +6957,13 @@ void __might_sleep(const char *file, int line, int preempt_offset)
debug_show_held_locks(current);
if (irqs_disabled())
print_irqtrace_events(current);
+#ifdef CONFIG_DEBUG_PREEMPT
+ if (!preempt_count_equals(preempt_offset)) {
+ pr_err("Preemption disabled at:");
+ print_ip_sym(current->preempt_disable_ip);
+ pr_cont("\n");
+ }
+#endif
dump_stack();
}
EXPORT_SYMBOL(__might_sleep);
@@ -6397,13 +6973,16 @@ EXPORT_SYMBOL(__might_sleep);
static void normalize_task(struct rq *rq, struct task_struct *p)
{
const struct sched_class *prev_class = p->sched_class;
+ struct sched_attr attr = {
+ .sched_policy = SCHED_NORMAL,
+ };
int old_prio = p->prio;
int on_rq;
on_rq = p->on_rq;
if (on_rq)
dequeue_task(rq, p, 0);
- __setscheduler(rq, p, SCHED_NORMAL, 0);
+ __setscheduler(rq, p, &attr);
if (on_rq) {
enqueue_task(rq, p, 0);
resched_task(rq->curr);
@@ -6433,12 +7012,12 @@ void normalize_rt_tasks(void)
p->se.statistics.block_start = 0;
#endif
- if (!rt_task(p)) {
+ if (!dl_task(p) && !rt_task(p)) {
/*
* Renice negative nice level userspace
* tasks back to 0:
*/
- if (TASK_NICE(p) < 0 && p->mm)
+ if (task_nice(p) < 0 && p->mm)
set_user_nice(p, 0);
continue;
}
@@ -6606,7 +7185,7 @@ void sched_move_task(struct task_struct *tsk)
if (unlikely(running))
tsk->sched_class->put_prev_task(rq, tsk);
- tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id,
+ tg = container_of(task_css_check(tsk, cpu_cgrp_id,
lockdep_is_held(&tsk->sighand->siglock)),
struct task_group, css);
tg = autogroup_task_group(tsk, tg);
@@ -6628,16 +7207,6 @@ void sched_move_task(struct task_struct *tsk)
}
#endif /* CONFIG_CGROUP_SCHED */
-#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
-static unsigned long to_ratio(u64 period, u64 runtime)
-{
- if (runtime == RUNTIME_INF)
- return 1ULL << 20;
-
- return div64_u64(runtime << 20, period);
-}
-#endif
-
#ifdef CONFIG_RT_GROUP_SCHED
/*
* Ensure that the real time constraints are schedulable.
@@ -6811,24 +7380,13 @@ static long sched_group_rt_period(struct task_group *tg)
do_div(rt_period_us, NSEC_PER_USEC);
return rt_period_us;
}
+#endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_RT_GROUP_SCHED
static int sched_rt_global_constraints(void)
{
- u64 runtime, period;
int ret = 0;
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
- runtime = global_rt_runtime();
- period = global_rt_period();
-
- /*
- * Sanity check on the sysctl variables.
- */
- if (runtime > period && runtime != RUNTIME_INF)
- return -EINVAL;
-
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
ret = __rt_schedulable(NULL, 0, 0);
@@ -6851,17 +7409,7 @@ static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
static int sched_rt_global_constraints(void)
{
unsigned long flags;
- int i;
-
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
- /*
- * There's always some RT tasks in the root group
- * -- migration, kstopmachine etc..
- */
- if (sysctl_sched_rt_runtime == 0)
- return -EBUSY;
+ int i, ret = 0;
raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
@@ -6873,36 +7421,91 @@ static int sched_rt_global_constraints(void)
}
raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
- return 0;
+ return ret;
}
#endif /* CONFIG_RT_GROUP_SCHED */
-int sched_rr_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+static int sched_dl_global_constraints(void)
{
- int ret;
- static DEFINE_MUTEX(mutex);
+ u64 runtime = global_rt_runtime();
+ u64 period = global_rt_period();
+ u64 new_bw = to_ratio(period, runtime);
+ int cpu, ret = 0;
+ unsigned long flags;
- mutex_lock(&mutex);
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
- /* make sure that internally we keep jiffies */
- /* also, writing zero resets timeslice to default */
- if (!ret && write) {
- sched_rr_timeslice = sched_rr_timeslice <= 0 ?
- RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+ /*
+ * Here we want to check the bandwidth not being set to some
+ * value smaller than the currently allocated bandwidth in
+ * any of the root_domains.
+ *
+ * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+ * cycling on root_domains... Discussion on different/better
+ * solutions is welcome!
+ */
+ for_each_possible_cpu(cpu) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ if (new_bw < dl_b->total_bw)
+ ret = -EBUSY;
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+ if (ret)
+ break;
}
- mutex_unlock(&mutex);
+
return ret;
}
+static void sched_dl_do_global(void)
+{
+ u64 new_bw = -1;
+ int cpu;
+ unsigned long flags;
+
+ def_dl_bandwidth.dl_period = global_rt_period();
+ def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+ if (global_rt_runtime() != RUNTIME_INF)
+ new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+ /*
+ * FIXME: As above...
+ */
+ for_each_possible_cpu(cpu) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ dl_b->bw = new_bw;
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+ }
+}
+
+static int sched_rt_global_validate(void)
+{
+ if (sysctl_sched_rt_period <= 0)
+ return -EINVAL;
+
+ if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+ (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+ return -EINVAL;
+
+ return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+ def_rt_bandwidth.rt_runtime = global_rt_runtime();
+ def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret;
int old_period, old_runtime;
static DEFINE_MUTEX(mutex);
+ int ret;
mutex_lock(&mutex);
old_period = sysctl_sched_rt_period;
@@ -6911,21 +7514,50 @@ int sched_rt_handler(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write) {
+ ret = sched_rt_global_validate();
+ if (ret)
+ goto undo;
+
ret = sched_rt_global_constraints();
- if (ret) {
- sysctl_sched_rt_period = old_period;
- sysctl_sched_rt_runtime = old_runtime;
- } else {
- def_rt_bandwidth.rt_runtime = global_rt_runtime();
- def_rt_bandwidth.rt_period =
- ns_to_ktime(global_rt_period());
- }
+ if (ret)
+ goto undo;
+
+ ret = sched_dl_global_constraints();
+ if (ret)
+ goto undo;
+
+ sched_rt_do_global();
+ sched_dl_do_global();
+ }
+ if (0) {
+undo:
+ sysctl_sched_rt_period = old_period;
+ sysctl_sched_rt_runtime = old_runtime;
}
mutex_unlock(&mutex);
return ret;
}
+int sched_rr_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+ static DEFINE_MUTEX(mutex);
+
+ mutex_lock(&mutex);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ /* make sure that internally we keep jiffies */
+ /* also, writing zero resets timeslice to default */
+ if (!ret && write) {
+ sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+ RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+ }
+ mutex_unlock(&mutex);
+ return ret;
+}
+
#ifdef CONFIG_CGROUP_SCHED
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -6980,7 +7612,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
{
struct task_struct *task;
- cgroup_taskset_for_each(task, css, tset) {
+ cgroup_taskset_for_each(task, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
@@ -6998,7 +7630,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
{
struct task_struct *task;
- cgroup_taskset_for_each(task, css, tset)
+ cgroup_taskset_for_each(task, tset)
sched_move_task(task);
}
@@ -7258,15 +7890,14 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
return ret;
}
-static int cpu_stats_show(struct cgroup_subsys_state *css, struct cftype *cft,
- struct cgroup_map_cb *cb)
+static int cpu_stats_show(struct seq_file *sf, void *v)
{
- struct task_group *tg = css_tg(css);
+ struct task_group *tg = css_tg(seq_css(sf));
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
- cb->fill(cb, "nr_periods", cfs_b->nr_periods);
- cb->fill(cb, "nr_throttled", cfs_b->nr_throttled);
- cb->fill(cb, "throttled_time", cfs_b->throttled_time);
+ seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
+ seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
+ seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
return 0;
}
@@ -7320,7 +7951,7 @@ static struct cftype cpu_files[] = {
},
{
.name = "stat",
- .read_map = cpu_stats_show,
+ .seq_show = cpu_stats_show,
},
#endif
#ifdef CONFIG_RT_GROUP_SCHED
@@ -7338,8 +7969,7 @@ static struct cftype cpu_files[] = {
{ } /* terminate */
};
-struct cgroup_subsys cpu_cgroup_subsys = {
- .name = "cpu",
+struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
.css_free = cpu_cgroup_css_free,
.css_online = cpu_cgroup_css_online,
@@ -7347,7 +7977,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.exit = cpu_cgroup_exit,
- .subsys_id = cpu_cgroup_subsys_id,
.base_cftypes = cpu_files,
.early_init = 1,
};
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index f64722ff0299..c143ee380e3a 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -41,7 +41,7 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
/* return cpu accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
- return css_ca(task_css(tsk, cpuacct_subsys_id));
+ return css_ca(task_css(tsk, cpuacct_cgrp_id));
}
static inline struct cpuacct *parent_ca(struct cpuacct *ca)
@@ -163,10 +163,9 @@ out:
return err;
}
-static int cpuacct_percpu_seq_read(struct cgroup_subsys_state *css,
- struct cftype *cft, struct seq_file *m)
+static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
{
- struct cpuacct *ca = css_ca(css);
+ struct cpuacct *ca = css_ca(seq_css(m));
u64 percpu;
int i;
@@ -183,10 +182,9 @@ static const char * const cpuacct_stat_desc[] = {
[CPUACCT_STAT_SYSTEM] = "system",
};
-static int cpuacct_stats_show(struct cgroup_subsys_state *css,
- struct cftype *cft, struct cgroup_map_cb *cb)
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
{
- struct cpuacct *ca = css_ca(css);
+ struct cpuacct *ca = css_ca(seq_css(sf));
int cpu;
s64 val = 0;
@@ -196,7 +194,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css,
val += kcpustat->cpustat[CPUTIME_NICE];
}
val = cputime64_to_clock_t(val);
- cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+ seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
val = 0;
for_each_online_cpu(cpu) {
@@ -207,7 +205,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css,
}
val = cputime64_to_clock_t(val);
- cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+ seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
return 0;
}
@@ -220,11 +218,11 @@ static struct cftype files[] = {
},
{
.name = "usage_percpu",
- .read_seq_string = cpuacct_percpu_seq_read,
+ .seq_show = cpuacct_percpu_seq_show,
},
{
.name = "stat",
- .read_map = cpuacct_stats_show,
+ .seq_show = cpuacct_stats_show,
},
{ } /* terminate */
};
@@ -277,11 +275,9 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val)
rcu_read_unlock();
}
-struct cgroup_subsys cpuacct_subsys = {
- .name = "cpuacct",
+struct cgroup_subsys cpuacct_cgrp_subsys = {
.css_alloc = cpuacct_css_alloc,
.css_free = cpuacct_css_free,
- .subsys_id = cpuacct_subsys_id,
.base_cftypes = files,
.early_init = 1,
};
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
new file mode 100644
index 000000000000..5b9bb42b2d47
--- /dev/null
+++ b/kernel/sched/cpudeadline.c
@@ -0,0 +1,216 @@
+/*
+ * kernel/sched/cpudl.c
+ *
+ * Global CPU deadline management
+ *
+ * Author: Juri Lelli <j.lelli@sssup.it>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include "cpudeadline.h"
+
+static inline int parent(int i)
+{
+ return (i - 1) >> 1;
+}
+
+static inline int left_child(int i)
+{
+ return (i << 1) + 1;
+}
+
+static inline int right_child(int i)
+{
+ return (i << 1) + 2;
+}
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+static void cpudl_exchange(struct cpudl *cp, int a, int b)
+{
+ int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
+
+ swap(cp->elements[a], cp->elements[b]);
+ swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+}
+
+static void cpudl_heapify(struct cpudl *cp, int idx)
+{
+ int l, r, largest;
+
+ /* adapted from lib/prio_heap.c */
+ while(1) {
+ l = left_child(idx);
+ r = right_child(idx);
+ largest = idx;
+
+ if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
+ cp->elements[l].dl))
+ largest = l;
+ if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
+ cp->elements[r].dl))
+ largest = r;
+ if (largest == idx)
+ break;
+
+ /* Push idx down the heap one level and bump one up */
+ cpudl_exchange(cp, largest, idx);
+ idx = largest;
+ }
+}
+
+static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+{
+ WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
+
+ if (dl_time_before(new_dl, cp->elements[idx].dl)) {
+ cp->elements[idx].dl = new_dl;
+ cpudl_heapify(cp, idx);
+ } else {
+ cp->elements[idx].dl = new_dl;
+ while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
+ cp->elements[idx].dl)) {
+ cpudl_exchange(cp, idx, parent(idx));
+ idx = parent(idx);
+ }
+ }
+}
+
+static inline int cpudl_maximum(struct cpudl *cp)
+{
+ return cp->elements[0].cpu;
+}
+
+/*
+ * cpudl_find - find the best (later-dl) CPU in the system
+ * @cp: the cpudl max-heap context
+ * @p: the task
+ * @later_mask: a mask to fill in with the selected CPUs (or NULL)
+ *
+ * Returns: int - best CPU (heap maximum if suitable)
+ */
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+ struct cpumask *later_mask)
+{
+ int best_cpu = -1;
+ const struct sched_dl_entity *dl_se = &p->dl;
+
+ if (later_mask && cpumask_and(later_mask, cp->free_cpus,
+ &p->cpus_allowed) && cpumask_and(later_mask,
+ later_mask, cpu_active_mask)) {
+ best_cpu = cpumask_any(later_mask);
+ goto out;
+ } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+ dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+ best_cpu = cpudl_maximum(cp);
+ if (later_mask)
+ cpumask_set_cpu(best_cpu, later_mask);
+ }
+
+out:
+ WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
+
+ return best_cpu;
+}
+
+/*
+ * cpudl_set - update the cpudl max-heap
+ * @cp: the cpudl max-heap context
+ * @cpu: the target cpu
+ * @dl: the new earliest deadline for this cpu
+ *
+ * Notes: assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
+{
+ int old_idx, new_cpu;
+ unsigned long flags;
+
+ WARN_ON(!cpu_present(cpu));
+
+ raw_spin_lock_irqsave(&cp->lock, flags);
+ old_idx = cp->cpu_to_idx[cpu];
+ if (!is_valid) {
+ /* remove item */
+ if (old_idx == IDX_INVALID) {
+ /*
+ * Nothing to remove if old_idx was invalid.
+ * This could happen if a rq_offline_dl is
+ * called for a CPU without -dl tasks running.
+ */
+ goto out;
+ }
+ new_cpu = cp->elements[cp->size - 1].cpu;
+ cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
+ cp->elements[old_idx].cpu = new_cpu;
+ cp->size--;
+ cp->cpu_to_idx[new_cpu] = old_idx;
+ cp->cpu_to_idx[cpu] = IDX_INVALID;
+ while (old_idx > 0 && dl_time_before(
+ cp->elements[parent(old_idx)].dl,
+ cp->elements[old_idx].dl)) {
+ cpudl_exchange(cp, old_idx, parent(old_idx));
+ old_idx = parent(old_idx);
+ }
+ cpumask_set_cpu(cpu, cp->free_cpus);
+ cpudl_heapify(cp, old_idx);
+
+ goto out;
+ }
+
+ if (old_idx == IDX_INVALID) {
+ cp->size++;
+ cp->elements[cp->size - 1].dl = 0;
+ cp->elements[cp->size - 1].cpu = cpu;
+ cp->cpu_to_idx[cpu] = cp->size - 1;
+ cpudl_change_key(cp, cp->size - 1, dl);
+ cpumask_clear_cpu(cpu, cp->free_cpus);
+ } else {
+ cpudl_change_key(cp, old_idx, dl);
+ }
+
+out:
+ raw_spin_unlock_irqrestore(&cp->lock, flags);
+}
+
+/*
+ * cpudl_init - initialize the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+int cpudl_init(struct cpudl *cp)
+{
+ int i;
+
+ memset(cp, 0, sizeof(*cp));
+ raw_spin_lock_init(&cp->lock);
+ cp->size = 0;
+ for (i = 0; i < NR_CPUS; i++)
+ cp->cpu_to_idx[i] = IDX_INVALID;
+ if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+ return -ENOMEM;
+ cpumask_setall(cp->free_cpus);
+
+ return 0;
+}
+
+/*
+ * cpudl_cleanup - clean up the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+void cpudl_cleanup(struct cpudl *cp)
+{
+ /*
+ * nothing to do for the moment
+ */
+}
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
new file mode 100644
index 000000000000..a202789a412c
--- /dev/null
+++ b/kernel/sched/cpudeadline.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID -1
+
+struct array_item {
+ u64 dl;
+ int cpu;
+};
+
+struct cpudl {
+ raw_spinlock_t lock;
+ int size;
+ int cpu_to_idx[NR_CPUS];
+ struct array_item elements[NR_CPUS];
+ cpumask_var_t free_cpus;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+ struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 99947919e30b..a95097cb4591 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -142,7 +142,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
p->utimescaled += cputime_scaled;
account_group_user_time(p, cputime);
- index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+ index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
/* Add user time to cpustat. */
task_group_account_field(p, index, (__force u64) cputime);
@@ -169,7 +169,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
p->gtime += cputime;
/* Add guest time to cpustat. */
- if (TASK_NICE(p) > 0) {
+ if (task_nice(p) > 0) {
cpustat[CPUTIME_NICE] += (__force u64) cputime;
cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
} else {
@@ -258,16 +258,22 @@ static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(&paravirt_steal_enabled)) {
- u64 steal, st = 0;
+ u64 steal;
+ cputime_t steal_ct;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
- st = steal_ticks(steal);
- this_rq()->prev_steal_time += st * TICK_NSEC;
+ /*
+ * cputime_t may be less precise than nsecs (eg: if it's
+ * based on jiffies). Lets cast the result to cputime
+ * granularity and account the rest on the next rounds.
+ */
+ steal_ct = nsecs_to_cputime(steal);
+ this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
- account_steal_time(st);
- return st;
+ account_steal_time(steal_ct);
+ return steal_ct;
}
#endif
return false;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
new file mode 100644
index 000000000000..27ef40925525
--- /dev/null
+++ b/kernel/sched/deadline.c
@@ -0,0 +1,1665 @@
+/*
+ * Deadline Scheduling Class (SCHED_DEADLINE)
+ *
+ * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
+ *
+ * Tasks that periodically executes their instances for less than their
+ * runtime won't miss any of their deadlines.
+ * Tasks that are not periodic or sporadic or that tries to execute more
+ * than their reserved bandwidth will be slowed down (and may potentially
+ * miss some of their deadlines), and won't affect any other task.
+ *
+ * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ * Juri Lelli <juri.lelli@gmail.com>,
+ * Michael Trimarchi <michael@amarulasolutions.com>,
+ * Fabio Checconi <fchecconi@gmail.com>
+ */
+#include "sched.h"
+
+#include <linux/slab.h>
+
+struct dl_bandwidth def_dl_bandwidth;
+
+static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
+{
+ return container_of(dl_se, struct task_struct, dl);
+}
+
+static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
+{
+ return container_of(dl_rq, struct rq, dl);
+}
+
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = task_rq(p);
+
+ return &rq->dl;
+}
+
+static inline int on_dl_rq(struct sched_dl_entity *dl_se)
+{
+ return !RB_EMPTY_NODE(&dl_se->rb_node);
+}
+
+static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ return dl_rq->rb_leftmost == &dl_se->rb_node;
+}
+
+void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
+{
+ raw_spin_lock_init(&dl_b->dl_runtime_lock);
+ dl_b->dl_period = period;
+ dl_b->dl_runtime = runtime;
+}
+
+extern unsigned long to_ratio(u64 period, u64 runtime);
+
+void init_dl_bw(struct dl_bw *dl_b)
+{
+ raw_spin_lock_init(&dl_b->lock);
+ raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
+ if (global_rt_runtime() == RUNTIME_INF)
+ dl_b->bw = -1;
+ else
+ dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
+ raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
+ dl_b->total_bw = 0;
+}
+
+void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
+{
+ dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+ /* zero means no -deadline tasks */
+ dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+ dl_rq->dl_nr_migratory = 0;
+ dl_rq->overloaded = 0;
+ dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#else
+ init_dl_bw(&dl_rq->dl_bw);
+#endif
+}
+
+#ifdef CONFIG_SMP
+
+static inline int dl_overloaded(struct rq *rq)
+{
+ return atomic_read(&rq->rd->dlo_count);
+}
+
+static inline void dl_set_overload(struct rq *rq)
+{
+ if (!rq->online)
+ return;
+
+ cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
+ /*
+ * Must be visible before the overload count is
+ * set (as in sched_rt.c).
+ *
+ * Matched by the barrier in pull_dl_task().
+ */
+ smp_wmb();
+ atomic_inc(&rq->rd->dlo_count);
+}
+
+static inline void dl_clear_overload(struct rq *rq)
+{
+ if (!rq->online)
+ return;
+
+ atomic_dec(&rq->rd->dlo_count);
+ cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
+}
+
+static void update_dl_migration(struct dl_rq *dl_rq)
+{
+ if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
+ if (!dl_rq->overloaded) {
+ dl_set_overload(rq_of_dl_rq(dl_rq));
+ dl_rq->overloaded = 1;
+ }
+ } else if (dl_rq->overloaded) {
+ dl_clear_overload(rq_of_dl_rq(dl_rq));
+ dl_rq->overloaded = 0;
+ }
+}
+
+static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+
+ if (p->nr_cpus_allowed > 1)
+ dl_rq->dl_nr_migratory++;
+
+ update_dl_migration(dl_rq);
+}
+
+static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+
+ if (p->nr_cpus_allowed > 1)
+ dl_rq->dl_nr_migratory--;
+
+ update_dl_migration(dl_rq);
+}
+
+/*
+ * The list of pushable -deadline task is not a plist, like in
+ * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
+ */
+static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+ struct dl_rq *dl_rq = &rq->dl;
+ struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct task_struct *entry;
+ int leftmost = 1;
+
+ BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct task_struct,
+ pushable_dl_tasks);
+ if (dl_entity_preempt(&p->dl, &entry->dl))
+ link = &parent->rb_left;
+ else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+
+ rb_link_node(&p->pushable_dl_tasks, parent, link);
+ rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+}
+
+static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+ struct dl_rq *dl_rq = &rq->dl;
+
+ if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
+ return;
+
+ if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+ struct rb_node *next_node;
+
+ next_node = rb_next(&p->pushable_dl_tasks);
+ dl_rq->pushable_dl_tasks_leftmost = next_node;
+ }
+
+ rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+ RB_CLEAR_NODE(&p->pushable_dl_tasks);
+}
+
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+ return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+}
+
+static int push_dl_task(struct rq *rq);
+
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+ return dl_task(prev);
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+ rq->post_schedule = has_pushable_dl_tasks(rq);
+}
+
+#else
+
+static inline
+void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline
+void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+ return false;
+}
+
+static inline int pull_dl_task(struct rq *rq)
+{
+ return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
+#endif /* CONFIG_SMP */
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+ int flags);
+
+/*
+ * We are being explicitly informed that a new instance is starting,
+ * and this means that:
+ * - the absolute deadline of the entity has to be placed at
+ * current time + relative deadline;
+ * - the runtime of the entity has to be set to the maximum value.
+ *
+ * The capability of specifying such event is useful whenever a -deadline
+ * entity wants to (try to!) synchronize its behaviour with the scheduler's
+ * one, and to (try to!) reconcile itself with its own scheduling
+ * parameters.
+ */
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+
+ /*
+ * We use the regular wall clock time to set deadlines in the
+ * future; in fact, we must consider execution overheads (time
+ * spent on hardirq context, etc.).
+ */
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ dl_se->dl_new = 0;
+}
+
+/*
+ * Pure Earliest Deadline First (EDF) scheduling does not deal with the
+ * possibility of a entity lasting more than what it declared, and thus
+ * exhausting its runtime.
+ *
+ * Here we are interested in making runtime overrun possible, but we do
+ * not want a entity which is misbehaving to affect the scheduling of all
+ * other entities.
+ * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS)
+ * is used, in order to confine each entity within its own bandwidth.
+ *
+ * This function deals exactly with that, and ensures that when the runtime
+ * of a entity is replenished, its deadline is also postponed. That ensures
+ * the overrunning entity can't interfere with other entity in the system and
+ * can't make them miss their deadlines. Reasons why this kind of overruns
+ * could happen are, typically, a entity voluntarily trying to overcome its
+ * runtime, or it just underestimated it during sched_setscheduler_ex().
+ */
+static void replenish_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ BUG_ON(pi_se->dl_runtime <= 0);
+
+ /*
+ * This could be the case for a !-dl task that is boosted.
+ * Just go with full inherited parameters.
+ */
+ if (dl_se->dl_deadline == 0) {
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+
+ /*
+ * We keep moving the deadline away until we get some
+ * available runtime for the entity. This ensures correct
+ * handling of situations where the runtime overrun is
+ * arbitrary large.
+ */
+ while (dl_se->runtime <= 0) {
+ dl_se->deadline += pi_se->dl_period;
+ dl_se->runtime += pi_se->dl_runtime;
+ }
+
+ /*
+ * At this point, the deadline really should be "in
+ * the future" with respect to rq->clock. If it's
+ * not, we are, for some reason, lagging too much!
+ * Anyway, after having warn userspace abut that,
+ * we still try to keep the things running by
+ * resetting the deadline and the budget of the
+ * entity.
+ */
+ if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
+ static bool lag_once = false;
+
+ if (!lag_once) {
+ lag_once = true;
+ printk_sched("sched: DL replenish lagged to much\n");
+ }
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+}
+
+/*
+ * Here we check if --at time t-- an entity (which is probably being
+ * [re]activated or, in general, enqueued) can use its remaining runtime
+ * and its current deadline _without_ exceeding the bandwidth it is
+ * assigned (function returns true if it can't). We are in fact applying
+ * one of the CBS rules: when a task wakes up, if the residual runtime
+ * over residual deadline fits within the allocated bandwidth, then we
+ * can keep the current (absolute) deadline and residual budget without
+ * disrupting the schedulability of the system. Otherwise, we should
+ * refill the runtime and set the deadline a period in the future,
+ * because keeping the current (absolute) deadline of the task would
+ * result in breaking guarantees promised to other tasks (refer to
+ * Documentation/scheduler/sched-deadline.txt for more informations).
+ *
+ * This function returns true if:
+ *
+ * runtime / (deadline - t) > dl_runtime / dl_period ,
+ *
+ * IOW we can't recycle current parameters.
+ *
+ * Notice that the bandwidth check is done against the period. For
+ * task with deadline equal to period this is the same of using
+ * dl_deadline instead of dl_period in the equation above.
+ */
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, u64 t)
+{
+ u64 left, right;
+
+ /*
+ * left and right are the two sides of the equation above,
+ * after a bit of shuffling to use multiplications instead
+ * of divisions.
+ *
+ * Note that none of the time values involved in the two
+ * multiplications are absolute: dl_deadline and dl_runtime
+ * are the relative deadline and the maximum runtime of each
+ * instance, runtime is the runtime left for the last instance
+ * and (deadline - t), since t is rq->clock, is the time left
+ * to the (absolute) deadline. Even if overflowing the u64 type
+ * is very unlikely to occur in both cases, here we scale down
+ * as we want to avoid that risk at all. Scaling down by 10
+ * means that we reduce granularity to 1us. We are fine with it,
+ * since this is only a true/false check and, anyway, thinking
+ * of anything below microseconds resolution is actually fiction
+ * (but still we want to give the user that illusion >;).
+ */
+ left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ right = ((dl_se->deadline - t) >> DL_SCALE) *
+ (pi_se->dl_runtime >> DL_SCALE);
+
+ return dl_time_before(right, left);
+}
+
+/*
+ * When a -deadline entity is queued back on the runqueue, its runtime and
+ * deadline might need updating.
+ *
+ * The policy here is that we update the deadline of the entity only if:
+ * - the current deadline is in the past,
+ * - using the remaining runtime with the current deadline would make
+ * the entity exceed its bandwidth.
+ */
+static void update_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ /*
+ * The arrival of a new instance needs special treatment, i.e.,
+ * the actual scheduling parameters have to be "renewed".
+ */
+ if (dl_se->dl_new) {
+ setup_new_dl_entity(dl_se, pi_se);
+ return;
+ }
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
+ dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+}
+
+/*
+ * If the entity depleted all its runtime, and if we want it to sleep
+ * while waiting for some new execution time to become available, we
+ * set the bandwidth enforcement timer to the replenishment instant
+ * and try to activate it.
+ *
+ * Notice that it is important for the caller to know if the timer
+ * actually started or not (i.e., the replenishment instant is in
+ * the future or in the past).
+ */
+static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+ ktime_t now, act;
+ ktime_t soft, hard;
+ unsigned long range;
+ s64 delta;
+
+ if (boosted)
+ return 0;
+ /*
+ * We want the timer to fire at the deadline, but considering
+ * that it is actually coming from rq->clock and not from
+ * hrtimer's time base reading.
+ */
+ act = ns_to_ktime(dl_se->deadline);
+ now = hrtimer_cb_get_time(&dl_se->dl_timer);
+ delta = ktime_to_ns(now) - rq_clock(rq);
+ act = ktime_add_ns(act, delta);
+
+ /*
+ * If the expiry time already passed, e.g., because the value
+ * chosen as the deadline is too small, don't even try to
+ * start the timer in the past!
+ */
+ if (ktime_us_delta(act, now) < 0)
+ return 0;
+
+ hrtimer_set_expires(&dl_se->dl_timer, act);
+
+ soft = hrtimer_get_softexpires(&dl_se->dl_timer);
+ hard = hrtimer_get_expires(&dl_se->dl_timer);
+ range = ktime_to_ns(ktime_sub(hard, soft));
+ __hrtimer_start_range_ns(&dl_se->dl_timer, soft,
+ range, HRTIMER_MODE_ABS, 0);
+
+ return hrtimer_active(&dl_se->dl_timer);
+}
+
+/*
+ * This is the bandwidth enforcement timer callback. If here, we know
+ * a task is not on its dl_rq, since the fact that the timer was running
+ * means the task is throttled and needs a runtime replenishment.
+ *
+ * However, what we actually do depends on the fact the task is active,
+ * (it is on its rq) or has been removed from there by a call to
+ * dequeue_task_dl(). In the former case we must issue the runtime
+ * replenishment and add the task back to the dl_rq; in the latter, we just
+ * do nothing but clearing dl_throttled, so that runtime and deadline
+ * updating (and the queueing back to dl_rq) will be done by the
+ * next call to enqueue_task_dl().
+ */
+static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
+{
+ struct sched_dl_entity *dl_se = container_of(timer,
+ struct sched_dl_entity,
+ dl_timer);
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = task_rq(p);
+ raw_spin_lock(&rq->lock);
+
+ /*
+ * We need to take care of a possible races here. In fact, the
+ * task might have changed its scheduling policy to something
+ * different from SCHED_DEADLINE or changed its reservation
+ * parameters (through sched_setscheduler()).
+ */
+ if (!dl_task(p) || dl_se->dl_new)
+ goto unlock;
+
+ sched_clock_tick();
+ update_rq_clock(rq);
+ dl_se->dl_throttled = 0;
+ if (p->on_rq) {
+ enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+ if (task_has_dl_policy(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ else
+ resched_task(rq->curr);
+#ifdef CONFIG_SMP
+ /*
+ * Queueing this task back might have overloaded rq,
+ * check if we need to kick someone away.
+ */
+ if (has_pushable_dl_tasks(rq))
+ push_dl_task(rq);
+#endif
+ }
+unlock:
+ raw_spin_unlock(&rq->lock);
+
+ return HRTIMER_NORESTART;
+}
+
+void init_dl_task_timer(struct sched_dl_entity *dl_se)
+{
+ struct hrtimer *timer = &dl_se->dl_timer;
+
+ if (hrtimer_active(timer)) {
+ hrtimer_try_to_cancel(timer);
+ return;
+ }
+
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ timer->function = dl_task_timer;
+}
+
+static
+int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+ int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
+ int rorun = dl_se->runtime <= 0;
+
+ if (!rorun && !dmiss)
+ return 0;
+
+ /*
+ * If we are beyond our current deadline and we are still
+ * executing, then we have already used some of the runtime of
+ * the next instance. Thus, if we do not account that, we are
+ * stealing bandwidth from the system at each deadline miss!
+ */
+ if (dmiss) {
+ dl_se->runtime = rorun ? dl_se->runtime : 0;
+ dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
+ }
+
+ return 1;
+}
+
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct sched_dl_entity *dl_se = &curr->dl;
+ u64 delta_exec;
+
+ if (!dl_task(curr) || !on_dl_rq(dl_se))
+ return;
+
+ /*
+ * Consumed budget is computed considering the time as
+ * observed by schedulable tasks (excluding time spent
+ * in hardirq context, etc.). Deadlines are instead
+ * computed using hard walltime. This seems to be the more
+ * natural solution, but the full ramifications of this
+ * approach need further study.
+ */
+ delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+ if (unlikely((s64)delta_exec <= 0))
+ return;
+
+ schedstat_set(curr->se.statistics.exec_max,
+ max(curr->se.statistics.exec_max, delta_exec));
+
+ curr->se.sum_exec_runtime += delta_exec;
+ account_group_exec_runtime(curr, delta_exec);
+
+ curr->se.exec_start = rq_clock_task(rq);
+ cpuacct_charge(curr, delta_exec);
+
+ sched_rt_avg_update(rq, delta_exec);
+
+ dl_se->runtime -= delta_exec;
+ if (dl_runtime_exceeded(rq, dl_se)) {
+ __dequeue_task_dl(rq, curr, 0);
+ if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
+ dl_se->dl_throttled = 1;
+ else
+ enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+
+ if (!is_leftmost(curr, &rq->dl))
+ resched_task(curr);
+ }
+
+ /*
+ * Because -- for now -- we share the rt bandwidth, we need to
+ * account our runtime there too, otherwise actual rt tasks
+ * would be able to exceed the shared quota.
+ *
+ * Account to the root rt group for now.
+ *
+ * The solution we're working towards is having the RT groups scheduled
+ * using deadline servers -- however there's a few nasties to figure
+ * out before that can happen.
+ */
+ if (rt_bandwidth_enabled()) {
+ struct rt_rq *rt_rq = &rq->rt;
+
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
+ /*
+ * We'll let actual RT tasks worry about the overflow here, we
+ * have our own CBS to keep us inline; only account when RT
+ * bandwidth is relevant.
+ */
+ if (sched_rt_bandwidth_account(rt_rq))
+ rt_rq->rt_time += delta_exec;
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ }
+}
+
+#ifdef CONFIG_SMP
+
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
+
+static inline u64 next_deadline(struct rq *rq)
+{
+ struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
+
+ if (next && dl_prio(next->prio))
+ return next->dl.deadline;
+ else
+ return 0;
+}
+
+static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ if (dl_rq->earliest_dl.curr == 0 ||
+ dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+ /*
+ * If the dl_rq had no -deadline tasks, or if the new task
+ * has shorter deadline than the current one on dl_rq, we
+ * know that the previous earliest becomes our next earliest,
+ * as the new task becomes the earliest itself.
+ */
+ dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
+ dl_rq->earliest_dl.curr = deadline;
+ cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
+ } else if (dl_rq->earliest_dl.next == 0 ||
+ dl_time_before(deadline, dl_rq->earliest_dl.next)) {
+ /*
+ * On the other hand, if the new -deadline task has a
+ * a later deadline than the earliest one on dl_rq, but
+ * it is earlier than the next (if any), we must
+ * recompute the next-earliest.
+ */
+ dl_rq->earliest_dl.next = next_deadline(rq);
+ }
+}
+
+static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ /*
+ * Since we may have removed our earliest (and/or next earliest)
+ * task we must recompute them.
+ */
+ if (!dl_rq->dl_nr_running) {
+ dl_rq->earliest_dl.curr = 0;
+ dl_rq->earliest_dl.next = 0;
+ cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+ } else {
+ struct rb_node *leftmost = dl_rq->rb_leftmost;
+ struct sched_dl_entity *entry;
+
+ entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
+ dl_rq->earliest_dl.curr = entry->deadline;
+ dl_rq->earliest_dl.next = next_deadline(rq);
+ cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
+ }
+}
+
+#else
+
+static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+
+#endif /* CONFIG_SMP */
+
+static inline
+void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ int prio = dl_task_of(dl_se)->prio;
+ u64 deadline = dl_se->deadline;
+
+ WARN_ON(!dl_prio(prio));
+ dl_rq->dl_nr_running++;
+ inc_nr_running(rq_of_dl_rq(dl_rq));
+
+ inc_dl_deadline(dl_rq, deadline);
+ inc_dl_migration(dl_se, dl_rq);
+}
+
+static inline
+void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ int prio = dl_task_of(dl_se)->prio;
+
+ WARN_ON(!dl_prio(prio));
+ WARN_ON(!dl_rq->dl_nr_running);
+ dl_rq->dl_nr_running--;
+ dec_nr_running(rq_of_dl_rq(dl_rq));
+
+ dec_dl_deadline(dl_rq, dl_se->deadline);
+ dec_dl_migration(dl_se, dl_rq);
+}
+
+static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rb_node **link = &dl_rq->rb_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct sched_dl_entity *entry;
+ int leftmost = 1;
+
+ BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct sched_dl_entity, rb_node);
+ if (dl_time_before(dl_se->deadline, entry->deadline))
+ link = &parent->rb_left;
+ else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ dl_rq->rb_leftmost = &dl_se->rb_node;
+
+ rb_link_node(&dl_se->rb_node, parent, link);
+ rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
+
+ inc_dl_tasks(dl_se, dl_rq);
+}
+
+static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+ if (RB_EMPTY_NODE(&dl_se->rb_node))
+ return;
+
+ if (dl_rq->rb_leftmost == &dl_se->rb_node) {
+ struct rb_node *next_node;
+
+ next_node = rb_next(&dl_se->rb_node);
+ dl_rq->rb_leftmost = next_node;
+ }
+
+ rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
+ RB_CLEAR_NODE(&dl_se->rb_node);
+
+ dec_dl_tasks(dl_se, dl_rq);
+}
+
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, int flags)
+{
+ BUG_ON(on_dl_rq(dl_se));
+
+ /*
+ * If this is a wakeup or a new instance, the scheduling
+ * parameters of the task might need updating. Otherwise,
+ * we want a replenishment of its runtime.
+ */
+ if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
+ replenish_dl_entity(dl_se, pi_se);
+ else
+ update_dl_entity(dl_se, pi_se);
+
+ __enqueue_dl_entity(dl_se);
+}
+
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ __dequeue_dl_entity(dl_se);
+}
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
+ struct sched_dl_entity *pi_se = &p->dl;
+
+ /*
+ * Use the scheduling parameters of the top pi-waiter
+ * task if we have one and its (relative) deadline is
+ * smaller than our one... OTW we keep our runtime and
+ * deadline.
+ */
+ if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+ pi_se = &pi_task->dl;
+
+ /*
+ * If p is throttled, we do nothing. In fact, if it exhausted
+ * its budget it needs a replenishment and, since it now is on
+ * its rq, the bandwidth timer callback (which clearly has not
+ * run yet) will take care of this.
+ */
+ if (p->dl.dl_throttled)
+ return;
+
+ enqueue_dl_entity(&p->dl, pi_se, flags);
+
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
+}
+
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ dequeue_dl_entity(&p->dl);
+ dequeue_pushable_dl_task(rq, p);
+}
+
+static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ update_curr_dl(rq);
+ __dequeue_task_dl(rq, p, flags);
+}
+
+/*
+ * Yield task semantic for -deadline tasks is:
+ *
+ * get off from the CPU until our next instance, with
+ * a new runtime. This is of little use now, since we
+ * don't have a bandwidth reclaiming mechanism. Anyway,
+ * bandwidth reclaiming is planned for the future, and
+ * yield_task_dl will indicate that some spare budget
+ * is available for other task instances to use it.
+ */
+static void yield_task_dl(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ /*
+ * We make the task go to sleep until its current deadline by
+ * forcing its runtime to zero. This way, update_curr_dl() stops
+ * it and the bandwidth timer will wake it up and will give it
+ * new scheduling parameters (thanks to dl_new=1).
+ */
+ if (p->dl.runtime > 0) {
+ rq->curr->dl.dl_new = 1;
+ p->dl.runtime = 0;
+ }
+ update_curr_dl(rq);
+}
+
+#ifdef CONFIG_SMP
+
+static int find_later_rq(struct task_struct *task);
+
+static int
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+ struct task_struct *curr;
+ struct rq *rq;
+
+ if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+ goto out;
+
+ rq = cpu_rq(cpu);
+
+ rcu_read_lock();
+ curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
+ /*
+ * If we are dealing with a -deadline task, we must
+ * decide where to wake it up.
+ * If it has a later deadline and the current task
+ * on this rq can't move (provided the waking task
+ * can!) we prefer to send it somewhere else. On the
+ * other hand, if it has a shorter deadline, we
+ * try to make it stay here, it might be important.
+ */
+ if (unlikely(dl_task(curr)) &&
+ (curr->nr_cpus_allowed < 2 ||
+ !dl_entity_preempt(&p->dl, &curr->dl)) &&
+ (p->nr_cpus_allowed > 1)) {
+ int target = find_later_rq(p);
+
+ if (target != -1)
+ cpu = target;
+ }
+ rcu_read_unlock();
+
+out:
+ return cpu;
+}
+
+static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
+{
+ /*
+ * Current can't be migrated, useless to reschedule,
+ * let's hope p can move out.
+ */
+ if (rq->curr->nr_cpus_allowed == 1 ||
+ cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
+ return;
+
+ /*
+ * p is migratable, so let's not schedule it and
+ * see if it is pushed or pulled somewhere else.
+ */
+ if (p->nr_cpus_allowed != 1 &&
+ cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
+ return;
+
+ resched_task(rq->curr);
+}
+
+static int pull_dl_task(struct rq *this_rq);
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Only called when both the current and waking task are -deadline
+ * tasks.
+ */
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+ int flags)
+{
+ if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
+ resched_task(rq->curr);
+ return;
+ }
+
+#ifdef CONFIG_SMP
+ /*
+ * In the unlikely case current and p have the same deadline
+ * let us try to decide what's the best thing to do...
+ */
+ if ((p->dl.deadline == rq->curr->dl.deadline) &&
+ !test_tsk_need_resched(rq->curr))
+ check_preempt_equal_dl(rq, p);
+#endif /* CONFIG_SMP */
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+{
+ s64 delta = p->dl.dl_runtime - p->dl.runtime;
+
+ if (delta > 10000)
+ hrtick_start(rq, p->dl.runtime);
+}
+#endif
+
+static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
+ struct dl_rq *dl_rq)
+{
+ struct rb_node *left = dl_rq->rb_leftmost;
+
+ if (!left)
+ return NULL;
+
+ return rb_entry(left, struct sched_dl_entity, rb_node);
+}
+
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
+{
+ struct sched_dl_entity *dl_se;
+ struct task_struct *p;
+ struct dl_rq *dl_rq;
+
+ dl_rq = &rq->dl;
+
+ if (need_pull_dl_task(rq, prev))
+ pull_dl_task(rq);
+ /*
+ * When prev is DL, we may throttle it in put_prev_task().
+ * So, we update time before we check for dl_nr_running.
+ */
+ if (prev->sched_class == &dl_sched_class)
+ update_curr_dl(rq);
+
+ if (unlikely(!dl_rq->dl_nr_running))
+ return NULL;
+
+ put_prev_task(rq, prev);
+
+ dl_se = pick_next_dl_entity(rq, dl_rq);
+ BUG_ON(!dl_se);
+
+ p = dl_task_of(dl_se);
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* Running task will never be pushed. */
+ dequeue_pushable_dl_task(rq, p);
+
+#ifdef CONFIG_SCHED_HRTICK
+ if (hrtick_enabled(rq))
+ start_hrtick_dl(rq, p);
+#endif
+
+ set_post_schedule(rq);
+
+ return p;
+}
+
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+{
+ update_curr_dl(rq);
+
+ if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
+}
+
+static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
+{
+ update_curr_dl(rq);
+
+#ifdef CONFIG_SCHED_HRTICK
+ if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+ start_hrtick_dl(rq, p);
+#endif
+}
+
+static void task_fork_dl(struct task_struct *p)
+{
+ /*
+ * SCHED_DEADLINE tasks cannot fork and this is achieved through
+ * sched_fork()
+ */
+}
+
+static void task_dead_dl(struct task_struct *p)
+{
+ struct hrtimer *timer = &p->dl.dl_timer;
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+ /*
+ * Since we are TASK_DEAD we won't slip out of the domain!
+ */
+ raw_spin_lock_irq(&dl_b->lock);
+ dl_b->total_bw -= p->dl.dl_bw;
+ raw_spin_unlock_irq(&dl_b->lock);
+
+ hrtimer_cancel(timer);
+}
+
+static void set_curr_task_dl(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* You can't push away the running task */
+ dequeue_pushable_dl_task(rq, p);
+}
+
+#ifdef CONFIG_SMP
+
+/* Only try algorithms three times */
+#define DL_MAX_TRIES 3
+
+static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
+{
+ if (!task_running(rq, p) &&
+ (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+ (p->nr_cpus_allowed > 1))
+ return 1;
+
+ return 0;
+}
+
+/* Returns the second earliest -deadline task, NULL otherwise */
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
+{
+ struct rb_node *next_node = rq->dl.rb_leftmost;
+ struct sched_dl_entity *dl_se;
+ struct task_struct *p = NULL;
+
+next_node:
+ next_node = rb_next(next_node);
+ if (next_node) {
+ dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
+ p = dl_task_of(dl_se);
+
+ if (pick_dl_task(rq, p, cpu))
+ return p;
+
+ goto next_node;
+ }
+
+ return NULL;
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+
+static int find_later_rq(struct task_struct *task)
+{
+ struct sched_domain *sd;
+ struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+ int this_cpu = smp_processor_id();
+ int best_cpu, cpu = task_cpu(task);
+
+ /* Make sure the mask is initialized first */
+ if (unlikely(!later_mask))
+ return -1;
+
+ if (task->nr_cpus_allowed == 1)
+ return -1;
+
+ best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
+ task, later_mask);
+ if (best_cpu == -1)
+ return -1;
+
+ /*
+ * If we are here, some target has been found,
+ * the most suitable of which is cached in best_cpu.
+ * This is, among the runqueues where the current tasks
+ * have later deadlines than the task's one, the rq
+ * with the latest possible one.
+ *
+ * Now we check how well this matches with task's
+ * affinity and system topology.
+ *
+ * The last cpu where the task run is our first
+ * guess, since it is most likely cache-hot there.
+ */
+ if (cpumask_test_cpu(cpu, later_mask))
+ return cpu;
+ /*
+ * Check if this_cpu is to be skipped (i.e., it is
+ * not in the mask) or not.
+ */
+ if (!cpumask_test_cpu(this_cpu, later_mask))
+ this_cpu = -1;
+
+ rcu_read_lock();
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_AFFINE) {
+
+ /*
+ * If possible, preempting this_cpu is
+ * cheaper than migrating.
+ */
+ if (this_cpu != -1 &&
+ cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+ rcu_read_unlock();
+ return this_cpu;
+ }
+
+ /*
+ * Last chance: if best_cpu is valid and is
+ * in the mask, that becomes our choice.
+ */
+ if (best_cpu < nr_cpu_ids &&
+ cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+ rcu_read_unlock();
+ return best_cpu;
+ }
+ }
+ }
+ rcu_read_unlock();
+
+ /*
+ * At this point, all our guesses failed, we just return
+ * 'something', and let the caller sort the things out.
+ */
+ if (this_cpu != -1)
+ return this_cpu;
+
+ cpu = cpumask_any(later_mask);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+
+ return -1;
+}
+
+/* Locks the rq it finds */
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
+{
+ struct rq *later_rq = NULL;
+ int tries;
+ int cpu;
+
+ for (tries = 0; tries < DL_MAX_TRIES; tries++) {
+ cpu = find_later_rq(task);
+
+ if ((cpu == -1) || (cpu == rq->cpu))
+ break;
+
+ later_rq = cpu_rq(cpu);
+
+ /* Retry if something changed. */
+ if (double_lock_balance(rq, later_rq)) {
+ if (unlikely(task_rq(task) != rq ||
+ !cpumask_test_cpu(later_rq->cpu,
+ &task->cpus_allowed) ||
+ task_running(rq, task) || !task->on_rq)) {
+ double_unlock_balance(rq, later_rq);
+ later_rq = NULL;
+ break;
+ }
+ }
+
+ /*
+ * If the rq we found has no -deadline task, or
+ * its earliest one has a later deadline than our
+ * task, the rq is a good one.
+ */
+ if (!later_rq->dl.dl_nr_running ||
+ dl_time_before(task->dl.deadline,
+ later_rq->dl.earliest_dl.curr))
+ break;
+
+ /* Otherwise we try again. */
+ double_unlock_balance(rq, later_rq);
+ later_rq = NULL;
+ }
+
+ return later_rq;
+}
+
+static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
+{
+ struct task_struct *p;
+
+ if (!has_pushable_dl_tasks(rq))
+ return NULL;
+
+ p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+ struct task_struct, pushable_dl_tasks);
+
+ BUG_ON(rq->cpu != task_cpu(p));
+ BUG_ON(task_current(rq, p));
+ BUG_ON(p->nr_cpus_allowed <= 1);
+
+ BUG_ON(!p->on_rq);
+ BUG_ON(!dl_task(p));
+
+ return p;
+}
+
+/*
+ * See if the non running -deadline tasks on this rq
+ * can be sent to some other CPU where they can preempt
+ * and start executing.
+ */
+static int push_dl_task(struct rq *rq)
+{
+ struct task_struct *next_task;
+ struct rq *later_rq;
+
+ if (!rq->dl.overloaded)
+ return 0;
+
+ next_task = pick_next_pushable_dl_task(rq);
+ if (!next_task)
+ return 0;
+
+retry:
+ if (unlikely(next_task == rq->curr)) {
+ WARN_ON(1);
+ return 0;
+ }
+
+ /*
+ * If next_task preempts rq->curr, and rq->curr
+ * can move away, it makes sense to just reschedule
+ * without going further in pushing next_task.
+ */
+ if (dl_task(rq->curr) &&
+ dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+ rq->curr->nr_cpus_allowed > 1) {
+ resched_task(rq->curr);
+ return 0;
+ }
+
+ /* We might release rq lock */
+ get_task_struct(next_task);
+
+ /* Will lock the rq it'll find */
+ later_rq = find_lock_later_rq(next_task, rq);
+ if (!later_rq) {
+ struct task_struct *task;
+
+ /*
+ * We must check all this again, since
+ * find_lock_later_rq releases rq->lock and it is
+ * then possible that next_task has migrated.
+ */
+ task = pick_next_pushable_dl_task(rq);
+ if (task_cpu(next_task) == rq->cpu && task == next_task) {
+ /*
+ * The task is still there. We don't try
+ * again, some other cpu will pull it when ready.
+ */
+ dequeue_pushable_dl_task(rq, next_task);
+ goto out;
+ }
+
+ if (!task)
+ /* No more tasks */
+ goto out;
+
+ put_task_struct(next_task);
+ next_task = task;
+ goto retry;
+ }
+
+ deactivate_task(rq, next_task, 0);
+ set_task_cpu(next_task, later_rq->cpu);
+ activate_task(later_rq, next_task, 0);
+
+ resched_task(later_rq->curr);
+
+ double_unlock_balance(rq, later_rq);
+
+out:
+ put_task_struct(next_task);
+
+ return 1;
+}
+
+static void push_dl_tasks(struct rq *rq)
+{
+ /* Terminates as it moves a -deadline task */
+ while (push_dl_task(rq))
+ ;
+}
+
+static int pull_dl_task(struct rq *this_rq)
+{
+ int this_cpu = this_rq->cpu, ret = 0, cpu;
+ struct task_struct *p;
+ struct rq *src_rq;
+ u64 dmin = LONG_MAX;
+
+ if (likely(!dl_overloaded(this_rq)))
+ return 0;
+
+ /*
+ * Match the barrier from dl_set_overloaded; this guarantees that if we
+ * see overloaded we must also see the dlo_mask bit.
