summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c67
-rw-r--r--kernel/audit.h5
-rw-r--r--kernel/audit_tree.c9
-rw-r--r--kernel/audit_watch.c4
-rw-r--r--kernel/auditfilter.c12
-rw-r--r--kernel/auditsc.c16
-rw-r--r--kernel/cgroup.c141
-rw-r--r--kernel/cgroup_freezer.c72
-rw-r--r--kernel/cpu.c29
-rw-r--r--kernel/cpuset.c13
-rw-r--r--kernel/cred.c4
-rw-r--r--kernel/debug/debug_core.c153
-rw-r--r--kernel/debug/debug_core.h1
-rw-r--r--kernel/debug/kdb/kdb_debugger.c3
-rw-r--r--kernel/debug/kdb/kdb_io.c2
-rw-r--r--kernel/debug/kdb/kdb_main.c87
-rw-r--r--kernel/debug/kdb/kdb_private.h48
-rw-r--r--kernel/exit.c22
-rw-r--r--kernel/fork.c25
-rw-r--r--kernel/futex.c240
-rw-r--r--kernel/futex_compat.c3
-rw-r--r--kernel/hrtimer.c83
-rw-r--r--kernel/hw_breakpoint.c5
-rw-r--r--kernel/irq/irqdesc.c15
-rw-r--r--kernel/irq/manage.c8
-rw-r--r--kernel/irq/proc.c2
-rw-r--r--kernel/irq_work.c4
-rw-r--r--kernel/jump_label.c77
-rw-r--r--kernel/kexec.c2
-rw-r--r--kernel/kprobes.c598
-rw-r--r--kernel/kthread.c13
-rw-r--r--kernel/latencytop.c17
-rw-r--r--kernel/lockdep_proc.c16
-rw-r--r--kernel/module.c185
-rw-r--r--kernel/mutex.c2
-rw-r--r--kernel/ns_cgroup.c8
-rw-r--r--kernel/perf_event.c835
-rw-r--r--kernel/pm_qos_params.c6
-rw-r--r--kernel/posix-cpu-timers.c12
-rw-r--r--kernel/posix-timers.c10
-rw-r--r--kernel/power/Kconfig4
-rw-r--r--kernel/power/hibernate.c22
-rw-r--r--kernel/power/snapshot.c18
-rw-r--r--kernel/power/suspend.c8
-rw-r--r--kernel/power/swap.c61
-rw-r--r--kernel/power/user.c4
-rw-r--r--kernel/printk.c36
-rw-r--r--kernel/ptrace.c36
-rw-r--r--kernel/range.c2
-rw-r--r--kernel/rcutiny.c105
-rw-r--r--kernel/rcutiny_plugin.h433
-rw-r--r--kernel/rcutorture.c270
-rw-r--r--kernel/rcutree.c156
-rw-r--r--kernel/rcutree.h61
-rw-r--r--kernel/rcutree_plugin.h135
-rw-r--r--kernel/rcutree_trace.c12
-rw-r--r--kernel/relay.c15
-rw-r--r--kernel/resource.c61
-rw-r--r--kernel/sched.c972
-rw-r--r--kernel/sched_autogroup.c238
-rw-r--r--kernel/sched_autogroup.h32
-rw-r--r--kernel/sched_clock.c2
-rw-r--r--kernel/sched_debug.c91
-rw-r--r--kernel/sched_fair.c395
-rw-r--r--kernel/sched_features.h2
-rw-r--r--kernel/sched_rt.c24
-rw-r--r--kernel/sched_stats.h20
-rw-r--r--kernel/sched_stoptask.c4
-rw-r--r--kernel/signal.c5
-rw-r--r--kernel/smp.c8
-rw-r--r--kernel/softirq.c22
-rw-r--r--kernel/srcu.c8
-rw-r--r--kernel/stop_machine.c6
-rw-r--r--kernel/sys.c4
-rw-r--r--kernel/sysctl.c76
-rw-r--r--kernel/sysctl_binary.c1
-rw-r--r--kernel/taskstats.c205
-rw-r--r--kernel/time/timecompare.c5
-rw-