+ */
+ smp_rmb();
+
+ for_each_cpu(cpu, this_rq->rd->dlo_mask) {
+ if (this_cpu == cpu)
+ continue;
+
+ src_rq = cpu_rq(cpu);
+
+ /*
+ * It looks racy, abd it is! However, as in sched_rt.c,
+ * we are fine with this.
+ */
+ if (this_rq->dl.dl_nr_running &&
+ dl_time_before(this_rq->dl.earliest_dl.curr,
+ src_rq->dl.earliest_dl.next))
+ continue;
+
+ /* Might drop this_rq->lock */
+ double_lock_balance(this_rq, src_rq);
+
+ /*
+ * If there are no more pullable tasks on the
+ * rq, we're done with it.
+ */
+ if (src_rq->dl.dl_nr_running <= 1)
+ goto skip;
+
+ p = pick_next_earliest_dl_task(src_rq, this_cpu);
+
+ /*
+ * We found a task to be pulled if:
+ * - it preempts our current (if there's one),
+ * - it will preempt the last one we pulled (if any).
+ */
+ if (p && dl_time_before(p->dl.deadline, dmin) &&
+ (!this_rq->dl.dl_nr_running ||
+ dl_time_before(p->dl.deadline,
+ this_rq->dl.earliest_dl.curr))) {
+ WARN_ON(p == src_rq->curr);
+ WARN_ON(!p->on_rq);
+
+ /*
+ * Then we pull iff p has actually an earlier
+ * deadline than the current task of its runqueue.
+ */
+ if (dl_time_before(p->dl.deadline,
+ src_rq->curr->dl.deadline))
+ goto skip;
+
+ ret = 1;
+
+ deactivate_task(src_rq, p, 0);
+ set_task_cpu(p, this_cpu);
+ activate_task(this_rq, p, 0);
+ dmin = p->dl.deadline;
+
+ /* Is there any other task even earlier? */
+ }
+skip:
+ double_unlock_balance(this_rq, src_rq);
+ }
+
+ return ret;
+}
+
+static void post_schedule_dl(struct rq *rq)
+{
+ push_dl_tasks(rq);
+}
+
+/*
+ * Since the task is not running and a reschedule is not going to happen
+ * anytime soon on its runqueue, we try pushing it away now.
+ */
+static void task_woken_dl(struct rq *rq, struct task_struct *p)
+{
+ if (!task_running(rq, p) &&
+ !test_tsk_need_resched(rq->curr) &&
+ has_pushable_dl_tasks(rq) &&
+ p->nr_cpus_allowed > 1 &&
+ dl_task(rq->curr) &&
+ (rq->curr->nr_cpus_allowed < 2 ||
+ dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+ push_dl_tasks(rq);
+ }
+}
+
+static void set_cpus_allowed_dl(struct task_struct *p,
+ const struct cpumask *new_mask)
+{
+ struct rq *rq;
+ int weight;
+
+ BUG_ON(!dl_task(p));
+
+ /*
+ * Update only if the task is actually running (i.e.,
+ * it is on the rq AND it is not throttled).
+ */
+ if (!on_dl_rq(&p->dl))
+ return;
+
+ weight = cpumask_weight(new_mask);
+
+ /*
+ * Only update if the process changes its state from whether it
+ * can migrate or not.
+ */
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
+ return;
+
+ rq = task_rq(p);
+
+ /*
+ * The process used to be able to migrate OR it can now migrate
+ */
+ if (weight <= 1) {
+ if (!task_current(rq, p))
+ dequeue_pushable_dl_task(rq, p);
+ BUG_ON(!rq->dl.dl_nr_migratory);
+ rq->dl.dl_nr_migratory--;
+ } else {
+ if (!task_current(rq, p))
+ enqueue_pushable_dl_task(rq, p);
+ rq->dl.dl_nr_migratory++;
+ }
+
+ update_dl_migration(&rq->dl);
+}
+
+/* Assumes rq->lock is held */
+static void rq_online_dl(struct rq *rq)
+{
+ if (rq->dl.overloaded)
+ dl_set_overload(rq);
+
+ if (rq->dl.dl_nr_running > 0)
+ cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
+}
+
+/* Assumes rq->lock is held */
+static void rq_offline_dl(struct rq *rq)
+{
+ if (rq->dl.overloaded)
+ dl_clear_overload(rq);
+
+ cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+}
+
+void init_sched_dl_class(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
+ GFP_KERNEL, cpu_to_node(i));
+}
+
+#endif /* CONFIG_SMP */
+
+static void switched_from_dl(struct rq *rq, struct task_struct *p)
+{
+ if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
+ hrtimer_try_to_cancel(&p->dl.dl_timer);
+
+#ifdef CONFIG_SMP
+ /*
+ * Since this might be the only -deadline task on the rq,
+ * this is the right place to try to pull some other one
+ * from an overloaded cpu, if any.
+ */
+ if (!rq->dl.dl_nr_running)
+ pull_dl_task(rq);
+#endif
+}
+
+/*
+ * When switching to -deadline, we may overload the rq, then
+ * we try to push someone off, if possible.
+ */
+static void switched_to_dl(struct rq *rq, struct task_struct *p)
+{
+ int check_resched = 1;
+
+ /*
+ * If p is throttled, don't consider the possibility
+ * of preempting rq->curr, the check will be done right
+ * after its runtime will get replenished.
+ */
+ if (unlikely(p->dl.dl_throttled))
+ return;
+
+ if (p->on_rq && rq->curr != p) {
+#ifdef CONFIG_SMP
+ if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+ /* Only reschedule if pushing failed */
+ check_resched = 0;
+#endif /* CONFIG_SMP */
+ if (check_resched && task_has_dl_policy(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ }
+}
+
+/*
+ * If the scheduling parameters of a -deadline task changed,
+ * a push or pull operation might be needed.
+ */
+static void prio_changed_dl(struct rq *rq, struct task_struct *p,
+ int oldprio)
+{
+ if (p->on_rq || rq->curr == p) {
+#ifdef CONFIG_SMP
+ /*
+ * This might be too much, but unfortunately
+ * we don't have the old deadline value, and
+ * we can't argue if the task is increasing
+ * or lowering its prio, so...
+ */
+ if (!rq->dl.overloaded)
+ pull_dl_task(rq);
+
+ /*
+ * If we now have a earlier deadline task than p,
+ * then reschedule, provided p is still on this
+ * runqueue.
+ */
+ if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
+ rq->curr == p)
+ resched_task(p);
+#else
+ /*
+ * Again, we don't know if p has a earlier
+ * or later deadline, so let's blindly set a
+ * (maybe not needed) rescheduling point.
+ */
+ resched_task(p);
+#endif /* CONFIG_SMP */
+ } else
+ switched_to_dl(rq, p);
+}
+
+const struct sched_class dl_sched_class = {
+ .next = &rt_sched_class,
+ .enqueue_task = enqueue_task_dl,
+ .dequeue_task = dequeue_task_dl,
+ .yield_task = yield_task_dl,
+
+ .check_preempt_curr = check_preempt_curr_dl,
+
+ .pick_next_task = pick_next_task_dl,
+ .put_prev_task = put_prev_task_dl,
+
+#ifdef CONFIG_SMP
+ .select_task_rq = select_task_rq_dl,
+ .set_cpus_allowed = set_cpus_allowed_dl,
+ .rq_online = rq_online_dl,
+ .rq_offline = rq_offline_dl,
+ .post_schedule = post_schedule_dl,
+ .task_woken = task_woken_dl,
+#endif
+
+ .set_curr_task = set_curr_task_dl,
+ .task_tick = task_tick_dl,
+ .task_fork = task_fork_dl,
+ .task_dead = task_dead_dl,
+
+ .prio_changed = prio_changed_dl,
+ .switched_from = switched_from_dl,
+ .switched_to = switched_to_dl,
+};
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 5c34d1817e8f..695f9773bb60 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,8 +111,7 @@ static char *task_group_path(struct task_group *tg)
if (autogroup_path(tg, group_path, PATH_MAX))
return group_path;
- cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
- return group_path;
+ return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
}
#endif
@@ -139,7 +138,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
- SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+ SEQ_printf(m, " %d", task_node(p));
#endif
#ifdef CONFIG_CGROUP_SCHED
SEQ_printf(m, " %s", task_group_path(task_group(p)));
@@ -321,6 +320,7 @@ do { \
P(sched_goidle);
#ifdef CONFIG_SMP
P64(avg_idle);
+ P64(max_idle_balance_cost);
#endif
P(ttwu_count);
@@ -371,7 +371,7 @@ static void sched_debug_header(struct seq_file *m)
PN(cpu_clk);
P(jiffies);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- P(sched_clock_stable);
+ P(sched_clock_stable());
#endif
#undef PN
#undef P
@@ -533,15 +533,15 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
unsigned long nr_faults = -1;
int cpu_current, home_node;
- if (p->numa_faults)
- nr_faults = p->numa_faults[2*node + i];
+ if (p->numa_faults_memory)
+ nr_faults = p->numa_faults_memory[2*node + i];
cpu_current = !i ? (task_node(p) == node) :
(pol && node_isset(node, pol->v.nodes));
home_node = (p->numa_preferred_nid == node);
- SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+ SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
i, node, cpu_current, home_node, nr_faults);
}
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e64b0794060e..7e9bd0b1fa9e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -322,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
-static inline int
+static inline struct cfs_rq *
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
if (se->cfs_rq == pse->cfs_rq)
- return 1;
+ return se->cfs_rq;
- return 0;
+ return NULL;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -336,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
return se->parent;
}
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
- int depth = 0;
-
- for_each_sched_entity(se)
- depth++;
-
- return depth;
-}
-
static void
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
{
@@ -360,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
*/
/* First walk up until both entities are at same depth */
- se_depth = depth_se(*se);
- pse_depth = depth_se(*pse);
+ se_depth = (*se)->depth;
+ pse_depth = (*pse)->depth;
while (se_depth > pse_depth) {
se_depth--;
@@ -426,12 +415,6 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
- return 1;
-}
-
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return NULL;
@@ -819,14 +802,6 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;
-/*
- * After skipping a page migration on a shared page, skip N more numa page
- * migrations unconditionally. This reduces the number of NUMA migrations
- * in shared memory workloads, and has the effect of pulling tasks towards
- * where their memory lives, over pulling the memory towards the task.
- */
-unsigned int sysctl_numa_balancing_migrate_deferred = 16;
-
static unsigned int task_nr_scan_windows(struct task_struct *p)
{
unsigned long rss = 0;
@@ -872,15 +847,6 @@ static unsigned int task_scan_max(struct task_struct *p)
return max(smin, smax);
}
-/*
- * Once a preferred node is selected the scheduler balancer will prefer moving
- * a task to that node for sysctl_numa_balancing_settle_count number of PTE
- * scans. This will give the process the chance to accumulate more faults on
- * the preferred node but still allow the scheduler to move the task again if
- * the nodes CPUs are overloaded.
- */
-unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
-
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -902,10 +868,26 @@ struct numa_group {
struct list_head task_list;
struct rcu_head rcu;
+ nodemask_t active_nodes;
unsigned long total_faults;
+ /*
+ * Faults_cpu is used to decide whether memory should move
+ * towards the CPU. As a consequence, these stats are weighted
+ * more by CPU use than by memory faults.
+ */
+ unsigned long *faults_cpu;
unsigned long faults[0];
};
+/* Shared or private faults. */
+#define NR_NUMA_HINT_FAULT_TYPES 2
+
+/* Memory and CPU locality */
+#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
+
+/* Averaged statistics, and temporary buffers. */
+#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
+
pid_t task_numa_group_id(struct task_struct *p)
{
return p->numa_group ? p->numa_group->gid : 0;
@@ -913,16 +895,16 @@ pid_t task_numa_group_id(struct task_struct *p)
static inline int task_faults_idx(int nid, int priv)
{
- return 2 * nid + priv;
+ return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
}
static inline unsigned long task_faults(struct task_struct *p, int nid)
{
- if (!p->numa_faults)
+ if (!p->numa_faults_memory)
return 0;
- return p->numa_faults[task_faults_idx(nid, 0)] +
- p->numa_faults[task_faults_idx(nid, 1)];
+ return p->numa_faults_memory[task_faults_idx(nid, 0)] +
+ p->numa_faults_memory[task_faults_idx(nid, 1)];
}
static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -930,7 +912,14 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
if (!p->numa_group)
return 0;
- return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1];
+ return p->numa_group->faults[task_faults_idx(nid, 0)] +
+ p->numa_group->faults[task_faults_idx(nid, 1)];
+}
+
+static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
+{
+ return group->faults_cpu[task_faults_idx(nid, 0)] +
+ group->faults_cpu[task_faults_idx(nid, 1)];
}
/*
@@ -943,7 +932,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid)
{
unsigned long total_faults;
- if (!p->numa_faults)
+ if (!p->numa_faults_memory)
return 0;
total_faults = p->total_numa_faults;
@@ -962,6 +951,69 @@ static inline unsigned long group_weight(struct task_struct *p, int nid)
return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
}
+bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+ int src_nid, int dst_cpu)
+{
+ struct numa_group *ng = p->numa_group;
+ int dst_nid = cpu_to_node(dst_cpu);
+ int last_cpupid, this_cpupid;
+
+ this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+
+ /*
+ * Multi-stage node selection is used in conjunction with a periodic
+ * migration fault to build a temporal task<->page relation. By using
+ * a two-stage filter we remove short/unlikely relations.
+ *
+ * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
+ * a task's usage of a particular page (n_p) per total usage of this
+ * page (n_t) (in a given time-span) to a probability.
+ *
+ * Our periodic faults will sample this probability and getting the
+ * same result twice in a row, given these samples are fully
+ * independent, is then given by P(n)^2, provided our sample period
+ * is sufficiently short compared to the usage pattern.
+ *
+ * This quadric squishes small probabilities, making it less likely we
+ * act on an unlikely task<->page relation.
+ */
+ last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+ if (!cpupid_pid_unset(last_cpupid) &&
+ cpupid_to_nid(last_cpupid) != dst_nid)
+ return false;
+
+ /* Always allow migrate on private faults */
+ if (cpupid_match_pid(p, last_cpupid))
+ return true;
+
+ /* A shared fault, but p->numa_group has not been set up yet. */
+ if (!ng)
+ return true;
+
+ /*
+ * Do not migrate if the destination is not a node that
+ * is actively used by this numa group.
+ */
+ if (!node_isset(dst_nid, ng->active_nodes))
+ return false;
+
+ /*
+ * Source is a node that is not actively used by this
+ * numa group, while the destination is. Migrate.
+ */
+ if (!node_isset(src_nid, ng->active_nodes))
+ return true;
+
+ /*
+ * Both source and destination are nodes in active
+ * use by this numa group. Maximize memory bandwidth
+ * by migrating from more heavily used groups, to less
+ * heavily used ones, spreading the load around.
+ * Use a 1/4 hysteresis to avoid spurious page movement.
+ */
+ return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+}
+
static unsigned long weighted_cpuload(const int cpu);
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
@@ -1023,7 +1075,7 @@ struct task_numa_env {
struct numa_stats src_stats, dst_stats;
- int imbalance_pct, idx;
+ int imbalance_pct;
struct task_struct *best_task;
long best_imp;
@@ -1211,7 +1263,7 @@ static int task_numa_migrate(struct task_struct *p)
* elsewhere, so there is no point in (re)trying.
*/
if (unlikely(!sd)) {
- p->numa_preferred_nid = cpu_to_node(task_cpu(p));
+ p->numa_preferred_nid = task_node(p);
return -EINVAL;
}
@@ -1258,11 +1310,15 @@ static int task_numa_migrate(struct task_struct *p)
p->numa_scan_period = task_scan_min(p);
if (env.best_task == NULL) {
- int ret = migrate_task_to(p, env.best_cpu);
+ ret = migrate_task_to(p, env.best_cpu);
+ if (ret != 0)
+ trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
return ret;
}
ret = migrate_swap(p, env.best_task);
+ if (ret != 0)
+ trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
put_task_struct(env.best_task);
return ret;
}
@@ -1271,14 +1327,14 @@ static int task_numa_migrate(struct task_struct *p)
static void numa_migrate_preferred(struct task_struct *p)
{
/* This task has no NUMA fault statistics yet */
- if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
+ if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
return;
/* Periodically retry migrating the task to the preferred node */
p->numa_migrate_retry = jiffies + HZ;
/* Success if task is already running on preferred CPU */
- if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+ if (task_node(p) == p->numa_preferred_nid)
return;
/* Otherwise, try migrate to a CPU on the preferred node */
@@ -1286,6 +1342,38 @@ static void numa_migrate_preferred(struct task_struct *p)
}
/*
+ * Find the nodes on which the workload is actively running. We do this by
+ * tracking the nodes from which NUMA hinting faults are triggered. This can
+ * be different from the set of nodes where the workload's memory is currently
+ * located.
+ *
+ * The bitmask is used to make smarter decisions on when to do NUMA page
+ * migrations, To prevent flip-flopping, and excessive page migrations, nodes
+ * are added when they cause over 6/16 of the maximum number of faults, but
+ * only removed when they drop below 3/16.
+ */
+static void update_numa_active_node_mask(struct numa_group *numa_group)
+{
+ unsigned long faults, max_faults = 0;
+ int nid;
+
+ for_each_online_node(nid) {
+ faults = group_faults_cpu(numa_group, nid);
+ if (faults > max_faults)
+ max_faults = faults;
+ }
+
+ for_each_online_node(nid) {
+ faults = group_faults_cpu(numa_group, nid);
+ if (!node_isset(nid, numa_group->active_nodes)) {
+ if (faults > max_faults * 6 / 16)
+ node_set(nid, numa_group->active_nodes);
+ } else if (faults < max_faults * 3 / 16)
+ node_clear(nid, numa_group->active_nodes);
+ }
+}
+
+/*
* When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
* increments. The more local the fault statistics are, the higher the scan
* period will be for the next scan window. If local/remote ratio is below
@@ -1350,7 +1438,6 @@ static void update_task_scan_period(struct task_struct *p,
* scanning faster if shared accesses dominate as it may
* simply bounce migrations uselessly
*/
- period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
}
@@ -1360,11 +1447,41 @@ static void update_task_scan_period(struct task_struct *p,
memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
}
+/*
+ * Get the fraction of time the task has been running since the last
+ * NUMA placement cycle. The scheduler keeps similar statistics, but
+ * decays those on a 32ms period, which is orders of magnitude off
+ * from the dozens-of-seconds NUMA balancing period. Use the scheduler
+ * stats only if the task is so new there are no NUMA statistics yet.
+ */
+static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
+{
+ u64 runtime, delta, now;
+ /* Use the start of this time slice to avoid calculations. */
+ now = p->se.exec_start;
+ runtime = p->se.sum_exec_runtime;
+
+ if (p->last_task_numa_placement) {
+ delta = runtime - p->last_sum_exec_runtime;
+ *period = now - p->last_task_numa_placement;
+ } else {
+ delta = p->se.avg.runnable_avg_sum;
+ *period = p->se.avg.runnable_avg_period;
+ }
+
+ p->last_sum_exec_runtime = runtime;
+ p->last_task_numa_placement = now;
+
+ return delta;
+}
+
static void task_numa_placement(struct task_struct *p)
{
int seq, nid, max_nid = -1, max_group_nid = -1;
unsigned long max_faults = 0, max_group_faults = 0;
unsigned long fault_types[2] = { 0, 0 };
+ unsigned long total_faults;
+ u64 runtime, period;
spinlock_t *group_lock = NULL;
seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1373,6 +1490,10 @@ static void task_numa_placement(struct task_struct *p)
p->numa_scan_seq = seq;
p->numa_scan_period_max = task_scan_max(p);
+ total_faults = p->numa_faults_locality[0] +
+ p->numa_faults_locality[1];
+ runtime = numa_get_avg_runtime(p, &period);
+
/* If the task is part of a group prevent parallel updates to group stats */
if (p->numa_group) {
group_lock = &p->numa_group->lock;
@@ -1384,24 +1505,37 @@ static void task_numa_placement(struct task_struct *p)
unsigned long faults = 0, group_faults = 0;
int priv, i;
- for (priv = 0; priv < 2; priv++) {
- long diff;
+ for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
+ long diff, f_diff, f_weight;
i = task_faults_idx(nid, priv);
- diff = -p->numa_faults[i];
/* Decay existing window, copy faults since last scan */
- p->numa_faults[i] >>= 1;
- p->numa_faults[i] += p->numa_faults_buffer[i];
- fault_types[priv] += p->numa_faults_buffer[i];
- p->numa_faults_buffer[i] = 0;
+ diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
+ fault_types[priv] += p->numa_faults_buffer_memory[i];
+ p->numa_faults_buffer_memory[i] = 0;
- faults += p->numa_faults[i];
- diff += p->numa_faults[i];
+ /*
+ * Normalize the faults_from, so all tasks in a group
+ * count according to CPU use, instead of by the raw
+ * number of faults. Tasks with little runtime have
+ * little over-all impact on throughput, and thus their
+ * faults are less important.
+ */
+ f_weight = div64_u64(runtime << 16, period + 1);
+ f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+ (total_faults + 1);
+ f_diff = f_weight - p->numa_faults_cpu[i] / 2;
+ p->numa_faults_buffer_cpu[i] = 0;
+
+ p->numa_faults_memory[i] += diff;
+ p->numa_faults_cpu[i] += f_diff;
+ faults += p->numa_faults_memory[i];
p->total_numa_faults += diff;
if (p->numa_group) {
/* safe because we can only change our own group */
p->numa_group->faults[i] += diff;
+ p->numa_group->faults_cpu[i] += f_diff;
p->numa_group->total_faults += diff;
group_faults += p->numa_group->faults[i];
}
@@ -1421,6 +1555,7 @@ static void task_numa_placement(struct task_struct *p)
update_task_scan_period(p, fault_types[0], fault_types[1]);
if (p->numa_group) {
+ update_numa_active_node_mask(p->numa_group);
/*
* If the preferred task and group nids are different,
* iterate over the nodes again to find the best place.
@@ -1470,7 +1605,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
if (unlikely(!p->numa_group)) {
unsigned int size = sizeof(struct numa_group) +
- 2*nr_node_ids*sizeof(unsigned long);
+ 4*nr_node_ids*sizeof(unsigned long);
grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
if (!grp)
@@ -1480,9 +1615,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
spin_lock_init(&grp->lock);
INIT_LIST_HEAD(&grp->task_list);
grp->gid = p->pid;
+ /* Second half of the array tracks nids where faults happen */
+ grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
+ nr_node_ids;
- for (i = 0; i < 2*nr_node_ids; i++)
- grp->faults[i] = p->numa_faults[i];
+ node_set(task_node(current), grp->active_nodes);
+
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+ grp->faults[i] = p->numa_faults_memory[i];
grp->total_faults = p->total_numa_faults;
@@ -1539,9 +1679,9 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
double_lock(&my_grp->lock, &grp->lock);
- for (i = 0; i < 2*nr_node_ids; i++) {
- my_grp->faults[i] -= p->numa_faults[i];
- grp->faults[i] += p->numa_faults[i];
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
+ my_grp->faults[i] -= p->numa_faults_memory[i];
+ grp->faults[i] += p->numa_faults_memory[i];
}
my_grp->total_faults -= p->total_numa_faults;
grp->total_faults += p->total_numa_faults;
@@ -1567,12 +1707,12 @@ void task_numa_free(struct task_struct *p)
{
struct numa_group *grp = p->numa_group;
int i;
- void *numa_faults = p->numa_faults;
+ void *numa_faults = p->numa_faults_memory;
if (grp) {
spin_lock(&grp->lock);
- for (i = 0; i < 2*nr_node_ids; i++)
- grp->faults[i] -= p->numa_faults[i];
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+ grp->faults[i] -= p->numa_faults_memory[i];
grp->total_faults -= p->total_numa_faults;
list_del(&p->numa_entry);
@@ -1582,18 +1722,21 @@ void task_numa_free(struct task_struct *p)
put_numa_group(grp);
}
- p->numa_faults = NULL;
- p->numa_faults_buffer = NULL;
+ p->numa_faults_memory = NULL;
+ p->numa_faults_buffer_memory = NULL;
+ p->numa_faults_cpu= NULL;
+ p->numa_faults_buffer_cpu = NULL;
kfree(numa_faults);
}
/*
* Got a PROT_NONE fault for a page on @node.
*/
-void task_numa_fault(int last_cpupid, int node, int pages, int flags)
+void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
{
struct task_struct *p = current;
bool migrated = flags & TNF_MIGRATED;
+ int cpu_node = task_node(current);
int priv;
if (!numabalancing_enabled)
@@ -1608,16 +1751,24 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
return;
/* Allocate buffer to track faults on a per-node basis */
- if (unlikely(!p->numa_faults)) {
- int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
+ if (unlikely(!p->numa_faults_memory)) {
+ int size = sizeof(*p->numa_faults_memory) *
+ NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
- /* numa_faults and numa_faults_buffer share the allocation */
- p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
- if (!p->numa_faults)
+ p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+ if (!p->numa_faults_memory)
return;
- BUG_ON(p->numa_faults_buffer);
- p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+ BUG_ON(p->numa_faults_buffer_memory);
+ /*
+ * The averaged statistics, shared & private, memory & cpu,
+ * occupy the first half of the array. The second half of the
+ * array is for current counters, which are averaged into the
+ * first set by task_numa_placement.
+ */
+ p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
+ p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
+ p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
p->total_numa_faults = 0;
memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
}
@@ -1646,7 +1797,8 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
if (migrated)
p->numa_pages_migrated += pages;
- p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+ p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
+ p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
}
@@ -1762,6 +1914,8 @@ void task_numa_work(struct callback_head *work)
start = end;
if (pages <= 0)
goto out;
+
+ cond_resched();
} while (end != vma->vm_end);
}
@@ -2222,13 +2376,20 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
se->avg.load_avg_contrib >>= NICE_0_SHIFT;
}
}
-#else
+
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
+{
+ __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+ __update_tg_runnable_avg(&rq->avg, &rq->cfs);
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
int force_update) {}
static inline void __update_tg_runnable_avg(struct sched_avg *sa,
struct cfs_rq *cfs_rq) {}
static inline void __update_group_entity_contrib(struct sched_entity *se) {}
-#endif
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
static inline void __update_task_entity_contrib(struct sched_entity *se)
{
@@ -2326,12 +2487,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
__update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
}
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
-{
- __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
- __update_tg_runnable_avg(&rq->avg, &rq->cfs);
-}
-
/* Add the load generated by se into cfs_rq's child load-average */
static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
struct sched_entity *se,
@@ -2365,13 +2520,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
}
wakeup = 0;
} else {
- /*
- * Task re-woke on same cpu (or else migrate_task_rq_fair()
- * would have made count negative); we must be careful to avoid
- * double-accounting blocked time after synchronizing decays.
- */
- se->avg.last_runnable_update += __synchronize_entity_decay(se)
- << 20;
+ __synchronize_entity_decay(se);
}
/* migrated tasks did not contribute to our blocked load */
@@ -2425,7 +2574,10 @@ void idle_exit_fair(struct rq *this_rq)
update_rq_runnable_avg(this_rq, 0);
}
-#else
+static int idle_balance(struct rq *this_rq);
+
+#else /* CONFIG_SMP */
+
static inline void update_entity_load_avg(struct sched_entity *se,
int update_cfs_rq) {}
static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
@@ -2437,7 +2589,13 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
int sleep) {}
static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
int force_update) {}
-#endif
+
+static inline int idle_balance(struct rq *rq)
+{
+ return 0;
+}
+
+#endif /* CONFIG_SMP */
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
@@ -2587,10 +2745,10 @@ static void __clear_buddies_last(struct sched_entity *se)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- if (cfs_rq->last == se)
- cfs_rq->last = NULL;
- else
+ if (cfs_rq->last != se)
break;
+
+ cfs_rq->last = NULL;
}
}
@@ -2598,10 +2756,10 @@ static void __clear_buddies_next(struct sched_entity *se)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- if (cfs_rq->next == se)
- cfs_rq->next = NULL;
- else
+ if (cfs_rq->next != se)
break;
+
+ cfs_rq->next = NULL;
}
}
@@ -2609,10 +2767,10 @@ static void __clear_buddies_skip(struct sched_entity *se)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- if (cfs_rq->skip == se)
- cfs_rq->skip = NULL;
- else
+ if (cfs_rq->skip != se)
break;
+
+ cfs_rq->skip = NULL;
}
}
@@ -2755,17 +2913,36 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
* 3) pick the "last" process, for cache locality
* 4) do not run the "skip" process, if something else is available
*/
-static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *
+pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
- struct sched_entity *se = __pick_first_entity(cfs_rq);
- struct sched_entity *left = se;
+ struct sched_entity *left = __pick_first_entity(cfs_rq);
+ struct sched_entity *se;
+
+ /*
+ * If curr is set we have to see if its left of the leftmost entity
+ * still in the tree, provided there was anything in the tree at all.
+ */
+ if (!left || (curr && entity_before(curr, left)))
+ left = curr;
+
+ se = left; /* ideally we run the leftmost entity */
/*
* Avoid running the skip buddy, if running something else can
* be done without getting too unfair.
*/
if (cfs_rq->skip == se) {
- struct sched_entity *second = __pick_next_entity(se);
+ struct sched_entity *second;
+
+ if (se == curr) {
+ second = __pick_first_entity(cfs_rq);
+ } else {
+ second = __pick_next_entity(se);
+ if (!second || (curr && entity_before(curr, second)))
+ second = curr;
+ }
+
if (second && wakeup_preempt_entity(second, left) < 1)
se = second;
}
@@ -2787,7 +2964,7 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
return se;
}
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
@@ -3442,22 +3619,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
if (!cfs_bandwidth_used())
- return;
+ return false;
if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
- return;
+ return false;
/*
* it's possible for a throttled entity to be forced into a running
* state (e.g. set_curr_task), in this case we're finished.
*/
if (cfs_rq_throttled(cfs_rq))
- return;
+ return true;
throttle_cfs_rq(cfs_rq);
+ return true;
}
static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -3567,7 +3745,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
}
static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -4101,12 +4279,16 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
- int this_cpu, int load_idx)
+ int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
unsigned long min_load = ULONG_MAX, this_load = 0;
+ int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
+ if (sd_flag & SD_BALANCE_WAKE)
+ load_idx = sd->wake_idx;
+
do {
unsigned long load, avg_load;
int local_group;
@@ -4218,13 +4400,14 @@ done:
}
/*
- * sched_balance_self: balance the current task (running on cpu) in domains
- * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
- * SD_BALANCE_EXEC.
+ * select_task_rq_fair: Select target runqueue for the waking task in domains
+ * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
*
- * Balance, ie. select the least loaded group.
+ * Balances load by selecting the idlest cpu in the idlest group, or under
+ * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
*
- * Returns the target CPU number, or the same CPU if no balancing is needed.
+ * Returns the target cpu number.
*
* preempt must be disabled.
*/
@@ -4274,7 +4457,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
}
while (sd) {
- int load_idx = sd->forkexec_idx;
struct sched_group *group;
int weight;
@@ -4283,10 +4465,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
continue;
}
- if (sd_flag & SD_BALANCE_WAKE)
- load_idx = sd->wake_idx;
-
- group = find_idlest_group(sd, p, cpu, load_idx);
+ group = find_idlest_group(sd, p, cpu, sd_flag);
if (!group) {
sd = sd->child;
continue;
@@ -4503,26 +4682,124 @@ preempt:
set_last_buddy(se);
}
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
{
- struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
+ struct task_struct *p;
+ int new_tasks;
+again:
+#ifdef CONFIG_FAIR_GROUP_SCHED
if (!cfs_rq->nr_running)
- return NULL;
+ goto idle;
+
+ if (prev->sched_class != &fair_sched_class)
+ goto simple;
+
+ /*
+ * Because of the set_next_buddy() in dequeue_task_fair() it is rather
+ * likely that a next task is from the same cgroup as the current.
+ *
+ * Therefore attempt to avoid putting and setting the entire cgroup
+ * hierarchy, only change the part that actually changes.
+ */
do {
- se = pick_next_entity(cfs_rq);
+ struct sched_entity *curr = cfs_rq->curr;
+
+ /*
+ * Since we got here without doing put_prev_entity() we also
+ * have to consider cfs_rq->curr. If it is still a runnable
+ * entity, update_curr() will update its vruntime, otherwise
+ * forget we've ever seen it.
+ */
+ if (curr && curr->on_rq)
+ update_curr(cfs_rq);
+ else
+ curr = NULL;
+
+ /*
+ * This call to check_cfs_rq_runtime() will do the throttle and
+ * dequeue its entity in the parent(s). Therefore the 'simple'
+ * nr_running test will indeed be correct.
+ */
+ if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+ goto simple;
+
+ se = pick_next_entity(cfs_rq, curr);
+ cfs_rq = group_cfs_rq(se);
+ } while (cfs_rq);
+
+ p = task_of(se);
+
+ /*
+ * Since we haven't yet done put_prev_entity and if the selected task
+ * is a different task than we started out with, try and touch the
+ * least amount of cfs_rqs.
+ */
+ if (prev != p) {
+ struct sched_entity *pse = &prev->se;
+
+ while (!(cfs_rq = is_same_group(se, pse))) {
+ int se_depth = se->depth;
+ int pse_depth = pse->depth;
+
+ if (se_depth <= pse_depth) {
+ put_prev_entity(cfs_rq_of(pse), pse);
+ pse = parent_entity(pse);
+ }
+ if (se_depth >= pse_depth) {
+ set_next_entity(cfs_rq_of(se), se);
+ se = parent_entity(se);
+ }
+ }
+
+ put_prev_entity(cfs_rq, pse);
+ set_next_entity(cfs_rq, se);
+ }
+
+ if (hrtick_enabled(rq))
+ hrtick_start_fair(rq, p);
+
+ return p;
+simple:
+ cfs_rq = &rq->cfs;
+#endif
+
+ if (!cfs_rq->nr_running)
+ goto idle;
+
+ put_prev_task(rq, prev);
+
+ do {
+ se = pick_next_entity(cfs_rq, NULL);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
+
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
return p;
+
+idle:
+ new_tasks = idle_balance(rq);
+ /*
+ * Because idle_balance() releases (and re-acquires) rq->lock, it is
+ * possible for any higher priority task to appear. In that case we
+ * must re-start the pick_next_entity() loop.
+ */
+ if (new_tasks < 0)
+ return RETRY_TASK;
+
+ if (new_tasks > 0)
+ goto again;
+
+ return NULL;
}
/*
@@ -4760,7 +5037,7 @@ static void move_task(struct task_struct *p, struct lb_env *env)
* Is this task likely cache-hot:
*/
static int
-task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
+task_hot(struct task_struct *p, u64 now)
{
s64 delta;
@@ -4794,7 +5071,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
{
int src_nid, dst_nid;
- if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+ if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
!(env->sd->flags & SD_NUMA)) {
return false;
}
@@ -4825,7 +5102,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
return false;
- if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+ if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
return false;
src_nid = cpu_to_node(env->src_cpu);
@@ -4921,7 +5198,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
* 2) task is cache cold, or
* 3) too many balance attempts have failed.
*/
- tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+ tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq));
if (!tsk_cache_hot)
tsk_cache_hot = migrate_degrades_locality(p, env);
@@ -5512,7 +5789,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs)
{
- unsigned long nr_running;
unsigned long load;
int i;
@@ -5521,8 +5797,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
- nr_running = rq->nr_running;
-
/* Bias balancing toward cpus of our domain */
if (local_group)
load = target_load(i, load_idx);
@@ -5530,7 +5804,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
load = source_load(i, load_idx);
sgs->group_load += load;
- sgs->sum_nr_running += nr_running;
+ sgs->sum_nr_running += rq->nr_running;
#ifdef CONFIG_NUMA_BALANCING
sgs->nr_numa_running += rq->nr_numa_running;
sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -5787,12 +6061,10 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
pwr_now /= SCHED_POWER_SCALE;
/* Amount of load we'd subtract */
- tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
- busiest->group_power;
- if (busiest->avg_load > tmp) {
+ if (busiest->avg_load > scaled_busy_load_per_task) {
pwr_move += busiest->group_power *
min(busiest->load_per_task,
- busiest->avg_load - tmp);
+ busiest->avg_load - scaled_busy_load_per_task);
}
/* Amount of load we'd add */
@@ -6371,17 +6643,23 @@ out:
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
-void idle_balance(int this_cpu, struct rq *this_rq)
+static int idle_balance(struct rq *this_rq)
{
struct sched_domain *sd;
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
u64 curr_cost = 0;
+ int this_cpu = this_rq->cpu;
+ idle_enter_fair(this_rq);
+ /*
+ * We must set idle_stamp _before_ calling idle_balance(), such that we
+ * measure the duration of idle_balance() as idle time.
+ */
this_rq->idle_stamp = rq_clock(this_rq);
if (this_rq->avg_idle < sysctl_sched_migration_cost)
- return;
+ goto out;
/*
* Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6419,15 +6697,22 @@ void idle_balance(int this_cpu, struct rq *this_rq)
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
- if (pulled_task) {
- this_rq->idle_stamp = 0;
+ if (pulled_task)
break;
- }
}
rcu_read_unlock();
raw_spin_lock(&this_rq->lock);
+ /*
+ * While browsing the domains, we released the rq lock.
+ * A task could have be enqueued in the meantime
+ */
+ if (this_rq->cfs.h_nr_running && !pulled_task) {
+ pulled_task = 1;
+ goto out;
+ }
+
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*
* We are going idle. next_balance may be set based on
@@ -6438,6 +6723,20 @@ void idle_balance(int this_cpu, struct rq *this_rq)
if (curr_cost > this_rq->max_idle_balance_cost)
this_rq->max_idle_balance_cost = curr_cost;
+
+out:
+ /* Is there a task of a high priority class? */
+ if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
+ (this_rq->dl.dl_nr_running ||
+ (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
+ pulled_task = -1;
+
+ if (pulled_task) {
+ idle_exit_fair(this_rq);
+ this_rq->idle_stamp = 0;
+ }
+
+ return pulled_task;
}
/*
@@ -6508,6 +6807,11 @@ out_unlock:
return 0;
}
+static inline int on_null_domain(struct rq *rq)
+{
+ return unlikely(!rcu_dereference_sched(rq->sd));
+}
+
#ifdef CONFIG_NO_HZ_COMMON
/*
* idle load balancing details
@@ -6521,7 +6825,7 @@ static struct {
unsigned long next_balance; /* in jiffy units */
} nohz ____cacheline_aligned;
-static inline int find_new_ilb(int call_cpu)
+static inline int find_new_ilb(void)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
@@ -6536,13 +6840,13 @@ static inline int find_new_ilb(int call_cpu)
* nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
* CPU (if there is one).
*/
-static void nohz_balancer_kick(int cpu)
+static void nohz_balancer_kick(void)
{
int ilb_cpu;
nohz.next_balance++;
- ilb_cpu = find_new_ilb(cpu);
+ ilb_cpu = find_new_ilb();
if (ilb_cpu >= nr_cpu_ids)
return;
@@ -6562,8 +6866,13 @@ static void nohz_balancer_kick(int cpu)
static inline void nohz_balance_exit_idle(int cpu)
{
if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
- cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
- atomic_dec(&nohz.nr_cpus);
+ /*
+ * Completely isolated CPUs don't ever set, so we must test.
+ */
+ if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
+ cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+ atomic_dec(&nohz.nr_cpus);
+ }
clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
}
}
@@ -6617,6 +6926,12 @@ void nohz_balance_enter_idle(int cpu)
if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
return;
+ /*
+ * If we're a completely isolated CPU, we don't play.
+ */
+ if (on_null_domain(cpu_rq(cpu)))
+ return;
+
cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
atomic_inc(&nohz.nr_cpus);
set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
@@ -6652,10 +6967,10 @@ void update_max_interval(void)
*
* Balancing parameters are set up in init_sched_domains.
*/
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
{
int continue_balancing = 1;
- struct rq *rq = cpu_rq(cpu);
+ int cpu = rq->cpu;
unsigned long interval;
struct sched_domain *sd;
/* Earliest time when we have to do rebalance again */
@@ -6752,9 +7067,9 @@ out:
* In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
* rebalancing for all the cpus for whom scheduler ticks are stopped.
*/
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
{
- struct rq *this_rq = cpu_rq(this_cpu);
+ int this_cpu = this_rq->cpu;
struct rq *rq;
int balance_cpu;
@@ -6781,7 +7096,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
update_idle_cpu_load(rq);
raw_spin_unlock_irq(&rq->lock);
- rebalance_domains(balance_cpu, CPU_IDLE);
+ rebalance_domains(rq, CPU_IDLE);
if (time_after(this_rq->next_balance, rq->next_balance))
this_rq->next_balance = rq->next_balance;
@@ -6800,14 +7115,14 @@ end:
* - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
* domain span are idle.
*/
-static inline int nohz_kick_needed(struct rq *rq, int cpu)
+static inline int nohz_kick_needed(struct rq *rq)
{
unsigned long now = jiffies;
struct sched_domain *sd;
struct sched_group_power *sgp;
- int nr_busy;
+ int nr_busy, cpu = rq->cpu;
- if (unlikely(idle_cpu(cpu)))
+ if (unlikely(rq->idle_balance))
return 0;
/*
@@ -6856,7 +7171,7 @@ need_kick:
return 1;
}
#else
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
#endif
/*
@@ -6865,38 +7180,34 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
*/
static void run_rebalance_domains(struct softirq_action *h)
{
- int this_cpu = smp_processor_id();
- struct rq *this_rq = cpu_rq(this_cpu);
+ struct rq *this_rq = this_rq();
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
- rebalance_domains(this_cpu, idle);
+ rebalance_domains(this_rq, idle);
/*
* If this cpu has a pending nohz_balance_kick, then do the
* balancing on behalf of the other idle cpus whose ticks are
* stopped.
*/
- nohz_idle_balance(this_cpu, idle);
-}
-
-static inline int on_null_domain(int cpu)
-{
- return !rcu_dereference_sched(cpu_rq(cpu)->sd);
+ nohz_idle_balance(this_rq, idle);
}
/*
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
*/
-void trigger_load_balance(struct rq *rq, int cpu)
+void trigger_load_balance(struct rq *rq)
{
/* Don't need to rebalance while attached to NULL domain */
- if (time_after_eq(jiffies, rq->next_balance) &&
- likely(!on_null_domain(cpu)))
+ if (unlikely(on_null_domain(rq)))
+ return;
+
+ if (time_after_eq(jiffies, rq->next_balance))
raise_softirq(SCHED_SOFTIRQ);
#ifdef CONFIG_NO_HZ_COMMON
- if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
- nohz_balancer_kick(cpu);
+ if (nohz_kick_needed(rq))
+ nohz_balancer_kick();
#endif
}
@@ -7012,15 +7323,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when its
+ * Ensure the task's vruntime is normalized, so that when it's
* switched back to the fair class the enqueue_entity(.flags=0) will
* do the right thing.
*
- * If it was on_rq, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it was !on_rq, then only when
+ * If it's on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it's !on_rq, then only when
* the task is sleeping will it still have non-normalized vruntime.
*/
- if (!se->on_rq && p->state != TASK_RUNNING) {
+ if (!p->on_rq && p->state != TASK_RUNNING) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
@@ -7047,7 +7358,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
*/
static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
- if (!p->se.on_rq)
+ struct sched_entity *se = &p->se;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ /*
+ * Since the real-depth could have been changed (only FAIR
+ * class maintain depth value), reset depth properly.
+ */
+ se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+ if (!se->on_rq)
return;
/*
@@ -7095,7 +7414,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
#ifdef CONFIG_FAIR_GROUP_SCHED
static void task_move_group_fair(struct task_struct *p, int on_rq)
{
+ struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq;
+
/*
* If the task was not on the rq at the time of this cgroup movement
* it must have been asleep, sleeping tasks keep their ->vruntime
@@ -7121,23 +7442,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
* To prevent boost or penalty in the new cfs_rq caused by delta
* min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
*/
- if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
+ if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
on_rq = 1;
if (!on_rq)
- p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+ se->vruntime -= cfs_rq_of(se)->min_vruntime;
set_task_rq(p, task_cpu(p));
+ se->depth = se->parent ? se->parent->depth + 1 : 0;
if (!on_rq) {
- cfs_rq = cfs_rq_of(&p->se);
- p->se.vruntime += cfs_rq->min_vruntime;
+ cfs_rq = cfs_rq_of(se);
+ se->vruntime += cfs_rq->min_vruntime;
#ifdef CONFIG_SMP
/*
* migrate_task_rq_fair() will have removed our previous
* contribution, but we must synchronize for ongoing future
* decay.
*/
- p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
- cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
+ se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+ cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
#endif
}
}
@@ -7233,10 +7555,13 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
if (!se)
return;
- if (!parent)
+ if (!parent) {
se->cfs_rq = &rq->cfs;
- else
+ se->depth = 0;
+ } else {
se->cfs_rq = parent->my_q;
+ se->depth = parent->depth + 1;
+ }
se->my_q = cfs_rq;
/* guarantee group entities always have weight */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
new file mode 100644
index 000000000000..8f4390a079c7
--- /dev/null
+++ b/kernel/sched/idle.c
@@ -0,0 +1,265 @@
+/*
+ * Generic entry point for the idle threads
+ */
+#include <linux/sched.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/tick.h>
+#include <linux/mm.h>
+#include <linux/stackprotector.h>
+
+#include <asm/tlb.h>
+
+#include <trace/events/power.h>
+
+static int __read_mostly cpu_idle_force_poll;
+
+void cpu_idle_poll_ctrl(bool enable)
+{
+ if (enable) {
+ cpu_idle_force_poll++;
+ } else {
+ cpu_idle_force_poll--;
+ WARN_ON_ONCE(cpu_idle_force_poll < 0);
+ }
+}
+
+#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
+static int __init cpu_idle_poll_setup(char *__unused)
+{
+ cpu_idle_force_poll = 1;
+ return 1;
+}
+__setup("nohlt", cpu_idle_poll_setup);
+
+static int __init cpu_idle_nopoll_setup(char *__unused)
+{
+ cpu_idle_force_poll = 0;
+ return 1;
+}
+__setup("hlt", cpu_idle_nopoll_setup);
+#endif
+
+static inline int cpu_idle_poll(void)
+{
+ rcu_idle_enter();
+ trace_cpu_idle_rcuidle(0, smp_processor_id());
+ local_irq_enable();
+ while (!tif_need_resched())
+ cpu_relax();
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+ rcu_idle_exit();
+ return 1;
+}
+
+/* Weak implementations for optional arch specific functions */
+void __weak arch_cpu_idle_prepare(void) { }
+void __weak arch_cpu_idle_enter(void) { }
+void __weak arch_cpu_idle_exit(void) { }
+void __weak arch_cpu_idle_dead(void) { }
+void __weak arch_cpu_idle(void)
+{
+ cpu_idle_force_poll = 1;
+ local_irq_enable();
+}
+
+/**
+ * cpuidle_idle_call - the main idle function
+ *
+ * NOTE: no locks or semaphores should be used here
+ * return non-zero on failure
+ */
+static int cpuidle_idle_call(void)
+{
+ struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+ int next_state, entered_state, ret;
+ bool broadcast;
+
+ /*
+ * Check if the idle task must be rescheduled. If it is the
+ * case, exit the function after re-enabling the local irq and
+ * set again the polling flag
+ */
+ if (current_clr_polling_and_test()) {
+ local_irq_enable();
+ __current_set_polling();
+ return 0;
+ }
+
+ /*
+ * During the idle period, stop measuring the disabled irqs
+ * critical sections latencies
+ */
+ stop_critical_timings();
+
+ /*
+ * Tell the RCU framework we are entering an idle section,
+ * so no more rcu read side critical sections and one more
+ * step to the grace period
+ */
+ rcu_idle_enter();
+
+ /*
+ * Check if the cpuidle framework is ready, otherwise fallback
+ * to the default arch specific idle method
+ */
+ ret = cpuidle_enabled(drv, dev);
+
+ if (!ret) {
+ /*
+ * Ask the governor to choose an idle state it thinks
+ * it is convenient to go to. There is *always* a
+ * convenient idle state
+ */
+ next_state = cpuidle_select(drv, dev);
+
+ /*
+ * The idle task must be scheduled, it is pointless to
+ * go to idle, just update no idle residency and get
+ * out of this function
+ */
+ if (current_clr_polling_and_test()) {
+ dev->last_residency = 0;
+ entered_state = next_state;
+ local_irq_enable();
+ } else {
+ broadcast = !!(drv->states[next_state].flags &
+ CPUIDLE_FLAG_TIMER_STOP);
+
+ if (broadcast)
+ /*
+ * Tell the time framework to switch
+ * to a broadcast timer because our
+ * local timer will be shutdown. If a
+ * local timer is used from another
+ * cpu as a broadcast timer, this call
+ * may fail if it is not available
+ */
+ ret = clockevents_notify(
+ CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
+ &dev->cpu);
+
+ if (!ret) {
+ trace_cpu_idle_rcuidle(next_state, dev->cpu);
+
+ /*
+ * Enter the idle state previously
+ * returned by the governor
+ * decision. This function will block
+ * until an interrupt occurs and will
+ * take care of re-enabling the local
+ * interrupts
+ */
+ entered_state = cpuidle_enter(drv, dev,
+ next_state);
+
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT,
+ dev->cpu);
+
+ if (broadcast)
+ clockevents_notify(
+ CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
+ &dev->cpu);
+
+ /*
+ * Give the governor an opportunity to reflect on the
+ * outcome
+ */
+ cpuidle_reflect(dev, entered_state);
+ }
+ }
+ }
+
+ /*
+ * We can't use the cpuidle framework, let's use the default
+ * idle routine
+ */
+ if (ret)
+ arch_cpu_idle();
+
+ __current_set_polling();
+
+ /*
+ * It is up to the idle functions to enable back the local
+ * interrupt
+ */
+ if (WARN_ON_ONCE(irqs_disabled()))
+ local_irq_enable();
+
+ rcu_idle_exit();
+ start_critical_timings();
+
+ return 0;
+}
+
+/*
+ * Generic idle loop implementation
+ */
+static void cpu_idle_loop(void)
+{
+ while (1) {
+ tick_nohz_idle_enter();
+
+ while (!need_resched()) {
+ check_pgt_cache();
+ rmb();
+
+ if (cpu_is_offline(smp_processor_id()))
+ arch_cpu_idle_dead();
+
+ local_irq_disable();
+ arch_cpu_idle_enter();
+
+ /*
+ * In poll mode we reenable interrupts and spin.
+ *
+ * Also if we detected in the wakeup from idle
+ * path that the tick broadcast device expired
+ * for us, we don't want to go deep idle as we
+ * know that the IPI is going to arrive right
+ * away
+ */
+ if (cpu_idle_force_poll || tick_check_broadcast_expired())
+ cpu_idle_poll();
+ else
+ cpuidle_idle_call();
+
+ arch_cpu_idle_exit();
+ }
+
+ /*
+ * Since we fell out of the loop above, we know
+ * TIF_NEED_RESCHED must be set, propagate it into
+ * PREEMPT_NEED_RESCHED.
+ *
+ * This is required because for polling idle loops we will
+ * not have had an IPI to fold the state for us.
+ */
+ preempt_set_need_resched();
+ tick_nohz_idle_exit();
+ schedule_preempt_disabled();
+ }
+}
+
+void cpu_startup_entry(enum cpuhp_state state)
+{
+ /*
+ * This #ifdef needs to die, but it's too late in the cycle to
+ * make this generic (arm and sh have never invoked the canary
+ * init for the non boot cpus!). Will be fixed in 3.11
+ */
+#ifdef CONFIG_X86
+ /*
+ * If we're the non-boot CPU, nothing set the stack canary up
+ * for us. The boot CPU already has it initialized but no harm
+ * in doing it again. This is a good place for updating it, as
+ * we wont ever return from this function (so the invalid
+ * canaries already on the stack wont ever trigger).
+ */
+ boot_init_stack_canary();
+#endif
+ __current_set_polling();
+ arch_cpu_idle_prepare();
+ cpu_idle_loop();
+}
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 516c3d9ceea1..879f2b75266a 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -13,18 +13,8 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
-
-static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
-{
- idle_exit_fair(rq);
- rq_last_tick_reset(rq);
-}
-
-static void post_schedule_idle(struct rq *rq)
-{
- idle_enter_fair(rq);
-}
#endif /* CONFIG_SMP */
+
/*
* Idle tasks are unconditionally rescheduled:
*/
@@ -33,13 +23,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
resched_task(rq->idle);
}
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
{
+ put_prev_task(rq, prev);
+
schedstat_inc(rq, sched_goidle);
-#ifdef CONFIG_SMP
- /* Trigger the post schedule to do an idle_enter for CFS */
- rq->post_schedule = 1;
-#endif
return rq->idle;
}
@@ -58,6 +47,8 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
+ idle_exit_fair(rq);
+ rq_last_tick_reset(rq);
}
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
@@ -101,8 +92,6 @@ const struct sched_class idle_sched_class = {
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_idle,
- .pre_schedule = pre_schedule_idle,
- .post_schedule = post_schedule_idle,
#endif
.set_curr_task = set_curr_task_idle,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1c4065575fa2..d8cdf1618551 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -229,6 +229,14 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
#ifdef CONFIG_SMP
+static int pull_rt_task(struct rq *this_rq);
+
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+ /* Try to pull RT tasks here if we lower this rq's prio */
+ return rq->rt.highest_prio.curr > prev->prio;
+}
+
static inline int rt_overloaded(struct rq *rq)
{
return atomic_read(&rq->rd->rto_count);
@@ -315,6 +323,15 @@ static inline int has_pushable_tasks(struct rq *rq)
return !plist_head_empty(&rq->rt.pushable_tasks);
}
+static inline void set_post_schedule(struct rq *rq)
+{
+ /*
+ * We detect this state here so that we can avoid taking the RQ
+ * lock again later if there is no need to push
+ */
+ rq->post_schedule = has_pushable_tasks(rq);
+}
+
static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
{
plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
@@ -359,6 +376,19 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
}
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+ return false;
+}
+
+static inline int pull_rt_task(struct rq *this_rq)
+{
+ return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
#endif /* CONFIG_SMP */
static inline int on_rt_rq(struct sched_rt_entity *rt_se)
@@ -440,11 +470,6 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
dequeue_rt_entity(rt_se);
}
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
static int rt_se_boosted(struct sched_rt_entity *rt_se)
{
struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -515,11 +540,6 @@ static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
}
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled;
-}
-
static inline const struct cpumask *sched_rt_period_mask(void)
{
return cpu_online_mask;
@@ -538,6 +558,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
#endif /* CONFIG_RT_GROUP_SCHED */
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+ return (hrtimer_active(&rt_b->rt_period_timer) ||
+ rt_rq->rt_time < rt_b->rt_runtime);
+}
+
#ifdef CONFIG_SMP
/*
* We ran out of runtime, see if we can borrow some from our neighbours.
@@ -1310,15 +1338,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
struct sched_rt_entity *rt_se;
struct task_struct *p;
- struct rt_rq *rt_rq;
-
- rt_rq = &rq->rt;
-
- if (!rt_rq->rt_nr_running)
- return NULL;
-
- if (rt_rq_throttled(rt_rq))
- return NULL;
+ struct rt_rq *rt_rq = &rq->rt;
do {
rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1332,21 +1352,45 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
return p;
}
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
{
- struct task_struct *p = _pick_next_task_rt(rq);
+ struct task_struct *p;
+ struct rt_rq *rt_rq = &rq->rt;
+
+ if (need_pull_rt_task(rq, prev)) {
+ pull_rt_task(rq);
+ /*
+ * pull_rt_task() can drop (and re-acquire) rq->lock; this
+ * means a dl task can slip in, in which case we need to
+ * re-start task selection.
+ */
+ if (unlikely(rq->dl.dl_nr_running))
+ return RETRY_TASK;
+ }
+
+ /*
+ * We may dequeue prev's rt_rq in put_prev_task().
+ * So, we update time before rt_nr_running check.
+ */
+ if (prev->sched_class == &rt_sched_class)
+ update_curr_rt(rq);
+
+ if (!rt_rq->rt_nr_running)
+ return NULL;
+
+ if (rt_rq_throttled(rt_rq))
+ return NULL;
+
+ put_prev_task(rq, prev);
+
+ p = _pick_next_task_rt(rq);
/* The running task is never eligible for pushing */
if (p)
dequeue_pushable_task(rq, p);
-#ifdef CONFIG_SMP
- /*
- * We detect this state here so that we can avoid taking the RQ
- * lock again later if there is no need to push
- */
- rq->post_schedule = has_pushable_tasks(rq);
-#endif
+ set_post_schedule(rq);
return p;
}
@@ -1716,13 +1760,6 @@ skip:
return ret;
}
-static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
-{
- /* Try to pull RT tasks here if we lower this rq's prio */
- if (rq->rt.highest_prio.curr > prev->prio)
- pull_rt_task(rq);
-}
-
static void post_schedule_rt(struct rq *rq)
{
push_rt_tasks(rq);
@@ -1738,7 +1775,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
p->nr_cpus_allowed > 1 &&
- rt_task(rq->curr) &&
+ (dl_task(rq->curr) || rt_task(rq->curr)) &&
(rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
@@ -1825,7 +1862,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
resched_task(rq->curr);
}
-void init_sched_rt_class(void)
+void __init init_sched_rt_class(void)
{
unsigned int i;
@@ -1999,7 +2036,6 @@ const struct sched_class rt_sched_class = {
.set_cpus_allowed = set_cpus_allowed_rt,
.rq_online = rq_online_rt,
.rq_offline = rq_offline_rt,
- .pre_schedule = pre_schedule_rt,
.post_schedule = post_schedule_rt,
.task_woken = task_woken_rt,
.switched_from = switched_from_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 88c85b21d633..c9007f28d3a2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,7 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
@@ -9,6 +10,7 @@
#include <linux/slab.h>
#include "cpupri.h"
+#include "cpudeadline.h"
#include "cpuacct.h"
struct rq;
@@ -22,24 +24,6 @@ extern long calc_load_fold_active(struct rq *this_rq);
extern void update_cpu_load_active(struct rq *this_rq);
/*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p) ((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
-
-/*
* Helpers for converting nanosecond timing to jiffy resolution
*/
#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
@@ -73,6 +57,13 @@ extern void update_cpu_load_active(struct rq *this_rq);
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
/*
+ * Single value that decides SCHED_DEADLINE internal math precision.
+ * 10 -> just above 1us
+ * 9 -> just above 0.5us
+ */
+#define DL_SCALE (10)
+
+/*
* These are the 'tuning knobs' of the scheduler:
*/
@@ -81,11 +72,19 @@ extern void update_cpu_load_active(struct rq *this_rq);
*/
#define RUNTIME_INF ((u64)~0ULL)
+static inline int fair_policy(int policy)
+{
+ return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+}
+
static inline int rt_policy(int policy)
{
- if (policy == SCHED_FIFO || policy == SCHED_RR)
- return 1;
- return 0;
+ return policy == SCHED_FIFO || policy == SCHED_RR;
+}
+
+static inline int dl_policy(int policy)
+{
+ return policy == SCHED_DEADLINE;
}
static inline int task_has_rt_policy(struct task_struct *p)
@@ -93,6 +92,25 @@ static inline int task_has_rt_policy(struct task_struct *p)
return rt_policy(p->policy);
}
+static inline int task_has_dl_policy(struct task_struct *p)
+{
+ return dl_policy(p->policy);
+}
+
+static inline bool dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline bool
+dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+ return dl_time_before(a->deadline, b->deadline);
+}
+
/*
* This is the priority-queue data structure of the RT scheduling class:
*/
@@ -108,6 +126,47 @@ struct rt_bandwidth {
u64 rt_runtime;
struct hrtimer rt_period_timer;
};
+/*
+ * To keep the bandwidth of -deadline tasks and groups under control
+ * we need some place where:
+ * - store the maximum -deadline bandwidth of the system (the group);
+ * - cache the fraction of that bandwidth that is currently allocated.
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, the bandwidth is given on a per-CPU basis,
+ * meaning that:
+ * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
+ * - dl_total_bw array contains, in the i-eth element, the currently
+ * allocated bandwidth on the i-eth CPU.
+ * Moreover, groups consume bandwidth on each CPU, while tasks only
+ * consume bandwidth on the CPU they're running on.
+ * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
+ * that will be shown the next time the proc or cgroup controls will
+ * be red. It on its turn can be changed by writing on its own
+ * control.
+ */
+struct dl_bandwidth {
+ raw_spinlock_t dl_runtime_lock;
+ u64 dl_runtime;
+ u64 dl_period;
+};
+
+static inline int dl_bandwidth_enabled(void)
+{
+ return sysctl_sched_rt_runtime >= 0;
+}
+
+extern struct dl_bw *dl_bw_of(int i);
+
+struct dl_bw {
+ raw_spinlock_t lock;
+ u64 bw, total_bw;
+};
extern struct mutex sched_domains_mutex;
@@ -364,6 +423,53 @@ struct rt_rq {
#endif
};
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+#else
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_throttled;
+}
+#endif
+
+/* Deadline class' related fields in a runqueue */
+struct dl_rq {
+ /* runqueue is an rbtree, ordered by deadline */
+ struct rb_root rb_root;
+ struct rb_node *rb_leftmost;
+
+ unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+ /*
+ * Deadline values of the currently executing and the
+ * earliest ready task on this rq. Caching these facilitates
+ * the decision wether or not a ready but not running task
+ * should migrate somewhere else.
+ */
+ struct {
+ u64 curr;
+ u64 next;
+ } earliest_dl;
+
+ unsigned long dl_nr_migratory;
+ int overloaded;
+
+ /*
+ * Tasks on this rq that can be pushed away. They are kept in
+ * an rb-tree, ordered by tasks' deadlines, with caching
+ * of the leftmost (earliest deadline) element.
+ */
+ struct rb_root pushable_dl_tasks_root;
+ struct rb_node *pushable_dl_tasks_leftmost;
+#else
+ struct dl_bw dl_bw;
+#endif
+};
+
#ifdef CONFIG_SMP
/*
@@ -382,6 +488,15 @@ struct root_domain {
cpumask_var_t online;
/*
+ * The bit corresponding to a CPU gets set here if such CPU has more
+ * than one runnable -deadline task (as it is below for RT tasks).
+ */
+ cpumask_var_t dlo_mask;
+ atomic_t dlo_count;
+ struct dl_bw dl_bw;
+ struct cpudl cpudl;
+
+ /*
* The "RT overload" flag: it gets set if a CPU has more than
* one runnable RT task.
*/
@@ -432,15 +547,14 @@ struct rq {
struct cfs_rq cfs;
struct rt_rq rt;
+ struct dl_rq dl;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
-#ifdef CONFIG_RT_GROUP_SCHED
- struct list_head leaf_rt_rq_list;
-#endif
+ struct sched_avg avg;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
/*
* This is part of a global counter where only the total sum
@@ -529,8 +643,6 @@ struct rq {
#ifdef CONFIG_SMP
struct llist_head wake_list;
#endif
-
- struct sched_avg avg;
};
static inline int cpu_of(struct rq *rq)
@@ -827,8 +939,6 @@ static inline u64 global_rt_runtime(void)
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
-
-
static inline int task_current(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
@@ -988,9 +1098,12 @@ static const u32 prio_to_wmult[40] = {
#else
#define ENQUEUE_WAKING 0
#endif
+#define ENQUEUE_REPLENISH 8
#define DEQUEUE_SLEEP 1
+#define RETRY_TASK ((void *)-1UL)
+
struct sched_class {
const struct sched_class *next;
@@ -1001,14 +1114,22 @@ struct sched_class {
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
- struct task_struct * (*pick_next_task) (struct rq *rq);
+ /*
+ * It is the responsibility of the pick_next_task() method that will
+ * return the next task to call put_prev_task() on the @prev task or
+ * something equivalent.
+ *
+ * May return RETRY_TASK when it finds a higher prio class has runnable
+ * tasks.
+ */
+ struct task_struct * (*pick_next_task) (struct rq *rq,
+ struct task_struct *prev);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
- void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
void (*post_schedule) (struct rq *this_rq);
void (*task_waking) (struct task_struct *task);
void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1023,6 +1144,7 @@ struct sched_class {
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
+ void (*task_dead) (struct task_struct *p);
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
@@ -1037,11 +1159,17 @@ struct sched_class {
#endif
};
+static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+ prev->sched_class->put_prev_task(rq, prev);
+}
+
#define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
for (class = sched_class_highest; class; class = class->next)
extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;
@@ -1051,25 +1179,26 @@ extern const struct sched_class idle_sched_class;
extern void update_group_power(struct sched_domain *sd, int cpu);
-extern void trigger_load_balance(struct rq *rq, int cpu);
-extern void idle_balance(int this_cpu, struct rq *this_rq);
+extern void trigger_load_balance(struct rq *rq);
extern void idle_enter_fair(struct rq *this_rq);
extern void idle_exit_fair(struct rq *this_rq);
-#else /* CONFIG_SMP */
+#else
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
+static inline void idle_enter_fair(struct rq *rq) { }
+static inline void idle_exit_fair(struct rq *rq) { }
#endif
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
+
+extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
+extern void init_sched_dl_class(void);
extern void resched_task(struct task_struct *p);
extern void resched_cpu(int cpu);
@@ -1077,19 +1206,15 @@ extern void resched_cpu(int cpu);
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
-extern void update_idle_cpu_load(struct rq *this_rq);
+extern struct dl_bandwidth def_dl_bandwidth;
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
+extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
-extern void init_task_runnable_average(struct task_struct *p);
+unsigned long to_ratio(u64 period, u64 runtime);
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
-{
- if (unlikely(steal > NSEC_PER_SEC))
- return div_u64(steal, TICK_NSEC);
+extern void update_idle_cpu_load(struct rq *this_rq);
- return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
+extern void init_task_runnable_average(struct task_struct *p);
static inline void inc_nr_running(struct rq *rq)
{
@@ -1353,6 +1478,7 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
extern void cfs_bandwidth_usage_inc(void);
extern void cfs_bandwidth_usage_dec(void);
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index da98af347e8b..a476bea17fbc 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void)
proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
return 0;
}
-module_init(proc_schedstat_init);
+subsys_initcall(proc_schedstat_init);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 47197de8abd9..d6ce65dde541 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,16 +23,19 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
/* we're never preempted */
}
-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *stop = rq->stop;
- if (stop && stop->on_rq) {
- stop->se.exec_start = rq_clock_task(rq);
- return stop;
- }
+ if (!stop || !stop->on_rq)
+ return NULL;
- return NULL;
+ put_prev_task(rq, prev);
+
+ stop->se.exec_start = rq_clock_task(rq);
+
+ return stop;
}
static void
@@ -103,7 +106,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
* Simple, special scheduling class for the per-CPU stop tasks:
*/
const struct sched_class stop_sched_class = {
- .next = &rt_sched_class,
+ .next = &dl_sched_class,
.enqueue_task = enqueue_task_stop,
.dequeue_task = dequeue_task_stop,
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index eda2da3df822..d8d046c0726a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -55,60 +55,33 @@ struct seccomp_filter {
atomic_t usage;
struct seccomp_filter *prev;
unsigned short len; /* Instruction count */
- struct sock_filter insns[];
+ struct sock_filter_int insnsi[];
};
/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
-/**
- * get_u32 - returns a u32 offset into data
- * @data: a unsigned 64 bit value
- * @index: 0 or 1 to return the first or second 32-bits
- *
- * This inline exists to hide the length of unsigned long. If a 32-bit
- * unsigned long is passed in, it will be extended and the top 32-bits will be
- * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
- * properly returned.
- *
+/*
* Endianness is explicitly ignored and left for BPF program authors to manage
* as per the specific architecture.
*/
-static inline u32 get_u32(u64 data, int index)
+static void populate_seccomp_data(struct seccomp_data *sd)
{
- return ((u32 *)&data)[index];
-}
+ struct task_struct *task = current;
+ struct pt_regs *regs = task_pt_regs(task);
-/* Helper for bpf_load below. */
-#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
-/**
- * bpf_load: checks and returns a pointer to the requested offset
- * @off: offset into struct seccomp_data to load from
- *
- * Returns the requested 32-bits of data.
- * seccomp_check_filter() should assure that @off is 32-bit aligned
- * and not out of bounds. Failure to do so is a BUG.
- */
-u32 seccomp_bpf_load(int off)
-{
- struct pt_regs *regs = task_pt_regs(current);
- if (off == BPF_DATA(nr))
- return syscall_get_nr(current, regs);
- if (off == BPF_DATA(arch))
- return syscall_get_arch();
- if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
- unsigned long value;
- int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
- int index = !!(off % sizeof(u64));
- syscall_get_arguments(current, regs, arg, 1, &value);
- return get_u32(value, index);
- }
- if (off == BPF_DATA(instruction_pointer))
- return get_u32(KSTK_EIP(current), 0);
- if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
- return get_u32(KSTK_EIP(current), 1);
- /* seccomp_check_filter should make this impossible. */
- BUG();
+ sd->nr = syscall_get_nr(task, regs);
+ sd->arch = syscall_get_arch();
+
+ /* Unroll syscall_get_args to help gcc on arm. */
+ syscall_get_arguments(task, regs, 0, 1, (unsigned long *) &sd->args[0]);
+ syscall_get_arguments(task, regs, 1, 1, (unsigned long *) &sd->args[1]);
+ syscall_get_arguments(task, regs, 2, 1, (unsigned long *) &sd->args[2]);
+ syscall_get_arguments(task, regs, 3, 1, (unsigned long *) &sd->args[3]);
+ syscall_get_arguments(task, regs, 4, 1, (unsigned long *) &sd->args[4]);
+ syscall_get_arguments(task, regs, 5, 1, (unsigned long *) &sd->args[5]);
+
+ sd->instruction_pointer = KSTK_EIP(task);
}
/**
@@ -133,17 +106,17 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
switch (code) {
case BPF_S_LD_W_ABS:
- ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+ ftest->code = BPF_LDX | BPF_W | BPF_ABS;
/* 32-bit aligned and not out of bounds. */
if (k >= sizeof(struct seccomp_data) || k & 3)
return -EINVAL;
continue;
case BPF_S_LD_W_LEN:
- ftest->code = BPF_S_LD_IMM;
+ ftest->code = BPF_LD | BPF_IMM;
ftest->k = sizeof(struct seccomp_data);
continue;
case BPF_S_LDX_W_LEN:
- ftest->code = BPF_S_LDX_IMM;
+ ftest->code = BPF_LDX | BPF_IMM;
ftest->k = sizeof(struct seccomp_data);
continue;
/* Explicitly include allowed calls. */
@@ -185,6 +158,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
case BPF_S_JMP_JGT_X:
case BPF_S_JMP_JSET_K:
case BPF_S_JMP_JSET_X:
+ sk_decode_filter(ftest, ftest);
continue;
default:
return -EINVAL;
@@ -202,18 +176,21 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
static u32 seccomp_run_filters(int syscall)
{
struct seccomp_filter *f;
+ struct seccomp_data sd;
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
if (WARN_ON(current->seccomp.filter == NULL))
return SECCOMP_RET_KILL;
+ populate_seccomp_data(&sd);
+
/*
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
for (f = current->seccomp.filter; f; f = f->prev) {
- u32 cur_ret = sk_run_filter(NULL, f->insns);
+ u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
ret = cur_ret;
}
@@ -231,6 +208,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
struct seccomp_filter *filter;
unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
unsigned long total_insns = fprog->len;
+ struct sock_filter *fp;
+ int new_len;
long ret;
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
@@ -252,28 +231,43 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
CAP_SYS_ADMIN) != 0)
return -EACCES;
- /* Allocate a new seccomp_filter */
- filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
- GFP_KERNEL|__GFP_NOWARN);
- if (!filter)
+ fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
+ if (!fp)
return -ENOMEM;
- atomic_set(&filter->usage, 1);
- filter->len = fprog->len;
/* Copy the instructions from fprog. */
ret = -EFAULT;
- if (copy_from_user(filter->insns, fprog->filter, fp_size))
- goto fail;
+ if (copy_from_user(fp, fprog->filter, fp_size))
+ goto free_prog;
/* Check and rewrite the fprog via the skb checker */
- ret = sk_chk_filter(filter->insns, filter->len);
+ ret = sk_chk_filter(fp, fprog->len);
if (ret)
- goto fail;
+ goto free_prog;
/* Check and rewrite the fprog for seccomp use */
- ret = seccomp_check_filter(filter->insns, filter->len);
+ ret = seccomp_check_filter(fp, fprog->len);
+ if (ret)
+ goto free_prog;
+
+ /* Convert 'sock_filter' insns to 'sock_filter_int' insns */
+ ret = sk_convert_filter(fp, fprog->len, NULL, &new_len);
+ if (ret)
+ goto free_prog;
+
+ /* Allocate a new seccomp_filter */
+ filter = kzalloc(sizeof(struct seccomp_filter) +
+ sizeof(struct sock_filter_int) * new_len,
+ GFP_KERNEL|__GFP_NOWARN);
+ if (!filter)
+ goto free_prog;
+
+ ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
if (ret)
- goto fail;
+ goto free_filter;
+
+ atomic_set(&filter->usage, 1);
+ filter->len = new_len;
/*
* If there is an existing filter, make it the prev and don't drop its
@@ -282,8 +276,11 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
filter->prev = current->seccomp.filter;
current->seccomp.filter = filter;
return 0;
-fail:
+
+free_filter:
kfree(filter);
+free_prog:
+ kfree(fp);
return ret;
}
@@ -293,7 +290,7 @@ fail:
*
* Returns 0 on success and non-zero otherwise.
*/
-long seccomp_attach_user_filter(char __user *user_filter)
+static long seccomp_attach_user_filter(char __user *user_filter)
{
struct sock_fprog fprog;
long ret = -EFAULT;
diff --git a/kernel/signal.c b/kernel/signal.c
index 940b30ee9a30..6ea13c09ae56 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -33,6 +33,8 @@
#include <linux/uprobes.h>
#include <linux/compat.h>
#include <linux/cn_proc.h>
+#include <linux/compiler.h>
+
#define CREATE_TRACE_POINTS
#include <trace/events/signal.h>
@@ -2047,8 +2049,8 @@ static bool do_signal_stop(int signr)
if (task_set_jobctl_pending(current, signr | gstop))
sig->group_stop_count++;
- for (t = next_thread(current); t != current;
- t = next_thread(t)) {
+ t = current;
+ while_each_thread(current, t) {
/*
* Setting state to TASK_STOPPED for a group
* stop is always done with the siglock held,
@@ -2382,7 +2384,7 @@ relock:
* @regs: user register state
* @stepping: nonzero if debugger single-step or block-step in use
*
- * This function should be called when a signal has succesfully been
+ * This function should be called when a signal has successfully been
* delivered. It updates the blocked signals accordingly (@ka->sa.sa_mask
* is always blocked, and the signal itself is blocked unless %SA_NODEFER
* is set in @ka->sa.sa_flags. Tracing is notified.
@@ -3125,8 +3127,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
rm_from_queue_full(&mask, &t->signal->shared_pending);
do {
rm_from_queue_full(&mask, &t->pending);
- t = next_thread(t);
- } while (t != current);
+ } while_each_thread(current, t);
}
}
@@ -3619,7 +3620,7 @@ SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask)
}
#endif
-__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma)
+__weak const char *arch_vma_name(struct vm_area_struct *vma)
{
return NULL;
}
diff --git a/kernel/smp.c b/kernel/smp.c
index bd9f94028838..06d574e42c72 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -23,17 +23,11 @@ enum {
struct call_function_data {
struct call_single_data __percpu *csd;
cpumask_var_t cpumask;
- cpumask_var_t cpumask_ipi;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
-struct call_single_queue {
- struct list_head list;
- raw_spinlock_t lock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
static int
hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -47,14 +41,8 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
cpu_to_node(cpu)))
return notifier_from_errno(-ENOMEM);
- if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
- cpu_to_node(cpu))) {
- free_cpumask_var(cfd->cpumask);
- return notifier_from_errno(-ENOMEM);
- }
cfd->csd = alloc_percpu(struct call_single_data);
if (!cfd->csd) {
- free_cpumask_var(cfd->cpumask_ipi);
free_cpumask_var(cfd->cpumask);
return notifier_from_errno(-ENOMEM);
}
@@ -67,7 +55,6 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
case CPU_DEAD:
case CPU_DEAD_FROZEN:
free_cpumask_var(cfd->cpumask);
- free_cpumask_var(cfd->cpumask_ipi);
free_percpu(cfd->csd);
break;
#endif
@@ -85,12 +72,8 @@ void __init call_function_init(void)
void *cpu = (void *)(long)smp_processor_id();
int i;
- for_each_possible_cpu(i) {
- struct call_single_queue *q = &per_cpu(call_single_queue, i);
-
- raw_spin_lock_init(&q->lock);
- INIT_LIST_HEAD(&q->list);
- }
+ for_each_possible_cpu(i)
+ init_llist_head(&per_cpu(call_single_queue, i));
hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
register_cpu_notifier(&hotplug_cfd_notifier);
@@ -134,25 +117,46 @@ static void csd_unlock(struct call_single_data *csd)
csd->flags &= ~CSD_FLAG_LOCK;
}
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
+
/*
* Insert a previously allocated call_single_data element
* for execution on the given CPU. data must already have
* ->func, ->info, and ->flags set.
*/
-static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
+static int generic_exec_single(int cpu, struct call_single_data *csd,
+ smp_call_func_t func, void *info, int wait)
{
- struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
+ struct call_single_data csd_stack = { .flags = 0 };
unsigned long flags;
- int ipi;
+
+
+ if (cpu == smp_processor_id()) {
+ local_irq_save(flags);
+ func(info);
+ local_irq_restore(flags);
+ return 0;
+ }
+
+
+ if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
+ return -ENXIO;
+
+
+ if (!csd) {
+ csd = &csd_stack;
+ if (!wait)
+ csd = &__get_cpu_var(csd_data);
+ }
+
+ csd_lock(csd);
+
+ csd->func = func;
+ csd->info = info;
if (wait)
csd->flags |= CSD_FLAG_WAIT;
- raw_spin_lock_irqsave(&dst->lock, flags);
- ipi = list_empty(&dst->list);
- list_add_tail(&csd->list, &dst->list);
- raw_spin_unlock_irqrestore(&dst->lock, flags);
-
/*
* The list addition should be visible before sending the IPI
* handler locks the list to pull the entry off it because of
@@ -164,11 +168,13 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
* locking and barrier primitives. Generic code isn't really
* equipped to do the right thing...
*/
- if (ipi)
+ if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
arch_send_call_function_single_ipi(cpu);
if (wait)
csd_lock_wait(csd);
+
+ return 0;
}
/*
@@ -177,32 +183,23 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
*/
void generic_smp_call_function_single_interrupt(void)
{
- struct call_single_queue *q = &__get_cpu_var(call_single_queue);
- LIST_HEAD(list);
+ struct llist_node *entry;
+ struct call_single_data *csd, *csd_next;
/*
* Shouldn't receive this interrupt on a cpu that is not yet online.
*/
WARN_ON_ONCE(!cpu_online(smp_processor_id()));
- raw_spin_lock(&q->lock);
- list_replace_init(&q->list, &list);
- raw_spin_unlock(&q->lock);
-
- while (!list_empty(&list)) {
- struct call_single_data *csd;
-
- csd = list_entry(list.next, struct call_single_data, list);
- list_del(&csd->list);
+ entry = llist_del_all(&__get_cpu_var(call_single_queue));
+ entry = llist_reverse_order(entry);
+ llist_for_each_entry_safe(csd, csd_next, entry, llist) {
csd->func(csd->info);
-
csd_unlock(csd);
}
}
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
-
/*
* smp_call_function_single - Run a function on a specific CPU
* @func: The function to run. This must be fast and non-blocking.
@@ -214,12 +211,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
int wait)
{
- struct call_single_data d = {
- .flags = 0,
- };
- unsigned long flags;
int this_cpu;
- int err = 0;
+ int err;
/*
* prevent preemption and reschedule on another processor,
@@ -236,32 +229,41 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
&& !oops_in_progress);
- if (cpu == this_cpu) {
- local_irq_save(flags);
- func(info);
- local_irq_restore(flags);
- } else {
- if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
- struct call_single_data *csd = &d;
+ err = generic_exec_single(cpu, NULL, func, info, wait);
- if (!wait)
- csd = &__get_cpu_var(csd_data);
+ put_cpu();
- csd_lock(csd);
+ return err;
+}
+EXPORT_SYMBOL(smp_call_function_single);
- csd->func = func;
- csd->info = info;
- generic_exec_single(cpu, csd, wait);
- } else {
- err = -ENXIO; /* CPU not online */
- }
- }
+/**
+ * smp_call_function_single_async(): Run an asynchronous function on a
+ * specific CPU.
+ * @cpu: The CPU to run on.
+ * @csd: Pre-allocated and setup data structure
+ *
+ * Like smp_call_function_single(), but the call is asynchonous and
+ * can thus be done from contexts with disabled interrupts.
+ *
+ * The caller passes his own pre-allocated data structure
+ * (ie: embedded in an object) and is responsible for synchronizing it
+ * such that the IPIs performed on the @csd are strictly serialized.
+ *
+ * NOTE: Be careful, there is unfortunately no current debugging facility to
+ * validate the correctness of this serialization.
+ */
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
+{
+ int err = 0;
- put_cpu();
+ preempt_disable();
+ err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
+ preempt_enable();
return err;
}
-EXPORT_SYMBOL(smp_call_function_single);
+EXPORT_SYMBOL_GPL(smp_call_function_single_async);
/*
* smp_call_function_any - Run a function on any of the given cpus
@@ -307,44 +309,6 @@ call:
EXPORT_SYMBOL_GPL(smp_call_function_any);
/**
- * __smp_call_function_single(): Run a function on a specific CPU
- * @cpu: The CPU to run on.
- * @data: Pre-allocated and setup data structure
- * @wait: If true, wait until function has completed on specified CPU.
- *
- * Like smp_call_function_single(), but allow caller to pass in a
- * pre-allocated data structure. Useful for embedding @data inside
- * other structures, for instance.
- */
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
- int wait)
-{
- unsigned int this_cpu;
- unsigned long flags;
-
- this_cpu = get_cpu();
- /*
- * Can deadlock when called with interrupts disabled.
- * We allow cpu's that are not yet online though, as no one else can
- * send smp call function interrupt to this cpu and as such deadlocks
- * can't happen.
- */
- WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
- && !oops_in_progress);
-
- if (cpu == this_cpu) {
- local_irq_save(flags);
- csd->func(csd->info);
- local_irq_restore(flags);
- } else {
- csd_lock(csd);
- generic_exec_single(cpu, csd, wait);
- }
- put_cpu();
-}
-EXPORT_SYMBOL_GPL(__smp_call_function_single);
-
-/**
* smp_call_function_many(): Run a function on a set of other CPUs.
* @mask: The set of cpus to run on (only runs on online subset).
* @func: The function to run. This must be fast and non-blocking.
@@ -402,30 +366,17 @@ void smp_call_function_many(const struct cpumask *mask,
if (unlikely(!cpumask_weight(cfd->cpumask)))
return;
- /*
- * After we put an entry into the list, cfd->cpumask may be cleared
- * again when another CPU sends another IPI for a SMP function call, so
- * cfd->cpumask will be zero.
- */
- cpumask_copy(cfd->cpumask_ipi, cfd->cpumask);
-
for_each_cpu(cpu, cfd->cpumask) {
struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
- struct call_single_queue *dst =
- &per_cpu(call_single_queue, cpu);
- unsigned long flags;
csd_lock(csd);
csd->func = func;
csd->info = info;
-
- raw_spin_lock_irqsave(&dst->lock, flags);
- list_add_tail(&csd->list, &dst->list);
- raw_spin_unlock_irqrestore(&dst->lock, flags);
+ llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
}
/* Send a message to all CPUs in the map */
- arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
+ arch_send_call_function_ipi_mask(cfd->cpumask);
if (wait) {
for_each_cpu(cpu, cfd->cpumask) {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025ccc06dd..b50990a5bea0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -8,6 +8,8 @@
* Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
@@ -23,6 +25,7 @@
#include <linux/smp.h>
#include <linux/smpboot.h>
#include <linux/tick.h>
+#include <linux/irq.h>
#define CREATE_TRACE_POINTS
#include <trace/events/irq.h>
@@ -54,7 +57,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
-char *softirq_to_name[NR_SOFTIRQS] = {
+const char * const softirq_to_name[NR_SOFTIRQS] = {
"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
"TASKLET", "SCHED", "HRTIMER", "RCU"
};
@@ -89,7 +92,7 @@ static void wakeup_softirqd(void)
* where hardirqs are disabled legitimately:
*/
#ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip, unsigned int cnt)
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
@@ -107,33 +110,21 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
/*
* Were softirqs turned off above:
*/
- if (softirq_count() == cnt)
+ if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
if (preempt_count() == cnt)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
-#else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
-{
- preempt_count_add(cnt);
- barrier();
-}
+EXPORT_SYMBOL(__local_bh_disable_ip);
#endif /* CONFIG_TRACE_IRQFLAGS */
-void local_bh_disable(void)
-{
- __local_bh_disable(_RET_IP_, SOFTIRQ_DISABLE_OFFSET);
-}
-
-EXPORT_SYMBOL(local_bh_disable);
-
static void __local_bh_enable(unsigned int cnt)
{
WARN_ON_ONCE(!irqs_disabled());
- if (softirq_count() == cnt)
+ if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
preempt_count_sub(cnt);
}
@@ -148,10 +139,9 @@ void _local_bh_enable(void)
WARN_ON_ONCE(in_irq());
__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}
-
EXPORT_SYMBOL(_local_bh_enable);
-static inline void _local_bh_enable_ip(unsigned long ip)
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -165,8 +155,8 @@ static inline void _local_bh_enable_ip(unsigned long ip)
/*
* Keep preemption disabled until we are done with
* softirq processing:
- */
- preempt_count_sub(SOFTIRQ_DISABLE_OFFSET - 1);
+ */
+ preempt_count_sub(cnt - 1);
if (unlikely(!in_interrupt() && local_softirq_pending())) {
/*
@@ -182,18 +172,7 @@ static inline void _local_bh_enable_ip(unsigned long ip)
#endif
preempt_check_resched();
}
-
-void local_bh_enable(void)
-{
- _local_bh_enable_ip(_RET_IP_);
-}
-EXPORT_SYMBOL(local_bh_enable);
-
-void local_bh_enable_ip(unsigned long ip)
-{
- _local_bh_enable_ip(ip);
-}
-EXPORT_SYMBOL(local_bh_enable_ip);
+EXPORT_SYMBOL(__local_bh_enable_ip);
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
@@ -211,14 +190,49 @@ EXPORT_SYMBOL(local_bh_enable_ip);
#define MAX_SOFTIRQ_TIME msecs_to_jiffies(2)
#define MAX_SOFTIRQ_RESTART 10
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+ bool in_hardirq = false;
+
+ if (trace_hardirq_context(current)) {
+ in_hardirq = true;
+ trace_hardirq_exit();
+ }
+
+ lockdep_softirq_enter();
+
+ return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+ lockdep_softirq_exit();
+
+ if (in_hardirq)
+ trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
asmlinkage void __do_softirq(void)
{
- struct softirq_action *h;
- __u32 pending;
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
- int cpu;
unsigned long old_flags = current->flags;
int max_restart = MAX_SOFTIRQ_RESTART;
+ struct softirq_action *h;
+ bool in_hardirq;
+ __u32 pending;
+ int softirq_bit;
+ int cpu;
/*
* Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -230,8 +244,8 @@ asmlinkage void __do_softirq(void)
pending = local_softirq_pending();
account_irq_enter_time(current);
- __local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
- lockdep_softirq_enter();
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ in_hardirq = lockdep_softirq_start();
cpu = smp_processor_id();
restart:
@@ -242,30 +256,30 @@ restart:
h = softirq_vec;
- do {
- if (pending & 1) {
- unsigned int vec_nr = h - softirq_vec;
- int prev_count = preempt_count();
-
- kstat_incr_softirqs_this_cpu(vec_nr);
-
- trace_softirq_entry(vec_nr);
- h->action(h);
- trace_softirq_exit(vec_nr);
- if (unlikely(prev_count != preempt_count())) {
- printk(KERN_ERR "huh, entered softirq %u %s %p"
- "with preempt_count %08x,"
- " exited with %08x?\n", vec_nr,
- softirq_to_name[vec_nr], h->action,
- prev_count, preempt_count());
- preempt_count_set(prev_count);
- }
+ while ((softirq_bit = ffs(pending))) {
+ unsigned int vec_nr;
+ int prev_count;
+
+ h += softirq_bit - 1;
+
+ vec_nr = h - softirq_vec;
+ prev_count = preempt_count();
+
+ kstat_incr_softirqs_this_cpu(vec_nr);
- rcu_bh_qs(cpu);
+ trace_softirq_entry(vec_nr);
+ h->action(h);
+ trace_softirq_exit(vec_nr);
+ if (unlikely(prev_count != preempt_count())) {
+ pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
+ vec_nr, softirq_to_name[vec_nr], h->action,
+ prev_count, preempt_count());
+ preempt_count_set(prev_count);
}
+ rcu_bh_qs(cpu);
h++;
- pending >>= 1;
- } while (pending);
+ pending >>= softirq_bit;
+ }
local_irq_disable();
@@ -278,16 +292,13 @@ restart:
wakeup_softirqd();
}
- lockdep_softirq_exit();
-
+ lockdep_softirq_end(in_hardirq);
account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
WARN_ON_ONCE(in_interrupt());
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
-
-
asmlinkage void do_softirq(void)
{
__u32 pending;
@@ -311,8 +322,6 @@ asmlinkage void do_softirq(void)
*/
void irq_enter(void)
{
- int cpu = smp_processor_id();
-
rcu_irq_enter();
if (is_idle_task(current) && !in_interrupt()) {
/*
@@ -320,7 +329,7 @@ void irq_enter(void)
* here, as softirq will be serviced on return from interrupt.
*/
local_bh_disable();
- tick_check_idle(cpu);
+ tick_irq_enter();
_local_bh_enable();
}
@@ -375,13 +384,13 @@ void irq_exit(void)
#endif
account_irq_exit_time(current);
- trace_hardirq_exit();
preempt_count_sub(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
tick_irq_exit();
rcu_irq_exit();
+ trace_hardirq_exit(); /* must be last! */
}
/*
@@ -427,8 +436,7 @@ void open_softirq(int nr, void (*action)(struct softirq_action *))
/*
* Tasklets
*/
-struct tasklet_head
-{
+struct tasklet_head {
struct tasklet_struct *head;
struct tasklet_struct **tail;
};
@@ -447,7 +455,6 @@ void __tasklet_schedule(struct tasklet_struct *t)
raise_softirq_irqoff(TASKLET_SOFTIRQ);
local_irq_restore(flags);
}
-
EXPORT_SYMBOL(__tasklet_schedule);
void __tasklet_hi_schedule(struct tasklet_struct *t)
@@ -461,7 +468,6 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_restore(flags);
}
-
EXPORT_SYMBOL(__tasklet_hi_schedule);
void __tasklet_hi_schedule_first(struct tasklet_struct *t)
@@ -472,7 +478,6 @@ void __tasklet_hi_schedule_first(struct tasklet_struct *t)
__this_cpu_write(tasklet_hi_vec.head, t);
__raise_softirq_irqoff(HI_SOFTIRQ);
}
-
EXPORT_SYMBOL(__tasklet_hi_schedule_first);
static void tasklet_action(struct softirq_action *a)
@@ -492,7 +497,8 @@ static void tasklet_action(struct softirq_action *a)
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
- if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+ if (!test_and_clear_bit(TASKLET_STATE_SCHED,
+ &t->state))
BUG();
t->func(t->data);
tasklet_unlock(t);
@@ -527,7 +533,8 @@ static void tasklet_hi_action(struct softirq_action *a)
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
- if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+ if (!test_and_clear_bit(TASKLET_STATE_SCHED,
+ &t->state))
BUG();
t->func(t->data);
tasklet_unlock(t);
@@ -545,7 +552,6 @@ static void tasklet_hi_action(struct softirq_action *a)
}
}
-
void tasklet_init(struct tasklet_struct *t,
void (*func)(unsigned long), unsigned long data)
{
@@ -555,13 +561,12 @@ void tasklet_init(struct tasklet_struct *t,
t->func = func;
t->data = data;
}
-
EXPORT_SYMBOL(tasklet_init);
void tasklet_kill(struct tasklet_struct *t)
{
if (in_interrupt())
- printk("Attempt to kill tasklet from interrupt\n");
+ pr_notice("Attempt to kill tasklet from interrupt\n");
while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
do {
@@ -571,7 +576,6 @@ void tasklet_kill(struct tasklet_struct *t)
tasklet_unlock_wait(t);
clear_bit(TASKLET_STATE_SCHED, &t->state);
}
-
EXPORT_SYMBOL(tasklet_kill);
/*
@@ -721,9 +725,8 @@ static void takeover_tasklets(unsigned int cpu)
}
#endif /* CONFIG_HOTPLUG_CPU */
-static int cpu_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static int cpu_callback(struct notifier_block *nfb, unsigned long action,
+ void *hcpu)
{
switch (action) {
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 84571e09c907..01fbae5b97b7 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
*/
smp_call_function_single(min(cpu1, cpu2),
&irq_cpu_stop_queue_work,
- &call_args, 0);
+ &call_args, 1);
lg_local_unlock(&stop_cpus_lock);
preempt_enable();
diff --git a/kernel/sys.c b/kernel/sys.c
index c72311324ea7..fba0f29401ea 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -174,10 +174,10 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
/* normalize: avoid signed division (rounding problems) */
error = -ESRCH;
- if (niceval < -20)
- niceval = -20;
- if (niceval > 19)
- niceval = 19;
+ if (niceval < MIN_NICE)
+ niceval = MIN_NICE;
+ if (niceval > MAX_NICE)
+ niceval = MAX_NICE;
rcu_read_lock();
read_lock(&tasklist_lock);
@@ -895,8 +895,7 @@ SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
* only important on a multi-user system anyway, to make sure one user
* can't send a signal to a process owned by another. -TYT, 12/12/91
*
- * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
- * LBT 04.03.94
+ * !PF_FORKNOEXEC check to conform completely to POSIX.
*/
SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
{
@@ -932,7 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
if (task_session(p) != task_session(group_leader))
goto out;
err = -EACCES;
- if (p->did_exec)
+ if (!(p->flags & PF_FORKNOEXEC))
goto out;
} else {
err = -ESRCH;
@@ -1572,8 +1571,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
t = p;
do {
accumulate_thread_rusage(t, r);
- t = next_thread(t);
- } while (t != p);
+ } while_each_thread(p, t);
break;
default:
@@ -1998,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
return current->no_new_privs ? 1 : 0;
+ case PR_GET_THP_DISABLE:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+ break;
+ case PR_SET_THP_DISABLE:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ down_write(&me->mm->mmap_sem);
+ if (arg2)
+ me->mm->def_flags |= VM_NOHUGEPAGE;
+ else
+ me->mm->def_flags &= ~VM_NOHUGEPAGE;
+ up_write(&me->mm->mmap_sem);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7078052284fd..bc8d1b74a6b9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -146,11 +146,13 @@ cond_syscall(sys_io_destroy);
cond_syscall(sys_io_submit);
cond_syscall(sys_io_cancel);
cond_syscall(sys_io_getevents);
+cond_syscall(sys_sysfs);
cond_syscall(sys_syslog);
cond_syscall(sys_process_vm_readv);
cond_syscall(sys_process_vm_writev);
cond_syscall(compat_sys_process_vm_readv);
cond_syscall(compat_sys_process_vm_writev);
+cond_syscall(sys_uselib);
/* arch-specific weak syscall entries */
cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 34a604726d0b..74f5b580fe34 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -62,6 +62,7 @@
#include <linux/capability.h>
#include <linux/binfmts.h>
#include <linux/sched/sysctl.h>
+#include <linux/kexec.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -95,8 +96,6 @@
#if defined(CONFIG_SYSCTL)
/* External variables not in a header file. */
-extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
extern int max_threads;
extern int suid_dumpable;
#ifdef CONFIG_COREDUMP
@@ -113,19 +112,18 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
#ifndef CONFIG_MMU
extern int sysctl_nr_trim_pages;
#endif
-#ifdef CONFIG_BLOCK
-extern int blk_iopoll_enabled;
-#endif
/* Constants used for minimum and maximum */
#ifdef CONFIG_LOCKUP_DETECTOR
static int sixty = 60;
#endif
+static int __maybe_unused neg_one = -1;
+
static int zero;
static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
-static int __maybe_unused three = 3;
+static int __maybe_unused four = 4;
static unsigned long one_ul = 1;
static int one_hundred = 100;
#ifdef CONFIG_PRINTK
@@ -143,6 +141,11 @@ static int min_percpu_pagelist_fract = 8;
static int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;
+/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+#ifdef CONFIG_DETECT_HUNG_TASK
+static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
+#endif
+
#ifdef CONFIG_INOTIFY_USER
#include <linux/inotify.h>
#endif
@@ -385,18 +388,13 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "numa_balancing_settle_count",
- .data = &sysctl_numa_balancing_settle_count,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "numa_balancing_migrate_deferred",
- .data = &sysctl_numa_balancing_migrate_deferred,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
+ .procname = "numa_balancing",
+ .data = NULL, /* filled in by handler */
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sysctl_numa_balancing,
+ .extra1 = &zero,
+ .extra2 = &one,
},
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
@@ -614,6 +612,18 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
+#ifdef CONFIG_KEXEC
+ {
+ .procname = "kexec_load_disabled",
+ .data = &kexec_load_disabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ /* only handle a transition from default "0" to "1" */
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &one,
+ },
+#endif
#ifdef CONFIG_MODULES
{
.procname = "modprobe",
@@ -980,13 +990,15 @@ static struct ctl_table kern_table[] = {
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_dohung_task_timeout_secs,
+ .extra2 = &hung_task_timeout_max,
},
{
.procname = "hung_task_warnings",
.data = &sysctl_hung_task_warnings,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &neg_one,
},
#endif
#ifdef CONFIG_COMPAT
@@ -1078,15 +1090,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#ifdef CONFIG_BLOCK
- {
- .procname = "blk_iopoll",
- .data = &blk_iopoll_enabled,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
{ }
};
@@ -1128,7 +1131,14 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = overcommit_ratio_handler,
+ },
+ {
+ .procname = "overcommit_kbytes",
+ .data = &sysctl_overcommit_kbytes,
+ .maxlen = sizeof(sysctl_overcommit_kbytes),
+ .mode = 0644,
+ .proc_handler = overcommit_kbytes_handler,
},
{
.procname = "page-cluster",
@@ -1260,7 +1270,7 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = drop_caches_sysctl_handler,
.extra1 = &one,
- .extra2 = &three,
+ .extra2 = &four,
},
#ifdef CONFIG_COMPACTION
{
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 3ce6e8c5f3fc..f448513a45ed 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -124,7 +124,7 @@ config NO_HZ_FULL
endchoice
config NO_HZ_FULL_ALL
- bool "Full dynticks system on all CPUs by default"
+ bool "Full dynticks system on all CPUs by default (except CPU 0)"
depends on NO_HZ_FULL
help
If the user doesn't pass the nohz_full boot option to
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 9250130646f5..57a413fd0ebf 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y += tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o
+endif
obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o
obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o
obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 086ad6043bcb..ad362c260ef4 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -439,6 +439,19 @@ void clockevents_config_and_register(struct clock_event_device *dev,
}
EXPORT_SYMBOL_GPL(clockevents_config_and_register);
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ clockevents_config(dev, freq);
+
+ if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+ return clockevents_program_event(dev, dev->next_event, false);
+
+ if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+ dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+
+ return 0;
+}
+
/**
* clockevents_update_freq - Update frequency and reprogram a clock event device.
* @dev: device to modify
@@ -446,17 +459,22 @@ EXPORT_SYMBOL_GPL(clockevents_config_and_register);
*
* Reconfigure and reprogram a clock event device in oneshot
* mode. Must be called on the cpu for which the device delivers per
- * cpu timer events with interrupts disabled! Returns 0 on success,
- * -ETIME when the event is in the past.
+ * cpu timer events. If called for the broadcast device the core takes
+ * care of serialization.
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
*/
int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
{
- clockevents_config(dev, freq);
-
- if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
- return 0;
+ unsigned long flags;
+ int ret;
- return clockevents_program_event(dev, dev->next_event, false);
+ local_irq_save(flags);
+ ret = tick_broadcast_update_freq(dev, freq);
+ if (ret == -ENODEV)
+ ret = __clockevents_update_freq(dev, freq);
+ local_irq_restore(flags);
+ return ret;
}
/*
@@ -524,12 +542,13 @@ void clockevents_resume(void)
#ifdef CONFIG_GENERIC_CLOCKEVENTS
/**
* clockevents_notify - notification about relevant events
+ * Returns 0 on success, any other value on error
*/
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
{
struct clock_event_device *dev, *tmp;
unsigned long flags;
- int cpu;
+ int cpu, ret = 0;
raw_spin_lock_irqsave(&clockevents_lock, flags);
@@ -542,7 +561,7 @@ void clockevents_notify(unsigned long reason, void *arg)
case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
- tick_broadcast_oneshot_control(reason);
+ ret = tick_broadcast_oneshot_control(reason);
break;
case CLOCK_EVT_NOTIFY_CPU_DYING:
@@ -585,6 +604,7 @@ void clockevents_notify(unsigned long reason, void *arg)
break;
}
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+ return ret;
}
EXPORT_SYMBOL_GPL(clockevents_notify);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba456fb..a6a5bf53e86d 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
* HZ shrinks, so values greater than 8 overflow 32bits when
* HZ=100.
*/
+#if HZ < 34
+#define JIFFIES_SHIFT 6
+#elif HZ < 67
+#define JIFFIES_SHIFT 7
+#else
#define JIFFIES_SHIFT 8
+#endif
static cycle_t jiffies_read(struct clocksource *cs)
{
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index af8d1d4f3d55..419a52cecd20 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -514,12 +514,13 @@ static void sync_cmos_clock(struct work_struct *work)
next.tv_sec++;
next.tv_nsec -= NSEC_PER_SEC;
}
- schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
+ queue_delayed_work(system_power_efficient_wq,
+ &sync_cmos_work, timespec_to_jiffies(&next));
}
void ntp_notify_cmos_timer(void)
{
- schedule_delayed_work(&sync_cmos_work, 0);
+ queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
}
#else
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0abb36464281..4d23dc4d8139 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -116,20 +116,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
void __init sched_clock_register(u64 (*read)(void), int bits,
unsigned long rate)
{
+ u64 res, wrap, new_mask, new_epoch, cyc, ns;
+ u32 new_mult, new_shift;
+ ktime_t new_wrap_kt;
unsigned long r;
- u64 res, wrap;
char r_unit;
if (cd.rate > rate)
return;
WARN_ON(!irqs_disabled());
- read_sched_clock = read;
- sched_clock_mask = CLOCKSOURCE_MASK(bits);
- cd.rate = rate;
/* calculate the mult/shift to convert counter ticks to ns. */
- clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+ new_mask = CLOCKSOURCE_MASK(bits);
+
+ /* calculate how many ns until we wrap */
+ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+ new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+ /* update epoch for new counter and update epoch_ns from old counter*/
+ new_epoch = read();
+ cyc = read_sched_clock();
+ ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+ cd.mult, cd.shift);
+
+ raw_write_seqcount_begin(&cd.seq);
+ read_sched_clock = read;
+ sched_clock_mask = new_mask;
+ cd.rate = rate;
+ cd.wrap_kt = new_wrap_kt;
+ cd.mult = new_mult;
+ cd.shift = new_shift;
+ cd.epoch_cyc = new_epoch;
+ cd.epoch_ns = ns;
+ raw_write_seqcount_end(&cd.seq);
r = rate;
if (r >= 4000000) {
@@ -141,22 +163,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
} else
r_unit = ' ';
- /* calculate how many ns until we wrap */
- wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
- cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
/* calculate the ns resolution of this counter */
- res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+ res = cyc_to_ns(1ULL, new_mult, new_shift);
+
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
- update_sched_clock();
-
- /*
- * Ensure that sched_clock() starts off at 0ns
- */
- cd.epoch_ns = 0;
-
/* Enable IRQ time accounting if we have a fast enough sched_clock */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 000000000000..eb682d5c697c
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *bc)
+{
+ switch (mode) {
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ /*
+ * Note, we cannot cancel the timer here as we might
+ * run into the following live lock scenario:
+ *
+ * cpu 0 cpu1
+ * lock(broadcast_lock);
+ * hrtimer_interrupt()
+ * bc_handler()
+ * tick_handle_oneshot_broadcast();
+ * lock(broadcast_lock);
+ * hrtimer_cancel()
+ * wait_for_callback()
+ */
+ hrtimer_try_to_cancel(&bctimer);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+ /*
+ * We try to cancel the timer first. If the callback is on
+ * flight on some other cpu then we let it handle it. If we
+ * were able to cancel the timer nothing can rearm it as we
+ * own broadcast_lock.
+ *
+ * However we can also be called from the event handler of
+ * ce_broadcast_hrtimer itself when it expires. We cannot
+ * restart the timer because we are in the callback, but we
+ * can set the expiry time and let the callback return
+ * HRTIMER_RESTART.
+ */
+ if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+ /* Bind the "device" to the cpu */
+ bc->bound_on = smp_processor_id();
+ } else if (bc->bound_on == smp_processor_id()) {
+ hrtimer_set_expires(&bctimer, expires);
+ }
+ return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+ .set_mode = bc_set_mode,
+ .set_next_ktime = bc_set_next,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_KTIME |
+ CLOCK_EVT_FEAT_HRTIMER,
+ .rating = 0,
+ .bound_on = -1,
+ .min_delta_ns = 1,
+ .max_delta_ns = KTIME_MAX,
+ .min_delta_ticks = 1,
+ .max_delta_ticks = ULONG_MAX,
+ .mult = 1,
+ .shift = 0,
+ .cpumask = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+ ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+ if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+ return HRTIMER_NORESTART;
+
+ return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ bctimer.function = bc_handler;
+ clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9532690daaa9..64c5990fd500 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -120,6 +120,19 @@ int tick_is_broadcast_device(struct clock_event_device *dev)
return (dev && tick_broadcast_device.evtdev == dev);
}
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ int ret = -ENODEV;
+
+ if (tick_is_broadcast_device(dev)) {
+ raw_spin_lock(&tick_broadcast_lock);
+ ret = __clockevents_update_freq(dev, freq);
+ raw_spin_unlock(&tick_broadcast_lock);
+ }
+ return ret;
+}
+
+
static void err_broadcast(const struct cpumask *mask)
{
pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
@@ -272,12 +285,8 @@ static void tick_do_broadcast(struct cpumask *mask)
*/
static void tick_do_periodic_broadcast(void)
{
- raw_spin_lock(&tick_broadcast_lock);
-
cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
tick_do_broadcast(tmpmask);
-
- raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -287,13 +296,15 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
{
ktime_t next;
+ raw_spin_lock(&tick_broadcast_lock);
+
tick_do_periodic_broadcast();
/*
* The device is in periodic mode. No reprogramming necessary:
*/
if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
- return;
+ goto unlock;
/*
* Setup the next period for devices, which do not have
@@ -306,9 +317,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
next = ktime_add(next, tick_period);
if (!clockevents_program_event(dev, next, false))
- return;
+ goto unlock;
tick_do_periodic_broadcast();
}
+unlock:
+ raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -538,10 +551,10 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
* Called from irq_enter() when idle was interrupted to reenable the
* per cpu device.
*/
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
{
- if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
- struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+ if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+ struct tick_device *td = &__get_cpu_var(tick_cpu_device);
/*
* We might be in the middle of switching over from
@@ -630,24 +643,61 @@ again:
raw_spin_unlock(&tick_broadcast_lock);
}
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+ if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+ return 0;
+ if (bc->next_event.tv64 == KTIME_MAX)
+ return 0;
+ return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+ struct clock_event_device *dev)
+{
+ /*
+ * For hrtimer based broadcasting we cannot shutdown the cpu
+ * local device if our own event is the first one to expire or
+ * if we own the broadcast timer.
+ */
+ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+ if (broadcast_needs_cpu(bc, smp_processor_id()))
+ return;
+ if (dev->next_event.tv64 < bc->next_event.tv64)
+ return;
+ }
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+ return;
+ /* This moves the broadcast assignment to this cpu */
+ clockevents_program_event(bc, bc->next_event, 1);
+}
+
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
*/
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
unsigned long flags;
ktime_t now;
- int cpu;
+ int cpu, ret = 0;
/*
* Periodic mode does not care about the enter/exit of power
* states
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
- return;
+ return 0;
/*
* We are called with preemtion disabled from the depth of the
@@ -658,7 +708,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
dev = td->evtdev;
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
- return;
+ return 0;
bc = tick_broadcast_device.evtdev;
@@ -666,7 +716,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
- clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+ broadcast_shutdown_local(bc, dev);
/*
* We only reprogram the broadcast timer if we
* did not mark ourself in the force mask and
@@ -679,6 +729,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
dev->next_event.tv64 < bc->next_event.tv64)
tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
}
+ /*
+ * If the current CPU owns the hrtimer broadcast
+ * mechanism, it cannot go deep idle and we remove the
+ * CPU from the broadcast mask. We don't have to go
+ * through the EXIT path as the local timer is not
+ * shutdown.
+ */
+ ret = broadcast_needs_cpu(bc, cpu);
+ if (ret)
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -746,6 +806,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
}
out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ return ret;
}
/*
@@ -756,6 +817,7 @@ out:
static void tick_broadcast_clear_oneshot(int cpu)
{
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
@@ -851,6 +913,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+ broadcast_move_bc(cpu);
+
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 162b03ab0ad2..015661279b68 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -85,6 +85,7 @@ static void tick_periodic(int cpu)
do_timer(1);
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
update_process_times(user_mode(get_irq_regs()));
@@ -97,18 +98,19 @@ static void tick_periodic(int cpu)
void tick_handle_periodic(struct clock_event_device *dev)
{
int cpu = smp_processor_id();
- ktime_t next;
+ ktime_t next = dev->next_event;
tick_periodic(cpu);
if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
return;
- /*
- * Setup the next period for devices, which do not have
- * periodic mode:
- */
- next = ktime_add(dev->next_event, tick_period);
for (;;) {
+ /*
+ * Setup the next period for devices, which do not have
+ * periodic mode:
+ */
+ next = ktime_add(next, tick_period);
+
if (!clockevents_program_event(dev, next, false))
return;
/*
@@ -117,12 +119,11 @@ void tick_handle_periodic(struct clock_event_device *dev)
* to be sure we're using a real hardware clocksource.
* Otherwise we could get trapped in an infinite
* loop, as the tick_periodic() increments jiffies,
- * when then will increment time, posibly causing
+ * which then will increment time, possibly causing
* the loop to trigger again and again.
*/
if (timekeeping_valid_for_hres())
tick_periodic(cpu);
- next = ktime_add(next, tick_period);
}
}
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 18e71f7fbc2a..7ab92b19965a 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -46,23 +46,23 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
extern void tick_resume_oneshot(void);
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
extern void tick_broadcast_switch_to_oneshot(void);
extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_broadcast_switch_to_oneshot(void) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
@@ -87,7 +87,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
@@ -111,6 +111,7 @@ extern int tick_resume_broadcast(void);
extern void tick_broadcast_init(void);
extern void
tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
#else /* !BROADCAST */
@@ -133,6 +134,8 @@ static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
static inline void tick_suspend_broadcast(void) { }
static inline int tick_resume_broadcast(void) { return 0; }
static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev,
+ u32 freq) { return -ENODEV; }
/*
* Set the periodic handler in non broadcast mode
@@ -152,6 +155,9 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
}
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
#endif
extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index ea20f7d1ac2c..9f8af69c67ec 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -86,6 +86,7 @@ static void tick_do_update_jiffies64(ktime_t now)
tick_next_period = ktime_add(last_jiffies_update, tick_period);
}
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
/*
@@ -177,7 +178,7 @@ static bool can_stop_full_tick(void)
* TODO: kick full dynticks CPUs when
* sched_clock_stable is set.
*/
- if (!sched_clock_stable) {
+ if (!sched_clock_stable()) {
trace_tick_stop(0, "unstable sched clock\n");
/*
* Don't allow the user to think they can get
@@ -391,11 +392,9 @@ __setup("nohz=", setup_tick_nohz);
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- ts->idle_waketime = now;
+ __this_cpu_write(tick_cpu_sched.idle_waketime, now);
local_irq_save(flags);
tick_do_update_jiffies64(now);
@@ -426,17 +425,15 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
}
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
- update_ts_time_stats(cpu, ts, now, NULL);
+ update_ts_time_stats(smp_processor_id(), ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event(0);
}
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
ktime_t now = ktime_get();
@@ -536,12 +533,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
+ time_delta = timekeeping_max_deferment();
+
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&jiffies_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
- time_delta = timekeeping_max_deferment();
} while (read_seqretry(&jiffies_lock, seq));
if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
@@ -681,18 +679,18 @@ out:
static void tick_nohz_full_stop_tick(struct tick_sched *ts)
{
#ifdef CONFIG_NO_HZ_FULL
- int cpu = smp_processor_id();
+ int cpu = smp_processor_id();
- if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
- return;
+ if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
+ return;
- if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
- return;
+ if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+ return;
- if (!can_stop_full_tick())
- return;
+ if (!can_stop_full_tick())
+ return;
- tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
+ tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
#endif
}
@@ -754,7 +752,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
ktime_t now, expires;
int cpu = smp_processor_id();
- now = tick_nohz_start_idle(cpu, ts);
+ now = tick_nohz_start_idle(ts);
if (can_stop_idle_tick(cpu, ts)) {
int was_stopped = ts->tick_stopped;
@@ -911,8 +909,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
*/
void tick_nohz_idle_exit(void)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
local_irq_disable();
@@ -925,7 +922,7 @@ void tick_nohz_idle_exit(void)
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_restart_sched_tick(ts, now);
@@ -1009,12 +1006,10 @@ static void tick_nohz_switch_to_nohz(void)
* timer and do not touch the other magic bits which need to be done
* when idle is left.
*/
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
{
#if 0
/* Switch back to 2.6.27 behaviour */
-
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t delta;
/*
@@ -1029,36 +1024,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
#endif
}
-static inline void tick_check_nohz(int cpu)
+static inline void tick_nohz_irq_enter(void)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
if (!ts->idle_active && !ts->tick_stopped)
return;
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_update_jiffies(now);
- tick_nohz_kick_tick(cpu, now);
+ tick_nohz_kick_tick(ts, now);
}
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_nohz_irq_enter(void) { }
#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter to notify about the possible interruption of idle()
*/
-void tick_check_idle(int cpu)
+void tick_irq_enter(void)
{
- tick_check_oneshot_broadcast(cpu);
- tick_check_nohz(cpu);
+ tick_check_oneshot_broadcast_this_cpu();
+ tick_nohz_irq_enter();
}
/*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 87b4f00284c9..f7df8ea21707 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -22,6 +22,7 @@
#include <linux/tick.h>
#include <linux/stop_machine.h>
#include <linux/pvclock_gtod.h>
+#include <linux/compiler.h>
#include "tick-internal.h"
#include "ntp_internal.h"
@@ -77,7 +78,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
tk->wall_to_monotonic = wtm;
set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
tk->offs_real = timespec_to_ktime(tmp);
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}
static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -90,8 +91,9 @@ static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
}
/**
- * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ * tk_setup_internals - Set up internals to use clocksource clock.
*
+ * @tk: The target timekeeper to setup.
* @clock: Pointer to clocksource.
*
* Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
@@ -595,7 +597,7 @@ s32 timekeeping_get_tai_offset(void)
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
tk->tai_offset = tai_offset;
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}
/**
@@ -610,6 +612,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
__timekeeping_set_tai_offset(tk, tai_offset);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clock_was_set();
@@ -758,7 +761,7 @@ u64 timekeeping_max_deferment(void)
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
+void __weak read_persistent_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
@@ -773,7 +776,7 @@ void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __attribute__((weak)) read_boot_clock(struct timespec *ts)
+void __weak read_boot_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
@@ -1023,6 +1026,8 @@ static int timekeeping_suspend(void)
timekeeping_suspend_time =
timespec_add(timekeeping_suspend_time, delta_delta);
}
+
+ timekeeping_update(tk, TK_MIRROR);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1130,16 +1135,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
* we can adjust by 1.
*/
error >>= 2;
- /*
- * XXX - In update_wall_time, we round up to the next
- * nanosecond, and store the amount rounded up into
- * the error. This causes the likely below to be unlikely.
- *
- * The proper fix is to avoid rounding up by using
- * the high precision tk->xtime_nsec instead of
- * xtime.tv_nsec everywhere. Fixing this will take some
- * time.
- */
if (likely(error <= interval))
adj = 1;
else
@@ -1255,7 +1250,7 @@ out_adjust:
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
- unsigned int action = 0;
+ unsigned int clock_set = 0;
while (tk->xtime_nsec >= nsecps) {
int leap;
@@ -1277,11 +1272,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
- clock_was_set_delayed();
- action = TK_CLOCK_WAS_SET;
+ clock_set = TK_CLOCK_WAS_SET;
}
}
- return action;
+ return clock_set;
}
/**
@@ -1294,7 +1288,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
* Returns the unconsumed cycles.
*/
static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
- u32 shift)
+ u32 shift,
+ unsigned int *clock_set)
{
cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
@@ -1308,7 +1303,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
tk->cycle_last += interval;
tk->xtime_nsec += tk->xtime_interval << shift;
- accumulate_nsecs_to_secs(tk);
+ *clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1359,14 +1354,14 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
* update_wall_time - Uses the current clocksource to increment the wall time
*
*/
-static void update_wall_time(void)
+void update_wall_time(void)
{
struct clocksource *clock;
struct timekeeper *real_tk = &timekeeper;
struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
- unsigned int action;
+ unsigned int clock_set = 0;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1401,7 +1396,8 @@ static void update_wall_time(void)
maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
shift = min(shift, maxshift);
while (offset >= tk->cycle_interval) {
- offset = logarithmic_accumulation(tk, offset, shift);
+ offset = logarithmic_accumulation(tk, offset, shift,
+ &clock_set);
if (offset < tk->cycle_interval<<shift)
shift--;
}
@@ -1419,7 +1415,7 @@ static void update_wall_time(void)
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
- action = accumulate_nsecs_to_secs(tk);
+ clock_set |= accumulate_nsecs_to_secs(tk);
write_seqcount_begin(&timekeeper_seq);
/* Update clock->cycle_last with the new value */
@@ -1435,10 +1431,13 @@ static void update_wall_time(void)
* updating.
*/
memcpy(real_tk, tk, sizeof(*tk));
- timekeeping_update(real_tk, action);
+ timekeeping_update(real_tk, clock_set);
write_seqcount_end(&timekeeper_seq);
out:
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (clock_set)
+ /* Have to call _delayed version, since in irq context*/
+ clock_was_set_delayed();
}
/**
@@ -1583,7 +1582,6 @@ struct timespec get_monotonic_coarse(void)
void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
- update_wall_time();
calc_global_load(ticks);
}
@@ -1698,12 +1696,14 @@ int do_adjtimex(struct timex *txc)
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tk, tai);
- update_pvclock_gtod(tk, true);
- clock_was_set_delayed();
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
}
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (tai != orig_tai)
+ clock_was_set();
+
ntp_notify_cmos_timer();
return ret;
@@ -1739,4 +1739,5 @@ void xtime_update(unsigned long ticks)
write_seqlock(&jiffies_lock);
do_timer(ticks);
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 802433a4f5eb..4d54f97558df 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -21,6 +21,8 @@
#include <linux/seq_file.h>
#include <linux/time.h>
+#include "timekeeping_internal.h"
+
static unsigned int sleep_time_bin[32] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
diff --git a/kernel/timer.c b/kernel/timer.c
index accfd241b9e5..87bd529879c2 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -52,7 +52,7 @@
#define CREATE_TRACE_POINTS
#include <trace/events/timer.h>
-u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
+__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
EXPORT_SYMBOL(jiffies_64);
@@ -81,6 +81,7 @@ struct tvec_base {
unsigned long timer_jiffies;
unsigned long next_timer;
unsigned long active_timers;
+ unsigned long all_timers;
struct tvec_root tv1;
struct tvec tv2;
struct tvec tv3;
@@ -337,6 +338,20 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
}
EXPORT_SYMBOL_GPL(set_timer_slack);
+/*
+ * If the list is empty, catch up ->timer_jiffies to the current time.
+ * The caller must hold the tvec_base lock. Returns true if the list
+ * was empty and therefore ->timer_jiffies was updated.
+ */
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+ if (!base->all_timers) {
+ base->timer_jiffies = jiffies;
+ return true;
+ }
+ return false;
+}
+
static void
__internal_add_timer(struct tvec_base *base, struct timer_list *timer)
{
@@ -383,15 +398,17 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
{
+ (void)catchup_timer_jiffies(base);
__internal_add_timer(base, timer);
/*
* Update base->active_timers and base->next_timer
*/
if (!tbase_get_deferrable(timer->base)) {
- if (time_before(timer->expires, base->next_timer))
+ if (!base->active_timers++ ||
+ time_before(timer->expires, base->next_timer))
base->next_timer = timer->expires;
- base->active_timers++;
}
+ base->all_timers++;
}
#ifdef CONFIG_TIMER_STATS
@@ -671,6 +688,8 @@ detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
detach_timer(timer, true);
if (!tbase_get_deferrable(timer->base))
base->active_timers--;
+ base->all_timers--;
+ (void)catchup_timer_jiffies(base);
}
static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
@@ -685,6 +704,8 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
if (timer->expires == base->next_timer)
base->next_timer = base->timer_jiffies;
}
+ base->all_timers--;
+ (void)catchup_timer_jiffies(base);
return 1;
}
@@ -739,12 +760,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
debug_activate(timer, expires);
- cpu = smp_processor_id();
-
-#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
- if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu))
- cpu = get_nohz_timer_target();
-#endif
+ cpu = get_nohz_timer_target(pinned);
new_base = per_cpu(tvec_bases, cpu);
if (base != new_base) {
@@ -939,8 +955,15 @@ void add_timer_on(struct timer_list *timer, int cpu)
* with the timer by holding the timer base lock. This also
* makes sure that a CPU on the way to stop its tick can not
* evaluate the timer wheel.
+ *
+ * Spare the IPI for deferrable timers on idle targets though.
+ * The next busy ticks will take care of it. Except full dynticks
+ * require special care against races with idle_cpu(), lets deal
+ * with that later.
*/
- wake_up_nohz_cpu(cpu);
+ if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu))
+ wake_up_nohz_cpu(cpu);
+
spin_unlock_irqrestore(&base->lock, flags);
}
EXPORT_SYMBOL_GPL(add_timer_on);
@@ -1146,6 +1169,10 @@ static inline void __run_timers(struct tvec_base *base)
struct timer_list *timer;
spin_lock_irq(&base->lock);
+ if (catchup_timer_jiffies(base)) {
+ spin_unlock_irq(&base->lock);
+ return;
+ }
while (time_after_eq(jiffies, base->timer_jiffies)) {
struct list_head work_list;
struct list_head *head = &work_list;
@@ -1160,7 +1187,7 @@ static inline void __run_timers(struct tvec_base *base)
!cascade(base, &base->tv4, INDEX(2)))
cascade(base, &base->tv5, INDEX(3));
++base->timer_jiffies;
- list_replace_init(base->tv1.vec + index, &work_list);
+ list_replace_init(base->tv1.vec + index, head);
while (!list_empty(head)) {
void (*fn)(unsigned long);
unsigned long data;
@@ -1523,9 +1550,8 @@ static int init_timers_cpu(int cpu)
if (!base)
return -ENOMEM;
- /* Make sure that tvec_base is 2 byte aligned */
- if (tbase_get_deferrable(base)) {
- WARN_ON(1);
+ /* Make sure tvec_base has TIMER_FLAG_MASK bits free */
+ if (WARN_ON(base != tbase_get_base(base))) {
kfree(base);
return -ENOMEM;
}
@@ -1559,6 +1585,7 @@ static int init_timers_cpu(int cpu)
base->timer_jiffies = jiffies;
base->next_timer = base->timer_jiffies;
base->active_timers = 0;
+ base->all_timers = 0;
return 0;
}
@@ -1648,9 +1675,9 @@ void __init init_timers(void)
err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
- init_timer_stats();
-
BUG_ON(err != NOTIFY_OK);
+
+ init_timer_stats();
register_cpu_notifier(&timers_nb);
open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
}
diff --git a/kernel/torture.c b/kernel/torture.c
new file mode 100644
index 000000000000..acc9afc2f26e
--- /dev/null
+++ b/kernel/torture.c
@@ -0,0 +1,719 @@
+/*
+ * Common functions for in-kernel torture tests.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ * Based on kernel/rcu/torture.c.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+
+static char *torture_type;
+static bool verbose;
+
+/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
+#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
+#define FULLSTOP_SHUTDOWN 1 /* System shutdown with torture running. */
+#define FULLSTOP_RMMOD 2 /* Normal rmmod of torture. */
+static int fullstop = FULLSTOP_RMMOD;
+static DEFINE_MUTEX(fullstop_mutex);
+static int *torture_runnable;
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Variables for online-offline handling. Only present if CPU hotplug
+ * is enabled, otherwise does nothing.
+ */
+
+static struct task_struct *onoff_task;
+static long onoff_holdoff;
+static long onoff_interval;
+static long n_offline_attempts;
+static long n_offline_successes;
+static unsigned long sum_offline;
+static int min_offline = -1;
+static int max_offline;
+static long n_online_attempts;
+static long n_online_successes;
+static unsigned long sum_online;
+static int min_online = -1;
+static int max_online;
+
+/*
+ * Execute random CPU-hotplug operations at the interval specified
+ * by the onoff_interval.
+ */
+static int
+torture_onoff(void *arg)
+{
+ int cpu;
+ unsigned long delta;
+ int maxcpu = -1;
+ DEFINE_TORTURE_RANDOM(rand);
+ int ret;
+ unsigned long starttime;
+
+ VERBOSE_TOROUT_STRING("torture_onoff task started");
+ for_each_online_cpu(cpu)
+ maxcpu = cpu;
+ WARN_ON(maxcpu < 0);
+ if (onoff_holdoff > 0) {
+ VERBOSE_TOROUT_STRING("torture_onoff begin holdoff");
+ schedule_timeout_interruptible(onoff_holdoff);
+ VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
+ }
+ while (!torture_must_stop()) {
+ cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
+ if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_onoff task: offlining %d\n",
+ torture_type, cpu);
+ starttime = jiffies;
+ n_offline_attempts++;
+ ret = cpu_down(cpu);
+ if (ret) {
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_onoff task: offline %d failed: errno %d\n",
+ torture_type, cpu, ret);
+ } else {
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_onoff task: offlined %d\n",
+ torture_type, cpu);
+ n_offline_successes++;
+ delta = jiffies - starttime;
+ sum_offline += delta;
+ if (min_offline < 0) {
+ min_offline = delta;
+ max_offline = delta;
+ }
+ if (min_offline > delta)
+ min_offline = delta;
+ if (max_offline < delta)
+ max_offline = delta;
+ }
+ } else if (cpu_is_hotpluggable(cpu)) {
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_onoff task: onlining %d\n",
+ torture_type, cpu);
+ starttime = jiffies;
+ n_online_attempts++;
+ ret = cpu_up(cpu);
+ if (ret) {
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_onoff task: online %d failed: errno %d\n",
+ torture_type, cpu, ret);
+ } else {
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_onoff task: onlined %d\n",
+ torture_type, cpu);
+ n_online_successes++;
+ delta = jiffies - starttime;
+ sum_online += delta;
+ if (min_online < 0) {
+ min_online = delta;
+ max_online = delta;
+ }
+ if (min_online > delta)
+ min_online = delta;
+ if (max_online < delta)
+ max_online = delta;
+ }
+ }
+ schedule_timeout_interruptible(onoff_interval);
+ }
+ torture_kthread_stopping("torture_onoff");
+ return 0;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Initiate online-offline handling.
+ */
+int torture_onoff_init(long ooholdoff, long oointerval)
+{
+ int ret = 0;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ onoff_holdoff = ooholdoff;
+ onoff_interval = oointerval;
+ if (onoff_interval <= 0)
+ return 0;
+ ret = torture_create_kthread(torture_onoff, NULL, onoff_task);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+ return ret;
+}
+EXPORT_SYMBOL_GPL(torture_onoff_init);
+
+/*
+ * Clean up after online/offline testing.
+ */
+static void torture_onoff_cleanup(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ if (onoff_task == NULL)
+ return;
+ VERBOSE_TOROUT_STRING("Stopping torture_onoff task");
+ kthread_stop(onoff_task);
+ onoff_task = NULL;
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+}
+EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
+
+/*
+ * Print online/offline testing statistics.
+ */
+char *torture_onoff_stats(char *page)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ page += sprintf(page,
+ "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+ n_online_successes, n_online_attempts,
+ n_offline_successes, n_offline_attempts,
+ min_online, max_online,
+ min_offline, max_offline,
+ sum_online, sum_offline, HZ);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+ return page;
+}
+EXPORT_SYMBOL_GPL(torture_onoff_stats);
+
+/*
+ * Were all the online/offline operations successful?
+ */
+bool torture_onoff_failures(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ return n_online_successes != n_online_attempts ||
+ n_offline_successes != n_offline_attempts;
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+ return false;
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+}
+EXPORT_SYMBOL_GPL(torture_onoff_failures);
+
+#define TORTURE_RANDOM_MULT 39916801 /* prime */
+#define TORTURE_RANDOM_ADD 479001701 /* prime */
+#define TORTURE_RANDOM_REFRESH 10000
+
+/*
+ * Crude but fast random-number generator. Uses a linear congruential
+ * generator, with occasional help from cpu_clock().
+ */
+unsigned long
+torture_random(struct torture_random_state *trsp)
+{
+ if (--trsp->trs_count < 0) {
+ trsp->trs_state += (unsigned long)local_clock();
+ trsp->trs_count = TORTURE_RANDOM_REFRESH;
+ }
+ trsp->trs_state = trsp->trs_state * TORTURE_RANDOM_MULT +
+ TORTURE_RANDOM_ADD;
+ return swahw32(trsp->trs_state);
+}
+EXPORT_SYMBOL_GPL(torture_random);
+
+/*
+ * Variables for shuffling. The idea is to ensure that each CPU stays
+ * idle for an extended period to test interactions with dyntick idle,
+ * as well as interactions with any per-CPU varibles.
+ */
+struct shuffle_task {
+ struct list_head st_l;
+ struct task_struct *st_t;
+};
+
+static long shuffle_interval; /* In jiffies. */
+static struct task_struct *shuffler_task;
+static cpumask_var_t shuffle_tmp_mask;
+static int shuffle_idle_cpu; /* Force all torture tasks off this CPU */
+static struct list_head shuffle_task_list = LIST_HEAD_INIT(shuffle_task_list);
+static DEFINE_MUTEX(shuffle_task_mutex);
+
+/*
+ * Register a task to be shuffled. If there is no memory, just splat
+ * and don't bother registering.
+ */
+void torture_shuffle_task_register(struct task_struct *tp)
+{
+ struct shuffle_task *stp;
+
+ if (WARN_ON_ONCE(tp == NULL))
+ return;
+ stp = kmalloc(sizeof(*stp), GFP_KERNEL);
+ if (WARN_ON_ONCE(stp == NULL))
+ return;
+ stp->st_t = tp;
+ mutex_lock(&shuffle_task_mutex);
+ list_add(&stp->st_l, &shuffle_task_list);
+ mutex_unlock(&shuffle_task_mutex);
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_task_register);
+
+/*
+ * Unregister all tasks, for example, at the end of the torture run.
+ */
+static void torture_shuffle_task_unregister_all(void)
+{
+ struct shuffle_task *stp;
+ struct shuffle_task *p;
+
+ mutex_lock(&shuffle_task_mutex);
+ list_for_each_entry_safe(stp, p, &shuffle_task_list, st_l) {
+ list_del(&stp->st_l);
+ kfree(stp);
+ }
+ mutex_unlock(&shuffle_task_mutex);
+}
+
+/* Shuffle tasks such that we allow shuffle_idle_cpu to become idle.
+ * A special case is when shuffle_idle_cpu = -1, in which case we allow
+ * the tasks to run on all CPUs.
+ */
+static void torture_shuffle_tasks(void)
+{
+ struct shuffle_task *stp;
+
+ cpumask_setall(shuffle_tmp_mask);
+ get_online_cpus();
+
+ /* No point in shuffling if there is only one online CPU (ex: UP) */
+ if (num_online_cpus() == 1) {
+ put_online_cpus();
+ return;
+ }
+
+ /* Advance to the next CPU. Upon overflow, don't idle any CPUs. */
+ shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask);
+ if (shuffle_idle_cpu >= nr_cpu_ids)
+ shuffle_idle_cpu = -1;
+ if (shuffle_idle_cpu != -1) {
+ cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
+ if (cpumask_empty(shuffle_tmp_mask)) {
+ put_online_cpus();
+ return;
+ }
+ }
+
+ mutex_lock(&shuffle_task_mutex);
+ list_for_each_entry(stp, &shuffle_task_list, st_l)
+ set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+ mutex_unlock(&shuffle_task_mutex);
+
+ put_online_cpus();
+}
+
+/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
+ * system to become idle at a time and cut off its timer ticks. This is meant
+ * to test the support for such tickless idle CPU in RCU.
+ */
+static int torture_shuffle(void *arg)
+{
+ VERBOSE_TOROUT_STRING("torture_shuffle task started");
+ do {
+ schedule_timeout_interruptible(shuffle_interval);
+ torture_shuffle_tasks();
+ torture_shutdown_absorb("torture_shuffle");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("torture_shuffle");
+ return 0;
+}
+
+/*
+ * Start the shuffler, with shuffint in jiffies.
+ */
+int torture_shuffle_init(long shuffint)
+{
+ shuffle_interval = shuffint;
+
+ shuffle_idle_cpu = -1;
+
+ if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
+ VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask");
+ return -ENOMEM;
+ }
+
+ /* Create the shuffler thread */
+ return torture_create_kthread(torture_shuffle, NULL, shuffler_task);
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_init);
+
+/*
+ * Stop the shuffling.
+ */
+static void torture_shuffle_cleanup(void)
+{
+ torture_shuffle_task_unregister_all();
+ if (shuffler_task) {
+ VERBOSE_TOROUT_STRING("Stopping torture_shuffle task");
+ kthread_stop(shuffler_task);
+ free_cpumask_var(shuffle_tmp_mask);
+ }
+ shuffler_task = NULL;
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_cleanup);
+
+/*
+ * Variables for auto-shutdown. This allows "lights out" torture runs
+ * to be fully scripted.
+ */
+static int shutdown_secs; /* desired test duration in seconds. */
+static struct task_struct *shutdown_task;
+static unsigned long shutdown_time; /* jiffies to system shutdown. */
+static void (*torture_shutdown_hook)(void);
+
+/*
+ * Absorb kthreads into a kernel function that won't return, so that
+ * they won't ever access module text or data again.
+ */
+void torture_shutdown_absorb(const char *title)
+{
+ while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+ pr_notice("torture thread %s parking due to system shutdown\n",
+ title);
+ schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
+ }
+}
+EXPORT_SYMBOL_GPL(torture_shutdown_absorb);
+
+/*
+ * Cause the torture test to shutdown the system after the test has
+ * run for the time specified by the shutdown_secs parameter.
+ */
+static int torture_shutdown(void *arg)
+{
+ long delta;
+ unsigned long jiffies_snap;
+
+ VERBOSE_TOROUT_STRING("torture_shutdown task started");
+ jiffies_snap = jiffies;
+ while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
+ !torture_must_stop()) {
+ delta = shutdown_time - jiffies_snap;
+ if (verbose)
+ pr_alert("%s" TORTURE_FLAG
+ "torture_shutdown task: %lu jiffies remaining\n",
+ torture_type, delta);
+ schedule_timeout_interruptible(delta);
+ jiffies_snap = jiffies;
+ }
+ if (torture_must_stop()) {
+ torture_kthread_stopping("torture_shutdown");
+ return 0;
+ }
+
+ /* OK, shut down the system. */
+
+ VERBOSE_TOROUT_STRING("torture_shutdown task shutting down system");
+ shutdown_task = NULL; /* Avoid self-kill deadlock. */
+ if (torture_shutdown_hook)
+ torture_shutdown_hook();
+ else
+ VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping.");
+ kernel_power_off(); /* Shut down the system. */
+ return 0;
+}
+
+/*
+ * Start up the shutdown task.
+ */
+int torture_shutdown_init(int ssecs, void (*cleanup)(void))
+{
+ int ret = 0;
+
+ shutdown_secs = ssecs;
+ torture_shutdown_hook = cleanup;
+ if (shutdown_secs > 0) {
+ shutdown_time = jiffies + shutdown_secs * HZ;
+ ret = torture_create_kthread(torture_shutdown, NULL,
+ shutdown_task);
+ }
+ return ret;
+}
+EXPORT_SYMBOL_GPL(torture_shutdown_init);
+
+/*
+ * Detect and respond to a system shutdown.
+ */
+static int torture_shutdown_notify(struct notifier_block *unused1,
+ unsigned long unused2, void *unused3)
+{
+ mutex_lock(&fullstop_mutex);
+ if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
+ VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected");
+ ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN;
+ } else {
+ pr_warn("Concurrent rmmod and shutdown illegal!\n");
+ }
+ mutex_unlock(&fullstop_mutex);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block torture_shutdown_nb = {
+ .notifier_call = torture_shutdown_notify,
+};
+
+/*
+ * Shut down the shutdown task. Say what??? Heh! This can happen if
+ * the torture module gets an rmmod before the shutdown time arrives. ;-)
+ */
+static void torture_shutdown_cleanup(void)
+{
+ unregister_reboot_notifier(&torture_shutdown_nb);
+ if (shutdown_task != NULL) {
+ VERBOSE_TOROUT_STRING("Stopping torture_shutdown task");
+ kthread_stop(shutdown_task);
+ }
+ shutdown_task = NULL;
+}
+
+/*
+ * Variables for stuttering, which means to periodically pause and
+ * restart testing in order to catch bugs that appear when load is
+ * suddenly applied to or removed from the system.
+ */
+static struct task_struct *stutter_task;
+static int stutter_pause_test;
+static int stutter;
+
+/*
+ * Block until the stutter interval ends. This must be called periodically
+ * by all running kthreads that need to be subject to stuttering.
+ */
+void stutter_wait(const char *title)
+{
+ while (ACCESS_ONCE(stutter_pause_test) ||
+ (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
+ if (stutter_pause_test)
+ schedule_timeout_interruptible(1);
+ else
+ schedule_timeout_interruptible(round_jiffies_relative(HZ));
+ torture_shutdown_absorb(title);
+ }
+}
+EXPORT_SYMBOL_GPL(stutter_wait);
+
+/*
+ * Cause the torture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int torture_stutter(void *arg)
+{
+ VERBOSE_TOROUT_STRING("torture_stutter task started");
+ do {
+ if (!torture_must_stop()) {
+ schedule_timeout_interruptible(stutter);
+ ACCESS_ONCE(stutter_pause_test) = 1;
+ }
+ if (!torture_must_stop())
+ schedule_timeout_interruptible(stutter);
+ ACCESS_ONCE(stutter_pause_test) = 0;
+ torture_shutdown_absorb("torture_stutter");
+ } while (!torture_must_stop());
+ torture_kthread_stopping("torture_stutter");
+ return 0;
+}
+
+/*
+ * Initialize and kick off the torture_stutter kthread.
+ */
+int torture_stutter_init(int s)
+{
+ int ret;
+
+ stutter = s;
+ ret = torture_create_kthread(torture_stutter, NULL, stutter_task);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(torture_stutter_init);
+
+/*
+ * Cleanup after the torture_stutter kthread.
+ */
+static void torture_stutter_cleanup(void)
+{
+ if (!stutter_task)
+ return;
+ VERBOSE_TOROUT_STRING("Stopping torture_stutter task");
+ kthread_stop(stutter_task);
+ stutter_task = NULL;
+}
+
+/*
+ * Initialize torture module. Please note that this is -not- invoked via
+ * the usual module_init() mechanism, but rather by an explicit call from
+ * the client torture module. This call must be paired with a later
+ * torture_init_end().
+ *
+ * The runnable parameter points to a flag that controls whether or not
+ * the test is currently runnable. If there is no such flag, pass in NULL.
+ */
+void __init torture_init_begin(char *ttype, bool v, int *runnable)
+{
+ mutex_lock(&fullstop_mutex);
+ torture_type = ttype;
+ verbose = v;
+ torture_runnable = runnable;
+ fullstop = FULLSTOP_DONTSTOP;
+
+}
+EXPORT_SYMBOL_GPL(torture_init_begin);
+
+/*
+ * Tell the torture module that initialization is complete.
+ */
+void __init torture_init_end(void)
+{
+ mutex_unlock(&fullstop_mutex);
+ register_reboot_notifier(&torture_shutdown_nb);
+}
+EXPORT_SYMBOL_GPL(torture_init_end);
+
+/*
+ * Clean up torture module. Please note that this is -not- invoked via
+ * the usual module_exit() mechanism, but rather by an explicit call from
+ * the client torture module. Returns true if a race with system shutdown
+ * is detected, otherwise, all kthreads started by functions in this file
+ * will be shut down.
+ *
+ * This must be called before the caller starts shutting down its own
+ * kthreads.
+ */
+bool torture_cleanup(void)
+{
+ mutex_lock(&fullstop_mutex);
+ if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+ pr_warn("Concurrent rmmod and shutdown illegal!\n");
+ mutex_unlock(&fullstop_mutex);
+ schedule_timeout_uninterruptible(10);
+ return true;
+ }
+ ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD;
+ mutex_unlock(&fullstop_mutex);
+ torture_shutdown_cleanup();
+ torture_shuffle_cleanup();
+ torture_stutter_cleanup();
+ torture_onoff_cleanup();
+ return false;
+}
+EXPORT_SYMBOL_GPL(torture_cleanup);
+
+/*
+ * Is it time for the current torture test to stop?
+ */
+bool torture_must_stop(void)
+{
+ return torture_must_stop_irq() || kthread_should_stop();
+}
+EXPORT_SYMBOL_GPL(torture_must_stop);
+
+/*
+ * Is it time for the current torture test to stop? This is the irq-safe
+ * version, hence no check for kthread_should_stop().
+ */
+bool torture_must_stop_irq(void)
+{
+ return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP;
+}
+EXPORT_SYMBOL_GPL(torture_must_stop_irq);
+
+/*
+ * Each kthread must wait for kthread_should_stop() before returning from
+ * its top-level function, otherwise segfaults ensue. This function
+ * prints a "stopping" message and waits for kthread_should_stop(), and
+ * should be called from all torture kthreads immediately prior to
+ * returning.
+ */
+void torture_kthread_stopping(char *title)
+{
+ if (verbose)
+ VERBOSE_TOROUT_STRING(title);
+ while (!kthread_should_stop()) {
+ torture_shutdown_absorb(title);
+ schedule_timeout_uninterruptible(1);
+ }
+}
+EXPORT_SYMBOL_GPL(torture_kthread_stopping);
+
+/*
+ * Create a generic torture kthread that is immediately runnable. If you
+ * need the kthread to be stopped so that you can do something to it before
+ * it starts, you will need to open-code your own.
+ */
+int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
+ char *f, struct task_struct **tp)
+{
+ int ret = 0;
+
+ VERBOSE_TOROUT_STRING(m);
+ *tp = kthread_run(fn, arg, s);
+ if (IS_ERR(*tp)) {
+ ret = PTR_ERR(*tp);
+ VERBOSE_TOROUT_ERRSTRING(f);
+ *tp = NULL;
+ }
+ torture_shuffle_task_register(*tp);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(_torture_create_kthread);
+
+/*
+ * Stop a generic kthread, emitting a message.
+ */
+void _torture_stop_kthread(char *m, struct task_struct **tp)
+{
+ if (*tp == NULL)
+ return;
+ VERBOSE_TOROUT_STRING(m);
+ kthread_stop(*tp);
+ *tp = NULL;
+}
+EXPORT_SYMBOL_GPL(_torture_stop_kthread);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 015f85aaca08..8639819f6cef 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -424,6 +424,7 @@ config UPROBE_EVENT
bool "Enable uprobes-based dynamic events"
depends on ARCH_SUPPORTS_UPROBES
depends on MMU
+ depends on PERF_EVENTS
select UPROBES
select PROBE_EVENTS
select TRACING
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d7e2068e4b71..1378e84fbe39 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -50,6 +50,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM_RUNTIME),y)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index f785aef65799..c1bd4ada2a04 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q)
* blk_add_trace_rq - Add a trace for a request oriented action
* @q: queue the io is for
* @rq: the source request
+ * @nr_bytes: number of completed bytes
* @what: the action
*
* Description:
@@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q)
*
**/
static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
- u32 what)
+ unsigned int nr_bytes, u32 what)
{
struct blk_trace *bt = q->blk_trace;
@@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
what |= BLK_TC_ACT(BLK_TC_PC);
- __blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+ __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
what, rq->errors, rq->cmd_len, rq->cmd);
} else {
what |= BLK_TC_ACT(BLK_TC_FS);
- __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+ __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
rq->cmd_flags, what, rq->errors, 0, NULL);
}
}
@@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
static void blk_add_trace_rq_abort(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
}
static void blk_add_trace_rq_insert(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
}
static void blk_add_trace_rq_issue(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
}
static void blk_add_trace_rq_requeue(void *ignore,
struct request_queue *q,
struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
}
static void blk_add_trace_rq_complete(void *ignore,
struct request_queue *q,
- struct request *rq)
+ struct request *rq,
+ unsigned int nr_bytes)
{
- blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+ blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
}
/**
@@ -781,8 +783,8 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
if (!error && !bio_flagged(bio, BIO_UPTODATE))
error = EIO;
- __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what,
- error, 0, NULL);
+ __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
+ bio->bi_rw, what, error, 0, NULL);
}
static void blk_add_trace_bio_bounce(void *ignore,
@@ -885,8 +887,9 @@ static void blk_add_trace_split(void *ignore,
if (bt) {
__be64 rpdu = cpu_to_be64(pdu);
- __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
- BLK_TA_SPLIT, !bio_flagged(bio, BIO_UPTODATE),
+ __blk_add_trace(bt, bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size, bio->bi_rw, BLK_TA_SPLIT,
+ !bio_flagged(bio, BIO_UPTODATE),
sizeof(rpdu), &rpdu);
}
}
@@ -918,9 +921,9 @@ static void blk_add_trace_bio_remap(void *ignore,
r.device_to = cpu_to_be32(bio->bi_bdev->bd_dev);
r.sector_from = cpu_to_be64(from);
- __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
- BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
- sizeof(r), &r);
+ __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
+ bio->bi_rw, BLK_TA_REMAP,
+ !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
}
/**
@@ -1426,7 +1429,8 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
return print_one_line(iter, true);
}
-static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+static int
+blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
/* don't output context-info for blk_classic output */
if (bit == TRACE_BLK_OPT_CLASSIC) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 72a0f81dc5a8..1fd4b9479210 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -85,6 +85,8 @@ int function_trace_stop __read_mostly;
/* Current function tracing op */
struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* What to set function_trace_op to */
+static struct ftrace_ops *set_function_trace_op;
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
@@ -235,14 +237,13 @@ static int control_ops_alloc(struct ftrace_ops *ops)
return 0;
}
-static void control_ops_free(struct ftrace_ops *ops)
-{
- free_percpu(ops->disabled);
-}
-
static void update_global_ops(void)
{
- ftrace_func_t func;
+ ftrace_func_t func = ftrace_global_list_func;
+ void *private = NULL;
+
+ /* The list has its own recursion protection. */
+ global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
/*
* If there's only one function registered, then call that
@@ -252,23 +253,17 @@ static void update_global_ops(void)
if (ftrace_global_list == &ftrace_list_end ||
ftrace_global_list->next == &ftrace_list_end) {
func = ftrace_global_list->func;
+ private = ftrace_global_list->private;
/*
* As we are calling the function directly.
* If it does not have recursion protection,
* the function_trace_op needs to be updated
* accordingly.
*/
- if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)
- global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
- else
+ if (!(ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE))
global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE;
- } else {
- func = ftrace_global_list_func;
- /* The list has its own recursion protection. */
- global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
}
-
/* If we filter on pids, update to use the pid function */
if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
@@ -276,8 +271,32 @@ static void update_global_ops(void)
}
global_ops.func = func;
+ global_ops.private = private;
+}
+
+static void ftrace_sync(struct work_struct *work)
+{
+ /*
+ * This function is just a stub to implement a hard force
+ * of synchronize_sched(). This requires synchronizing
+ * tasks even in userspace and idle.
+ *
+ * Yes, function tracing is rude.
+ */
}
+static void ftrace_sync_ipi(void *data)
+{
+ /* Probably not needed, but do it anyway */
+ smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
static void update_ftrace_function(void)
{
ftrace_func_t func;
@@ -296,16 +315,61 @@ static void update_ftrace_function(void)
!FTRACE_FORCE_LIST_FUNC)) {
/* Set the ftrace_ops that the arch callback uses */
if (ftrace_ops_list == &global_ops)
- function_trace_op = ftrace_global_list;
+ set_function_trace_op = ftrace_global_list;
else
- function_trace_op = ftrace_ops_list;
+ set_function_trace_op = ftrace_ops_list;
func = ftrace_ops_list->func;
} else {
/* Just use the default ftrace_ops */
- function_trace_op = &ftrace_list_end;
+ set_function_trace_op = &ftrace_list_end;
func = ftrace_ops_list_func;
}
+ /* If there's no change, then do nothing more here */
+ if (ftrace_trace_function == func)
+ return;
+
+ update_function_graph_func();
+
+ /*
+ * If we are using the list function, it doesn't care
+ * about the function_trace_ops.
+ */
+ if (func == ftrace_ops_list_func) {
+ ftrace_trace_function = func;
+ /*
+ * Don't even bother setting function_trace_ops,
+ * it would be racy to do so anyway.
+ */
+ return;
+ }
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+ /*
+ * For static tracing, we need to be a bit more careful.
+ * The function change takes affect immediately. Thus,
+ * we need to coorditate the setting of the function_trace_ops
+ * with the setting of the ftrace_trace_function.
+ *
+ * Set the function to the list ops, which will call the
+ * function we want, albeit indirectly, but it handles the
+ * ftrace_ops and doesn't depend on function_trace_op.
+ */
+ ftrace_trace_function = ftrace_ops_list_func;
+ /*
+ * Make sure all CPUs see this. Yes this is slow, but static
+ * tracing is slow and nasty to have enabled.
+ */
+ schedule_on_each_cpu(ftrace_sync);
+ /* Now all cpus are using the list ops. */
+ function_trace_op = set_function_trace_op;
+ /* Make sure the function_trace_op is visible on all CPUs */
+ smp_wmb();
+ /* Nasty way to force a rmb on all cpus */
+ smp_call_function(ftrace_sync_ipi, NULL, 1);
+ /* OK, we are all set to update the ftrace_trace_function now! */
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
ftrace_trace_function = func;
}
@@ -367,6 +431,9 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
static int __register_ftrace_function(struct ftrace_ops *ops)
{
+ if (ops->flags & FTRACE_OPS_FL_DELETED)
+ return -EINVAL;
+
if (FTRACE_WARN_ON(ops == &global_ops))
return -EINVAL;
@@ -410,17 +477,6 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
return 0;
}
-static void ftrace_sync(struct work_struct *work)
-{
- /*
- * This function is just a stub to implement a hard force
- * of synchronize_sched(). This requires synchronizing
- * tasks even in userspace and idle.
- *
- * Yes, function tracing is rude.
- */
-}
-
static int __unregister_ftrace_function(struct ftrace_ops *ops)
{
int ret;
@@ -439,20 +495,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
ret = remove_ftrace_list_ops(&ftrace_control_list,
&control_ops, ops);
- if (!ret) {
- /*
- * The ftrace_ops is now removed from the list,
- * so there'll be no new users. We must ensure
- * all current users are done before we free
- * the control data.
- * Note synchronize_sched() is not enough, as we
- * use preempt_disable() to do RCU, but the function
- * tracer can be called where RCU is not active
- * (before user_exit()).
- */
- schedule_on_each_cpu(ftrace_sync);
- control_ops_free(ops);
- }
} else
ret = remove_ftrace_ops(&ftrace_ops_list, ops);
@@ -462,17 +504,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (ftrace_enabled)
update_ftrace_function();
- /*
- * Dynamic ops may be freed, we must make sure that all
- * callers are done before leaving this function.
- *
- * Again, normal synchronize_sched() is not good enough.
- * We need to do a hard force of sched synchronization.
- */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
- schedule_on_each_cpu(ftrace_sync);
-
-
return 0;
}
@@ -1082,19 +1113,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
-loff_t
-ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
-{
- loff_t ret;
-
- if (file->f_mode & FMODE_READ)
- ret = seq_lseek(file, offset, whence);
- else
- file->f_pos = ret = 1;
-
- return ret;
-}
-
#ifdef CONFIG_DYNAMIC_FTRACE
#ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -1151,8 +1169,6 @@ struct ftrace_page {
int size;
};
-static struct ftrace_page *ftrace_new_pgs;
-
#define ENTRY_SIZE sizeof(struct dyn_ftrace)
#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE)
@@ -1539,7 +1555,7 @@ unsigned long ftrace_location(unsigned long ip)
* the function tracer. It checks the ftrace internal tables to
* determine if the address belongs or not.
*/
-int ftrace_text_reserved(void *start, void *end)
+int ftrace_text_reserved(const void *start, const void *end)
{
unsigned long ret;
@@ -1973,6 +1989,7 @@ int __weak ftrace_arch_code_modify_post_process(void)
void ftrace_modify_all_code(int command)
{
int update = command & FTRACE_UPDATE_TRACE_FUNC;
+ int err = 0;
/*
* If the ftrace_caller calls a ftrace_ops func directly,
@@ -1984,21 +2001,33 @@ void ftrace_modify_all_code(int command)
* to make sure the ops are having the right functions
* traced.
*/
- if (update)
- ftrace_update_ftrace_func(ftrace_ops_list_func);
+ if (update) {
+ err = ftrace_update_ftrace_func(ftrace_ops_list_func);
+ if (FTRACE_WARN_ON(err))
+ return;
+ }
if (command & FTRACE_UPDATE_CALLS)
ftrace_replace_code(1);
else if (command & FTRACE_DISABLE_CALLS)
ftrace_replace_code(0);
- if (update && ftrace_trace_function != ftrace_ops_list_func)
- ftrace_update_ftrace_func(ftrace_trace_function);
+ if (update && ftrace_trace_function != ftrace_ops_list_func) {
+ function_trace_op = set_function_trace_op;
+ smp_wmb();
+ /* If irqs are disabled, we are in stop machine */
+ if (!irqs_disabled())
+ smp_call_function(ftrace_sync_ipi, NULL, 1);
+ err = ftrace_update_ftrace_func(ftrace_trace_function);
+ if (FTRACE_WARN_ON(err))
+ return;
+ }
if (command & FTRACE_START_FUNC_RET)
- ftrace_enable_ftrace_graph_caller();
+ err = ftrace_enable_ftrace_graph_caller();
else if (command & FTRACE_STOP_FUNC_RET)
- ftrace_disable_ftrace_graph_caller();
+ err = ftrace_disable_ftrace_graph_caller();
+ FTRACE_WARN_ON(err);
}
static int __ftrace_modify_code(void *data)
@@ -2066,6 +2095,11 @@ static ftrace_func_t saved_ftrace_func;
static int ftrace_start_up;
static int global_start_up;
+static void control_ops_free(struct ftrace_ops *ops)
+{
+ free_percpu(ops->disabled);
+}
+
static void ftrace_startup_enable(int command)
{
if (saved_ftrace_func != ftrace_trace_function) {
@@ -2156,10 +2190,41 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
command |= FTRACE_UPDATE_TRACE_FUNC;
}
- if (!command || !ftrace_enabled)
+ if (!command || !ftrace_enabled) {
+ /*
+ * If these are control ops, they still need their
+ * per_cpu field freed. Since, function tracing is
+ * not currently active, we can just free them
+ * without synchronizing all CPUs.
+ */
+ if (ops->flags & FTRACE_OPS_FL_CONTROL)
+ control_ops_free(ops);
return 0;
+ }
ftrace_run_update_code(command);
+
+ /*
+ * Dynamic ops may be freed, we must make sure that all
+ * callers are done before leaving this function.
+ * The same goes for freeing the per_cpu data of the control
+ * ops.
+ *
+ * Again, normal synchronize_sched() is not good enough.
+ * We need to do a hard force of sched synchronization.
+ * This is because we use preempt_disable() to do RCU, but
+ * the function tracers can be called where RCU is not watching
+ * (like before user_exit()). We can not rely on the RCU
+ * infrastructure to do the synchronization, thus we must do it
+ * ourselves.
+ */
+ if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+ schedule_on_each_cpu(ftrace_sync);
+
+ if (ops->flags & FTRACE_OPS_FL_CONTROL)
+ control_ops_free(ops);
+ }
+
return 0;
}
@@ -2186,7 +2251,6 @@ static void ftrace_shutdown_sysctl(void)
}
static cycle_t ftrace_update_time;
-static unsigned long ftrace_update_cnt;
unsigned long ftrace_update_tot_cnt;
static inline int ops_traces_mod(struct ftrace_ops *ops)
@@ -2242,11 +2306,12 @@ static int referenced_filters(struct dyn_ftrace *rec)
return cnt;
}
-static int ftrace_update_code(struct module *mod)
+static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
{
struct ftrace_page *pg;
struct dyn_ftrace *p;
cycle_t start, stop;
+ unsigned long update_cnt = 0;
unsigned long ref = 0;
bool test = false;
int i;
@@ -2272,9 +2337,8 @@ static int ftrace_update_code(struct module *mod)
}
start = ftrace_now(raw_smp_processor_id());
- ftrace_update_cnt = 0;
- for (pg = ftrace_new_pgs; pg; pg = pg->next) {
+ for (pg = new_pgs; pg; pg = pg->next) {
for (i = 0; i < pg->index; i++) {
int cnt = ref;
@@ -2295,7 +2359,7 @@ static int ftrace_update_code(struct module *mod)
if (!ftrace_code_disable(mod, p))
break;
- ftrace_update_cnt++;
+ update_cnt++;
/*
* If the tracing is enabled, go ahead and enable the record.
@@ -2314,11 +2378,9 @@ static int ftrace_update_code(struct module *mod)
}
}
- ftrace_new_pgs = NULL;
-
stop = ftrace_now(raw_smp_processor_id());
ftrace_update_time = stop - start;
- ftrace_update_tot_cnt += ftrace_update_cnt;
+ ftrace_update_tot_cnt += update_cnt;
return 0;
}
@@ -2410,22 +2472,6 @@ ftrace_allocate_pages(unsigned long num_to_init)
return NULL;
}
-static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
-{
- int cnt;
-
- if (!num_to_init) {
- pr_info("ftrace: No functions to be traced?\n");
- return -1;
- }
-
- cnt = num_to_init / ENTRIES_PER_PAGE;
- pr_info("ftrace: allocating %ld entries in %d pages\n",
- num_to_init, cnt + 1);
-
- return 0;
-}
-
#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
struct ftrace_iterator {
@@ -2739,7 +2785,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
* routine, you can use ftrace_filter_write() for the write
* routine if @flag has FTRACE_ITER_FILTER set, or
* ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_filter_lseek() should be used as the lseek routine, and
+ * tracing_lseek() should be used as the lseek routine, and
* release must call ftrace_regex_release().
*/
int
@@ -2813,7 +2859,9 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
static int
ftrace_filter_open(struct inode *inode, struct file *file)
{
- return ftrace_regex_open(&global_ops,
+ struct ftrace_ops *ops = inode->i_private;
+
+ return ftrace_regex_open(ops,
FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH,
inode, file);
}
@@ -2821,7 +2869,9 @@ ftrace_filter_open(struct inode *inode, struct file *file)
static int
ftrace_notrace_open(struct inode *inode, struct file *file)
{
- return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE,
+ struct ftrace_ops *ops = inode->i_private;
+
+ return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE,
inode, file);
}
@@ -3767,7 +3817,7 @@ static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
@@ -3775,7 +3825,7 @@ static const struct file_operations ftrace_notrace_fops = {
.open = ftrace_notrace_open,
.read = seq_read,
.write = ftrace_notrace_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
@@ -4038,7 +4088,7 @@ static const struct file_operations ftrace_graph_fops = {
.open = ftrace_graph_open,
.read = seq_read,
.write = ftrace_graph_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_graph_release,
};
@@ -4046,11 +4096,41 @@ static const struct file_operations ftrace_graph_notrace_fops = {
.open = ftrace_graph_notrace_open,
.read = seq_read,
.write = ftrace_graph_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_graph_release,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+ struct dentry *parent)
+{
+
+ trace_create_file("set_ftrace_filter", 0644, parent,
+ ops, &ftrace_filter_fops);
+
+ trace_create_file("set_ftrace_notrace", 0644, parent,
+ ops, &ftrace_notrace_fops);
+}
+
+/*
+ * The name "destroy_filter_files" is really a misnomer. Although
+ * in the future, it may actualy delete the files, but this is
+ * really intended to make sure the ops passed in are disabled
+ * and that when this function returns, the caller is free to
+ * free the ops.
+ *
+ * The "destroy" name is only to match the "create" name that this
+ * should be paired with.
+ */
+void ftrace_destroy_filter_files(struct ftrace_ops *ops)
+{
+ mutex_lock(&ftrace_lock);
+ if (ops->flags & FTRACE_OPS_FL_ENABLED)
+ ftrace_shutdown(ops, 0);
+ ops->flags |= FTRACE_OPS_FL_DELETED;
+ mutex_unlock(&ftrace_lock);
+}
+
static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
{
@@ -4060,11 +4140,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
trace_create_file("enabled_functions", 0444,
d_tracer, NULL, &ftrace_enabled_fops);
- trace_create_file("set_ftrace_filter", 0644, d_tracer,
- NULL, &ftrace_filter_fops);
-
- trace_create_file("set_ftrace_notrace", 0644, d_tracer,
- NULL, &ftrace_notrace_fops);
+ ftrace_create_filter_files(&global_ops, d_tracer);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
trace_create_file("set_graph_function", 0444, d_tracer,
@@ -4180,9 +4256,6 @@ static int ftrace_process_locs(struct module *mod,
/* Assign the last page to ftrace_pages */
ftrace_pages = pg;
- /* These new locations need to be initialized */
- ftrace_new_pgs = start_pg;
-
/*
* We only need to disable interrupts on start up
* because we are modifying code that an interrupt
@@ -4193,7 +4266,7 @@ static int ftrace_process_locs(struct module *mod,
*/
if (!mod)
local_irq_save(flags);
- ftrace_update_code(mod);
+ ftrace_update_code(mod, start_pg);
if (!mod)
local_irq_restore(flags);
ret = 0;
@@ -4302,30 +4375,27 @@ struct notifier_block ftrace_module_exit_nb = {
.priority = INT_MIN, /* Run after anything that can remove kprobes */
};
-extern unsigned long __start_mcount_loc[];
-extern unsigned long __stop_mcount_loc[];
-
void __init ftrace_init(void)
{
- unsigned long count, addr, flags;
+ extern unsigned long __start_mcount_loc[];
+ extern unsigned long __stop_mcount_loc[];
+ unsigned long count, flags;
int ret;
- /* Keep the ftrace pointer to the stub */
- addr = (unsigned long)ftrace_stub;
-
local_irq_save(flags);
- ftrace_dyn_arch_init(&addr);
+ ret = ftrace_dyn_arch_init();
local_irq_restore(flags);
-
- /* ftrace_dyn_arch_init places the return code in addr */
- if (addr)
+ if (ret)
goto failed;
count = __stop_mcount_loc - __start_mcount_loc;
-
- ret = ftrace_dyn_table_alloc(count);
- if (ret)
+ if (!count) {
+ pr_info("ftrace: No functions to be traced?\n");
goto failed;
+ }
+
+ pr_info("ftrace: allocating %ld entries in %ld pages\n",
+ count, count / ENTRIES_PER_PAGE + 1);
last_ftrace_enabled = ftrace_enabled = 1;
@@ -4373,7 +4443,13 @@ static inline void ftrace_startup_enable(int command) { }
(ops)->flags |= FTRACE_OPS_FL_ENABLED; \
___ret; \
})
-# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+# define ftrace_shutdown(ops, command) \
+ ({ \
+ int ___ret = __unregister_ftrace_function(ops); \
+ if (!___ret) \
+ (ops)->flags &= ~FTRACE_OPS_FL_ENABLED; \
+ ___ret; \
+ })
# define ftrace_startup_sysctl() do { } while (0)
# define ftrace_shutdown_sysctl() do { } while (0)
@@ -4719,7 +4795,7 @@ static const struct file_operations ftrace_pid_fops = {
.open = ftrace_pid_open,
.write = ftrace_pid_write,
.read = seq_read,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_pid_release,
};
@@ -4862,6 +4938,7 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
trace_func_graph_ret_t ftrace_graph_return =
(trace_func_graph_ret_t)ftrace_stub;
trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -5003,6 +5080,30 @@ static struct ftrace_ops fgraph_ops __read_mostly = {
FTRACE_OPS_FL_RECURSION_SAFE,
};
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+ if (!ftrace_ops_test(&global_ops, trace->func, NULL))
+ return 0;
+ return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+ if (ftrace_ops_list == &ftrace_list_end ||
+ (ftrace_ops_list == &global_ops &&
+ global_ops.next == &ftrace_list_end))
+ ftrace_graph_entry = __ftrace_graph_entry;
+ else
+ ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc)
{
@@ -5027,7 +5128,16 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
}
ftrace_graph_return = retfunc;
- ftrace_graph_entry = entryfunc;
+
+ /*
+ * Update the indirect function to the entryfunc, and the
+ * function that gets called to the entry_test first. Then
+ * call the update fgraph entry function to determine if
+ * the entryfunc should be called directly or not.
+ */
+ __ftrace_graph_entry = entryfunc;
+ ftrace_graph_entry = ftrace_graph_entry_test;
+ update_function_graph_func();
ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
@@ -5046,6 +5156,7 @@ void unregister_ftrace_graph(void)
ftrace_graph_active--;
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
+ __ftrace_graph_entry = ftrace_graph_entry_stub;
ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cc2f66f68dc5..c634868c2921 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1301,7 +1301,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
* In that off case, we need to allocate for all possible cpus.
*/
#ifdef CONFIG_HOTPLUG_CPU
- get_online_cpus();
+ cpu_notifier_register_begin();
cpumask_copy(buffer->cpumask, cpu_online_mask);
#else
cpumask_copy(buffer->cpumask, cpu_possible_mask);
@@ -1324,10 +1324,10 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
#ifdef CONFIG_HOTPLUG_CPU
buffer->cpu_notify.notifier_call = rb_cpu_notify;
buffer->cpu_notify.priority = 0;
- register_cpu_notifier(&buffer->cpu_notify);
+ __register_cpu_notifier(&buffer->cpu_notify);
+ cpu_notifier_register_done();
#endif
- put_online_cpus();
mutex_init(&buffer->mutex);
return buffer;
@@ -1341,7 +1341,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
fail_free_cpumask:
free_cpumask_var(buffer->cpumask);
- put_online_cpus();
+#ifdef CONFIG_HOTPLUG_CPU
+ cpu_notifier_register_done();
+#endif
fail_free_buffer:
kfree(buffer);
@@ -1358,16 +1360,17 @@ ring_buffer_free(struct ring_buffer *buffer)
{
int cpu;
- get_online_cpus();
-
#ifdef CONFIG_HOTPLUG_CPU
- unregister_cpu_notifier(&buffer->cpu_notify);
+ cpu_notifier_register_begin();
+ __unregister_cpu_notifier(&buffer->cpu_notify);
#endif
for_each_buffer_cpu(buffer, cpu)
rb_free_cpu_buffer(buffer->buffers[cpu]);
- put_online_cpus();
+#ifdef CONFIG_HOTPLUG_CPU
+ cpu_notifier_register_done();
+#endif
kfree(buffer->buffers);
free_cpumask_var(buffer->cpumask);
@@ -2397,6 +2400,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
write &= RB_WRITE_MASK;
tail = write - length;
+ /*
+ * If this is the first commit on the page, then it has the same
+ * timestamp as the page itself.
+ */
+ if (!tail)
+ delta = 0;
+
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE))
return rb_move_tail(cpu_buffer, length, tail,
@@ -2558,7 +2568,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
if (unlikely(test_time_stamp(delta))) {
int local_clock_stable = 1;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- local_clock_stable = sched_clock_stable;
+ local_clock_stable = sched_clock_stable();
#endif
WARN_ONCE(delta > (1ULL << 59),
KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index a5457d577b98..0434ff1b808e 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -40,8 +40,8 @@ static int write_iteration = 50;
module_param(write_iteration, uint, 0644);
MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
-static int producer_nice = 19;
-static int consumer_nice = 19;
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
static int producer_fifo = -1;
static int consumer_fifo = -1;
@@ -308,7 +308,7 @@ static void ring_buffer_producer(void)
/* Let the user know that the test is running at low priority */
if (producer_fifo < 0 && consumer_fifo < 0 &&
- producer_nice == 19 && consumer_nice == 19)
+ producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
trace_printk("WARNING!!! This test is running at lowest priority.\n");
trace_printk("Time: %lld (usecs)\n", time);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9d20cd9743ef..9be67c5e5b0f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -73,7 +73,8 @@ static struct tracer_flags dummy_tracer_flags = {
.opts = dummy_tracer_opt
};
-static int dummy_set_flag(u32 old_flags, u32 bit, int set)
+static int
+dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
return 0;
}
@@ -118,7 +119,7 @@ enum ftrace_dump_mode ftrace_dump_on_oops;
/* When set, tracing will stop when a WARN*() is hit */
int __disable_trace_on_warning;
-static int tracing_set_tracer(const char *buf);
+static int tracing_set_tracer(struct trace_array *tr, const char *buf);
#define MAX_TRACER_SIZE 100
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
@@ -180,6 +181,17 @@ static int __init set_trace_boot_options(char *str)
}
__setup("trace_options=", set_trace_boot_options);
+static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata;
+static char *trace_boot_clock __initdata;
+
+static int __init set_trace_boot_clock(char *str)
+{
+ strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
+ trace_boot_clock = trace_boot_clock_buf;
+ return 0;
+}
+__setup("trace_clock=", set_trace_boot_clock);
+
unsigned long long ns2usecs(cycle_t nsec)
{
@@ -455,6 +467,9 @@ int __trace_puts(unsigned long ip, const char *str, int size)
unsigned long irq_flags;
int alloc;
+ if (unlikely(tracing_selftest_running || tracing_disabled))
+ return 0;
+
alloc = sizeof(*entry) + size + 2; /* possible \n added */
local_save_flags(irq_flags);
@@ -495,6 +510,9 @@ int __trace_bputs(unsigned long ip, const char *str)
unsigned long irq_flags;
int size = sizeof(struct bputs_entry);
+ if (unlikely(tracing_selftest_running || tracing_disabled))
+ return 0;
+
local_save_flags(irq_flags);
buffer = global_trace.trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
@@ -595,6 +613,28 @@ void free_snapshot(struct trace_array *tr)
}
/**
+ * tracing_alloc_snapshot - allocate snapshot buffer.
+ *
+ * This only allocates the snapshot buffer if it isn't already
+ * allocated - it doesn't also take a snapshot.
+ *
+ * This is meant to be used in cases where the snapshot buffer needs
+ * to be set up for events that can't sleep but need to be able to
+ * trigger a snapshot.
+ */
+int tracing_alloc_snapshot(void)
+{
+ struct trace_array *tr = &global_trace;
+ int ret;
+
+ ret = alloc_snapshot(tr);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
+
+/**
* trace_snapshot_alloc - allocate and take a snapshot of the current buffer.
*
* This is similar to trace_snapshot(), but it will allocate the
@@ -607,11 +647,10 @@ void free_snapshot(struct trace_array *tr)
*/
void tracing_snapshot_alloc(void)
{
- struct trace_array *tr = &global_trace;
int ret;
- ret = alloc_snapshot(tr);
- if (WARN_ON(ret < 0))
+ ret = tracing_alloc_snapshot();
+ if (ret < 0)
return;
tracing_snapshot();
@@ -623,6 +662,12 @@ void tracing_snapshot(void)
WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used");
}
EXPORT_SYMBOL_GPL(tracing_snapshot);
+int tracing_alloc_snapshot(void)
+{
+ WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used");
+ return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(tracing_alloc_snapshot);
void tracing_snapshot_alloc(void)
{
/* Give warning */
@@ -1197,7 +1242,7 @@ int register_tracer(struct tracer *type)
printk(KERN_INFO "Starting tracer '%s'\n", type->name);
/* Do we want this tracer to start on bootup? */
- tracing_set_tracer(type->name);
+ tracing_set_tracer(&global_trace, type->name);
default_bootup_tracer = NULL;
/* disable other selftests, since this will break it. */
tracing_selftest_disabled = true;
@@ -1567,15 +1612,31 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
}
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
+static struct ring_buffer *temp_buffer;
+
struct ring_buffer_event *
trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
struct ftrace_event_file *ftrace_file,
int type, unsigned long len,
unsigned long flags, int pc)
{
+ struct ring_buffer_event *entry;
+
*current_rb = ftrace_file->tr->trace_buffer.buffer;
- return trace_buffer_lock_reserve(*current_rb,
+ entry = trace_buffer_lock_reserve(*current_rb,
type, len, flags, pc);
+ /*
+ * If tracing is off, but we have triggers enabled
+ * we still need to look at the event data. Use the temp_buffer
+ * to store the trace event for the tigger to use. It's recusive
+ * safe and will not be recorded anywhere.
+ */
+ if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) {
+ *current_rb = temp_buffer;
+ entry = trace_buffer_lock_reserve(*current_rb,
+ type, len, flags, pc);
+ }
+ return entry;
}
EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
@@ -3088,27 +3149,52 @@ static int tracing_open(struct inode *inode, struct file *file)
return ret;
}
+/*
+ * Some tracers are not suitable for instance buffers.
+ * A tracer is always available for the global array (toplevel)
+ * or if it explicitly states that it is.
+ */
+static bool
+trace_ok_for_array(struct tracer *t, struct trace_array *tr)
+{
+ return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances;
+}
+
+/* Find the next tracer that this trace array may use */
+static struct tracer *
+get_tracer_for_array(struct trace_array *tr, struct tracer *t)
+{
+ while (t && !trace_ok_for_array(t, tr))
+ t = t->next;
+
+ return t;
+}
+
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
+ struct trace_array *tr = m->private;
struct tracer *t = v;
(*pos)++;
if (t)
- t = t->next;
+ t = get_tracer_for_array(tr, t->next);
return t;
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
+ struct trace_array *tr = m->private;
struct tracer *t;
loff_t l = 0;
mutex_lock(&trace_types_lock);
- for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
- ;
+
+ t = get_tracer_for_array(tr, trace_types);
+ for (; t && l < *pos; t = t_next(m, t, &l))
+ ;
return t;
}
@@ -3143,10 +3229,21 @@ static const struct seq_operations show_traces_seq_ops = {
static int show_traces_open(struct inode *inode, struct file *file)
{
+ struct trace_array *tr = inode->i_private;
+ struct seq_file *m;
+ int ret;
+
if (tracing_disabled)
return -ENODEV;
- return seq_open(file, &show_traces_seq_ops);
+ ret = seq_open(file, &show_traces_seq_ops);
+ if (ret)
+ return ret;
+
+ m = file->private_data;
+ m->private = tr;
+
+ return 0;
}
static ssize_t
@@ -3156,19 +3253,23 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
return count;
}
-static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence)
{
+ int ret;
+
if (file->f_mode & FMODE_READ)
- return seq_lseek(file, offset, origin);
+ ret = seq_lseek(file, offset, whence);
else
- return 0;
+ file->f_pos = ret = 0;
+
+ return ret;
}
static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.write = tracing_write_stub,
- .llseek = tracing_seek,
+ .llseek = tracing_lseek,
.release = tracing_release,
};
@@ -3302,13 +3403,14 @@ static int tracing_trace_options_show(struct seq_file *m, void *v)
return 0;
}
-static int __set_tracer_option(struct tracer *trace,
+static int __set_tracer_option(struct trace_array *tr,
struct tracer_flags *tracer_flags,
struct tracer_opt *opts, int neg)
{
+ struct tracer *trace = tr->current_trace;
int ret;
- ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
+ ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg);
if (ret)
return ret;
@@ -3320,8 +3422,9 @@ static int __set_tracer_option(struct tracer *trace,
}
/* Try to assign a tracer specific option */
-static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
+static int set_tracer_option(struct trace_array *tr, char *cmp, int neg)
{
+ struct tracer *trace = tr->current_trace;
struct tracer_flags *tracer_flags = trace->flags;
struct tracer_opt *opts = NULL;
int i;
@@ -3330,8 +3433,7 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
opts = &tracer_flags->opts[i];
if (strcmp(cmp, opts->name) == 0)
- return __set_tracer_option(trace, trace->flags,
- opts, neg);
+ return __set_tracer_option(tr, trace->flags, opts, neg);
}
return -EINVAL;
@@ -3354,7 +3456,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
/* Give the tracer a chance to approve the change */
if (tr->current_trace->flag_changed)
- if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled))
+ if (tr->current_trace->flag_changed(tr, mask, !!enabled))
return -EINVAL;
if (enabled)
@@ -3403,7 +3505,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
/* If no option could be set, test the specific tracer options */
if (!trace_options[i])
- ret = set_tracer_option(tr->current_trace, cmp, neg);
+ ret = set_tracer_option(tr, cmp, neg);
mutex_unlock(&trace_types_lock);
@@ -3488,60 +3590,103 @@ static const char readme_msg[] =
" instances\t\t- Make sub-buffers with: mkdir instances/foo\n"
"\t\t\t Remove sub-buffer with rmdir\n"
" trace_options\t\t- Set format or modify how tracing happens\n"
- "\t\t\t Disable an option by adding a suffix 'no' to the option name\n"
+ "\t\t\t Disable an option by adding a suffix 'no' to the\n"
+ "\t\t\t option name\n"
#ifdef CONFIG_DYNAMIC_FTRACE
"\n available_filter_functions - list of functions that can be filtered on\n"
- " set_ftrace_filter\t- echo function name in here to only trace these functions\n"
- " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
- " modules: Can select a group via module\n"
- " Format: :mod:<module-name>\n"
- " example: echo :mod:ext3 > set_ftrace_filter\n"
- " triggers: a command to perform when function is hit\n"
- " Format: <function>:<trigger>[:count]\n"
- " trigger: traceon, traceoff\n"
- " enable_event:<system>:<event>\n"
- " disable_event:<system>:<event>\n"
+ " set_ftrace_filter\t- echo function name in here to only trace these\n"
+ "\t\t\t functions\n"
+ "\t accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+ "\t modules: Can select a group via module\n"
+ "\t Format: :mod:<module-name>\n"
+ "\t example: echo :mod:ext3 > set_ftrace_filter\n"
+ "\t triggers: a command to perform when function is hit\n"
+ "\t Format: <function>:<trigger>[:count]\n"
+ "\t trigger: traceon, traceoff\n"
+ "\t\t enable_event:<system>:<event>\n"
+ "\t\t disable_event:<system>:<event>\n"
#ifdef CONFIG_STACKTRACE
- " stacktrace\n"
+ "\t\t stacktrace\n"
#endif
#ifdef CONFIG_TRACER_SNAPSHOT
- " snapshot\n"
+ "\t\t snapshot\n"
#endif
- " example: echo do_fault:traceoff > set_ftrace_filter\n"
- " echo do_trap:traceoff:3 > set_ftrace_filter\n"
- " The first one will disable tracing every time do_fault is hit\n"
- " The second will disable tracing at most 3 times when do_trap is hit\n"
- " The first time do trap is hit and it disables tracing, the counter\n"
- " will decrement to 2. If tracing is already disabled, the counter\n"
- " will not decrement. It only decrements when the trigger did work\n"
- " To remove trigger without count:\n"
- " echo '!<function>:<trigger> > set_ftrace_filter\n"
- " To remove trigger with a count:\n"
- " echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
+ "\t example: echo do_fault:traceoff > set_ftrace_filter\n"
+ "\t echo do_trap:traceoff:3 > set_ftrace_filter\n"
+ "\t The first one will disable tracing every time do_fault is hit\n"
+ "\t The second will disable tracing at most 3 times when do_trap is hit\n"
+ "\t The first time do trap is hit and it disables tracing, the\n"
+ "\t counter will decrement to 2. If tracing is already disabled,\n"
+ "\t the counter will not decrement. It only decrements when the\n"
+ "\t trigger did work\n"
+ "\t To remove trigger without count:\n"
+ "\t echo '!<function>:<trigger> > set_ftrace_filter\n"
+ "\t To remove trigger with a count:\n"
+ "\t echo '!<function>:<trigger>:0 > set_ftrace_filter\n"
" set_ftrace_notrace\t- echo function name in here to never trace.\n"
- " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
- " modules: Can select a group via module command :mod:\n"
- " Does not accept triggers\n"
+ "\t accepts: func_full_name, *func_end, func_begin*, *func_middle*\n"
+ "\t modules: Can select a group via module command :mod:\n"
+ "\t Does not accept triggers\n"
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_TRACER
- " set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n"
+ " set_ftrace_pid\t- Write pid(s) to only function trace those pids\n"
+ "\t\t (function)\n"
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
" set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
" max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n"
#endif
#ifdef CONFIG_TRACER_SNAPSHOT
- "\n snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n"
- "\t\t\t Read the contents for more information\n"
+ "\n snapshot\t\t- Like 'trace' but shows the content of the static\n"
+ "\t\t\t snapshot buffer. Read the contents for more\n"
+ "\t\t\t information\n"
#endif
#ifdef CONFIG_STACK_TRACER
" stack_trace\t\t- Shows the max stack trace when active\n"
" stack_max_size\t- Shows current max stack size that was traced\n"
- "\t\t\t Write into this file to reset the max size (trigger a new trace)\n"
+ "\t\t\t Write into this file to reset the max size (trigger a\n"
+ "\t\t\t new trace)\n"
#ifdef CONFIG_DYNAMIC_FTRACE
- " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n"
+ " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace\n"
+ "\t\t\t traces\n"
#endif
#endif /* CONFIG_STACK_TRACER */
+ " events/\t\t- Directory containing all trace event subsystems:\n"
+ " enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
+ " events/<system>/\t- Directory containing all trace events for <system>:\n"
+ " enable\t\t- Write 0/1 to enable/disable tracing of all <system>\n"
+ "\t\t\t events\n"
+ " filter\t\t- If set, only events passing filter are traced\n"
+ " events/<system>/<event>/\t- Directory containing control files for\n"
+ "\t\t\t <event>:\n"
+ " enable\t\t- Write 0/1 to enable/disable tracing of <event>\n"
+ " filter\t\t- If set, only events passing filter are traced\n"
+ " trigger\t\t- If set, a command to perform when event is hit\n"
+ "\t Format: <trigger>[:count][if <filter>]\n"
+ "\t trigger: traceon, traceoff\n"
+ "\t enable_event:<system>:<event>\n"
+ "\t disable_event:<system>:<event>\n"
+#ifdef CONFIG_STACKTRACE
+ "\t\t stacktrace\n"
+#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+ "\t\t snapshot\n"
+#endif
+ "\t example: echo traceoff > events/block/block_unplug/trigger\n"
+ "\t echo traceoff:3 > events/block/block_unplug/trigger\n"
+ "\t echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n"
+ "\t events/block/block_unplug/trigger\n"
+ "\t The first disables tracing every time block_unplug is hit.\n"
+ "\t The second disables tracing the first 3 times block_unplug is hit.\n"
+ "\t The third enables the kmalloc event the first 3 times block_unplug\n"
+ "\t is hit and has value of greater than 1 for the 'nr_rq' event field.\n"
+ "\t Like function triggers, the counter is only decremented if it\n"
+ "\t enabled or disabled tracing.\n"
+ "\t To remove a trigger without a count:\n"
+ "\t echo '!<trigger> > <system>/<event>/trigger\n"
+ "\t To remove a trigger with a count:\n"
+ "\t echo '!<trigger>:0 > <system>/<event>/trigger\n"
+ "\t Filters can be ignored when removing a trigger.\n"
;
static ssize_t
@@ -3789,10 +3934,26 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
static void
destroy_trace_option_files(struct trace_option_dentry *topts);
-static int tracing_set_tracer(const char *buf)
+/*
+ * Used to clear out the tracer before deletion of an instance.
+ * Must have trace_types_lock held.
+ */
+static void tracing_set_nop(struct trace_array *tr)
+{
+ if (tr->current_trace == &nop_trace)
+ return;
+
+ tr->current_trace->enabled--;
+
+ if (tr->current_trace->reset)
+ tr->current_trace->reset(tr);
+
+ tr->current_trace = &nop_trace;
+}
+
+static int tracing_set_tracer(struct trace_array *tr, const char *buf)
{
static struct trace_option_dentry *topts;
- struct trace_array *tr = &global_trace;
struct tracer *t;
#ifdef CONFIG_TRACER_MAX_TRACE
bool had_max_tr;
@@ -3820,9 +3981,15 @@ static int tracing_set_tracer(const char *buf)
if (t == tr->current_trace)
goto out;
+ /* Some tracers are only allowed for the top level buffer */
+ if (!trace_ok_for_array(t, tr)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
trace_branch_disable();
- tr->current_trace->enabled = false;
+ tr->current_trace->enabled--;
if (tr->current_trace->reset)
tr->current_trace->reset(tr);
@@ -3845,9 +4012,11 @@ static int tracing_set_tracer(const char *buf)
free_snapshot(tr);
}
#endif
- destroy_trace_option_files(topts);
-
- topts = create_trace_option_files(tr, t);
+ /* Currently, only the top instance has options */
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+ destroy_trace_option_files(topts);
+ topts = create_trace_option_files(tr, t);
+ }
#ifdef CONFIG_TRACER_MAX_TRACE
if (t->use_max_tr && !had_max_tr) {
@@ -3864,7 +4033,7 @@ static int tracing_set_tracer(const char *buf)
}
tr->current_trace = t;
- tr->current_trace->enabled = true;
+ tr->current_trace->enabled++;
trace_branch_enable(tr);
out:
mutex_unlock(&trace_types_lock);
@@ -3876,6 +4045,7 @@ static ssize_t
tracing_set_trace_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
+ struct trace_array *tr = filp->private_data;
char buf[MAX_TRACER_SIZE+1];
int i;
size_t ret;
@@ -3895,7 +4065,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
buf[i] = 0;
- err = tracing_set_tracer(buf);
+ err = tracing_set_tracer(tr, buf);
if (err)
return err;
@@ -4212,12 +4382,6 @@ out:
return sret;
}
-static void tracing_pipe_buf_release(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- __free_page(buf->page);
-}
-
static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
unsigned int idx)
{
@@ -4229,7 +4393,7 @@ static const struct pipe_buf_operations tracing_pipe_buf_ops = {
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
.confirm = generic_pipe_buf_confirm,
- .release = tracing_pipe_buf_release,
+ .release = generic_pipe_buf_release,
.steal = generic_pipe_buf_steal,
.get = generic_pipe_buf_get,
};
@@ -4609,25 +4773,10 @@ static int tracing_clock_show(struct seq_file *m, void *v)
return 0;
}
-static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
- size_t cnt, loff_t *fpos)
+static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
{
- struct seq_file *m = filp->private_data;
- struct trace_array *tr = m->private;
- char buf[64];
- const char *clockstr;
int i;
- if (cnt >= sizeof(buf))
- return -EINVAL;
-
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
-
- buf[cnt] = 0;
-
- clockstr = strstrip(buf);
-
for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
if (strcmp(trace_clocks[i].name, clockstr) == 0)
break;
@@ -4655,6 +4804,32 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
mutex_unlock(&trace_types_lock);
+ return 0;
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *fpos)
+{
+ struct seq_file *m = filp->private_data;
+ struct trace_array *tr = m->private;
+ char buf[64];
+ const char *clockstr;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ clockstr = strstrip(buf);
+
+ ret = tracing_set_clock(tr, clockstr);
+ if (ret)
+ return ret;
+
*fpos += cnt;
return cnt;
@@ -4913,7 +5088,7 @@ static const struct file_operations snapshot_fops = {
.open = tracing_snapshot_open,
.read = seq_read,
.write = tracing_snapshot_write,
- .llseek = tracing_seek,
+ .llseek = tracing_lseek,
.release = tracing_snapshot_release,
};
@@ -5615,7 +5790,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (!!(topt->flags->val & topt->opt->bit) != val) {
mutex_lock(&trace_types_lock);
- ret = __set_tracer_option(topt->tr->current_trace, topt->flags,
+ ret = __set_tracer_option(topt->tr, topt->flags,
topt->opt, !val);
mutex_unlock(&trace_types_lock);
if (ret)
@@ -5883,6 +6058,8 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+ buf->tr = tr;
+
buf->buffer = ring_buffer_alloc(size, rb_flags);
if (!buf->buffer)
return -ENOMEM;
@@ -6020,7 +6197,9 @@ static int instance_delete(const char *name)
list_del(&tr->list);
+ tracing_set_nop(tr);
event_trace_del_tracer(tr);
+ ftrace_destroy_function_files(tr);
debugfs_remove_recursive(tr->dir);
free_percpu(tr->trace_buffer.data);
ring_buffer_free(tr->trace_buffer.buffer);
@@ -6115,6 +6294,12 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
{
int cpu;
+ trace_create_file("available_tracers", 0444, d_tracer,
+ tr, &show_traces_fops);
+
+ trace_create_file("current_tracer", 0644, d_tracer,
+ tr, &set_tracer_fops);
+
trace_create_file("tracing_cpumask", 0644, d_tracer,
tr, &tracing_cpumask_fops);
@@ -6145,6 +6330,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
trace_create_file("tracing_on", 0644, d_tracer,
tr, &rb_simple_fops);
+ if (ftrace_create_function_files(tr, d_tracer))
+ WARN(1, "Could not allocate function filter files");
+
#ifdef CONFIG_TRACER_SNAPSHOT
trace_create_file("snapshot", 0644, d_tracer,
tr, &snapshot_fops);
@@ -6167,12 +6355,6 @@ static __init int tracer_init_debugfs(void)
init_tracer_debugfs(&global_trace, d_tracer);
- trace_create_file("available_tracers", 0444, d_tracer,
- &global_trace, &show_traces_fops);
-
- trace_create_file("current_tracer", 0644, d_tracer,
- &global_trace, &set_tracer_fops);
-
#ifdef CONFIG_TRACER_MAX_TRACE
trace_create_file("tracing_max_latency", 0644, d_tracer,
&tracing_max_latency, &tracing_max_lat_fops);
@@ -6418,11 +6600,16 @@ __init static int tracer_alloc_buffers(void)
raw_spin_lock_init(&global_trace.start_lock);
+ /* Used for event triggers */
+ temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
+ if (!temp_buffer)
+ goto out_free_cpumask;
+
/* TODO: make the number of buffers hot pluggable with CPUS */
if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
WARN_ON(1);
- goto out_free_cpumask;
+ goto out_free_temp_buffer;
}
if (global_trace.buffer_disabled)
@@ -6430,6 +6617,13 @@ __init static int tracer_alloc_buffers(void)
trace_init_cmdlines();
+ if (trace_boot_clock) {
+ ret = tracing_set_clock(&global_trace, trace_boot_clock);
+ if (ret < 0)
+ pr_warning("Trace clock %s not defined, going back to default\n",
+ trace_boot_clock);
+ }
+
/*
* register_tracer() might reference current_trace, so it
* needs to be set before we register anything. This is
@@ -6464,6 +6658,8 @@ __init static int tracer_alloc_buffers(void)
return 0;
+out_free_temp_buffer:
+ ring_buffer_free(temp_buffer);
out_free_cpumask:
free_percpu(global_trace.trace_buffer.data);
#ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ea189e027b80..2e29d7ba5a52 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1,3 +1,4 @@
+
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H
@@ -12,6 +13,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/trace_seq.h>
#include <linux/ftrace_event.h>
+#include <linux/compiler.h>
#ifdef CONFIG_FTRACE_SYSCALLS
#include <asm/unistd.h> /* For NR_SYSCALLS */
@@ -209,6 +211,11 @@ struct trace_array {
struct list_head events;
cpumask_var_t tracing_cpumask; /* only trace on set CPUs */
int ref;
+#ifdef CONFIG_FUNCTION_TRACER
+ struct ftrace_ops *ops;
+ /* function tracing enabled */
+ int function_enabled;
+#endif
};
enum {
@@ -354,14 +361,16 @@ struct tracer {
void (*print_header)(struct seq_file *m);
enum print_line_t (*print_line)(struct trace_iterator *iter);
/* If you handled the flag setting, return 0 */
- int (*set_flag)(u32 old_flags, u32 bit, int set);
+ int (*set_flag)(struct trace_array *tr,
+ u32 old_flags, u32 bit, int set);
/* Return 0 if OK with change, else return non-zero */
- int (*flag_changed)(struct tracer *tracer,
+ int (*flag_changed)(struct trace_array *tr,
u32 mask, int set);
struct tracer *next;
struct tracer_flags *flags;
+ int enabled;
bool print_max;
- bool enabled;
+ bool allow_instances;
#ifdef CONFIG_TRACER_MAX_TRACE
bool use_max_tr;
#endif
@@ -587,6 +596,8 @@ void tracing_start_sched_switch_record(void);
int register_tracer(struct tracer *type);
int is_tracing_stopped(void);
+loff_t tracing_lseek(struct file *file, loff_t offset, int whence);
+
extern cpumask_var_t __read_mostly tracing_buffer_mask;
#define for_each_tracing_cpu(cpu) \
@@ -809,13 +820,36 @@ static inline int ftrace_trace_task(struct task_struct *task)
return test_tsk_trace_trace(task);
}
extern int ftrace_is_dead(void);
+int ftrace_create_function_files(struct trace_array *tr,
+ struct dentry *parent);
+void ftrace_destroy_function_files(struct trace_array *tr);
#else
static inline int ftrace_trace_task(struct task_struct *task)
{
return 1;
}
static inline int ftrace_is_dead(void) { return 0; }
-#endif
+static inline int
+ftrace_create_function_files(struct trace_array *tr,
+ struct dentry *parent)
+{
+ return 0;
+}
+static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+ struct dentry *parent);
+void ftrace_destroy_filter_files(struct ftrace_ops *ops);
+#else
+/*
+ * The ops parameter passed in is usually undefined.
+ * This must be a macro.
+ */
+#define ftrace_create_filter_files(ops, parent) do { } while (0)
+#define ftrace_destroy_filter_files(ops) do { } while (0)
+#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */
int ftrace_event_is_function(struct ftrace_event_call *call);
@@ -1020,6 +1054,10 @@ extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
extern void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s);
extern int filter_assign_type(const char *type);
+extern int create_event_filter(struct ftrace_event_call *call,
+ char *filter_str, bool set_str,
+ struct event_filter **filterp);
+extern void free_event_filter(struct event_filter *filter);
struct ftrace_event_field *
trace_find_event_field(struct ftrace_event_call *call, char *name);
@@ -1028,9 +1066,195 @@ extern void trace_event_enable_cmd_record(bool enable);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
+extern struct ftrace_event_file *find_event_file(struct trace_array *tr,
+ const char *system,
+ const char *event);
+
+static inline void *event_file_data(struct file *filp)
+{
+ return ACCESS_ONCE(file_inode(filp)->i_private);
+}
+
extern struct mutex event_mutex;
extern struct list_head ftrace_events;
+extern const struct file_operations event_trigger_fops;
+
+extern int register_trigger_cmds(void);
+extern void clear_event_triggers(struct trace_array *tr);
+
+struct event_trigger_data {
+ unsigned long count;
+ int ref;
+ struct event_trigger_ops *ops;
+ struct event_command *cmd_ops;
+ struct event_filter __rcu *filter;
+ char *filter_str;
+ void *private_data;
+ struct list_head list;
+};
+
+/**
+ * struct event_trigger_ops - callbacks for trace event triggers
+ *
+ * The methods in this structure provide per-event trigger hooks for
+ * various trigger operations.
+ *
+ * All the methods below, except for @init() and @free(), must be
+ * implemented.
+ *
+ * @func: The trigger 'probe' function called when the triggering
+ * event occurs. The data passed into this callback is the data
+ * that was supplied to the event_command @reg() function that
+ * registered the trigger (see struct event_command).
+ *
+ * @init: An optional initialization function called for the trigger
+ * when the trigger is registered (via the event_command reg()
+ * function). This can be used to perform per-trigger
+ * initialization such as incrementing a per-trigger reference
+ * count, for instance. This is usually implemented by the
+ * generic utility function @event_trigger_init() (see
+ * trace_event_triggers.c).
+ *
+ * @free: An optional de-initialization function called for the
+ * trigger when the trigger is unregistered (via the
+ * event_command @reg() function). This can be used to perform
+ * per-trigger de-initialization such as decrementing a
+ * per-trigger reference count and freeing corresponding trigger
+ * data, for instance. This is usually implemented by the
+ * generic utility function @event_trigger_free() (see
+ * trace_event_triggers.c).
+ *
+ * @print: The callback function invoked to have the trigger print
+ * itself. This is usually implemented by a wrapper function
+ * that calls the generic utility function @event_trigger_print()
+ * (see trace_event_triggers.c).
+ */
+struct event_trigger_ops {
+ void (*func)(struct event_trigger_data *data);
+ int (*init)(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+ void (*free)(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+ int (*print)(struct seq_file *m,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+};
+
+/**
+ * struct event_command - callbacks and data members for event commands
+ *
+ * Event commands are invoked by users by writing the command name
+ * into the 'trigger' file associated with a trace event. The
+ * parameters associated with a specific invocation of an event
+ * command are used to create an event trigger instance, which is
+ * added to the list of trigger instances associated with that trace
+ * event. When the event is hit, the set of triggers associated with
+ * that event is invoked.
+ *
+ * The data members in this structure provide per-event command data
+ * for various event commands.
+ *
+ * All the data members below, except for @post_trigger, must be set
+ * for each event command.
+ *
+ * @name: The unique name that identifies the event command. This is
+ * the name used when setting triggers via trigger files.
+ *
+ * @trigger_type: A unique id that identifies the event command
+ * 'type'. This value has two purposes, the first to ensure that
+ * only one trigger of the same type can be set at a given time
+ * for a particular event e.g. it doesn't make sense to have both
+ * a traceon and traceoff trigger attached to a single event at
+ * the same time, so traceon and traceoff have the same type
+ * though they have different names. The @trigger_type value is
+ * also used as a bit value for deferring the actual trigger
+ * action until after the current event is finished. Some
+ * commands need to do this if they themselves log to the trace
+ * buffer (see the @post_trigger() member below). @trigger_type
+ * values are defined by adding new values to the trigger_type
+ * enum in include/linux/ftrace_event.h.
+ *
+ * @post_trigger: A flag that says whether or not this command needs
+ * to have its action delayed until after the current event has
+ * been closed. Some triggers need to avoid being invoked while
+ * an event is currently in the process of being logged, since
+ * the trigger may itself log data into the trace buffer. Thus
+ * we make sure the current event is committed before invoking
+ * those triggers. To do that, the trigger invocation is split
+ * in two - the first part checks the filter using the current
+ * trace record; if a command has the @post_trigger flag set, it
+ * sets a bit for itself in the return value, otherwise it
+ * directly invokes the trigger. Once all commands have been
+ * either invoked or set their return flag, the current record is
+ * either committed or discarded. At that point, if any commands
+ * have deferred their triggers, those commands are finally
+ * invoked following the close of the current event. In other
+ * words, if the event_trigger_ops @func() probe implementation
+ * itself logs to the trace buffer, this flag should be set,
+ * otherwise it can be left unspecified.
+ *
+ * All the methods below, except for @set_filter(), must be
+ * implemented.
+ *
+ * @func: The callback function responsible for parsing and
+ * registering the trigger written to the 'trigger' file by the
+ * user. It allocates the trigger instance and registers it with
+ * the appropriate trace event. It makes use of the other
+ * event_command callback functions to orchestrate this, and is
+ * usually implemented by the generic utility function
+ * @event_trigger_callback() (see trace_event_triggers.c).
+ *
+ * @reg: Adds the trigger to the list of triggers associated with the
+ * event, and enables the event trigger itself, after
+ * initializing it (via the event_trigger_ops @init() function).
+ * This is also where commands can use the @trigger_type value to
+ * make the decision as to whether or not multiple instances of
+ * the trigger should be allowed. This is usually implemented by
+ * the generic utility function @register_trigger() (see
+ * trace_event_triggers.c).
+ *
+ * @unreg: Removes the trigger from the list of triggers associated
+ * with the event, and disables the event trigger itself, after
+ * initializing it (via the event_trigger_ops @free() function).
+ * This is usually implemented by the generic utility function
+ * @unregister_trigger() (see trace_event_triggers.c).
+ *
+ * @set_filter: An optional function called to parse and set a filter
+ * for the trigger. If no @set_filter() method is set for the
+ * event command, filters set by the user for the command will be
+ * ignored. This is usually implemented by the generic utility
+ * function @set_trigger_filter() (see trace_event_triggers.c).
+ *
+ * @get_trigger_ops: The callback function invoked to retrieve the
+ * event_trigger_ops implementation associated with the command.
+ */
+struct event_command {
+ struct list_head list;
+ char *name;
+ enum event_trigger_type trigger_type;
+ bool post_trigger;
+ int (*func)(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *params);
+ int (*reg)(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ void (*unreg)(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ int (*set_filter)(char *filter_str,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file);
+ struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
+};
+
+extern int trace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable);
+extern int tracing_alloc_snapshot(void);
+
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
@@ -1056,7 +1280,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \
extern struct ftrace_event_call \
- __attribute__((__aligned__(4))) event_##call;
+ __aligned(4) event_##call;
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e854f420e033..c894614de14d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -31,9 +31,25 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
}
/* The ftrace function trace is allowed only for root. */
- if (ftrace_event_is_function(tp_event) &&
- perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
- return -EPERM;
+ if (ftrace_event_is_function(tp_event)) {
+ if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /*
+ * We don't allow user space callchains for function trace
+ * event, due to issues with page faults while tracing page
+ * fault handler and its overall trickiness nature.
+ */
+ if (!p_event->attr.exclude_callchain_user)
+ return -EINVAL;
+
+ /*
+ * Same reason to disable user stack dump as for user space
+ * callchains above.
+ */
+ if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
+ return -EINVAL;
+ }
/* No tracing, just counting, so no obvious leak */
if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index a11800ae96de..83a4378dc5e0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
DEFINE_MUTEX(event_mutex);
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
LIST_HEAD(ftrace_events);
static LIST_HEAD(ftrace_common_fields);
@@ -194,6 +188,36 @@ int trace_event_raw_init(struct ftrace_event_call *call)
}
EXPORT_SYMBOL_GPL(trace_event_raw_init);
+void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
+ struct ftrace_event_file *ftrace_file,
+ unsigned long len)
+{
+ struct ftrace_event_call *event_call = ftrace_file->event_call;
+
+ local_save_flags(fbuffer->flags);
+ fbuffer->pc = preempt_count();
+ fbuffer->ftrace_file = ftrace_file;
+
+ fbuffer->event =
+ trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file,
+ event_call->event.type, len,
+ fbuffer->flags, fbuffer->pc);
+ if (!fbuffer->event)
+ return NULL;
+
+ fbuffer->entry = ring_buffer_event_data(fbuffer->event);
+ return fbuffer->entry;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve);
+
+void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer)
+{
+ event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer,
+ fbuffer->event, fbuffer->entry,
+ fbuffer->flags, fbuffer->pc);
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit);
+
int ftrace_event_reg(struct ftrace_event_call *call,
enum trace_reg type, void *data)
{
@@ -342,6 +366,12 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
return ret;
}
+int trace_event_enable_disable(struct ftrace_event_file *file,
+ int enable, int soft_disable)
+{
+ return __ftrace_event_enable_disable(file, enable, soft_disable);
+}
+
static int ftrace_event_enable_disable(struct ftrace_event_file *file,
int enable)
{
@@ -421,11 +451,6 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir)
}
}
-static void *event_file_data(struct file *filp)
-{
- return ACCESS_ONCE(file_inode(filp)->i_private);
-}
-
static void remove_event_file_dir(struct ftrace_event_file *file)
{
struct dentry *dir = file->dir;
@@ -1549,6 +1574,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
trace_create_file("filter", 0644, file->dir, file,
&ftrace_event_filter_fops);
+ trace_create_file("trigger", 0644, file->dir, file,
+ &event_trigger_fops);
+
trace_create_file("format", 0444, file->dir, call,
&ftrace_event_format_fops);
@@ -1645,6 +1673,8 @@ trace_create_new_event(struct ftrace_event_call *call,
file->event_call = call;
file->tr = tr;
atomic_set(&file->sm_ref, 0);
+ atomic_set(&file->tm_ref, 0);
+ INIT_LIST_HEAD(&file->triggers);
list_add(&file->list, &tr->events);
return file;
@@ -1771,6 +1801,16 @@ static void trace_module_add_events(struct module *mod)
{
struct ftrace_event_call **call, **start, **end;
+ if (!mod->num_trace_events)
+ return;
+
+ /* Don't add infrastructure for mods without tracepoints */
+ if (trace_module_has_bad_taint(mod)) {
+ pr_err("%s: module has bad taint, not creating trace events\n",
+ mod->name);
+ return;
+ }
+
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
@@ -1849,20 +1889,7 @@ __trace_add_event_dirs(struct trace_array *tr)
}
}
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-/* Avoid typos */
-#define ENABLE_EVENT_STR "enable_event"
-#define DISABLE_EVENT_STR "disable_event"
-
-struct event_probe_data {
- struct ftrace_event_file *file;
- unsigned long count;
- int ref;
- bool enable;
-};
-
-static struct ftrace_event_file *
+struct ftrace_event_file *
find_event_file(struct trace_array *tr, const char *system, const char *event)
{
struct ftrace_event_file *file;
@@ -1885,6 +1912,19 @@ find_event_file(struct trace_array *tr, const char *system, const char *event)
return NULL;
}
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct event_probe_data {
+ struct ftrace_event_file *file;
+ unsigned long count;
+ int ref;
+ bool enable;
+};
+
static void
event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
{
@@ -2311,6 +2351,9 @@ int event_trace_del_tracer(struct trace_array *tr)
{
mutex_lock(&event_mutex);
+ /* Disable any event triggers and associated soft-disabled events */
+ clear_event_triggers(tr);
+
/* Disable any running events */
__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
@@ -2377,6 +2420,8 @@ static __init int event_trace_enable(void)
register_event_cmds();
+ register_trigger_cmds();
+
return 0;
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 2468f56dc5db..8a8631926a07 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -799,6 +799,11 @@ static void __free_filter(struct event_filter *filter)
kfree(filter);
}
+void free_event_filter(struct event_filter *filter)
+{
+ __free_filter(filter);
+}
+
void destroy_call_preds(struct ftrace_event_call *call)
{
__free_filter(call->filter);
@@ -1938,6 +1943,13 @@ static int create_filter(struct ftrace_event_call *call,
return err;
}
+int create_event_filter(struct ftrace_event_call *call,
+ char *filter_str, bool set_str,
+ struct event_filter **filterp)
+{
+ return create_filter(call, filter_str, set_str, filterp);
+}
+
/**
* create_system_filter - create a filter for an event_subsystem
* @system: event_subsystem to create a filter for
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
new file mode 100644
index 000000000000..8efbb69b04f0
--- /dev/null
+++ b/kernel/trace/trace_events_trigger.c
@@ -0,0 +1,1437 @@
+/*
+ * trace_events_trigger - trace event triggers
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include "trace.h"
+
+static LIST_HEAD(trigger_commands);
+static DEFINE_MUTEX(trigger_cmd_mutex);
+
+static void
+trigger_data_free(struct event_trigger_data *data)
+{
+ if (data->cmd_ops->set_filter)
+ data->cmd_ops->set_filter(NULL, data, NULL);
+
+ synchronize_sched(); /* make sure current triggers exit before free */
+ kfree(data);
+}
+
+/**
+ * event_triggers_call - Call triggers associated with a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @rec: The trace entry for the event, NULL for unconditional invocation
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command. If rec is
+ * non-NULL, it means that the trigger requires further processing and
+ * shouldn't be unconditionally invoked. If rec is non-NULL and the
+ * trigger has a filter associated with it, rec will checked against
+ * the filter and if the record matches the trigger will be invoked.
+ * If the trigger is a 'post_trigger', meaning it shouldn't be invoked
+ * in any case until the current event is written, the trigger
+ * function isn't invoked but the bit associated with the deferred
+ * trigger is set in the return value.
+ *
+ * Returns an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ *
+ * Return: an enum event_trigger_type value containing a set bit for
+ * any trigger that should be deferred, ETT_NONE if nothing to defer.
+ */
+enum event_trigger_type
+event_triggers_call(struct ftrace_event_file *file, void *rec)
+{
+ struct event_trigger_data *data;
+ enum event_trigger_type tt = ETT_NONE;
+ struct event_filter *filter;
+
+ if (list_empty(&file->triggers))
+ return tt;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (!rec) {
+ data->ops->func(data);
+ continue;
+ }
+ filter = rcu_dereference(data->filter);
+ if (filter && !filter_match_preds(filter, rec))
+ continue;
+ if (data->cmd_ops->post_trigger) {
+ tt |= data->cmd_ops->trigger_type;
+ continue;
+ }
+ data->ops->func(data);
+ }
+ return tt;
+}
+EXPORT_SYMBOL_GPL(event_triggers_call);
+
+/**
+ * event_triggers_post_call - Call 'post_triggers' for a trace event
+ * @file: The ftrace_event_file associated with the event
+ * @tt: enum event_trigger_type containing a set bit for each trigger to invoke
+ *
+ * For each trigger associated with an event, invoke the trigger
+ * function registered with the associated trigger command, if the
+ * corresponding bit is set in the tt enum passed into this function.
+ * See @event_triggers_call for details on how those bits are set.
+ *
+ * Called from tracepoint handlers (with rcu_read_lock_sched() held).
+ */
+void
+event_triggers_post_call(struct ftrace_event_file *file,
+ enum event_trigger_type tt)
+{
+ struct event_trigger_data *data;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->cmd_ops->trigger_type & tt)
+ data->ops->func(data);
+ }
+}
+EXPORT_SYMBOL_GPL(event_triggers_post_call);
+
+#define SHOW_AVAILABLE_TRIGGERS (void *)(1UL)
+
+static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
+{
+ struct ftrace_event_file *event_file = event_file_data(m->private);
+
+ if (t == SHOW_AVAILABLE_TRIGGERS)
+ return NULL;
+
+ return seq_list_next(t, &event_file->triggers, pos);
+}
+
+static void *trigger_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_event_file *event_file;
+
+ /* ->stop() is called even if ->start() fails */
+ mutex_lock(&event_mutex);
+ event_file = event_file_data(m->private);
+ if (unlikely(!event_file))
+ return ERR_PTR(-ENODEV);
+
+ if (list_empty(&event_file->triggers))
+ return *pos == 0 ? SHOW_AVAILABLE_TRIGGERS : NULL;
+
+ return seq_list_start(&event_file->triggers, *pos);
+}
+
+static void trigger_stop(struct seq_file *m, void *t)
+{
+ mutex_unlock(&event_mutex);
+}
+
+static int trigger_show(struct seq_file *m, void *v)
+{
+ struct event_trigger_data *data;
+ struct event_command *p;
+
+ if (v == SHOW_AVAILABLE_TRIGGERS) {
+ seq_puts(m, "# Available triggers:\n");
+ seq_putc(m, '#');
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry_reverse(p, &trigger_commands, list)
+ seq_printf(m, " %s", p->name);
+ seq_putc(m, '\n');
+ mutex_unlock(&trigger_cmd_mutex);
+ return 0;
+ }
+
+ data = list_entry(v, struct event_trigger_data, list);
+ data->ops->print(m, data->ops, data);
+
+ return 0;
+}
+
+static const struct seq_operations event_triggers_seq_ops = {
+ .start = trigger_start,
+ .next = trigger_next,
+ .stop = trigger_stop,
+ .show = trigger_show,
+};
+
+static int event_trigger_regex_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ mutex_lock(&event_mutex);
+
+ if (unlikely(!event_file_data(file))) {
+ mutex_unlock(&event_mutex);
+ return -ENODEV;
+ }
+
+ if (file->f_mode & FMODE_READ) {
+ ret = seq_open(file, &event_triggers_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = file;
+ }
+ }
+
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+static int trigger_process_regex(struct ftrace_event_file *file, char *buff)
+{
+ char *command, *next = buff;
+ struct event_command *p;
+ int ret = -EINVAL;
+
+ command = strsep(&next, ": \t");
+ command = (command[0] != '!') ? command : command + 1;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (strcmp(p->name, command) == 0) {
+ ret = p->func(p, file, buff, command, next);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+static ssize_t event_trigger_regex_write(struct file *file,
+ const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct ftrace_event_file *event_file;
+ ssize_t ret;
+ char *buf;
+
+ if (!cnt)
+ return 0;
+
+ if (cnt >= PAGE_SIZE)
+ return -EINVAL;
+
+ buf = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, ubuf, cnt)) {
+ free_page((unsigned long)buf);
+ return -EFAULT;
+ }
+ buf[cnt] = '\0';
+ strim(buf);
+
+ mutex_lock(&event_mutex);
+ event_file = event_file_data(file);
+ if (unlikely(!event_file)) {
+ mutex_unlock(&event_mutex);
+ free_page((unsigned long)buf);
+ return -ENODEV;
+ }
+ ret = trigger_process_regex(event_file, buf);
+ mutex_unlock(&event_mutex);
+
+ free_page((unsigned long)buf);
+ if (ret < 0)
+ goto out;
+
+ *ppos += cnt;
+ ret = cnt;
+ out:
+ return ret;
+}
+
+static int event_trigger_regex_release(struct inode *inode, struct file *file)
+{
+ mutex_lock(&event_mutex);
+
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+
+ mutex_unlock(&event_mutex);
+
+ return 0;
+}
+
+static ssize_t
+event_trigger_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ return event_trigger_regex_write(filp, ubuf, cnt, ppos);
+}
+
+static int
+event_trigger_open(struct inode *inode, struct file *filp)
+{
+ return event_trigger_regex_open(inode, filp);
+}
+
+static int
+event_trigger_release(struct inode *inode, struct file *file)
+{
+ return event_trigger_regex_release(inode, file);
+}
+
+const struct file_operations event_trigger_fops = {
+ .open = event_trigger_open,
+ .read = seq_read,
+ .write = event_trigger_write,
+ .llseek = tracing_lseek,
+ .release = event_trigger_release,
+};
+
+/*
+ * Currently we only register event commands from __init, so mark this
+ * __init too.
+ */
+static __init int register_event_command(struct event_command *cmd)
+{
+ struct event_command *p;
+ int ret = 0;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ }
+ list_add(&cmd->list, &trigger_commands);
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+/*
+ * Currently we only unregister event commands from __init, so mark
+ * this __init too.
+ */
+static __init int unregister_event_command(struct event_command *cmd)
+{
+ struct event_command *p, *n;
+ int ret = -ENODEV;
+
+ mutex_lock(&trigger_cmd_mutex);
+ list_for_each_entry_safe(p, n, &trigger_commands, list) {
+ if (strcmp(cmd->name, p->name) == 0) {
+ ret = 0;
+ list_del_init(&p->list);
+ goto out_unlock;
+ }
+ }
+ out_unlock:
+ mutex_unlock(&trigger_cmd_mutex);
+
+ return ret;
+}
+
+/**
+ * event_trigger_print - Generic event_trigger_ops @print implementation
+ * @name: The name of the event trigger
+ * @m: The seq_file being printed to
+ * @data: Trigger-specific data
+ * @filter_str: filter_str to print, if present
+ *
+ * Common implementation for event triggers to print themselves.
+ *
+ * Usually wrapped by a function that simply sets the @name of the
+ * trigger command and then invokes this.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_print(const char *name, struct seq_file *m,
+ void *data, char *filter_str)
+{
+ long count = (long)data;
+
+ seq_printf(m, "%s", name);
+
+ if (count == -1)
+ seq_puts(m, ":unlimited");
+ else
+ seq_printf(m, ":count=%ld", count);
+
+ if (filter_str)
+ seq_printf(m, " if %s\n", filter_str);
+ else
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+/**
+ * event_trigger_init - Generic event_trigger_ops @init implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger initialization.
+ *
+ * Usually used directly as the @init method in event trigger
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_init(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ data->ref++;
+ return 0;
+}
+
+/**
+ * event_trigger_free - Generic event_trigger_ops @free implementation
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data
+ *
+ * Common implementation of event trigger de-initialization.
+ *
+ * Usually used directly as the @free method in event trigger
+ * implementations.
+ */
+static void
+event_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ if (WARN_ON_ONCE(data->ref <= 0))
+ return;
+
+ data->ref--;
+ if (!data->ref)
+ trigger_data_free(data);
+}
+
+static int trace_event_trigger_enable_disable(struct ftrace_event_file *file,
+ int trigger_enable)
+{
+ int ret = 0;
+
+ if (trigger_enable) {
+ if (atomic_inc_return(&file->tm_ref) > 1)
+ return ret;
+ set_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+ ret = trace_event_enable_disable(file, 1, 1);
+ } else {
+ if (atomic_dec_return(&file->tm_ref) > 0)
+ return ret;
+ clear_bit(FTRACE_EVENT_FL_TRIGGER_MODE_BIT, &file->flags);
+ ret = trace_event_enable_disable(file, 0, 1);
+ }
+
+ return ret;
+}
+
+/**
+ * clear_event_triggers - Clear all triggers associated with a trace array
+ * @tr: The trace array to clear
+ *
+ * For each trigger, the triggering event has its tm_ref decremented
+ * via trace_event_trigger_enable_disable(), and any associated event
+ * (in the case of enable/disable_event triggers) will have its sm_ref
+ * decremented via free()->trace_event_enable_disable(). That
+ * combination effectively reverses the soft-mode/trigger state added
+ * by trigger registration.
+ *
+ * Must be called with event_mutex held.
+ */
+void
+clear_event_triggers(struct trace_array *tr)
+{
+ struct ftrace_event_file *file;
+
+ list_for_each_entry(file, &tr->events, list) {
+ struct event_trigger_data *data;
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ trace_event_trigger_enable_disable(file, 0);
+ if (data->ops->free)
+ data->ops->free(data->ops, data);
+ }
+ }
+}
+
+/**
+ * update_cond_flag - Set or reset the TRIGGER_COND bit
+ * @file: The ftrace_event_file associated with the event
+ *
+ * If an event has triggers and any of those triggers has a filter or
+ * a post_trigger, trigger invocation needs to be deferred until after
+ * the current event has logged its data, and the event should have
+ * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be
+ * cleared.
+ */
+static void update_cond_flag(struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+ bool set_cond = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->filter || data->cmd_ops->post_trigger) {
+ set_cond = true;
+ break;
+ }
+ }
+
+ if (set_cond)
+ set_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+ else
+ clear_bit(FTRACE_EVENT_FL_TRIGGER_COND_BIT, &file->flags);
+}
+
+/**
+ * register_trigger - Generic event_command @reg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @data: Trigger-specific data to associate with the trigger
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger registration.
+ *
+ * Usually used directly as the @reg method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int register_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *test;
+ int ret = 0;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (data->ops->init) {
+ ret = data->ops->init(data->ops, data);
+ if (ret < 0)
+ goto out;
+ }
+
+ list_add_rcu(&data->list, &file->triggers);
+ ret++;
+
+ if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ list_del_rcu(&data->list);
+ ret--;
+ }
+ update_cond_flag(file);
+out:
+ return ret;
+}
+
+/**
+ * unregister_trigger - Generic event_command @unreg implementation
+ * @glob: The raw string used to register the trigger
+ * @ops: The trigger ops associated with the trigger
+ * @test: Trigger-specific data used to find the trigger to remove
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event trigger unregistration.
+ *
+ * Usually used directly as the @unreg method in event command
+ * implementations.
+ */
+static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data;
+ bool unregistered = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+ unregistered = true;
+ list_del_rcu(&data->list);
+ update_cond_flag(file);
+ trace_event_trigger_enable_disable(file, 0);
+ break;
+ }
+ }
+
+ if (unregistered && data->ops->free)
+ data->ops->free(data->ops, data);
+}
+
+/**
+ * event_trigger_callback - Generic event_command @func implementation
+ * @cmd_ops: The command ops, used for trigger registration
+ * @file: The ftrace_event_file associated with the event
+ * @glob: The raw string used to register the trigger
+ * @cmd: The cmd portion of the string used to register the trigger
+ * @param: The params portion of the string used to register the trigger
+ *
+ * Common implementation for event command parsing and trigger
+ * instantiation.
+ *
+ * Usually used directly as the @func method in event command
+ * implementations.
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int
+event_trigger_callback(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ struct event_trigger_data *trigger_data;
+ struct event_trigger_ops *trigger_ops;
+ char *trigger = NULL;
+ char *number;
+ int ret;
+
+ /* separate the trigger from the filter (t:n [if filter]) */
+ if (param && isdigit(param[0]))
+ trigger = strsep(&param, " \t");
+
+ trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+ ret = -ENOMEM;
+ trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ if (!trigger_data)
+ goto out;
+
+ trigger_data->count = -1;
+ trigger_data->ops = trigger_ops;
+ trigger_data->cmd_ops = cmd_ops;
+ INIT_LIST_HEAD(&trigger_data->list);
+
+ if (glob[0] == '!') {
+ cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+ kfree(trigger_data);
+ ret = 0;
+ goto out;
+ }
+
+ if (trigger) {
+ number = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &trigger_data->count);
+ if (ret)
+ goto out_free;
+ }
+
+ if (!param) /* if param is non-empty, it's supposed to be a filter */
+ goto out_reg;
+
+ if (!cmd_ops->set_filter)
+ goto out_reg;
+
+ ret = cmd_ops->set_filter(param, trigger_data, file);
+ if (ret < 0)
+ goto out_free;
+
+ out_reg:
+ ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+ /*
+ * The above returns on success the # of functions enabled,
+ * but if it didn't find any functions it returns zero.
+ * Consider no functions a failure too.
+ */
+ if (!ret) {
+ ret = -ENOENT;
+ goto out_free;
+ } else if (ret < 0)
+ goto out_free;
+ ret = 0;
+ out:
+ return ret;
+
+ out_free:
+ if (cmd_ops->set_filter)
+ cmd_ops->set_filter(NULL, trigger_data, NULL);
+ kfree(trigger_data);
+ goto out;
+}
+
+/**
+ * set_trigger_filter - Generic event_command @set_filter implementation
+ * @filter_str: The filter string for the trigger, NULL to remove filter
+ * @trigger_data: Trigger-specific data
+ * @file: The ftrace_event_file associated with the event
+ *
+ * Common implementation for event command filter parsing and filter
+ * instantiation.
+ *
+ * Usually used directly as the @set_filter method in event command
+ * implementations.
+ *
+ * Also used to remove a filter (if filter_str = NULL).
+ *
+ * Return: 0 on success, errno otherwise
+ */
+static int set_trigger_filter(char *filter_str,
+ struct event_trigger_data *trigger_data,
+ struct ftrace_event_file *file)
+{
+ struct event_trigger_data *data = trigger_data;
+ struct event_filter *filter = NULL, *tmp;
+ int ret = -EINVAL;
+ char *s;
+
+ if (!filter_str) /* clear the current filter */
+ goto assign;
+
+ s = strsep(&filter_str, " \t");
+
+ if (!strlen(s) || strcmp(s, "if") != 0)
+ goto out;
+
+ if (!filter_str)
+ goto out;
+
+ /* The filter is for the 'trigger' event, not the triggered event */
+ ret = create_event_filter(file->event_call, filter_str, false, &filter);
+ if (ret)
+ goto out;
+ assign:
+ tmp = rcu_access_pointer(data->filter);
+
+ rcu_assign_pointer(data->filter, filter);
+
+ if (tmp) {
+ /* Make sure the call is done with the filter */
+ synchronize_sched();
+ free_event_filter(tmp);
+ }
+
+ kfree(data->filter_str);
+ data->filter_str = NULL;
+
+ if (filter_str) {
+ data->filter_str = kstrdup(filter_str, GFP_KERNEL);
+ if (!data->filter_str) {
+ free_event_filter(rcu_access_pointer(data->filter));
+ data->filter = NULL;
+ ret = -ENOMEM;
+ }
+ }
+ out:
+ return ret;
+}
+
+static void
+traceon_trigger(struct event_trigger_data *data)
+{
+ if (tracing_is_on())
+ return;
+
+ tracing_on();
+}
+
+static void
+traceon_count_trigger(struct event_trigger_data *data)
+{
+ if (tracing_is_on())
+ return;
+
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ tracing_on();
+}
+
+static void
+traceoff_trigger(struct event_trigger_data *data)
+{
+ if (!tracing_is_on())
+ return;
+
+ tracing_off();
+}
+
+static void
+traceoff_count_trigger(struct event_trigger_data *data)
+{
+ if (!tracing_is_on())
+ return;
+
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ tracing_off();
+}
+
+static int
+traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("traceon", m, (void *)data->count,
+ data->filter_str);
+}
+
+static int
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("traceoff", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops traceon_trigger_ops = {
+ .func = traceon_trigger,
+ .print = traceon_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceon_count_trigger_ops = {
+ .func = traceon_count_trigger,
+ .print = traceon_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_trigger_ops = {
+ .func = traceoff_trigger,
+ .print = traceoff_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops traceoff_count_trigger_ops = {
+ .func = traceoff_count_trigger,
+ .print = traceoff_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+onoff_get_trigger_ops(char *cmd, char *param)
+{
+ struct event_trigger_ops *ops;
+
+ /* we register both traceon and traceoff to this callback */
+ if (strcmp(cmd, "traceon") == 0)
+ ops = param ? &traceon_count_trigger_ops :
+ &traceon_trigger_ops;
+ else
+ ops = param ? &traceoff_count_trigger_ops :
+ &traceoff_trigger_ops;
+
+ return ops;
+}
+
+static struct event_command trigger_traceon_cmd = {
+ .name = "traceon",
+ .trigger_type = ETT_TRACE_ONOFF,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = onoff_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static struct event_command trigger_traceoff_cmd = {
+ .name = "traceoff",
+ .trigger_type = ETT_TRACE_ONOFF,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = onoff_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+#ifdef CONFIG_TRACER_SNAPSHOT
+static void
+snapshot_trigger(struct event_trigger_data *data)
+{
+ tracing_snapshot();
+}
+
+static void
+snapshot_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ snapshot_trigger(data);
+}
+
+static int
+register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ int ret = register_trigger(glob, ops, data, file);
+
+ if (ret > 0 && tracing_alloc_snapshot() != 0) {
+ unregister_trigger(glob, ops, data, file);
+ ret = 0;
+ }
+
+ return ret;
+}
+
+static int
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("snapshot", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops snapshot_trigger_ops = {
+ .func = snapshot_trigger,
+ .print = snapshot_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops snapshot_count_trigger_ops = {
+ .func = snapshot_count_trigger,
+ .print = snapshot_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+snapshot_get_trigger_ops(char *cmd, char *param)
+{
+ return param ? &snapshot_count_trigger_ops : &snapshot_trigger_ops;
+}
+
+static struct event_command trigger_snapshot_cmd = {
+ .name = "snapshot",
+ .trigger_type = ETT_SNAPSHOT,
+ .func = event_trigger_callback,
+ .reg = register_snapshot_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = snapshot_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static __init int register_trigger_snapshot_cmd(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_snapshot_cmd);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+#else
+static __init int register_trigger_snapshot_cmd(void) { return 0; }
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+#ifdef CONFIG_STACKTRACE
+/*
+ * Skip 3:
+ * stacktrace_trigger()
+ * event_triggers_post_call()
+ * ftrace_raw_event_xxx()
+ */
+#define STACK_SKIP 3
+
+static void
+stacktrace_trigger(struct event_trigger_data *data)
+{
+ trace_dump_stack(STACK_SKIP);
+}
+
+static void
+stacktrace_count_trigger(struct event_trigger_data *data)
+{
+ if (!data->count)
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ stacktrace_trigger(data);
+}
+
+static int
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return event_trigger_print("stacktrace", m, (void *)data->count,
+ data->filter_str);
+}
+
+static struct event_trigger_ops stacktrace_trigger_ops = {
+ .func = stacktrace_trigger,
+ .print = stacktrace_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops stacktrace_count_trigger_ops = {
+ .func = stacktrace_count_trigger,
+ .print = stacktrace_trigger_print,
+ .init = event_trigger_init,
+ .free = event_trigger_free,
+};
+
+static struct event_trigger_ops *
+stacktrace_get_trigger_ops(char *cmd, char *param)
+{
+ return param ? &stacktrace_count_trigger_ops : &stacktrace_trigger_ops;
+}
+
+static struct event_command trigger_stacktrace_cmd = {
+ .name = "stacktrace",
+ .trigger_type = ETT_STACKTRACE,
+ .post_trigger = true,
+ .func = event_trigger_callback,
+ .reg = register_trigger,
+ .unreg = unregister_trigger,
+ .get_trigger_ops = stacktrace_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static __init int register_trigger_stacktrace_cmd(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_stacktrace_cmd);
+ WARN_ON(ret < 0);
+
+ return ret;
+}
+#else
+static __init int register_trigger_stacktrace_cmd(void) { return 0; }
+#endif /* CONFIG_STACKTRACE */
+
+static __init void unregister_trigger_traceon_traceoff_cmds(void)
+{
+ unregister_event_command(&trigger_traceon_cmd);
+ unregister_event_command(&trigger_traceoff_cmd);
+}
+
+/* Avoid typos */
+#define ENABLE_EVENT_STR "enable_event"
+#define DISABLE_EVENT_STR "disable_event"
+
+struct enable_trigger_data {
+ struct ftrace_event_file *file;
+ bool enable;
+};
+
+static void
+event_enable_trigger(struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (enable_data->enable)
+ clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+ else
+ set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &enable_data->file->flags);
+}
+
+static void
+event_enable_count_trigger(struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (!data->count)
+ return;
+
+ /* Skip if the event is in a state we want to switch to */
+ if (enable_data->enable == !(enable_data->file->flags & FTRACE_EVENT_FL_SOFT_DISABLED))
+ return;
+
+ if (data->count != -1)
+ (data->count)--;
+
+ event_enable_trigger(data);
+}
+
+static int
+event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ seq_printf(m, "%s:%s:%s",
+ enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
+ enable_data->file->event_call->class->system,
+ enable_data->file->event_call->name);
+
+ if (data->count == -1)
+ seq_puts(m, ":unlimited");
+ else
+ seq_printf(m, ":count=%ld", data->count);
+
+ if (data->filter_str)
+ seq_printf(m, " if %s\n", data->filter_str);
+ else
+ seq_puts(m, "\n");
+
+ return 0;
+}
+
+static void
+event_enable_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+
+ if (WARN_ON_ONCE(data->ref <= 0))
+ return;
+
+ data->ref--;
+ if (!data->ref) {
+ /* Remove the SOFT_MODE flag */
+ trace_event_enable_disable(enable_data->file, 0, 1);
+ module_put(enable_data->file->event_call->mod);
+ trigger_data_free(data);
+ kfree(enable_data);
+ }
+}
+
+static struct event_trigger_ops event_enable_trigger_ops = {
+ .func = event_enable_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_enable_count_trigger_ops = {
+ .func = event_enable_count_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_trigger_ops = {
+ .func = event_enable_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static struct event_trigger_ops event_disable_count_trigger_ops = {
+ .func = event_enable_count_trigger,
+ .print = event_enable_trigger_print,
+ .init = event_trigger_init,
+ .free = event_enable_trigger_free,
+};
+
+static int
+event_enable_trigger_func(struct event_command *cmd_ops,
+ struct ftrace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ struct ftrace_event_file *event_enable_file;
+ struct enable_trigger_data *enable_data;
+ struct event_trigger_data *trigger_data;
+ struct event_trigger_ops *trigger_ops;
+ struct trace_array *tr = file->tr;
+ const char *system;
+ const char *event;
+ char *trigger;
+ char *number;
+ bool enable;
+ int ret;
+
+ if (!param)
+ return -EINVAL;
+
+ /* separate the trigger from the filter (s:e:n [if filter]) */
+ trigger = strsep(&param, " \t");
+ if (!trigger)
+ return -EINVAL;
+
+ system = strsep(&trigger, ":");
+ if (!trigger)
+ return -EINVAL;
+
+ event = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ event_enable_file = find_event_file(tr, system, event);
+ if (!event_enable_file)
+ goto out;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+ ret = -ENOMEM;
+ trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ if (!trigger_data)
+ goto out;
+
+ enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
+ if (!enable_data) {
+ kfree(trigger_data);
+ goto out;
+ }
+
+ trigger_data->count = -1;
+ trigger_data->ops = trigger_ops;
+ trigger_data->cmd_ops = cmd_ops;
+ INIT_LIST_HEAD(&trigger_data->list);
+ RCU_INIT_POINTER(trigger_data->filter, NULL);
+
+ enable_data->enable = enable;
+ enable_data->file = event_enable_file;
+ trigger_data->private_data = enable_data;
+
+ if (glob[0] == '!') {
+ cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+ kfree(trigger_data);
+ kfree(enable_data);
+ ret = 0;
+ goto out;
+ }
+
+ if (trigger) {
+ number = strsep(&trigger, ":");
+
+ ret = -EINVAL;
+ if (!strlen(number))
+ goto out_free;
+
+ /*
+ * We use the callback data field (which is a pointer)
+ * as our counter.
+ */
+ ret = kstrtoul(number, 0, &trigger_data->count);
+ if (ret)
+ goto out_free;
+ }
+
+ if (!param) /* if param is non-empty, it's supposed to be a filter */
+ goto out_reg;
+
+ if (!cmd_ops->set_filter)
+ goto out_reg;
+
+ ret = cmd_ops->set_filter(param, trigger_data, file);
+ if (ret < 0)
+ goto out_free;
+
+ out_reg:
+ /* Don't let event modules unload while probe registered */
+ ret = try_module_get(event_enable_file->event_call->mod);
+ if (!ret) {
+ ret = -EBUSY;
+ goto out_free;
+ }
+
+ ret = trace_event_enable_disable(event_enable_file, 1, 1);
+ if (ret < 0)
+ goto out_put;
+ ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+ /*
+ * The above returns on success the # of functions enabled,
+ * but if it didn't find any functions it returns zero.
+ * Consider no functions a failure too.
+ */
+ if (!ret) {
+ ret = -ENOENT;
+ goto out_disable;
+ } else if (ret < 0)
+ goto out_disable;
+ /* Just return zero, not the number of enabled functions */
+ ret = 0;
+ out:
+ return ret;
+
+ out_disable:
+ trace_event_enable_disable(event_enable_file, 0, 1);
+ out_put:
+ module_put(event_enable_file->event_call->mod);
+ out_free:
+ if (cmd_ops->set_filter)
+ cmd_ops->set_filter(NULL, trigger_data, NULL);
+ kfree(trigger_data);
+ kfree(enable_data);
+ goto out;
+}
+
+static int event_enable_register_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct ftrace_event_file *file)
+{
+ struct enable_trigger_data *enable_data = data->private_data;
+ struct enable_trigger_data *test_enable_data;
+ struct event_trigger_data *test;
+ int ret = 0;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ test_enable_data = test->private_data;
+ if (test_enable_data &&
+ (test_enable_data->file == enable_data->file)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (data->ops->init) {
+ ret = data->ops->init(data->ops, data);
+ if (ret < 0)
+ goto out;
+ }
+
+ list_add_rcu(&data->list, &file->triggers);
+ ret++;
+
+ if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ list_del_rcu(&data->list);
+ ret--;
+ }
+ update_cond_flag(file);
+out:
+ return ret;
+}
+
+static void event_enable_unregister_trigger(char *glob,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct ftrace_event_file *file)
+{
+ struct enable_trigger_data *test_enable_data = test->private_data;
+ struct enable_trigger_data *enable_data;
+ struct event_trigger_data *data;
+ bool unregistered = false;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ enable_data = data->private_data;
+ if (enable_data &&
+ (enable_data->file == test_enable_data->file)) {
+ unregistered = true;
+ list_del_rcu(&data->list);
+ update_cond_flag(file);
+ trace_event_trigger_enable_disable(file, 0);
+ break;
+ }
+ }
+
+ if (unregistered && data->ops->free)
+ data->ops->free(data->ops, data);
+}
+
+static struct event_trigger_ops *
+event_enable_get_trigger_ops(char *cmd, char *param)
+{
+ struct event_trigger_ops *ops;
+ bool enable;
+
+ enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
+
+ if (enable)
+ ops = param ? &event_enable_count_trigger_ops :
+ &event_enable_trigger_ops;
+ else
+ ops = param ? &event_disable_count_trigger_ops :
+ &event_disable_trigger_ops;
+
+ return ops;
+}
+
+static struct event_command trigger_enable_cmd = {
+ .name = ENABLE_EVENT_STR,
+ .trigger_type = ETT_EVENT_ENABLE,
+ .func = event_enable_trigger_func,
+ .reg = event_enable_register_trigger,
+ .unreg = event_enable_unregister_trigger,
+ .get_trigger_ops = event_enable_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static struct event_command trigger_disable_cmd = {
+ .name = DISABLE_EVENT_STR,
+ .trigger_type = ETT_EVENT_ENABLE,
+ .func = event_enable_trigger_func,
+ .reg = event_enable_register_trigger,
+ .unreg = event_enable_unregister_trigger,
+ .get_trigger_ops = event_enable_get_trigger_ops,
+ .set_filter = set_trigger_filter,
+};
+
+static __init void unregister_trigger_enable_disable_cmds(void)
+{
+ unregister_event_command(&trigger_enable_cmd);
+ unregister_event_command(&trigger_disable_cmd);
+}
+
+static __init int register_trigger_enable_disable_cmds(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_enable_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_event_command(&trigger_disable_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_trigger_enable_disable_cmds();
+
+ return ret;
+}
+
+static __init int register_trigger_traceon_traceoff_cmds(void)
+{
+ int ret;
+
+ ret = register_event_command(&trigger_traceon_cmd);
+ if (WARN_ON(ret < 0))
+ return ret;
+ ret = register_event_command(&trigger_traceoff_cmd);
+ if (WARN_ON(ret < 0))
+ unregister_trigger_traceon_traceoff_cmds();
+
+ return ret;
+}
+
+__init int register_trigger_cmds(void)
+{
+ register_trigger_traceon_traceoff_cmds();
+ register_trigger_snapshot_cmd();
+ register_trigger_stacktrace_cmd();
+ register_trigger_enable_disable_cmds();
+
+ return 0;
+}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e72e2b6..ee0a5098ac43 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void) \
#undef __array
#define __array(type, item, len) \
do { \
+ char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- mutex_lock(&event_storage_mutex); \
- snprintf(event_storage, sizeof(event_storage), \
- "%s[%d]", #type, len); \
- ret = trace_define_field(event_call, event_storage, #item, \
+ ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), filter_type); \
- mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
} while (0);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 38fe1483c508..5b781d2be383 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -13,32 +13,106 @@
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
+#include <linux/slab.h>
#include <linux/fs.h>
#include "trace.h"
-/* function tracing enabled */
-static int ftrace_function_enabled;
+static void tracing_start_function_trace(struct trace_array *tr);
+static void tracing_stop_function_trace(struct trace_array *tr);
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs);
+static void
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs);
+static struct ftrace_ops trace_ops;
+static struct ftrace_ops trace_stack_ops;
+static struct tracer_flags func_flags;
+
+/* Our option */
+enum {
+ TRACE_FUNC_OPT_STACK = 0x1,
+};
+
+static int allocate_ftrace_ops(struct trace_array *tr)
+{
+ struct ftrace_ops *ops;
+
+ ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+ if (!ops)
+ return -ENOMEM;
-static struct trace_array *func_trace;
+ /* Currently only the non stack verision is supported */
+ ops->func = function_trace_call;
+ ops->flags = FTRACE_OPS_FL_RECURSION_SAFE;
+
+ tr->ops = ops;
+ ops->private = tr;
+ return 0;
+}
+
+
+int ftrace_create_function_files(struct trace_array *tr,
+ struct dentry *parent)
+{
+ int ret;
+
+ /* The top level array uses the "global_ops". */
+ if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) {
+ ret = allocate_ftrace_ops(tr);
+ if (ret)
+ return ret;
+ }
+
+ ftrace_create_filter_files(tr->ops, parent);
+
+ return 0;
+}
-static void tracing_start_function_trace(void);
-static void tracing_stop_function_trace(void);
+void ftrace_destroy_function_files(struct trace_array *tr)
+{
+ ftrace_destroy_filter_files(tr->ops);
+ kfree(tr->ops);
+ tr->ops = NULL;
+}
static int function_trace_init(struct trace_array *tr)
{
- func_trace = tr;
+ struct ftrace_ops *ops;
+
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+ /* There's only one global tr */
+ if (!trace_ops.private) {
+ trace_ops.private = tr;
+ trace_stack_ops.private = tr;
+ }
+
+ if (func_flags.val & TRACE_FUNC_OPT_STACK)
+ ops = &trace_stack_ops;
+ else
+ ops = &trace_ops;
+ tr->ops = ops;
+ } else if (!tr->ops) {
+ /*
+ * Instance trace_arrays get their ops allocated
+ * at instance creation. Unless it failed
+ * the allocation.
+ */
+ return -ENOMEM;
+ }
+
tr->trace_buffer.cpu = get_cpu();
put_cpu();
tracing_start_cmdline_record();
- tracing_start_function_trace();
+ tracing_start_function_trace(tr);
return 0;
}
static void function_trace_reset(struct trace_array *tr)
{
- tracing_stop_function_trace();
+ tracing_stop_function_trace(tr);
tracing_stop_cmdline_record();
}
@@ -47,25 +121,18 @@ static void function_trace_start(struct trace_array *tr)
tracing_reset_online_cpus(&tr->trace_buffer);
}
-/* Our option */
-enum {
- TRACE_FUNC_OPT_STACK = 0x1,
-};
-
-static struct tracer_flags func_flags;
-
static void
function_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
- struct trace_array *tr = func_trace;
+ struct trace_array *tr = op->private;
struct trace_array_cpu *data;
unsigned long flags;
int bit;
int cpu;
int pc;
- if (unlikely(!ftrace_function_enabled))
+ if (unlikely(!tr->function_enabled))
return;
pc = preempt_count();
@@ -91,14 +158,14 @@ static void
function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *pt_regs)
{
- struct trace_array *tr = func_trace;
+ struct trace_array *tr = op->private;
struct trace_array_cpu *data;
unsigned long flags;
long disabled;
int cpu;
int pc;
- if (unlikely(!ftrace_function_enabled))
+ if (unlikely(!tr->function_enabled))
return;
/*
@@ -128,7 +195,6 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
local_irq_restore(flags);
}
-
static struct ftrace_ops trace_ops __read_mostly =
{
.func = function_trace_call,
@@ -153,29 +219,21 @@ static struct tracer_flags func_flags = {
.opts = func_opts
};
-static void tracing_start_function_trace(void)
+static void tracing_start_function_trace(struct trace_array *tr)
{
- ftrace_function_enabled = 0;
-
- if (func_flags.val & TRACE_FUNC_OPT_STACK)
- register_ftrace_function(&trace_stack_ops);
- else
- register_ftrace_function(&trace_ops);
-
- ftrace_function_enabled = 1;
+ tr->function_enabled = 0;
+ register_ftrace_function(tr->ops);
+ tr->function_enabled = 1;
}
-static void tracing_stop_function_trace(void)
+static void tracing_stop_function_trace(struct trace_array *tr)
{
- ftrace_function_enabled = 0;
-
- if (func_flags.val & TRACE_FUNC_OPT_STACK)
- unregister_ftrace_function(&trace_stack_ops);
- else
- unregister_ftrace_function(&trace_ops);
+ tr->function_enabled = 0;
+ unregister_ftrace_function(tr->ops);
}
-static int func_set_flag(u32 old_flags, u32 bit, int set)
+static int
+func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
switch (bit) {
case TRACE_FUNC_OPT_STACK:
@@ -183,12 +241,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set)
if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
break;
+ unregister_ftrace_function(tr->ops);
+
if (set) {
- unregister_ftrace_function(&trace_ops);
- register_ftrace_function(&trace_stack_ops);
+ tr->ops = &trace_stack_ops;
+ register_ftrace_function(tr->ops);
} else {
- unregister_ftrace_function(&trace_stack_ops);
- register_ftrace_function(&trace_ops);
+ tr->ops = &trace_ops;
+ register_ftrace_function(tr->ops);
}
break;
@@ -208,6 +268,7 @@ static struct tracer function_trace __tracer_data =
.wait_pipe = poll_wait_pipe,
.flags = &func_flags,
.set_flag = func_set_flag,
+ .allow_instances = true,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_function,
#endif
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 0b99120d395c..deff11200261 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1476,7 +1476,8 @@ void graph_trace_close(struct trace_iterator *iter)
}
}
-static int func_graph_set_flag(u32 old_flags, u32 bit, int set)
+static int
+func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
if (bit == TRACE_GRAPH_PRINT_IRQS)
ftrace_graph_skip_irqs = !set;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2aefbee93a6d..8ff02cbb892f 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -160,7 +160,8 @@ static struct ftrace_ops trace_ops __read_mostly =
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+static int
+irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
int cpu;
@@ -266,7 +267,8 @@ __trace_function(struct trace_array *tr,
#else
#define __trace_function trace_function
-static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+static int
+irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
return -EINVAL;
}
@@ -498,14 +500,14 @@ void trace_hardirqs_off(void)
}
EXPORT_SYMBOL(trace_hardirqs_off);
-void trace_hardirqs_on_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
{
if (!preempt_trace() && irq_trace())
stop_critical_timing(CALLER_ADDR0, caller_addr);
}
EXPORT_SYMBOL(trace_hardirqs_on_caller);
-void trace_hardirqs_off_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(CALLER_ADDR0, caller_addr);
@@ -570,8 +572,10 @@ static void irqsoff_function_set(int set)
unregister_irqsoff_function(is_graph());
}
-static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set)
+static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
{
+ struct tracer *tracer = tr->current_trace;
+
if (mask & TRACE_ITER_FUNCTION)
irqsoff_function_set(set);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index dae9541ada9e..d021d21dd150 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -27,75 +27,54 @@
/**
* Kprobe event core functions
*/
-struct trace_probe {
+struct trace_kprobe {
struct list_head list;
struct kretprobe rp; /* Use rp.kp for kprobe use */
unsigned long nhit;
- unsigned int flags; /* For TP_FLAG_* */
const char *symbol; /* symbol name */
- struct ftrace_event_class class;
- struct ftrace_event_call call;
- struct list_head files;
- ssize_t size; /* trace entry size */
- unsigned int nr_args;
- struct probe_arg args[];
+ struct trace_probe tp;
};
-struct event_file_link {
- struct ftrace_event_file *file;
- struct list_head list;
-};
-
-#define SIZEOF_TRACE_PROBE(n) \
- (offsetof(struct trace_probe, args) + \
+#define SIZEOF_TRACE_KPROBE(n) \
+ (offsetof(struct trace_kprobe, tp.args) + \
(sizeof(struct probe_arg) * (n)))
-static __kprobes bool trace_probe_is_return(struct trace_probe *tp)
-{
- return tp->rp.handler != NULL;
-}
-
-static __kprobes const char *trace_probe_symbol(struct trace_probe *tp)
-{
- return tp->symbol ? tp->symbol : "unknown";
-}
-
-static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_is_return(struct trace_kprobe *tk)
{
- return tp->rp.kp.offset;
+ return tk->rp.handler != NULL;
}
-static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp)
+static __kprobes const char *trace_kprobe_symbol(struct trace_kprobe *tk)
{
- return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+ return tk->symbol ? tk->symbol : "unknown";
}
-static __kprobes bool trace_probe_is_registered(struct trace_probe *tp)
+static __kprobes unsigned long trace_kprobe_offset(struct trace_kprobe *tk)
{
- return !!(tp->flags & TP_FLAG_REGISTERED);
+ return tk->rp.kp.offset;
}
-static __kprobes bool trace_probe_has_gone(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_has_gone(struct trace_kprobe *tk)
{
- return !!(kprobe_gone(&tp->rp.kp));
+ return !!(kprobe_gone(&tk->rp.kp));
}
-static __kprobes bool trace_probe_within_module(struct trace_probe *tp,
- struct module *mod)
+static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk,
+ struct module *mod)
{
int len = strlen(mod->name);
- const char *name = trace_probe_symbol(tp);
+ const char *name = trace_kprobe_symbol(tk);
return strncmp(mod->name, name, len) == 0 && name[len] == ':';
}
-static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp)
+static __kprobes bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
{
- return !!strchr(trace_probe_symbol(tp), ':');
+ return !!strchr(trace_kprobe_symbol(tk), ':');
}
-static int register_probe_event(struct trace_probe *tp);
-static int unregister_probe_event(struct trace_probe *tp);
+static int register_kprobe_event(struct trace_kprobe *tk);
+static int unregister_kprobe_event(struct trace_kprobe *tk);
static DEFINE_MUTEX(probe_lock);
static LIST_HEAD(probe_list);
@@ -104,45 +83,224 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
static int kretprobe_dispatcher(struct kretprobe_instance *ri,
struct pt_regs *regs);
+/* Memory fetching by symbol */
+struct symbol_cache {
+ char *symbol;
+ long offset;
+ unsigned long addr;
+};
+
+unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+ sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+
+ if (sc->addr)
+ sc->addr += sc->offset;
+
+ return sc->addr;
+}
+
+void free_symbol_cache(struct symbol_cache *sc)
+{
+ kfree(sc->symbol);
+ kfree(sc);
+}
+
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+ struct symbol_cache *sc;
+
+ if (!sym || strlen(sym) == 0)
+ return NULL;
+
+ sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+ if (!sc)
+ return NULL;
+
+ sc->symbol = kstrdup(sym, GFP_KERNEL);
+ if (!sc->symbol) {
+ kfree(sc);
+ return NULL;
+ }
+ sc->offset = offset;
+ update_symbol_cache(sc);
+
+ return sc;
+}
+
+/*
+ * Kprobes-specific fetch functions
+ */
+#define DEFINE_FETCH_stack(type) \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
+ (unsigned int)((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
+
+#define DEFINE_FETCH_memory(type) \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+ void *addr, void *dest) \
+{ \
+ type retval; \
+ if (probe_kernel_address(addr, retval)) \
+ *(type *)dest = 0; \
+ else \
+ *(type *)dest = retval; \
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ long ret;
+ int maxlen = get_rloc_len(*(u32 *)dest);
+ u8 *dst = get_rloc_data(dest);
+ u8 *src = addr;
+ mm_segment_t old_fs = get_fs();
+
+ if (!maxlen)
+ return;
+
+ /*
+ * Try to get string again, since the string can be changed while
+ * probing.
+ */
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do
+ ret = __copy_from_user_inatomic(dst++, src++, 1);
+ while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
+
+ dst[-1] = '\0';
+ pagefault_enable();
+ set_fs(old_fs);
+
+ if (ret < 0) { /* Failed to fetch string */
+ ((u8 *)get_rloc_data(dest))[0] = '\0';
+ *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
+ } else {
+ *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
+ get_rloc_offs(*(u32 *)dest));
+ }
+}
+
+/* Return the length of string -- including null terminal byte */
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ mm_segment_t old_fs;
+ int ret, len = 0;
+ u8 c;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do {
+ ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+ len++;
+ } while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+ pagefault_enable();
+ set_fs(old_fs);
+
+ if (ret < 0) /* Failed to check the length */
+ *(u32 *)dest = 0;
+ else
+ *(u32 *)dest = len;
+}
+
+#define DEFINE_FETCH_symbol(type) \
+__kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, \
+ void *data, void *dest) \
+{ \
+ struct symbol_cache *sc = data; \
+ if (sc->addr) \
+ fetch_memory_##type(regs, (void *)sc->addr, dest); \
+ else \
+ *(type *)dest = 0; \
+}
+DEFINE_BASIC_FETCH_FUNCS(symbol)
+DEFINE_FETCH_symbol(string)
+DEFINE_FETCH_symbol(string_size)
+
+/* kprobes don't support file_offset fetch methods */
+#define fetch_file_offset_u8 NULL
+#define fetch_file_offset_u16 NULL
+#define fetch_file_offset_u32 NULL
+#define fetch_file_offset_u64 NULL
+#define fetch_file_offset_string NULL
+#define fetch_file_offset_string_size NULL
+
+/* Fetch type information table */
+const struct fetch_type kprobes_fetch_type_table[] = {
+ /* Special types */
+ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+ sizeof(u32), 1, "__data_loc char[]"),
+ [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+ string_size, sizeof(u32), 0, "u32"),
+ /* Basic types */
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+
+ ASSIGN_FETCH_TYPE_END
+};
+
/*
* Allocate new trace_probe and initialize it (including kprobes).
*/
-static struct trace_probe *alloc_trace_probe(const char *group,
+static struct trace_kprobe *alloc_trace_kprobe(const char *group,
const char *event,
void *addr,
const char *symbol,
unsigned long offs,
int nargs, bool is_return)
{
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int ret = -ENOMEM;
- tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
- if (!tp)
+ tk = kzalloc(SIZEOF_TRACE_KPROBE(nargs), GFP_KERNEL);
+ if (!tk)
return ERR_PTR(ret);
if (symbol) {
- tp->symbol = kstrdup(symbol, GFP_KERNEL);
- if (!tp->symbol)
+ tk->symbol = kstrdup(symbol, GFP_KERNEL);
+ if (!tk->symbol)
goto error;
- tp->rp.kp.symbol_name = tp->symbol;
- tp->rp.kp.offset = offs;
+ tk->rp.kp.symbol_name = tk->symbol;
+ tk->rp.kp.offset = offs;
} else
- tp->rp.kp.addr = addr;
+ tk->rp.kp.addr = addr;
if (is_return)
- tp->rp.handler = kretprobe_dispatcher;
+ tk->rp.handler = kretprobe_dispatcher;
else
- tp->rp.kp.pre_handler = kprobe_dispatcher;
+ tk->rp.kp.pre_handler = kprobe_dispatcher;
if (!event || !is_good_name(event)) {
ret = -EINVAL;
goto error;
}
- tp->call.class = &tp->class;
- tp->call.name = kstrdup(event, GFP_KERNEL);
- if (!tp->call.name)
+ tk->tp.call.class = &tk->tp.class;
+ tk->tp.call.name = kstrdup(event, GFP_KERNEL);
+ if (!tk->tp.call.name)
goto error;
if (!group || !is_good_name(group)) {
@@ -150,42 +308,42 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
- tp->class.system = kstrdup(group, GFP_KERNEL);
- if (!tp->class.system)
+ tk->tp.class.system = kstrdup(group, GFP_KERNEL);
+ if (!tk->tp.class.system)
goto error;
- INIT_LIST_HEAD(&tp->list);
- INIT_LIST_HEAD(&tp->files);
- return tp;
+ INIT_LIST_HEAD(&tk->list);
+ INIT_LIST_HEAD(&tk->tp.files);
+ return tk;
error:
- kfree(tp->call.name);
- kfree(tp->symbol);
- kfree(tp);
+ kfree(tk->tp.call.name);
+ kfree(tk->symbol);
+ kfree(tk);
return ERR_PTR(ret);
}
-static void free_trace_probe(struct trace_probe *tp)
+static void free_trace_kprobe(struct trace_kprobe *tk)
{
int i;
- for (i = 0; i < tp->nr_args; i++)
- traceprobe_free_probe_arg(&tp->args[i]);
+ for (i = 0; i < tk->tp.nr_args; i++)
+ traceprobe_free_probe_arg(&tk->tp.args[i]);
- kfree(tp->call.class->system);
- kfree(tp->call.name);
- kfree(tp->symbol);
- kfree(tp);
+ kfree(tk->tp.call.class->system);
+ kfree(tk->tp.call.name);
+ kfree(tk->symbol);
+ kfree(tk);
}
-static struct trace_probe *find_trace_probe(const char *event,
- const char *group)
+static struct trace_kprobe *find_trace_kprobe(const char *event,
+ const char *group)
{
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
- list_for_each_entry(tp, &probe_list, list)
- if (strcmp(tp->call.name, event) == 0 &&
- strcmp(tp->call.class->system, group) == 0)
- return tp;
+ list_for_each_entry(tk, &probe_list, list)
+ if (strcmp(tk->tp.call.name, event) == 0 &&
+ strcmp(tk->tp.call.class->system, group) == 0)
+ return tk;
return NULL;
}
@@ -194,7 +352,7 @@ static struct trace_probe *find_trace_probe(const char *event,
* if the file is NULL, enable "perf" handler, or enable "trace" handler.
*/
static int
-enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
+enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
{
int ret = 0;
@@ -208,47 +366,35 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
}
link->file = file;
- list_add_tail_rcu(&link->list, &tp->files);
+ list_add_tail_rcu(&link->list, &tk->tp.files);
- tp->flags |= TP_FLAG_TRACE;
+ tk->tp.flags |= TP_FLAG_TRACE;
} else
- tp->flags |= TP_FLAG_PROFILE;
+ tk->tp.flags |= TP_FLAG_PROFILE;
- if (trace_probe_is_registered(tp) && !trace_probe_has_gone(tp)) {
- if (trace_probe_is_return(tp))
- ret = enable_kretprobe(&tp->rp);
+ if (trace_probe_is_registered(&tk->tp) && !trace_kprobe_has_gone(tk)) {
+ if (trace_kprobe_is_return(tk))
+ ret = enable_kretprobe(&tk->rp);
else
- ret = enable_kprobe(&tp->rp.kp);
+ ret = enable_kprobe(&tk->rp.kp);
}
out:
return ret;
}
-static struct event_file_link *
-find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
-{
- struct event_file_link *link;
-
- list_for_each_entry(link, &tp->files, list)
- if (link->file == file)
- return link;
-
- return NULL;
-}
-
/*
* Disable trace_probe
* if the file is NULL, disable "perf" handler, or disable "trace" handler.
*/
static int
-disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
+disable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
{
struct event_file_link *link = NULL;
int wait = 0;
int ret = 0;
if (file) {
- link = find_event_file_link(tp, file);
+ link = find_event_file_link(&tk->tp, file);
if (!link) {
ret = -EINVAL;
goto out;
@@ -256,18 +402,18 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
list_del_rcu(&link->list);
wait = 1;
- if (!list_empty(&tp->files))
+ if (!list_empty(&tk->tp.files))
goto out;
- tp->flags &= ~TP_FLAG_TRACE;
+ tk->tp.flags &= ~TP_FLAG_TRACE;
} else
- tp->flags &= ~TP_FLAG_PROFILE;
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
- if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
- if (trace_probe_is_return(tp))
- disable_kretprobe(&tp->rp);
+ if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) {
+ if (trace_kprobe_is_return(tk))
+ disable_kretprobe(&tk->rp);
else
- disable_kprobe(&tp->rp.kp);
+ disable_kprobe(&tk->rp.kp);
wait = 1;
}
out:
@@ -288,40 +434,40 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
}
/* Internal register function - just handle k*probes and flags */
-static int __register_trace_probe(struct trace_probe *tp)
+static int __register_trace_kprobe(struct trace_kprobe *tk)
{
int i, ret;
- if (trace_probe_is_registered(tp))
+ if (trace_probe_is_registered(&tk->tp))
return -EINVAL;
- for (i = 0; i < tp->nr_args; i++)
- traceprobe_update_arg(&tp->args[i]);
+ for (i = 0; i < tk->tp.nr_args; i++)
+ traceprobe_update_arg(&tk->tp.args[i]);
/* Set/clear disabled flag according to tp->flag */
- if (trace_probe_is_enabled(tp))
- tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
+ if (trace_probe_is_enabled(&tk->tp))
+ tk->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
else
- tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+ tk->rp.kp.flags |= KPROBE_FLAG_DISABLED;
- if (trace_probe_is_return(tp))
- ret = register_kretprobe(&tp->rp);
+ if (trace_kprobe_is_return(tk))
+ ret = register_kretprobe(&tk->rp);
else
- ret = register_kprobe(&tp->rp.kp);
+ ret = register_kprobe(&tk->rp.kp);
if (ret == 0)
- tp->flags |= TP_FLAG_REGISTERED;
+ tk->tp.flags |= TP_FLAG_REGISTERED;
else {
pr_warning("Could not insert probe at %s+%lu: %d\n",
- trace_probe_symbol(tp), trace_probe_offset(tp), ret);
- if (ret == -ENOENT && trace_probe_is_on_module(tp)) {
+ trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
+ if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
pr_warning("This probe might be able to register after"
"target module is loaded. Continue.\n");
ret = 0;
} else if (ret == -EILSEQ) {
pr_warning("Probing address(0x%p) is not an "
"instruction boundary.\n",
- tp->rp.kp.addr);
+ tk->rp.kp.addr);
ret = -EINVAL;
}
}
@@ -330,67 +476,67 @@ static int __register_trace_probe(struct trace_probe *tp)
}
/* Internal unregister function - just handle k*probes and flags */
-static void __unregister_trace_probe(struct trace_probe *tp)
+static void __unregister_trace_kprobe(struct trace_kprobe *tk)
{
- if (trace_probe_is_registered(tp)) {
- if (trace_probe_is_return(tp))
- unregister_kretprobe(&tp->rp);
+ if (trace_probe_is_registered(&tk->tp)) {
+ if (trace_kprobe_is_return(tk))
+ unregister_kretprobe(&tk->rp);
else
- unregister_kprobe(&tp->rp.kp);
- tp->flags &= ~TP_FLAG_REGISTERED;
+ unregister_kprobe(&tk->rp.kp);
+ tk->tp.flags &= ~TP_FLAG_REGISTERED;
/* Cleanup kprobe for reuse */
- if (tp->rp.kp.symbol_name)
- tp->rp.kp.addr = NULL;
+ if (tk->rp.kp.symbol_name)
+ tk->rp.kp.addr = NULL;
}
}
/* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static int unregister_trace_probe(struct trace_probe *tp)
+static int unregister_trace_kprobe(struct trace_kprobe *tk)
{
/* Enabled event can not be unregistered */
- if (trace_probe_is_enabled(tp))
+ if (trace_probe_is_enabled(&tk->tp))
return -EBUSY;
/* Will fail if probe is being used by ftrace or perf */
- if (unregister_probe_event(tp))
+ if (unregister_kprobe_event(tk))
return -EBUSY;
- __unregister_trace_probe(tp);
- list_del(&tp->list);
+ __unregister_trace_kprobe(tk);
+ list_del(&tk->list);
return 0;
}
/* Register a trace_probe and probe_event */
-static int register_trace_probe(struct trace_probe *tp)
+static int register_trace_kprobe(struct trace_kprobe *tk)
{
- struct trace_probe *old_tp;
+ struct trace_kprobe *old_tk;
int ret;
mutex_lock(&probe_lock);
/* Delete old (same name) event if exist */
- old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
- if (old_tp) {
- ret = unregister_trace_probe(old_tp);
+ old_tk = find_trace_kprobe(tk->tp.call.name, tk->tp.call.class->system);
+ if (old_tk) {
+ ret = unregister_trace_kprobe(old_tk);
if (ret < 0)
goto end;
- free_trace_probe(old_tp);
+ free_trace_kprobe(old_tk);
}
/* Register new event */
- ret = register_probe_event(tp);
+ ret = register_kprobe_event(tk);
if (ret) {
pr_warning("Failed to register probe event(%d)\n", ret);
goto end;
}
/* Register k*probe */
- ret = __register_trace_probe(tp);
+ ret = __register_trace_kprobe(tk);
if (ret < 0)
- unregister_probe_event(tp);
+ unregister_kprobe_event(tk);
else
- list_add_tail(&tp->list, &probe_list);
+ list_add_tail(&tk->list, &probe_list);
end:
mutex_unlock(&probe_lock);
@@ -398,11 +544,11 @@ end:
}
/* Module notifier call back, checking event on the module */
-static int trace_probe_module_callback(struct notifier_block *nb,
+static int trace_kprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
{
struct module *mod = data;
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int ret;
if (val != MODULE_STATE_COMING)
@@ -410,15 +556,15 @@ static int trace_probe_module_callback(struct notifier_block *nb,
/* Update probes on coming module */
mutex_lock(&probe_lock);
- list_for_each_entry(tp, &probe_list, list) {
- if (trace_probe_within_module(tp, mod)) {
+ list_for_each_entry(tk, &probe_list, list) {
+ if (trace_kprobe_within_module(tk, mod)) {
/* Don't need to check busy - this should have gone. */
- __unregister_trace_probe(tp);
- ret = __register_trace_probe(tp);
+ __unregister_trace_kprobe(tk);
+ ret = __register_trace_kprobe(tk);
if (ret)
pr_warning("Failed to re-register probe %s on"
"%s: %d\n",
- tp->call.name, mod->name, ret);
+ tk->tp.call.name, mod->name, ret);
}
}
mutex_unlock(&probe_lock);
@@ -426,12 +572,12 @@ static int trace_probe_module_callback(struct notifier_block *nb,
return NOTIFY_DONE;
}
-static struct notifier_block trace_probe_module_nb = {
- .notifier_call = trace_probe_module_callback,
+static struct notifier_block trace_kprobe_module_nb = {
+ .notifier_call = trace_kprobe_module_callback,
.priority = 1 /* Invoked after kprobe module callback */
};
-static int create_trace_probe(int argc, char **argv)
+static int create_trace_kprobe(int argc, char **argv)
{
/*
* Argument syntax:
@@ -451,7 +597,7 @@ static int create_trace_probe(int argc, char **argv)
* Type of args:
* FETCHARG:TYPE : use TYPE instead of unsigned long.
*/
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int i, ret = 0;
bool is_return = false, is_delete = false;
char *symbol = NULL, *event = NULL, *group = NULL;
@@ -498,16 +644,16 @@ static int create_trace_probe(int argc, char **argv)
return -EINVAL;
}
mutex_lock(&probe_lock);
- tp = find_trace_probe(event, group);
- if (!tp) {
+ tk = find_trace_kprobe(event, group);
+ if (!tk) {
mutex_unlock(&probe_lock);
pr_info("Event %s/%s doesn't exist.\n", group, event);
return -ENOENT;
}
/* delete an event */
- ret = unregister_trace_probe(tp);
+ ret = unregister_trace_kprobe(tk);
if (ret == 0)
- free_trace_probe(tp);
+ free_trace_kprobe(tk);
mutex_unlock(&probe_lock);
return ret;
}
@@ -554,47 +700,49 @@ static int create_trace_probe(int argc, char **argv)
is_return ? 'r' : 'p', addr);
event = buf;
}
- tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, argc,
is_return);
- if (IS_ERR(tp)) {
+ if (IS_ERR(tk)) {
pr_info("Failed to allocate trace_probe.(%d)\n",
- (int)PTR_ERR(tp));
- return PTR_ERR(tp);
+ (int)PTR_ERR(tk));
+ return PTR_ERR(tk);
}
/* parse arguments */
ret = 0;
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ struct probe_arg *parg = &tk->tp.args[i];
+
/* Increment count for freeing args in error case */
- tp->nr_args++;
+ tk->tp.nr_args++;
/* Parse argument name */
arg = strchr(argv[i], '=');
if (arg) {
*arg++ = '\0';
- tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ parg->name = kstrdup(argv[i], GFP_KERNEL);
} else {
arg = argv[i];
/* If argument name is omitted, set "argN" */
snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
- tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+ parg->name = kstrdup(buf, GFP_KERNEL);
}
- if (!tp->args[i].name) {
+ if (!parg->name) {
pr_info("Failed to allocate argument[%d] name.\n", i);
ret = -ENOMEM;
goto error;
}
- if (!is_good_name(tp->args[i].name)) {
+ if (!is_good_name(parg->name)) {
pr_info("Invalid argument[%d] name: %s\n",
- i, tp->args[i].name);
+ i, parg->name);
ret = -EINVAL;
goto error;
}
- if (traceprobe_conflict_field_name(tp->args[i].name,
- tp->args, i)) {
+ if (traceprobe_conflict_field_name(parg->name,
+ tk->tp.args, i)) {
pr_info("Argument[%d] name '%s' conflicts with "
"another field.\n", i, argv[i]);
ret = -EINVAL;
@@ -602,7 +750,7 @@ static int create_trace_probe(int argc, char **argv)
}
/* Parse fetch argument */
- ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i],
+ ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg,
is_return, true);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
@@ -610,35 +758,35 @@ static int create_trace_probe(int argc, char **argv)
}
}
- ret = register_trace_probe(tp);
+ ret = register_trace_kprobe(tk);
if (ret)
goto error;
return 0;
error:
- free_trace_probe(tp);
+ free_trace_kprobe(tk);
return ret;
}
-static int release_all_trace_probes(void)
+static int release_all_trace_kprobes(void)
{
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
int ret = 0;
mutex_lock(&probe_lock);
/* Ensure no probe is in use. */
- list_for_each_entry(tp, &probe_list, list)
- if (trace_probe_is_enabled(tp)) {
+ list_for_each_entry(tk, &probe_list, list)
+ if (trace_probe_is_enabled(&tk->tp)) {
ret = -EBUSY;
goto end;
}
/* TODO: Use batch unregistration */
while (!list_empty(&probe_list)) {
- tp = list_entry(probe_list.next, struct trace_probe, list);
- ret = unregister_trace_probe(tp);
+ tk = list_entry(probe_list.next, struct trace_kprobe, list);
+ ret = unregister_trace_kprobe(tk);
if (ret)
goto end;
- free_trace_probe(tp);
+ free_trace_kprobe(tk);
}
end:
@@ -666,22 +814,22 @@ static void probes_seq_stop(struct seq_file *m, void *v)
static int probes_seq_show(struct seq_file *m, void *v)
{
- struct trace_probe *tp = v;
+ struct trace_kprobe *tk = v;
int i;
- seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p');
- seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
+ seq_printf(m, "%c", trace_kprobe_is_return(tk) ? 'r' : 'p');
+ seq_printf(m, ":%s/%s", tk->tp.call.class->system, tk->tp.call.name);
- if (!tp->symbol)
- seq_printf(m, " 0x%p", tp->rp.kp.addr);
- else if (tp->rp.kp.offset)
- seq_printf(m, " %s+%u", trace_probe_symbol(tp),
- tp->rp.kp.offset);
+ if (!tk->symbol)
+ seq_printf(m, " 0x%p", tk->rp.kp.addr);
+ else if (tk->rp.kp.offset)
+ seq_printf(m, " %s+%u", trace_kprobe_symbol(tk),
+ tk->rp.kp.offset);
else
- seq_printf(m, " %s", trace_probe_symbol(tp));
+ seq_printf(m, " %s", trace_kprobe_symbol(tk));
- for (i = 0; i < tp->nr_args; i++)
- seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
+ for (i = 0; i < tk->tp.nr_args; i++)
+ seq_printf(m, " %s=%s", tk->tp.args[i].name, tk->tp.args[i].comm);
seq_printf(m, "\n");
return 0;
@@ -699,7 +847,7 @@ static int probes_open(struct inode *inode, struct file *file)
int ret;
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
- ret = release_all_trace_probes();
+ ret = release_all_trace_kprobes();
if (ret < 0)
return ret;
}
@@ -711,7 +859,7 @@ static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
return traceprobe_probes_write(file, buffer, count, ppos,
- create_trace_probe);
+ create_trace_kprobe);
}
static const struct file_operations kprobe_events_ops = {
@@ -726,10 +874,10 @@ static const struct file_operations kprobe_events_ops = {
/* Probes profiling interfaces */
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
- struct trace_probe *tp = v;
+ struct trace_kprobe *tk = v;
- seq_printf(m, " %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
- tp->rp.kp.nmissed);
+ seq_printf(m, " %-44s %15lu %15lu\n", tk->tp.call.name, tk->nhit,
+ tk->rp.kp.nmissed);
return 0;
}
@@ -754,57 +902,9 @@ static const struct file_operations kprobe_profile_ops = {
.release = seq_release,
};
-/* Sum up total data length for dynamic arraies (strings) */
-static __kprobes int __get_data_size(struct trace_probe *tp,
- struct pt_regs *regs)
-{
- int i, ret = 0;
- u32 len;
-
- for (i = 0; i < tp->nr_args; i++)
- if (unlikely(tp->args[i].fetch_size.fn)) {
- call_fetch(&tp->args[i].fetch_size, regs, &len);
- ret += len;
- }
-
- return ret;
-}
-
-/* Store the value of each argument */
-static __kprobes void store_trace_args(int ent_size, struct trace_probe *tp,
- struct pt_regs *regs,
- u8 *data, int maxlen)
-{
- int i;
- u32 end = tp->size;
- u32 *dl; /* Data (relative) location */
-
- for (i = 0; i < tp->nr_args; i++) {
- if (unlikely(tp->args[i].fetch_size.fn)) {
- /*
- * First, we set the relative location and
- * maximum data length to *dl
- */
- dl = (u32 *)(data + tp->args[i].offset);
- *dl = make_data_rloc(maxlen, end - tp->args[i].offset);
- /* Then try to fetch string or dynamic array data */
- call_fetch(&tp->args[i].fetch, regs, dl);
- /* Reduce maximum length */
- end += get_rloc_len(*dl);
- maxlen -= get_rloc_len(*dl);
- /* Trick here, convert data_rloc to data_loc */
- *dl = convert_rloc_to_loc(*dl,
- ent_size + tp->args[i].offset);
- } else
- /* Just fetching data normally */
- call_fetch(&tp->args[i].fetch, regs,
- data + tp->args[i].offset);
- }
-}
-
/* Kprobe handler */
static __kprobes void
-__kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
+__kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
struct ftrace_event_file *ftrace_file)
{
struct kprobe_trace_entry_head *entry;
@@ -812,18 +912,18 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
struct ring_buffer *buffer;
int size, dsize, pc;
unsigned long irq_flags;
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
WARN_ON(call != ftrace_file->event_call);
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
local_save_flags(irq_flags);
pc = preempt_count();
- dsize = __get_data_size(tp, regs);
- size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ size = sizeof(*entry) + tk->tp.size + dsize;
event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
call->event.type,
@@ -832,26 +932,25 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
return;
entry = ring_buffer_event_data(event);
- entry->ip = (unsigned long)tp->rp.kp.addr;
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ entry->ip = (unsigned long)tk->rp.kp.addr;
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- if (!filter_check_discard(ftrace_file, entry, buffer, event))
- trace_buffer_unlock_commit_regs(buffer, event,
- irq_flags, pc, regs);
+ event_trigger_unlock_commit_regs(ftrace_file, buffer, event,
+ entry, irq_flags, pc, regs);
}
static __kprobes void
-kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs)
+kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
struct event_file_link *link;
- list_for_each_entry_rcu(link, &tp->files, list)
- __kprobe_trace_func(tp, regs, link->file);
+ list_for_each_entry_rcu(link, &tk->tp.files, list)
+ __kprobe_trace_func(tk, regs, link->file);
}
/* Kretprobe handler */
static __kprobes void
-__kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+__kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs,
struct ftrace_event_file *ftrace_file)
{
@@ -860,18 +959,18 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
struct ring_buffer *buffer;
int size, pc, dsize;
unsigned long irq_flags;
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
WARN_ON(call != ftrace_file->event_call);
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
local_save_flags(irq_flags);
pc = preempt_count();
- dsize = __get_data_size(tp, regs);
- size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ size = sizeof(*entry) + tk->tp.size + dsize;
event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
call->event.type,
@@ -880,23 +979,22 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
return;
entry = ring_buffer_event_data(event);
- entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- if (!filter_check_discard(ftrace_file, entry, buffer, event))
- trace_buffer_unlock_commit_regs(buffer, event,
- irq_flags, pc, regs);
+ event_trigger_unlock_commit_regs(ftrace_file, buffer, event,
+ entry, irq_flags, pc, regs);
}
static __kprobes void
-kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct event_file_link *link;
- list_for_each_entry_rcu(link, &tp->files, list)
- __kretprobe_trace_func(tp, ri, regs, link->file);
+ list_for_each_entry_rcu(link, &tk->tp.files, list)
+ __kretprobe_trace_func(tk, ri, regs, link->file);
}
/* Event entry printers */
@@ -983,16 +1081,18 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
{
int ret, i;
struct kprobe_trace_entry_head field;
- struct trace_probe *tp = (struct trace_probe *)event_call->data;
+ struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
/* Set argument names as fields */
- for (i = 0; i < tp->nr_args; i++) {
- ret = trace_define_field(event_call, tp->args[i].type->fmttype,
- tp->args[i].name,
- sizeof(field) + tp->args[i].offset,
- tp->args[i].type->size,
- tp->args[i].type->is_signed,
+ for (i = 0; i < tk->tp.nr_args; i++) {
+ struct probe_arg *parg = &tk->tp.args[i];
+
+ ret = trace_define_field(event_call, parg->type->fmttype,
+ parg->name,
+ sizeof(field) + parg->offset,
+ parg->type->size,
+ parg->type->is_signed,
FILTER_OTHER);
if (ret)
return ret;
@@ -1004,17 +1104,19 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
{
int ret, i;
struct kretprobe_trace_entry_head field;
- struct trace_probe *tp = (struct trace_probe *)event_call->data;
+ struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
/* Set argument names as fields */
- for (i = 0; i < tp->nr_args; i++) {
- ret = trace_define_field(event_call, tp->args[i].type->fmttype,
- tp->args[i].name,
- sizeof(field) + tp->args[i].offset,
- tp->args[i].type->size,
- tp->args[i].type->is_signed,
+ for (i = 0; i < tk->tp.nr_args; i++) {
+ struct probe_arg *parg = &tk->tp.args[i];
+
+ ret = trace_define_field(event_call, parg->type->fmttype,
+ parg->name,
+ sizeof(field) + parg->offset,
+ parg->type->size,
+ parg->type->is_signed,
FILTER_OTHER);
if (ret)
return ret;
@@ -1022,74 +1124,13 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
return 0;
}
-static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
-{
- int i;
- int pos = 0;
-
- const char *fmt, *arg;
-
- if (!trace_probe_is_return(tp)) {
- fmt = "(%lx)";
- arg = "REC->" FIELD_STRING_IP;
- } else {
- fmt = "(%lx <- %lx)";
- arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
- }
-
- /* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
-
- for (i = 0; i < tp->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
- tp->args[i].name, tp->args[i].type->fmt);
- }
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-
- for (i = 0; i < tp->nr_args; i++) {
- if (strcmp(tp->args[i].type->name, "string") == 0)
- pos += snprintf(buf + pos, LEN_OR_ZERO,
- ", __get_str(%s)",
- tp->args[i].name);
- else
- pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
- tp->args[i].name);
- }
-
-#undef LEN_OR_ZERO
-
- /* return the length of print_fmt */
- return pos;
-}
-
-static int set_print_fmt(struct trace_probe *tp)
-{
- int len;
- char *print_fmt;
-
- /* First: called with 0 length to calculate the needed length */
- len = __set_print_fmt(tp, NULL, 0);
- print_fmt = kmalloc(len + 1, GFP_KERNEL);
- if (!print_fmt)
- return -ENOMEM;
-
- /* Second: actually write the @print_fmt */
- __set_print_fmt(tp, print_fmt, len + 1);
- tp->call.print_fmt = print_fmt;
-
- return 0;
-}
-
#ifdef CONFIG_PERF_EVENTS
/* Kprobe profile handler */
static __kprobes void
-kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
+kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
struct kprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
@@ -1099,8 +1140,8 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
if (hlist_empty(head))
return;
- dsize = __get_data_size(tp, regs);
- __size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ __size = sizeof(*entry) + tk->tp.size + dsize;
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
@@ -1108,18 +1149,18 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs)
if (!entry)
return;
- entry->ip = (unsigned long)tp->rp.kp.addr;
+ entry->ip = (unsigned long)tk->rp.kp.addr;
memset(&entry[1], 0, dsize);
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
}
/* Kretprobe profile handler */
static __kprobes void
-kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
+kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
struct kretprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
@@ -1129,8 +1170,8 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
if (hlist_empty(head))
return;
- dsize = __get_data_size(tp, regs);
- __size = sizeof(*entry) + tp->size + dsize;
+ dsize = __get_data_size(&tk->tp, regs);
+ __size = sizeof(*entry) + tk->tp.size + dsize;
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
@@ -1138,9 +1179,9 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri,
if (!entry)
return;
- entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
- store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+ store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
}
#endif /* CONFIG_PERF_EVENTS */
@@ -1155,20 +1196,20 @@ static __kprobes
int kprobe_register(struct ftrace_event_call *event,
enum trace_reg type, void *data)
{
- struct trace_probe *tp = (struct trace_probe *)event->data;
+ struct trace_kprobe *tk = (struct trace_kprobe *)event->data;
struct ftrace_event_file *file = data;
switch (type) {
case TRACE_REG_REGISTER:
- return enable_trace_probe(tp, file);
+ return enable_trace_kprobe(tk, file);
case TRACE_REG_UNREGISTER:
- return disable_trace_probe(tp, file);
+ return disable_trace_kprobe(tk, file);
#ifdef CONFIG_PERF_EVENTS
case TRACE_REG_PERF_REGISTER:
- return enable_trace_probe(tp, NULL);
+ return enable_trace_kprobe(tk, NULL);
case TRACE_REG_PERF_UNREGISTER:
- return disable_trace_probe(tp, NULL);
+ return disable_trace_kprobe(tk, NULL);
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
@@ -1182,15 +1223,15 @@ int kprobe_register(struct ftrace_event_call *event,
static __kprobes
int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
{
- struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
- tp->nhit++;
+ tk->nhit++;
- if (tp->flags & TP_FLAG_TRACE)
- kprobe_trace_func(tp, regs);
+ if (tk->tp.flags & TP_FLAG_TRACE)
+ kprobe_trace_func(tk, regs);
#ifdef CONFIG_PERF_EVENTS
- if (tp->flags & TP_FLAG_PROFILE)
- kprobe_perf_func(tp, regs);
+ if (tk->tp.flags & TP_FLAG_PROFILE)
+ kprobe_perf_func(tk, regs);
#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1198,15 +1239,15 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
static __kprobes
int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
{
- struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
- tp->nhit++;
+ tk->nhit++;
- if (tp->flags & TP_FLAG_TRACE)
- kretprobe_trace_func(tp, ri, regs);
+ if (tk->tp.flags & TP_FLAG_TRACE)
+ kretprobe_trace_func(tk, ri, regs);
#ifdef CONFIG_PERF_EVENTS
- if (tp->flags & TP_FLAG_PROFILE)
- kretprobe_perf_func(tp, ri, regs);
+ if (tk->tp.flags & TP_FLAG_PROFILE)
+ kretprobe_perf_func(tk, ri, regs);
#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1219,21 +1260,21 @@ static struct trace_event_functions kprobe_funcs = {
.trace = print_kprobe_event
};
-static int register_probe_event(struct trace_probe *tp)
+static int register_kprobe_event(struct trace_kprobe *tk)
{
- struct ftrace_event_call *call = &tp->call;
+ struct ftrace_event_call *call = &tk->tp.call;
int ret;
/* Initialize ftrace_event_call */
INIT_LIST_HEAD(&call->class->fields);
- if (trace_probe_is_return(tp)) {
+ if (trace_kprobe_is_return(tk)) {
call->event.funcs = &kretprobe_funcs;
call->class->define_fields = kretprobe_event_define_fields;
} else {
call->event.funcs = &kprobe_funcs;
call->class->define_fields = kprobe_event_define_fields;
}
- if (set_print_fmt(tp) < 0)
+ if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
return -ENOMEM;
ret = register_ftrace_event(&call->event);
if (!ret) {
@@ -1242,7 +1283,7 @@ static int register_probe_event(struct trace_probe *tp)
}
call->flags = 0;
call->class->reg = kprobe_register;
- call->data = tp;
+ call->data = tk;
ret = trace_add_event_call(call);
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
@@ -1252,14 +1293,14 @@ static int register_probe_event(struct trace_probe *tp)
return ret;
}
-static int unregister_probe_event(struct trace_probe *tp)
+static int unregister_kprobe_event(struct trace_kprobe *tk)
{
int ret;
/* tp->event is unregistered in trace_remove_event_call() */
- ret = trace_remove_event_call(&tp->call);
+ ret = trace_remove_event_call(&tk->tp.call);
if (!ret)
- kfree(tp->call.print_fmt);
+ kfree(tk->tp.call.print_fmt);
return ret;
}
@@ -1269,7 +1310,7 @@ static __init int init_kprobe_trace(void)
struct dentry *d_tracer;
struct dentry *entry;
- if (register_module_notifier(&trace_probe_module_nb))
+ if (register_module_notifier(&trace_kprobe_module_nb))
return -EINVAL;
d_tracer = tracing_init_dentry();
@@ -1309,26 +1350,26 @@ static __used int kprobe_trace_selftest_target(int a1, int a2, int a3,
}
static struct ftrace_event_file *
-find_trace_probe_file(struct trace_probe *tp, struct trace_array *tr)
+find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
{
struct ftrace_event_file *file;
list_for_each_entry(file, &tr->events, list)
- if (file->event_call == &tp->call)
+ if (file->event_call == &tk->tp.call)
return file;
return NULL;
}
/*
- * Nobody but us can call enable_trace_probe/disable_trace_probe at this
+ * Nobody but us can call enable_trace_kprobe/disable_trace_kprobe at this
* stage, we can do this lockless.
*/
static __init int kprobe_trace_self_tests_init(void)
{
int ret, warn = 0;
int (*target)(int, int, int, int, int, int);
- struct trace_probe *tp;
+ struct trace_kprobe *tk;
struct ftrace_event_file *file;
target = kprobe_trace_selftest_target;
@@ -1337,44 +1378,44 @@ static __init int kprobe_trace_self_tests_init(void)
ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
"$stack $stack0 +0($stack)",
- create_trace_probe);
+ create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on probing function entry.\n");
warn++;
} else {
/* Enable trace point */
- tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting new probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- enable_trace_probe(tp, file);
+ enable_trace_kprobe(tk, file);
}
}
ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
- "$retval", create_trace_probe);
+ "$retval", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on probing function return.\n");
warn++;
} else {
/* Enable trace point */
- tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting 2nd new probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- enable_trace_probe(tp, file);
+ enable_trace_kprobe(tk, file);
}
}
@@ -1384,46 +1425,46 @@ static __init int kprobe_trace_self_tests_init(void)
ret = target(1, 2, 3, 4, 5, 6);
/* Disable trace points before removing it */
- tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting test probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- disable_trace_probe(tp, file);
+ disable_trace_kprobe(tk, file);
}
- tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
- if (WARN_ON_ONCE(tp == NULL)) {
+ tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tk == NULL)) {
pr_warn("error on getting 2nd test probe.\n");
warn++;
} else {
- file = find_trace_probe_file(tp, top_trace_array());
+ file = find_trace_probe_file(tk, top_trace_array());
if (WARN_ON_ONCE(file == NULL)) {
pr_warn("error on getting probe file.\n");
warn++;
} else
- disable_trace_probe(tp, file);
+ disable_trace_kprobe(tk, file);
}
- ret = traceprobe_command("-:testprobe", create_trace_probe);
+ ret = traceprobe_command("-:testprobe", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on deleting a probe.\n");
warn++;
}
- ret = traceprobe_command("-:testprobe2", create_trace_probe);
+ ret = traceprobe_command("-:testprobe2", create_trace_kprobe);
if (WARN_ON_ONCE(ret)) {
pr_warn("error on deleting a probe.\n");
warn++;
}
end:
- release_all_trace_probes();
+ release_all_trace_kprobes();
if (warn)
pr_cont("NG: Some tests are failed. Please check them.\n");
else
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 394f94417e2f..69a5cc94c01a 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -62,7 +62,7 @@ static void nop_trace_reset(struct trace_array *tr)
* If you don't implement it, then the flag setting will be
* automatically accepted.
*/
-static int nop_set_flag(u32 old_flags, u32 bit, int set)
+static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
/*
* Note that you don't need to update nop_flags.val yourself.
@@ -96,6 +96,7 @@ struct tracer nop_trace __read_mostly =
.selftest = trace_selftest_startup_nop,
#endif
.flags = &nop_flags,
- .set_flag = nop_set_flag
+ .set_flag = nop_set_flag,
+ .allow_instances = true,
};
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ed32284fbe32..ca0e79e2abaa 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -439,6 +439,37 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
}
EXPORT_SYMBOL(ftrace_raw_output_prep);
+static int ftrace_output_raw(struct trace_iterator *iter, char *name,
+ char *fmt, va_list ap)
+{
+ struct trace_seq *s = &iter->seq;
+ int ret;
+
+ ret = trace_seq_printf(s, "%s: ", name);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_vprintf(s, fmt, ap);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
+{
+ va_list ap;
+ int ret;
+
+ va_start(ap, fmt);
+ ret = ftrace_output_raw(iter, name, fmt, ap);
+ va_end(ap);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ftrace_output_call);
+
#ifdef CONFIG_KRETPROBES
static inline const char *kretprobed(const char *name)
{
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 412e959709b4..8364a421b4df 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -35,46 +35,27 @@ const char *reserved_field_names[] = {
FIELD_STRING_FUNC,
};
-/* Printing function type */
-#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
-#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
-
/* Printing in basic type function template */
-#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \
-static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt) \
+__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
const char *name, \
- void *data, void *ent)\
+ void *data, void *ent) \
{ \
- return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+ return trace_seq_printf(s, " %s=" fmt, name, *(type *)data); \
} \
-static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
-
-DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
-
-static inline void *get_rloc_data(u32 *dl)
-{
- return (u8 *)dl + get_rloc_offs(*dl);
-}
+const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
-/* For data_loc conversion */
-static inline void *get_loc_data(u32 *dl, void *ent)
-{
- return (u8 *)ent + get_rloc_offs(*dl);
-}
-
-/* For defining macros, define string/string_size types */
-typedef u32 string;
-typedef u32 string_size;
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "0x%Lx")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld")
/* Print type function for string type */
-static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
+__kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
const char *name,
void *data, void *ent)
{
@@ -87,18 +68,7 @@ static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
(const char *)get_loc_data(data, ent));
}
-static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
-
-#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
-/*
- * Define macro for basic types - we don't need to define s* types, because
- * we have to care only about bitwidth at recording time.
- */
-#define DEFINE_BASIC_FETCH_FUNCS(method) \
-DEFINE_FETCH_##method(u8) \
-DEFINE_FETCH_##method(u16) \
-DEFINE_FETCH_##method(u32) \
-DEFINE_FETCH_##method(u64)
+const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
#define CHECK_FETCH_FUNCS(method, fn) \
(((FETCH_FUNC_NAME(method, u8) == fn) || \
@@ -111,7 +81,7 @@ DEFINE_FETCH_##method(u64)
/* Data fetch function templates */
#define DEFINE_FETCH_reg(type) \
-static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
+__kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
void *offset, void *dest) \
{ \
*(type *)dest = (type)regs_get_register(regs, \
@@ -122,20 +92,8 @@ DEFINE_BASIC_FETCH_FUNCS(reg)
#define fetch_reg_string NULL
#define fetch_reg_string_size NULL
-#define DEFINE_FETCH_stack(type) \
-static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
- void *offset, void *dest) \
-{ \
- *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
- (unsigned int)((unsigned long)offset)); \
-}
-DEFINE_BASIC_FETCH_FUNCS(stack)
-/* No string on the stack entry */
-#define fetch_stack_string NULL
-#define fetch_stack_string_size NULL
-
#define DEFINE_FETCH_retval(type) \
-static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \
void *dummy, void *dest) \
{ \
*(type *)dest = (type)regs_return_value(regs); \
@@ -145,150 +103,16 @@ DEFINE_BASIC_FETCH_FUNCS(retval)
#define fetch_retval_string NULL
#define fetch_retval_string_size NULL
-#define DEFINE_FETCH_memory(type) \
-static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
- void *addr, void *dest) \
-{ \
- type retval; \
- if (probe_kernel_address(addr, retval)) \
- *(type *)dest = 0; \
- else \
- *(type *)dest = retval; \
-}
-DEFINE_BASIC_FETCH_FUNCS(memory)
-/*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
- * length and relative data location.
- */
-static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- long ret;
- int maxlen = get_rloc_len(*(u32 *)dest);
- u8 *dst = get_rloc_data(dest);
- u8 *src = addr;
- mm_segment_t old_fs = get_fs();
-
- if (!maxlen)
- return;
-
- /*
- * Try to get string again, since the string can be changed while
- * probing.
- */
- set_fs(KERNEL_DS);
- pagefault_disable();
-
- do
- ret = __copy_from_user_inatomic(dst++, src++, 1);
- while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
-
- dst[-1] = '\0';
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) { /* Failed to fetch string */
- ((u8 *)get_rloc_data(dest))[0] = '\0';
- *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
- } else {
- *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
- get_rloc_offs(*(u32 *)dest));
- }
-}
-
-/* Return the length of string -- including null terminal byte */
-static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- mm_segment_t old_fs;
- int ret, len = 0;
- u8 c;
-
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- pagefault_disable();
-
- do {
- ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
- len++;
- } while (c && ret == 0 && len < MAX_STRING_SIZE);
-
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) /* Failed to check the length */
- *(u32 *)dest = 0;
- else
- *(u32 *)dest = len;
-}
-
-/* Memory fetching by symbol */
-struct symbol_cache {
- char *symbol;
- long offset;
- unsigned long addr;
-};
-
-static unsigned long update_symbol_cache(struct symbol_cache *sc)
-{
- sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
-
- if (sc->addr)
- sc->addr += sc->offset;
-
- return sc->addr;
-}
-
-static void free_symbol_cache(struct symbol_cache *sc)
-{
- kfree(sc->symbol);
- kfree(sc);
-}
-
-static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
-{
- struct symbol_cache *sc;
-
- if (!sym || strlen(sym) == 0)
- return NULL;
-
- sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
- if (!sc)
- return NULL;
-
- sc->symbol = kstrdup(sym, GFP_KERNEL);
- if (!sc->symbol) {
- kfree(sc);
- return NULL;
- }
- sc->offset = offset;
- update_symbol_cache(sc);
-
- return sc;
-}
-
-#define DEFINE_FETCH_symbol(type) \
-static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
- void *data, void *dest) \
-{ \
- struct symbol_cache *sc = data; \
- if (sc->addr) \
- fetch_memory_##type(regs, (void *)sc->addr, dest); \
- else \
- *(type *)dest = 0; \
-}
-DEFINE_BASIC_FETCH_FUNCS(symbol)
-DEFINE_FETCH_symbol(string)
-DEFINE_FETCH_symbol(string_size)
-
/* Dereference memory access function */
struct deref_fetch_param {
struct fetch_param orig;
long offset;
+ fetch_func_t fetch;
+ fetch_func_t fetch_size;
};
#define DEFINE_FETCH_deref(type) \
-static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \
void *data, void *dest) \
{ \
struct deref_fetch_param *dprm = data; \
@@ -296,13 +120,26 @@ static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
call_fetch(&dprm->orig, regs, &addr); \
if (addr) { \
addr += dprm->offset; \
- fetch_memory_##type(regs, (void *)addr, dest); \
+ dprm->fetch(regs, (void *)addr, dest); \
} else \
*(type *)dest = 0; \
}
DEFINE_BASIC_FETCH_FUNCS(deref)
DEFINE_FETCH_deref(string)
-DEFINE_FETCH_deref(string_size)
+
+__kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
+ void *data, void *dest)
+{
+ struct deref_fetch_param *dprm = data;
+ unsigned long addr;
+
+ call_fetch(&dprm->orig, regs, &addr);
+ if (addr && dprm->fetch_size) {
+ addr += dprm->offset;
+ dprm->fetch_size(regs, (void *)addr, dest);
+ } else
+ *(string_size *)dest = 0;
+}
static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
{
@@ -329,7 +166,7 @@ struct bitfield_fetch_param {
};
#define DEFINE_FETCH_bitfield(type) \
-static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+__kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \
void *data, void *dest) \
{ \
struct bitfield_fetch_param *bprm = data; \
@@ -374,58 +211,8 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
kfree(data);
}
-/* Default (unsigned long) fetch type */
-#define __DEFAULT_FETCH_TYPE(t) u##t
-#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
-#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
-#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
-
-#define ASSIGN_FETCH_FUNC(method, type) \
- [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
-
-#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
- {.name = _name, \
- .size = _size, \
- .is_signed = sign, \
- .print = PRINT_TYPE_FUNC_NAME(ptype), \
- .fmt = PRINT_TYPE_FMT_NAME(ptype), \
- .fmttype = _fmttype, \
- .fetch = { \
-ASSIGN_FETCH_FUNC(reg, ftype), \
-ASSIGN_FETCH_FUNC(stack, ftype), \
-ASSIGN_FETCH_FUNC(retval, ftype), \
-ASSIGN_FETCH_FUNC(memory, ftype), \
-ASSIGN_FETCH_FUNC(symbol, ftype), \
-ASSIGN_FETCH_FUNC(deref, ftype), \
-ASSIGN_FETCH_FUNC(bitfield, ftype), \
- } \
- }
-
-#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
- __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
-
-#define FETCH_TYPE_STRING 0
-#define FETCH_TYPE_STRSIZE 1
-
-/* Fetch type information table */
-static const struct fetch_type fetch_type_table[] = {
- /* Special types */
- [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
- sizeof(u32), 1, "__data_loc char[]"),
- [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
- string_size, sizeof(u32), 0, "u32"),
- /* Basic types */
- ASSIGN_FETCH_TYPE(u8, u8, 0),
- ASSIGN_FETCH_TYPE(u16, u16, 0),
- ASSIGN_FETCH_TYPE(u32, u32, 0),
- ASSIGN_FETCH_TYPE(u64, u64, 0),
- ASSIGN_FETCH_TYPE(s8, u8, 1),
- ASSIGN_FETCH_TYPE(s16, u16, 1),
- ASSIGN_FETCH_TYPE(s32, u32, 1),
- ASSIGN_FETCH_TYPE(s64, u64, 1),
-};
-
-static const struct fetch_type *find_fetch_type(const char *type)
+static const struct fetch_type *find_fetch_type(const char *type,
+ const struct fetch_type *ftbl)
{
int i;
@@ -446,44 +233,52 @@ static const struct fetch_type *find_fetch_type(const char *type)
switch (bs) {
case 8:
- return find_fetch_type("u8");
+ return find_fetch_type("u8", ftbl);
case 16:
- return find_fetch_type("u16");
+ return find_fetch_type("u16", ftbl);
case 32:
- return find_fetch_type("u32");
+ return find_fetch_type("u32", ftbl);
case 64:
- return find_fetch_type("u64");
+ return find_fetch_type("u64", ftbl);
default:
goto fail;
}
}
- for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
- if (strcmp(type, fetch_type_table[i].name) == 0)
- return &fetch_type_table[i];
+ for (i = 0; ftbl[i].name; i++) {
+ if (strcmp(type, ftbl[i].name) == 0)
+ return &ftbl[i];
+ }
fail:
return NULL;
}
/* Special function : only accept unsigned long */
-static __kprobes void fetch_stack_address(struct pt_regs *regs,
- void *dummy, void *dest)
+static __kprobes void fetch_kernel_stack_address(struct pt_regs *regs,
+ void *dummy, void *dest)
{
*(unsigned long *)dest = kernel_stack_pointer(regs);
}
+static __kprobes void fetch_user_stack_address(struct pt_regs *regs,
+ void *dummy, void *dest)
+{
+ *(unsigned long *)dest = user_stack_pointer(regs);
+}
+
static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
- fetch_func_t orig_fn)
+ fetch_func_t orig_fn,
+ const struct fetch_type *ftbl)
{
int i;
- if (type != &fetch_type_table[FETCH_TYPE_STRING])
+ if (type != &ftbl[FETCH_TYPE_STRING])
return NULL; /* Only string type needs size function */
for (i = 0; i < FETCH_MTD_END; i++)
if (type->fetch[i] == orig_fn)
- return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
+ return ftbl[FETCH_TYPE_STRSIZE].fetch[i];
WARN_ON(1); /* This should not happen */
@@ -516,7 +311,8 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
static int parse_probe_vars(char *arg, const struct fetch_type *t,
- struct fetch_param *f, bool is_return)
+ struct fetch_param *f, bool is_return,
+ bool is_kprobe)
{
int ret = 0;
unsigned long param;
@@ -528,13 +324,16 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
ret = -EINVAL;
} else if (strncmp(arg, "stack", 5) == 0) {
if (arg[5] == '\0') {
- if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
- f->fn = fetch_stack_address;
+ if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR))
+ return -EINVAL;
+
+ if (is_kprobe)
+ f->fn = fetch_kernel_stack_address;
else
- ret = -EINVAL;
+ f->fn = fetch_user_stack_address;
} else if (isdigit(arg[5])) {
ret = kstrtoul(arg + 5, 10, &param);
- if (ret || param > PARAM_MAX_STACK)
+ if (ret || (is_kprobe && param > PARAM_MAX_STACK))
ret = -EINVAL;
else {
f->fn = t->fetch[FETCH_MTD_stack];
@@ -552,20 +351,18 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
static int parse_probe_arg(char *arg, const struct fetch_type *t,
struct fetch_param *f, bool is_return, bool is_kprobe)
{
+ const struct fetch_type *ftbl;
unsigned long param;
long offset;
char *tmp;
- int ret;
-
- ret = 0;
+ int ret = 0;
- /* Until uprobe_events supports only reg arguments */
- if (!is_kprobe && arg[0] != '%')
- return -EINVAL;
+ ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
+ BUG_ON(ftbl == NULL);
switch (arg[0]) {
case '$':
- ret = parse_probe_vars(arg + 1, t, f, is_return);
+ ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe);
break;
case '%': /* named register */
@@ -577,7 +374,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
}
break;
- case '@': /* memory or symbol */
+ case '@': /* memory, file-offset or symbol */
if (isdigit(arg[1])) {
ret = kstrtoul(arg + 1, 0, &param);
if (ret)
@@ -585,7 +382,22 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
f->fn = t->fetch[FETCH_MTD_memory];
f->data = (void *)param;
+ } else if (arg[1] == '+') {
+ /* kprobes don't support file offsets */
+ if (is_kprobe)
+ return -EINVAL;
+
+ ret = kstrtol(arg + 2, 0, &offset);
+ if (ret)
+ break;
+
+ f->fn = t->fetch[FETCH_MTD_file_offset];
+ f->data = (void *)offset;
} else {
+ /* uprobes don't support symbols */
+ if (!is_kprobe)
+ return -EINVAL;
+
ret = traceprobe_split_symbol_offset(arg + 1, &offset);
if (ret)
break;
@@ -616,7 +428,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
struct deref_fetch_param *dprm;
const struct fetch_type *t2;
- t2 = find_fetch_type(NULL);
+ t2 = find_fetch_type(NULL, ftbl);
*tmp = '\0';
dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL);
@@ -624,6 +436,9 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
return -ENOMEM;
dprm->offset = offset;
+ dprm->fetch = t->fetch[FETCH_MTD_memory];
+ dprm->fetch_size = get_fetch_size_function(t,
+ dprm->fetch, ftbl);
ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
is_kprobe);
if (ret)
@@ -685,9 +500,13 @@ static int __parse_bitfield_probe_arg(const char *bf,
int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
struct probe_arg *parg, bool is_return, bool is_kprobe)
{
+ const struct fetch_type *ftbl;
const char *t;
int ret;
+ ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
+ BUG_ON(ftbl == NULL);
+
if (strlen(arg) > MAX_ARGSTR_LEN) {
pr_info("Argument is too long.: %s\n", arg);
return -ENOSPC;
@@ -702,7 +521,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
arg[t - parg->comm] = '\0';
t++;
}
- parg->type = find_fetch_type(t);
+ parg->type = find_fetch_type(t, ftbl);
if (!parg->type) {
pr_info("Unsupported type: %s\n", t);
return -EINVAL;
@@ -716,7 +535,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
if (ret >= 0) {
parg->fetch_size.fn = get_fetch_size_function(parg->type,
- parg->fetch.fn);
+ parg->fetch.fn,
+ ftbl);
parg->fetch_size.data = parg->fetch.data;
}
@@ -837,3 +657,65 @@ out:
return ret;
}
+
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
+ bool is_return)
+{
+ int i;
+ int pos = 0;
+
+ const char *fmt, *arg;
+
+ if (!is_return) {
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+ } else {
+ fmt = "(%lx <- %lx)";
+ arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ }
+
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+ tp->args[i].name, tp->args[i].type->fmt);
+ }
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+ for (i = 0; i < tp->nr_args; i++) {
+ if (strcmp(tp->args[i].type->name, "string") == 0)
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", __get_str(%s)",
+ tp->args[i].name);
+ else
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+ tp->args[i].name);
+ }
+
+#undef LEN_OR_ZERO
+
+ /* return the length of print_fmt */
+ return pos;
+}
+
+int set_print_fmt(struct trace_probe *tp, bool is_return)
+{
+ int len;
+ char *print_fmt;
+
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_print_fmt(tp, NULL, 0, is_return);
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
+
+ /* Second: actually write the @print_fmt */
+ __set_print_fmt(tp, print_fmt, len + 1, is_return);
+ tp->call.print_fmt = print_fmt;
+
+ return 0;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5c7e09d10d74..fb1ab5dfbd42 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -81,6 +81,17 @@
*/
#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs))
+static inline void *get_rloc_data(u32 *dl)
+{
+ return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static inline void *get_loc_data(u32 *dl, void *ent)
+{
+ return (u8 *)ent + get_rloc_offs(*dl);
+}
+
/* Data fetch function type */
typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
/* Printing function type */
@@ -95,6 +106,7 @@ enum {
FETCH_MTD_symbol,
FETCH_MTD_deref,
FETCH_MTD_bitfield,
+ FETCH_MTD_file_offset,
FETCH_MTD_END,
};
@@ -115,6 +127,148 @@ struct fetch_param {
void *data;
};
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
+#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
+
+/* Printing in basic type function template */
+#define DECLARE_BASIC_PRINT_TYPE_FUNC(type) \
+__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
+ const char *name, \
+ void *data, void *ent); \
+extern const char PRINT_TYPE_FMT_NAME(type)[]
+
+DECLARE_BASIC_PRINT_TYPE_FUNC(u8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(string);
+
+#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
+
+/* Declare macro for basic types */
+#define DECLARE_FETCH_FUNC(method, type) \
+extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, \
+ void *data, void *dest)
+
+#define DECLARE_BASIC_FETCH_FUNCS(method) \
+DECLARE_FETCH_FUNC(method, u8); \
+DECLARE_FETCH_FUNC(method, u16); \
+DECLARE_FETCH_FUNC(method, u32); \
+DECLARE_FETCH_FUNC(method, u64)
+
+DECLARE_BASIC_FETCH_FUNCS(reg);
+#define fetch_reg_string NULL
+#define fetch_reg_string_size NULL
+
+DECLARE_BASIC_FETCH_FUNCS(retval);
+#define fetch_retval_string NULL
+#define fetch_retval_string_size NULL
+
+DECLARE_BASIC_FETCH_FUNCS(symbol);
+DECLARE_FETCH_FUNC(symbol, string);
+DECLARE_FETCH_FUNC(symbol, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(deref);
+DECLARE_FETCH_FUNC(deref, string);
+DECLARE_FETCH_FUNC(deref, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(bitfield);
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8) \
+DEFINE_FETCH_##method(u16) \
+DEFINE_FETCH_##method(u32) \
+DEFINE_FETCH_##method(u64)
+
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(method, type) \
+ [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
+ {.name = _name, \
+ .size = _size, \
+ .is_signed = sign, \
+ .print = PRINT_TYPE_FUNC_NAME(ptype), \
+ .fmt = PRINT_TYPE_FMT_NAME(ptype), \
+ .fmttype = _fmttype, \
+ .fetch = { \
+ASSIGN_FETCH_FUNC(reg, ftype), \
+ASSIGN_FETCH_FUNC(stack, ftype), \
+ASSIGN_FETCH_FUNC(retval, ftype), \
+ASSIGN_FETCH_FUNC(memory, ftype), \
+ASSIGN_FETCH_FUNC(symbol, ftype), \
+ASSIGN_FETCH_FUNC(deref, ftype), \
+ASSIGN_FETCH_FUNC(bitfield, ftype), \
+ASSIGN_FETCH_FUNC(file_offset, ftype), \
+ } \
+ }
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
+ __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+#define ASSIGN_FETCH_TYPE_END {}
+
+#define FETCH_TYPE_STRING 0
+#define FETCH_TYPE_STRSIZE 1
+
+/*
+ * Fetch type information table.
+ * It's declared as a weak symbol due to conditional compilation.
+ */
+extern __weak const struct fetch_type kprobes_fetch_type_table[];
+extern __weak const struct fetch_type uprobes_fetch_type_table[];
+
+#ifdef CONFIG_KPROBE_EVENT
+struct symbol_cache;
+unsigned long update_symbol_cache(struct symbol_cache *sc);
+void free_symbol_cache(struct symbol_cache *sc);
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
+#else
+/* uprobes do not support symbol fetch methods */
+#define fetch_symbol_u8 NULL
+#define fetch_symbol_u16 NULL
+#define fetch_symbol_u32 NULL
+#define fetch_symbol_u64 NULL
+#define fetch_symbol_string NULL
+#define fetch_symbol_string_size NULL
+
+struct symbol_cache {
+};
+static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc)
+{
+ return 0;
+}
+
+static inline void __used free_symbol_cache(struct symbol_cache *sc)
+{
+}
+
+static inline struct symbol_cache * __used
+alloc_symbol_cache(const char *sym, long offset)
+{
+ return NULL;
+}
+#endif /* CONFIG_KPROBE_EVENT */
+
struct probe_arg {
struct fetch_param fetch;
struct fetch_param fetch_size;
@@ -124,6 +278,31 @@ struct probe_arg {
const struct fetch_type *type; /* Type of this argument */
};
+struct trace_probe {
+ unsigned int flags; /* For TP_FLAG_* */
+ struct ftrace_event_class class;
+ struct ftrace_event_call call;
+ struct list_head files;
+ ssize_t size; /* trace entry size */
+ unsigned int nr_args;
+ struct probe_arg args[];
+};
+
+struct event_file_link {
+ struct ftrace_event_file *file;
+ struct list_head list;
+};
+
+static inline bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+ return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static inline bool trace_probe_is_registered(struct trace_probe *tp)
+{
+ return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
static inline __kprobes void call_fetch(struct fetch_param *fprm,
struct pt_regs *regs, void *dest)
{
@@ -142,6 +321,18 @@ static inline int is_good_name(const char *name)
return 1;
}
+static inline struct event_file_link *
+find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
+{
+ struct event_file_link *link;
+
+ list_for_each_entry(link, &tp->files, list)
+ if (link->file == file)
+ return link;
+
+ return NULL;
+}
+
extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
struct probe_arg *parg, bool is_return, bool is_kprobe);
@@ -158,3 +349,53 @@ extern ssize_t traceprobe_probes_write(struct file *file,
int (*createfn)(int, char**));
extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
+
+/* Sum up total data length for dynamic arraies (strings) */
+static inline __kprobes int
+__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
+{
+ int i, ret = 0;
+ u32 len;
+
+ for (i = 0; i < tp->nr_args; i++)
+ if (unlikely(tp->args[i].fetch_size.fn)) {
+ call_fetch(&tp->args[i].fetch_size, regs, &len);
+ ret += len;
+ }
+
+ return ret;
+}
+
+/* Store the value of each argument */
+static inline __kprobes void
+store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
+ u8 *data, int maxlen)
+{
+ int i;
+ u32 end = tp->size;
+ u32 *dl; /* Data (relative) location */
+
+ for (i = 0; i < tp->nr_args; i++) {
+ if (unlikely(tp->args[i].fetch_size.fn)) {
+ /*
+ * First, we set the relative location and
+ * maximum data length to *dl
+ */
+ dl = (u32 *)(data + tp->args[i].offset);
+ *dl = make_data_rloc(maxlen, end - tp->args[i].offset);
+ /* Then try to fetch string or dynamic array data */
+ call_fetch(&tp->args[i].fetch, regs, dl);
+ /* Reduce maximum length */
+ end += get_rloc_len(*dl);
+ maxlen -= get_rloc_len(*dl);
+ /* Trick here, convert data_rloc to data_loc */
+ *dl = convert_rloc_to_loc(*dl,
+ ent_size + tp->args[i].offset);
+ } else
+ /* Just fetching data normally */
+ call_fetch(&tp->args[i].fetch, regs,
+ data + tp->args[i].offset);
+ }
+}
+
+extern int set_print_fmt(struct trace_probe *tp, bool is_return);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index fee77e15d815..e14da5e97a69 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -16,6 +16,7 @@
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <trace/events/sched.h>
#include "trace.h"
@@ -27,6 +28,8 @@ static int wakeup_cpu;
static int wakeup_current_cpu;
static unsigned wakeup_prio = -1;
static int wakeup_rt;
+static int wakeup_dl;
+static int tracing_dl = 0;
static arch_spinlock_t wakeup_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -176,8 +179,10 @@ static void wakeup_function_set(int set)
unregister_wakeup_function(is_graph());
}
-static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set)
+static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
{
+ struct tracer *tracer = tr->current_trace;
+
if (mask & TRACE_ITER_FUNCTION)
wakeup_function_set(set);
@@ -206,7 +211,8 @@ static void stop_func_tracer(int graph)
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+static int
+wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
if (!(bit & TRACE_DISPLAY_GRAPH))
@@ -308,7 +314,8 @@ __trace_function(struct trace_array *tr,
#else
#define __trace_function trace_function
-static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+static int
+wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
return -EINVAL;
}
@@ -437,6 +444,7 @@ static void __wakeup_reset(struct trace_array *tr)
{
wakeup_cpu = -1;
wakeup_prio = -1;
+ tracing_dl = 0;
if (wakeup_task)
put_task_struct(wakeup_task);
@@ -472,9 +480,17 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
tracing_record_cmdline(p);
tracing_record_cmdline(current);
- if ((wakeup_rt && !rt_task(p)) ||
- p->prio >= wakeup_prio ||
- p->prio >= current->prio)
+ /*
+ * Semantic is like this:
+ * - wakeup tracer handles all tasks in the system, independently
+ * from their scheduling class;
+ * - wakeup_rt tracer handles tasks belonging to sched_dl and
+ * sched_rt class;
+ * - wakeup_dl handles tasks belonging to sched_dl class only.
+ */
+ if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+ (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+ (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
return;
pc = preempt_count();
@@ -486,7 +502,8 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
arch_spin_lock(&wakeup_lock);
/* check for races. */
- if (!tracer_enabled || p->prio >= wakeup_prio)
+ if (!tracer_enabled || tracing_dl ||
+ (!dl_task(p) && p->prio >= wakeup_prio))
goto out_locked;
/* reset the trace */
@@ -496,6 +513,15 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
wakeup_current_cpu = wakeup_cpu;
wakeup_prio = p->prio;
+ /*
+ * Once you start tracing a -deadline task, don't bother tracing
+ * another task until the first one wakes up.
+ */
+ if (dl_task(p))
+ tracing_dl = 1;
+ else
+ tracing_dl = 0;
+
wakeup_task = p;
get_task_struct(wakeup_task);
@@ -597,16 +623,25 @@ static int __wakeup_tracer_init(struct trace_array *tr)
static int wakeup_tracer_init(struct trace_array *tr)
{
+ wakeup_dl = 0;
wakeup_rt = 0;
return __wakeup_tracer_init(tr);
}
static int wakeup_rt_tracer_init(struct trace_array *tr)
{
+ wakeup_dl = 0;
wakeup_rt = 1;
return __wakeup_tracer_init(tr);
}
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+ wakeup_dl = 1;
+ wakeup_rt = 0;
+ return __wakeup_tracer_init(tr);
+}
+
static void wakeup_tracer_reset(struct trace_array *tr)
{
int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
@@ -674,6 +709,28 @@ static struct tracer wakeup_rt_tracer __read_mostly =
.use_max_tr = true,
};
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+ .name = "wakeup_dl",
+ .init = wakeup_dl_tracer_init,
+ .reset = wakeup_tracer_reset,
+ .start = wakeup_tracer_start,
+ .stop = wakeup_tracer_stop,
+ .wait_pipe = poll_wait_pipe,
+ .print_max = true,
+ .print_header = wakeup_print_header,
+ .print_line = wakeup_print_line,
+ .flags = &tracer_flags,
+ .set_flag = wakeup_set_flag,
+ .flag_changed = wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_wakeup,
+#endif
+ .open = wakeup_trace_open,
+ .close = wakeup_trace_close,
+ .use_max_tr = true,
+};
+
__init static int init_wakeup_tracer(void)
{
int ret;
@@ -686,6 +743,10 @@ __init static int init_wakeup_tracer(void)
if (ret)
return ret;
+ ret = register_tracer(&wakeup_dl_tracer);
+ if (ret)
+ return ret;
+
return 0;
}
core_initcall(init_wakeup_tracer);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index a7329b7902f8..e98fca60974f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1022,11 +1022,16 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
#ifdef CONFIG_SCHED_TRACER
static int trace_wakeup_test_thread(void *data)
{
- /* Make this a RT thread, doesn't need to be too high */
- static const struct sched_param param = { .sched_priority = 5 };
+ /* Make this a -deadline thread */
+ static const struct sched_attr attr = {
+ .sched_policy = SCHED_DEADLINE,
+ .sched_runtime = 100000ULL,
+ .sched_deadline = 10000000ULL,
+ .sched_period = 10000000ULL
+ };
struct completion *x = data;
- sched_setscheduler(current, SCHED_FIFO, &param);
+ sched_setattr(current, &attr);
/* Make it know we have a new prio */
complete(x);
@@ -1040,8 +1045,8 @@ static int trace_wakeup_test_thread(void *data)
/* we are awake, now wait to disappear */
while (!kthread_should_stop()) {
/*
- * This is an RT task, do short sleeps to let
- * others run.
+ * This will likely be the system top priority
+ * task, do short sleeps to let others run.
*/
msleep(100);
}
@@ -1054,21 +1059,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
{
unsigned long save_max = tracing_max_latency;
struct task_struct *p;
- struct completion isrt;
+ struct completion is_ready;
unsigned long count;
int ret;
- init_completion(&isrt);
+ init_completion(&is_ready);
- /* create a high prio thread */
- p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+ /* create a -deadline thread */
+ p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
if (IS_ERR(p)) {
printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
return -1;
}
- /* make sure the thread is running at an RT prio */
- wait_for_completion(&isrt);
+ /* make sure the thread is running at -deadline policy */
+ wait_for_completion(&is_ready);
/* start the tracing */
ret = tracer_init(trace, tr);
@@ -1082,19 +1087,19 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
while (p->on_rq) {
/*
- * Sleep to make sure the RT thread is asleep too.
+ * Sleep to make sure the -deadline thread is asleep too.
* On virtual machines we can't rely on timings,
* but we want to make sure this test still works.
*/
msleep(100);
}
- init_completion(&isrt);
+ init_completion(&is_ready);
wake_up_process(p);
/* Wait for the task to wake up */
- wait_for_completion(&isrt);
+ wait_for_completion(&is_ready);
/* stop the tracing. */
tracing_stop();
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b20428c5efe2..21b320e5d163 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -13,6 +13,7 @@
#include <linux/sysctl.h>
#include <linux/init.h>
#include <linux/fs.h>
+#include <linux/magic.h>
#include <asm/setup.h>
@@ -144,6 +145,8 @@ check_stack(unsigned long ip, unsigned long *stack)
i++;
}
+ BUG_ON(current != &init_task &&
+ *(end_of_stack(current)) != STACK_END_MAGIC);
out:
arch_spin_unlock(&max_stack_lock);
local_irq_restore(flags);
@@ -382,7 +385,7 @@ static const struct file_operations stack_trace_filter_fops = {
.open = stack_trace_filter_open,
.read = seq_read,
.write = ftrace_filter_write,
- .llseek = ftrace_filter_lseek,
+ .llseek = tracing_lseek,
.release = ftrace_regex_release,
};
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ea90eb5f6f17..759d5e004517 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -321,7 +321,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
if (!ftrace_file)
return;
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -343,9 +343,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
- if (!filter_check_discard(ftrace_file, entry, buffer, event))
- trace_current_buffer_unlock_commit(buffer, event,
- irq_flags, pc);
+ event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+ irq_flags, pc);
}
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -369,7 +368,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
if (!ftrace_file)
return;
- if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
+ if (ftrace_trigger_soft_disabled(ftrace_file))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -390,9 +389,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
entry->nr = syscall_nr;
entry->ret = syscall_get_return_value(current, regs);
- if (!filter_check_discard(ftrace_file, entry, buffer, event))
- trace_current_buffer_unlock_commit(buffer, event,
- irq_flags, pc);
+ event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+ irq_flags, pc);
}
static int reg_event_syscall_enter(struct ftrace_event_file *file,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index b6dcc42ef7f5..e4473367e7a4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -51,22 +51,17 @@ struct trace_uprobe_filter {
*/
struct trace_uprobe {
struct list_head list;
- struct ftrace_event_class class;
- struct ftrace_event_call call;
struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
struct inode *inode;
char *filename;
unsigned long offset;
unsigned long nhit;
- unsigned int flags; /* For TP_FLAG_* */
- ssize_t size; /* trace entry size */
- unsigned int nr_args;
- struct probe_arg args[];
+ struct trace_probe tp;
};
-#define SIZEOF_TRACE_UPROBE(n) \
- (offsetof(struct trace_uprobe, args) + \
+#define SIZEOF_TRACE_UPROBE(n) \
+ (offsetof(struct trace_uprobe, tp.args) + \
(sizeof(struct probe_arg) * (n)))
static int register_uprobe_event(struct trace_uprobe *tu);
@@ -75,10 +70,151 @@ static int unregister_uprobe_event(struct trace_uprobe *tu);
static DEFINE_MUTEX(uprobe_lock);
static LIST_HEAD(uprobe_list);
+struct uprobe_dispatch_data {
+ struct trace_uprobe *tu;
+ unsigned long bp_addr;
+};
+
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs);
+#ifdef CONFIG_STACK_GROWSUP
+static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
+{
+ return addr - (n * sizeof(long));
+}
+#else
+static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n)
+{
+ return addr + (n * sizeof(long));
+}
+#endif
+
+static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+ unsigned long ret;
+ unsigned long addr = user_stack_pointer(regs);
+
+ addr = adjust_stack_addr(addr, n);
+
+ if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret)))
+ return 0;
+
+ return ret;
+}
+
+/*
+ * Uprobes-specific fetch functions
+ */
+#define DEFINE_FETCH_stack(type) \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)get_user_stack_nth(regs, \
+ ((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
+
+#define DEFINE_FETCH_memory(type) \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+ void *addr, void *dest) \
+{ \
+ type retval; \
+ void __user *vaddr = (void __force __user *) addr; \
+ \
+ if (copy_from_user(&retval, vaddr, sizeof(type))) \
+ *(type *)dest = 0; \
+ else \
+ *(type *) dest = retval; \
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ long ret;
+ u32 rloc = *(u32 *)dest;
+ int maxlen = get_rloc_len(rloc);
+ u8 *dst = get_rloc_data(dest);
+ void __user *src = (void __force __user *) addr;
+
+ if (!maxlen)
+ return;
+
+ ret = strncpy_from_user(dst, src, maxlen);
+
+ if (ret < 0) { /* Failed to fetch string */
+ ((u8 *)get_rloc_data(dest))[0] = '\0';
+ *(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc));
+ } else {
+ *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc));
+ }
+}
+
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ int len;
+ void __user *vaddr = (void __force __user *) addr;
+
+ len = strnlen_user(vaddr, MAX_STRING_SIZE);
+
+ if (len == 0 || len > MAX_STRING_SIZE) /* Failed to check length */
+ *(u32 *)dest = 0;
+ else
+ *(u32 *)dest = len;
+}
+
+static unsigned long translate_user_vaddr(void *file_offset)
+{
+ unsigned long base_addr;
+ struct uprobe_dispatch_data *udd;
+
+ udd = (void *) current->utask->vaddr;
+
+ base_addr = udd->bp_addr - udd->tu->offset;
+ return base_addr + (unsigned long)file_offset;
+}
+
+#define DEFINE_FETCH_file_offset(type) \
+static __kprobes void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ void *vaddr = (void *)translate_user_vaddr(offset); \
+ \
+ FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest); \
+}
+DEFINE_BASIC_FETCH_FUNCS(file_offset)
+DEFINE_FETCH_file_offset(string)
+DEFINE_FETCH_file_offset(string_size)
+
+/* Fetch type information table */
+const struct fetch_type uprobes_fetch_type_table[] = {
+ /* Special types */
+ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+ sizeof(u32), 1, "__data_loc char[]"),
+ [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+ string_size, sizeof(u32), 0, "u32"),
+ /* Basic types */
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+
+ ASSIGN_FETCH_TYPE_END
+};
+
static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
{
rwlock_init(&filter->rwlock);
@@ -114,25 +250,26 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
if (!tu)
return ERR_PTR(-ENOMEM);
- tu->call.class = &tu->class;
- tu->call.name = kstrdup(event, GFP_KERNEL);
- if (!tu->call.name)
+ tu->tp.call.class = &tu->tp.class;
+ tu->tp.call.name = kstrdup(event, GFP_KERNEL);
+ if (!tu->tp.call.name)
goto error;
- tu->class.system = kstrdup(group, GFP_KERNEL);
- if (!tu->class.system)
+ tu->tp.class.system = kstrdup(group, GFP_KERNEL);
+ if (!tu->tp.class.system)
goto error;
INIT_LIST_HEAD(&tu->list);
+ INIT_LIST_HEAD(&tu->tp.files);
tu->consumer.handler = uprobe_dispatcher;
if (is_ret)
tu->consumer.ret_handler = uretprobe_dispatcher;
init_trace_uprobe_filter(&tu->filter);
- tu->call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
+ tu->tp.call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
return tu;
error:
- kfree(tu->call.name);
+ kfree(tu->tp.call.name);
kfree(tu);
return ERR_PTR(-ENOMEM);
@@ -142,12 +279,12 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
{
int i;
- for (i = 0; i < tu->nr_args; i++)
- traceprobe_free_probe_arg(&tu->args[i]);
+ for (i = 0; i < tu->tp.nr_args; i++)
+ traceprobe_free_probe_arg(&tu->tp.args[i]);
iput(tu->inode);
- kfree(tu->call.class->system);
- kfree(tu->call.name);
+ kfree(tu->tp.call.class->system);
+ kfree(tu->tp.call.name);
kfree(tu->filename);
kfree(tu);
}
@@ -157,8 +294,8 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou
struct trace_uprobe *tu;
list_for_each_entry(tu, &uprobe_list, list)
- if (strcmp(tu->call.name, event) == 0 &&
- strcmp(tu->call.class->system, group) == 0)
+ if (strcmp(tu->tp.call.name, event) == 0 &&
+ strcmp(tu->tp.call.class->system, group) == 0)
return tu;
return NULL;
@@ -181,16 +318,16 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
/* Register a trace_uprobe and probe_event */
static int register_trace_uprobe(struct trace_uprobe *tu)
{
- struct trace_uprobe *old_tp;
+ struct trace_uprobe *old_tu;
int ret;
mutex_lock(&uprobe_lock);
/* register as an event */
- old_tp = find_probe_event(tu->call.name, tu->call.class->system);
- if (old_tp) {
+ old_tu = find_probe_event(tu->tp.call.name, tu->tp.call.class->system);
+ if (old_tu) {
/* delete old event */
- ret = unregister_trace_uprobe(old_tp);
+ ret = unregister_trace_uprobe(old_tu);
if (ret)
goto end;
}
@@ -211,7 +348,7 @@ end:
/*
* Argument syntax:
- * - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS]
+ * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
*
* - Remove uprobe: -:[GRP/]EVENT
*/
@@ -360,34 +497,36 @@ static int create_trace_uprobe(int argc, char **argv)
/* parse arguments */
ret = 0;
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ struct probe_arg *parg = &tu->tp.args[i];
+
/* Increment count for freeing args in error case */
- tu->nr_args++;
+ tu->tp.nr_args++;
/* Parse argument name */
arg = strchr(argv[i], '=');
if (arg) {
*arg++ = '\0';
- tu->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ parg->name = kstrdup(argv[i], GFP_KERNEL);
} else {
arg = argv[i];
/* If argument name is omitted, set "argN" */
snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
- tu->args[i].name = kstrdup(buf, GFP_KERNEL);
+ parg->name = kstrdup(buf, GFP_KERNEL);
}
- if (!tu->args[i].name) {
+ if (!parg->name) {
pr_info("Failed to allocate argument[%d] name.\n", i);
ret = -ENOMEM;
goto error;
}
- if (!is_good_name(tu->args[i].name)) {
- pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name);
+ if (!is_good_name(parg->name)) {
+ pr_info("Invalid argument[%d] name: %s\n", i, parg->name);
ret = -EINVAL;
goto error;
}
- if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) {
+ if (traceprobe_conflict_field_name(parg->name, tu->tp.args, i)) {
pr_info("Argument[%d] name '%s' conflicts with "
"another field.\n", i, argv[i]);
ret = -EINVAL;
@@ -395,7 +534,8 @@ static int create_trace_uprobe(int argc, char **argv)
}
/* Parse fetch argument */
- ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false);
+ ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg,
+ is_return, false);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -459,11 +599,11 @@ static int probes_seq_show(struct seq_file *m, void *v)
char c = is_ret_probe(tu) ? 'r' : 'p';
int i;
- seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name);
+ seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, tu->tp.call.name);
seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
- for (i = 0; i < tu->nr_args; i++)
- seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm);
+ for (i = 0; i < tu->tp.nr_args; i++)
+ seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm);
seq_printf(m, "\n");
return 0;
@@ -509,7 +649,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
{
struct trace_uprobe *tu = v;
- seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit);
+ seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->tp.call.name, tu->nhit);
return 0;
}
@@ -533,19 +673,116 @@ static const struct file_operations uprobe_profile_ops = {
.release = seq_release,
};
-static void uprobe_trace_print(struct trace_uprobe *tu,
- unsigned long func, struct pt_regs *regs)
+struct uprobe_cpu_buffer {
+ struct mutex mutex;
+ void *buf;
+};
+static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer;
+static int uprobe_buffer_refcnt;
+
+static int uprobe_buffer_init(void)
+{
+ int cpu, err_cpu;
+
+ uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer);
+ if (uprobe_cpu_buffer == NULL)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ struct page *p = alloc_pages_node(cpu_to_node(cpu),
+ GFP_KERNEL, 0);
+ if (p == NULL) {
+ err_cpu = cpu;
+ goto err;
+ }
+ per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p);
+ mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex);
+ }
+
+ return 0;
+
+err:
+ for_each_possible_cpu(cpu) {
+ if (cpu == err_cpu)
+ break;
+ free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf);
+ }
+
+ free_percpu(uprobe_cpu_buffer);
+ return -ENOMEM;
+}
+
+static int uprobe_buffer_enable(void)
+{
+ int ret = 0;
+
+ BUG_ON(!mutex_is_locked(&event_mutex));
+
+ if (uprobe_buffer_refcnt++ == 0) {
+ ret = uprobe_buffer_init();
+ if (ret < 0)
+ uprobe_buffer_refcnt--;
+ }
+
+ return ret;
+}
+
+static void uprobe_buffer_disable(void)
+{
+ BUG_ON(!mutex_is_locked(&event_mutex));
+
+ if (--uprobe_buffer_refcnt == 0) {
+ free_percpu(uprobe_cpu_buffer);
+ uprobe_cpu_buffer = NULL;
+ }
+}
+
+static struct uprobe_cpu_buffer *uprobe_buffer_get(void)
+{
+ struct uprobe_cpu_buffer *ucb;
+ int cpu;
+
+ cpu = raw_smp_processor_id();
+ ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu);
+
+ /*
+ * Use per-cpu buffers for fastest access, but we might migrate
+ * so the mutex makes sure we have sole access to it.
+ */
+ mutex_lock(&ucb->mutex);
+
+ return ucb;
+}
+
+static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
+{
+ mutex_unlock(&ucb->mutex);
+}
+
+static void __uprobe_trace_func(struct trace_uprobe *tu,
+ unsigned long func, struct pt_regs *regs,
+ struct uprobe_cpu_buffer *ucb, int dsize,
+ struct ftrace_event_file *ftrace_file)
{
struct uprobe_trace_entry_head *entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
void *data;
- int size, i;
- struct ftrace_event_call *call = &tu->call;
+ int size, esize;
+ struct ftrace_event_call *call = &tu->tp.call;
+
+ WARN_ON(call != ftrace_file->event_call);
- size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
- event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
- size + tu->size, 0, 0);
+ if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE))
+ return;
+
+ if (ftrace_trigger_soft_disabled(ftrace_file))
+ return;
+
+ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+ size = esize + tu->tp.size + dsize;
+ event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
+ call->event.type, size, 0, 0);
if (!event)
return;
@@ -559,25 +796,38 @@ static void uprobe_trace_print(struct trace_uprobe *tu,
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->nr_args; i++)
- call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+ memcpy(data, ucb->buf, tu->tp.size + dsize);
- if (!call_filter_check_discard(call, entry, buffer, event))
- trace_buffer_unlock_commit(buffer, event, 0, 0);
+ event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0);
}
/* uprobe handler */
-static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
+ struct uprobe_cpu_buffer *ucb, int dsize)
{
- if (!is_ret_probe(tu))
- uprobe_trace_print(tu, 0, regs);
+ struct event_file_link *link;
+
+ if (is_ret_probe(tu))
+ return 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(link, &tu->tp.files, list)
+ __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file);
+ rcu_read_unlock();
+
return 0;
}
static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
- struct pt_regs *regs)
+ struct pt_regs *regs,
+ struct uprobe_cpu_buffer *ucb, int dsize)
{
- uprobe_trace_print(tu, func, regs);
+ struct event_file_link *link;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(link, &tu->tp.files, list)
+ __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file);
+ rcu_read_unlock();
}
/* Event entry printers */
@@ -591,23 +841,24 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
int i;
entry = (struct uprobe_trace_entry_head *)iter->ent;
- tu = container_of(event, struct trace_uprobe, call.event);
+ tu = container_of(event, struct trace_uprobe, tp.call.event);
if (is_ret_probe(tu)) {
- if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name,
+ if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->tp.call.name,
entry->vaddr[1], entry->vaddr[0]))
goto partial;
data = DATAOF_TRACE_ENTRY(entry, true);
} else {
- if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name,
+ if (!trace_seq_printf(s, "%s: (0x%lx)", tu->tp.call.name,
entry->vaddr[0]))
goto partial;
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->nr_args; i++) {
- if (!tu->args[i].type->print(s, tu->args[i].name,
- data + tu->args[i].offset, entry))
+ for (i = 0; i < tu->tp.nr_args; i++) {
+ struct probe_arg *parg = &tu->tp.args[i];
+
+ if (!parg->type->print(s, parg->name, data + parg->offset, entry))
goto partial;
}
@@ -618,43 +869,81 @@ partial:
return TRACE_TYPE_PARTIAL_LINE;
}
-static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu)
-{
- return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE);
-}
-
typedef bool (*filter_func_t)(struct uprobe_consumer *self,
enum uprobe_filter_ctx ctx,
struct mm_struct *mm);
static int
-probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
+probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
+ filter_func_t filter)
{
- int ret = 0;
+ bool enabled = trace_probe_is_enabled(&tu->tp);
+ struct event_file_link *link = NULL;
+ int ret;
+
+ if (file) {
+ link = kmalloc(sizeof(*link), GFP_KERNEL);
+ if (!link)
+ return -ENOMEM;
+
+ link->file = file;
+ list_add_tail_rcu(&link->list, &tu->tp.files);
- if (is_trace_uprobe_enabled(tu))
- return -EINTR;
+ tu->tp.flags |= TP_FLAG_TRACE;
+ } else
+ tu->tp.flags |= TP_FLAG_PROFILE;
+
+ ret = uprobe_buffer_enable();
+ if (ret < 0)
+ return ret;
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
- tu->flags |= flag;
+ if (enabled)
+ return 0;
+
tu->consumer.filter = filter;
ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
- if (ret)
- tu->flags &= ~flag;
+ if (ret) {
+ if (file) {
+ list_del(&link->list);
+ kfree(link);
+ tu->tp.flags &= ~TP_FLAG_TRACE;
+ } else
+ tu->tp.flags &= ~TP_FLAG_PROFILE;
+ }
return ret;
}
-static void probe_event_disable(struct trace_uprobe *tu, int flag)
+static void
+probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file)
{
- if (!is_trace_uprobe_enabled(tu))
+ if (!trace_probe_is_enabled(&tu->tp))
return;
+ if (file) {
+ struct event_file_link *link;
+
+ link = find_event_file_link(&tu->tp, file);
+ if (!link)
+ return;
+
+ list_del_rcu(&link->list);
+ /* synchronize with u{,ret}probe_trace_func */
+ synchronize_sched();
+ kfree(link);
+
+ if (!list_empty(&tu->tp.files))
+ return;
+ }
+
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
- tu->flags &= ~flag;
+ tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
+
+ uprobe_buffer_disable();
}
static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
@@ -672,12 +961,12 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
size = SIZEOF_TRACE_ENTRY(false);
}
/* Set argument names as fields */
- for (i = 0; i < tu->nr_args; i++) {
- ret = trace_define_field(event_call, tu->args[i].type->fmttype,
- tu->args[i].name,
- size + tu->args[i].offset,
- tu->args[i].type->size,
- tu->args[i].type->is_signed,
+ for (i = 0; i < tu->tp.nr_args; i++) {
+ struct probe_arg *parg = &tu->tp.args[i];
+
+ ret = trace_define_field(event_call, parg->type->fmttype,
+ parg->name, size + parg->offset,
+ parg->type->size, parg->type->is_signed,
FILTER_OTHER);
if (ret)
@@ -686,59 +975,6 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
return 0;
}
-#define LEN_OR_ZERO (len ? len - pos : 0)
-static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len)
-{
- const char *fmt, *arg;
- int i;
- int pos = 0;
-
- if (is_ret_probe(tu)) {
- fmt = "(%lx <- %lx)";
- arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
- } else {
- fmt = "(%lx)";
- arg = "REC->" FIELD_STRING_IP;
- }
-
- /* When len=0, we just calculate the needed length */
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
-
- for (i = 0; i < tu->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
- tu->args[i].name, tu->args[i].type->fmt);
- }
-
- pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-
- for (i = 0; i < tu->nr_args; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
- tu->args[i].name);
- }
-
- return pos; /* return the length of print_fmt */
-}
-#undef LEN_OR_ZERO
-
-static int set_print_fmt(struct trace_uprobe *tu)
-{
- char *print_fmt;
- int len;
-
- /* First: called with 0 length to calculate the needed length */
- len = __set_print_fmt(tu, NULL, 0);
- print_fmt = kmalloc(len + 1, GFP_KERNEL);
- if (!print_fmt)
- return -ENOMEM;
-
- /* Second: actually write the @print_fmt */
- __set_print_fmt(tu, print_fmt, len + 1);
- tu->call.print_fmt = print_fmt;
-
- return 0;
-}
-
#ifdef CONFIG_PERF_EVENTS
static bool
__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
@@ -828,17 +1064,23 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
return ret;
}
-static void uprobe_perf_print(struct trace_uprobe *tu,
- unsigned long func, struct pt_regs *regs)
+static void __uprobe_perf_func(struct trace_uprobe *tu,
+ unsigned long func, struct pt_regs *regs,
+ struct uprobe_cpu_buffer *ucb, int dsize)
{
- struct ftrace_event_call *call = &tu->call;
+ struct ftrace_event_call *call = &tu->tp.call;
struct uprobe_trace_entry_head *entry;
struct hlist_head *head;
void *data;
- int size, rctx, i;
+ int size, esize;
+ int rctx;
- size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
- size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32);
+ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+ size = esize + tu->tp.size + dsize;
+ size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32);
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
+ return;
preempt_disable();
head = this_cpu_ptr(call->perf_events);
@@ -858,8 +1100,13 @@ static void uprobe_perf_print(struct trace_uprobe *tu,
data = DATAOF_TRACE_ENTRY(entry, false);
}
- for (i = 0; i < tu->nr_args; i++)
- call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+ memcpy(data, ucb->buf, tu->tp.size + dsize);
+
+ if (size - esize > tu->tp.size + dsize) {
+ int len = tu->tp.size + dsize;
+
+ memset(data + len, 0, size - esize - len);
+ }
perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
out:
@@ -867,42 +1114,46 @@ static void uprobe_perf_print(struct trace_uprobe *tu,
}
/* uprobe profile handler */
-static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs,
+ struct uprobe_cpu_buffer *ucb, int dsize)
{
if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
return UPROBE_HANDLER_REMOVE;
if (!is_ret_probe(tu))
- uprobe_perf_print(tu, 0, regs);
+ __uprobe_perf_func(tu, 0, regs, ucb, dsize);
return 0;
}
static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
- struct pt_regs *regs)
+ struct pt_regs *regs,
+ struct uprobe_cpu_buffer *ucb, int dsize)
{
- uprobe_perf_print(tu, func, regs);
+ __uprobe_perf_func(tu, func, regs, ucb, dsize);
}
#endif /* CONFIG_PERF_EVENTS */
-static
-int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data)
+static int
+trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
+ void *data)
{
struct trace_uprobe *tu = event->data;
+ struct ftrace_event_file *file = data;
switch (type) {
case TRACE_REG_REGISTER:
- return probe_event_enable(tu, TP_FLAG_TRACE, NULL);
+ return probe_event_enable(tu, file, NULL);
case TRACE_REG_UNREGISTER:
- probe_event_disable(tu, TP_FLAG_TRACE);
+ probe_event_disable(tu, file);
return 0;
#ifdef CONFIG_PERF_EVENTS
case TRACE_REG_PERF_REGISTER:
- return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter);
+ return probe_event_enable(tu, NULL, uprobe_perf_filter);
case TRACE_REG_PERF_UNREGISTER:
- probe_event_disable(tu, TP_FLAG_PROFILE);
+ probe_event_disable(tu, NULL);
return 0;
case TRACE_REG_PERF_OPEN:
@@ -921,18 +1172,43 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
{
struct trace_uprobe *tu;
+ struct uprobe_dispatch_data udd;
+ struct uprobe_cpu_buffer *ucb;
+ int dsize, esize;
int ret = 0;
+
tu = container_of(con, struct trace_uprobe, consumer);
tu->nhit++;
- if (tu->flags & TP_FLAG_TRACE)
- ret |= uprobe_trace_func(tu, regs);
+ udd.tu = tu;
+ udd.bp_addr = instruction_pointer(regs);
+
+ current->utask->vaddr = (unsigned long) &udd;
#ifdef CONFIG_PERF_EVENTS
- if (tu->flags & TP_FLAG_PROFILE)
- ret |= uprobe_perf_func(tu, regs);
+ if ((tu->tp.flags & TP_FLAG_TRACE) == 0 &&
+ !uprobe_perf_filter(&tu->consumer, 0, current->mm))
+ return UPROBE_HANDLER_REMOVE;
#endif
+
+ if (WARN_ON_ONCE(!uprobe_cpu_buffer))
+ return 0;
+
+ dsize = __get_data_size(&tu->tp, regs);
+ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+ ucb = uprobe_buffer_get();
+ store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+
+ if (tu->tp.flags & TP_FLAG_TRACE)
+ ret |= uprobe_trace_func(tu, regs, ucb, dsize);
+
+#ifdef CONFIG_PERF_EVENTS
+ if (tu->tp.flags & TP_FLAG_PROFILE)
+ ret |= uprobe_perf_func(tu, regs, ucb, dsize);
+#endif
+ uprobe_buffer_put(ucb);
return ret;
}
@@ -940,16 +1216,34 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
unsigned long func, struct pt_regs *regs)
{
struct trace_uprobe *tu;
+ struct uprobe_dispatch_data udd;
+ struct uprobe_cpu_buffer *ucb;
+ int dsize, esize;
tu = container_of(con, struct trace_uprobe, consumer);
- if (tu->flags & TP_FLAG_TRACE)
- uretprobe_trace_func(tu, func, regs);
+ udd.tu = tu;
+ udd.bp_addr = func;
+
+ current->utask->vaddr = (unsigned long) &udd;
+
+ if (WARN_ON_ONCE(!uprobe_cpu_buffer))
+ return 0;
+
+ dsize = __get_data_size(&tu->tp, regs);
+ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+ ucb = uprobe_buffer_get();
+ store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+
+ if (tu->tp.flags & TP_FLAG_TRACE)
+ uretprobe_trace_func(tu, func, regs, ucb, dsize);
#ifdef CONFIG_PERF_EVENTS
- if (tu->flags & TP_FLAG_PROFILE)
- uretprobe_perf_func(tu, func, regs);
+ if (tu->tp.flags & TP_FLAG_PROFILE)
+ uretprobe_perf_func(tu, func, regs, ucb, dsize);
#endif
+ uprobe_buffer_put(ucb);
return 0;
}
@@ -959,7 +1253,7 @@ static struct trace_event_functions uprobe_funcs = {
static int register_uprobe_event(struct trace_uprobe *tu)
{
- struct ftrace_event_call *call = &tu->call;
+ struct ftrace_event_call *call = &tu->tp.call;
int ret;
/* Initialize ftrace_event_call */
@@ -967,7 +1261,7 @@ static int register_uprobe_event(struct trace_uprobe *tu)
call->event.funcs = &uprobe_funcs;
call->class->define_fields = uprobe_event_define_fields;
- if (set_print_fmt(tu) < 0)
+ if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
return -ENOMEM;
ret = register_ftrace_event(&call->event);
@@ -994,11 +1288,11 @@ static int unregister_uprobe_event(struct trace_uprobe *tu)
int ret;
/* tu->event is unregistered in trace_remove_event_call() */
- ret = trace_remove_event_call(&tu->call);
+ ret = trace_remove_event_call(&tu->tp.call);
if (ret)
return ret;
- kfree(tu->call.print_fmt);
- tu->call.print_fmt = NULL;
+ kfree(tu->tp.call.print_fmt);
+ tu->tp.call.print_fmt = NULL;
return 0;
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f26540e9c9..fb0a38a26555 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -62,14 +62,12 @@ struct tracepoint_entry {
struct hlist_node hlist;
struct tracepoint_func *funcs;
int refcount; /* Number of times armed. 0 if disarmed. */
+ int enabled; /* Tracepoint enabled */
char name[0];
};
struct tp_probes {
- union {
- struct rcu_head rcu;
- struct list_head list;
- } u;
+ struct rcu_head rcu;
struct tracepoint_func probes[0];
};
@@ -82,7 +80,7 @@ static inline void *allocate_probes(int count)
static void rcu_free_old_probes(struct rcu_head *head)
{
- kfree(container_of(head, struct tp_probes, u.rcu));
+ kfree(container_of(head, struct tp_probes, rcu));
}
static inline void release_probes(struct tracepoint_func *old)
@@ -90,7 +88,7 @@ static inline void release_probes(struct tracepoint_func *old)
if (old) {
struct tp_probes *tp_probes = container_of(old,
struct tp_probes, probes[0]);
- call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes);
+ call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
}
}
@@ -237,6 +235,7 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
memcpy(&e->name[0], name, name_len);
e->funcs = NULL;
e->refcount = 0;
+ e->enabled = 0;
hlist_add_head(&e->hlist, head);
return e;
}
@@ -316,6 +315,7 @@ static void tracepoint_update_probe_range(struct tracepoint * const *begin,
if (mark_entry) {
set_tracepoint(&mark_entry, *iter,
!!mark_entry->refcount);
+ mark_entry->enabled = !!mark_entry->refcount;
} else {
disable_tracepoint(*iter);
}
@@ -373,13 +373,26 @@ tracepoint_add_probe(const char *name, void *probe, void *data)
* tracepoint_probe_register - Connect a probe to a tracepoint
* @name: tracepoint name
* @probe: probe handler
+ * @data: probe private data
+ *
+ * Returns:
+ * - 0 if the probe was successfully registered, and tracepoint
+ * callsites are currently loaded for that probe,
+ * - -ENODEV if the probe was successfully registered, but no tracepoint
+ * callsite is currently loaded for that probe,
+ * - other negative error value on error.
+ *
+ * When tracepoint_probe_register() returns either 0 or -ENODEV,
+ * parameters @name, @probe, and @data may be used by the tracepoint
+ * infrastructure until the probe is unregistered.
*
- * Returns 0 if ok, error value on error.
* The probe address must at least be aligned on the architecture pointer size.
*/
int tracepoint_probe_register(const char *name, void *probe, void *data)
{
struct tracepoint_func *old;
+ struct tracepoint_entry *entry;
+ int ret = 0;
mutex_lock(&tracepoints_mutex);
old = tracepoint_add_probe(name, probe, data);
@@ -388,9 +401,13 @@ int tracepoint_probe_register(const char *name, void *probe, void *data)
return PTR_ERR(old);
}
tracepoint_update_probes(); /* may update entry */
+ entry = get_tracepoint(name);
+ /* Make sure the entry was enabled */
+ if (!entry || !entry->enabled)
+ ret = -ENODEV;
mutex_unlock(&tracepoints_mutex);
release_probes(old);
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(tracepoint_probe_register);
@@ -415,6 +432,7 @@ tracepoint_remove_probe(const char *name, void *probe, void *data)
* tracepoint_probe_unregister - Disconnect a probe from a tracepoint
* @name: tracepoint name
* @probe: probe function pointer
+ * @data: probe private data
*
* We do not need to call a synchronize_sched to make sure the probes have
* finished running before doing a module unload, because the module unload
@@ -438,210 +456,28 @@ int tracepoint_probe_unregister(const char *name, void *probe, void *data)
}
EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
-static LIST_HEAD(old_probes);
-static int need_update;
-
-static void tracepoint_add_old_probes(void *old)
-{
- need_update = 1;
- if (old) {
- struct tp_probes *tp_probes = container_of(old,
- struct tp_probes, probes[0]);
- list_add(&tp_probes->u.list, &old_probes);
- }
-}
-
-/**
- * tracepoint_probe_register_noupdate - register a probe but not connect
- * @name: tracepoint name
- * @probe: probe handler
- *
- * caller must call tracepoint_probe_update_all()
- */
-int tracepoint_probe_register_noupdate(const char *name, void *probe,
- void *data)
-{
- struct tracepoint_func *old;
-
- mutex_lock(&tracepoints_mutex);
- old = tracepoint_add_probe(name, probe, data);
- if (IS_ERR(old)) {
- mutex_unlock(&tracepoints_mutex);
- return PTR_ERR(old);
- }
- tracepoint_add_old_probes(old);
- mutex_unlock(&tracepoints_mutex);
- return 0;
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
-
-/**
- * tracepoint_probe_unregister_noupdate - remove a probe but not disconnect
- * @name: tracepoint name
- * @probe: probe function pointer
- *
- * caller must call tracepoint_probe_update_all()
- */
-int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
- void *data)
-{
- struct tracepoint_func *old;
-
- mutex_lock(&tracepoints_mutex);
- old = tracepoint_remove_probe(name, probe, data);
- if (IS_ERR(old)) {
- mutex_unlock(&tracepoints_mutex);
- return PTR_ERR(old);
- }
- tracepoint_add_old_probes(old);
- mutex_unlock(&tracepoints_mutex);
- return 0;
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate);
-
-/**
- * tracepoint_probe_update_all - update tracepoints
- */
-void tracepoint_probe_update_all(void)
-{
- LIST_HEAD(release_probes);
- struct tp_probes *pos, *next;
-
- mutex_lock(&tracepoints_mutex);
- if (!need_update) {
- mutex_unlock(&tracepoints_mutex);
- return;
- }
- if (!list_empty(&old_probes))
- list_replace_init(&old_probes, &release_probes);
- need_update = 0;
- tracepoint_update_probes();
- mutex_unlock(&tracepoints_mutex);
- list_for_each_entry_safe(pos, next, &release_probes, u.list) {
- list_del(&pos->u.list);
- call_rcu_sched(&pos->u.rcu, rcu_free_old_probes);
- }
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
-
-/**
- * tracepoint_get_iter_range - Get a next tracepoint iterator given a range.
- * @tracepoint: current tracepoints (in), next tracepoint (out)
- * @begin: beginning of the range
- * @end: end of the range
- *
- * Returns whether a next tracepoint has been found (1) or not (0).
- * Will return the first tracepoint in the range if the input tracepoint is
- * NULL.
- */
-static int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
- struct tracepoint * const *begin, struct tracepoint * const *end)
-{
- if (!*tracepoint && begin != end) {
- *tracepoint = begin;
- return 1;
- }
- if (*tracepoint >= begin && *tracepoint < end)
- return 1;
- return 0;
-}
#ifdef CONFIG_MODULES
-static void tracepoint_get_iter(struct tracepoint_iter *iter)
+bool trace_module_has_bad_taint(struct module *mod)
{
- int found = 0;
- struct tp_module *iter_mod;
-
- /* Core kernel tracepoints */
- if (!iter->module) {
- found = tracepoint_get_iter_range(&iter->tracepoint,
- __start___tracepoints_ptrs,
- __stop___tracepoints_ptrs);
- if (found)
- goto end;
- }
- /* Tracepoints in modules */
- mutex_lock(&tracepoints_mutex);
- list_for_each_entry(iter_mod, &tracepoint_module_list, list) {
- /*
- * Sorted module list
- */
- if (iter_mod < iter->module)
- continue;
- else if (iter_mod > iter->module)
- iter->tracepoint = NULL;
- found = tracepoint_get_iter_range(&iter->tracepoint,
- iter_mod->tracepoints_ptrs,
- iter_mod->tracepoints_ptrs
- + iter_mod->num_tracepoints);
- if (found) {
- iter->module = iter_mod;
- break;
- }
- }
- mutex_unlock(&tracepoints_mutex);
-end:
- if (!found)
- tracepoint_iter_reset(iter);
+ return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
+ (1 << TAINT_UNSIGNED_MODULE));
}
-#else /* CONFIG_MODULES */
-static void tracepoint_get_iter(struct tracepoint_iter *iter)
-{
- int found = 0;
- /* Core kernel tracepoints */
- found = tracepoint_get_iter_range(&iter->tracepoint,
- __start___tracepoints_ptrs,
- __stop___tracepoints_ptrs);
- if (!found)
- tracepoint_iter_reset(iter);
-}
-#endif /* CONFIG_MODULES */
-
-void tracepoint_iter_start(struct tracepoint_iter *iter)
-{
- tracepoint_get_iter(iter);
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_start);
-
-void tracepoint_iter_next(struct tracepoint_iter *iter)
-{
- iter->tracepoint++;
- /*
- * iter->tracepoint may be invalid because we blindly incremented it.
- * Make sure it is valid by marshalling on the tracepoints, getting the
- * tracepoints from following modules if necessary.
- */
- tracepoint_get_iter(iter);
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_next);
-
-void tracepoint_iter_stop(struct tracepoint_iter *iter)
-{
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_stop);
-
-void tracepoint_iter_reset(struct tracepoint_iter *iter)
-{
-#ifdef CONFIG_MODULES
- iter->module = NULL;
-#endif /* CONFIG_MODULES */
- iter->tracepoint = NULL;
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
-
-#ifdef CONFIG_MODULES
static int tracepoint_module_coming(struct module *mod)
{
- struct tp_module *tp_mod, *iter;
+ struct tp_module *tp_mod;
int ret = 0;
+ if (!mod->num_tracepoints)
+ return 0;
+
/*
* We skip modules that taint the kernel, especially those with different
* module headers (for forced load), to make sure we don't cause a crash.
- * Staging and out-of-tree GPL modules are fine.
+ * Staging, out-of-tree, and unsigned GPL modules are fine.
*/
- if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+ if (trace_module_has_bad_taint(mod))
return 0;
mutex_lock(&tracepoints_mutex);
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
@@ -651,23 +487,7 @@ static int tracepoint_module_coming(struct module *mod)
}
tp_mod->num_tracepoints = mod->num_tracepoints;
tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs;
-
- /*
- * tracepoint_module_list is kept sorted by struct module pointer
- * address for iteration on tracepoints from a seq_file that can release
- * the mutex between calls.
- */
- list_for_each_entry_reverse(iter, &tracepoint_module_list, list) {
- BUG_ON(iter == tp_mod); /* Should never be in the list twice */
- if (iter < tp_mod) {
- /* We belong to the location right after iter. */
- list_add(&tp_mod->list, &iter->list);
- goto module_added;
- }
- }
- /* We belong to the beginning of the list */
- list_add(&tp_mod->list, &tracepoint_module_list);
-module_added:
+ list_add_tail(&tp_mod->list, &tracepoint_module_list);
tracepoint_update_probe_range(mod->tracepoints_ptrs,
mod->tracepoints_ptrs + mod->num_tracepoints);
end:
@@ -679,6 +499,9 @@ static int tracepoint_module_going(struct module *mod)
{
struct tp_module *pos;
+ if (!mod->num_tracepoints)
+ return 0;
+
mutex_lock(&tracepoints_mutex);
tracepoint_update_probe_range(mod->tracepoints_ptrs,
mod->tracepoints_ptrs + mod->num_tracepoints);
diff --git a/kernel/up.c b/kernel/up.c
index 509403e3fbc6..1760bf3d1463 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,16 +22,16 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
}
EXPORT_SYMBOL(smp_call_function_single);
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
- int wait)
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
{
unsigned long flags;
local_irq_save(flags);
csd->func(csd->info);
local_irq_restore(flags);
+ return 0;
}
-EXPORT_SYMBOL(__smp_call_function_single);
+EXPORT_SYMBOL(smp_call_function_single_async);
int on_each_cpu(smp_call_func_t func, void *info, int wait)
{
diff --git a/kernel/user.c b/kernel/user.c
index c006131beb77..294fc6a94168 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -222,5 +222,4 @@ static int __init uid_cache_init(void)
return 0;
}
-
-module_init(uid_cache_init);
+subsys_initcall(uid_cache_init);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 240fb62cf394..0d8f6023fd8d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -225,7 +225,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id)
*
* When there is no mapping defined for the user-namespace uid
* pair INVALID_UID is returned. Callers are expected to test
- * for and handle handle INVALID_UID being returned. INVALID_UID
+ * for and handle INVALID_UID being returned. INVALID_UID
* may be tested for using uid_valid().
*/
kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
@@ -902,4 +902,4 @@ static __init int user_namespaces_init(void)
user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
return 0;
}
-module_init(user_namespaces_init);
+subsys_initcall(user_namespaces_init);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4431610f049a..e90089fd78e0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -158,14 +158,14 @@ void touch_all_softlockup_watchdogs(void)
#ifdef CONFIG_HARDLOCKUP_DETECTOR
void touch_nmi_watchdog(void)
{
- if (watchdog_user_enabled) {
- unsigned cpu;
-
- for_each_present_cpu(cpu) {
- if (per_cpu(watchdog_nmi_touch, cpu) != true)
- per_cpu(watchdog_nmi_touch, cpu) = true;
- }
- }
+ /*
+ * Using __raw here because some code paths have
+ * preemption enabled. If preemption is enabled
+ * then interrupts should be enabled too, in which
+ * case we shouldn't have to worry about the watchdog
+ * going off.
+ */
+ __raw_get_cpu_var(watchdog_nmi_touch) = true;
touch_softlockup_watchdog();
}
EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -505,7 +505,6 @@ static void restart_watchdog_hrtimer(void *info)
static void update_timers(int cpu)
{
- struct call_single_data data = {.func = restart_watchdog_hrtimer};
/*
* Make sure that perf event counter will adopt to a new
* sampling period. Updating the sampling period directly would
@@ -515,7 +514,7 @@ static void update_timers(int cpu)
* might be late already so we have to restart the timer as well.
*/
watchdog_nmi_disable(cpu);
- __smp_call_function_single(cpu, &data, 1);
+ smp_call_function_single(cpu, restart_watchdog_hrtimer, NULL, 1);
watchdog_nmi_enable(cpu);
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b010eac595d2..0ee63af30bd1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -516,6 +516,13 @@ void destroy_work_on_stack(struct work_struct *work)
}
EXPORT_SYMBOL_GPL(destroy_work_on_stack);
+void destroy_delayed_work_on_stack(struct delayed_work *work)
+{
+ destroy_timer_on_stack(&work->timer);
+ debug_object_free(&work->work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack);
+
#else
static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
@@ -1851,6 +1858,12 @@ static void destroy_worker(struct worker *worker)
if (worker->flags & WORKER_IDLE)
pool->nr_idle--;
+ /*
+ * Once WORKER_DIE is set, the kworker may destroy itself at any
+ * point. Pin to ensure the task stays until we're done with it.
+ */
+ get_task_struct(worker->task);
+
list_del_init(&worker->entry);
worker->flags |= WORKER_DIE;
@@ -1859,6 +1872,7 @@ static void destroy_worker(struct worker *worker)
spin_unlock_irq(&pool->lock);
kthread_stop(worker->task);
+ put_task_struct(worker->task);
kfree(worker);
spin_lock_irq(&pool->lock);
@@ -3218,7 +3232,7 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
return -ENOMEM;
if (sscanf(buf, "%d", &attrs->nice) == 1 &&
- attrs->nice >= -20 && attrs->nice <= 19)
+ attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
ret = apply_workqueue_attrs(wq, attrs);
else
ret = -EINVAL;
@@ -4789,6 +4803,7 @@ static int workqueue_cpu_down_callback(struct notifier_block *nfb,
/* wait for per-cpu unbinding to finish */
flush_work(&unbind_work);
+ destroy_work_on_stack(&unbind_work);
break;
}
return NOTIFY_OK;
@@ -4828,6 +4843,7 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
schedule_work_on(cpu, &wfc.work);
flush_work(&wfc.work);
+ destroy_work_on_stack(&wfc.work);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);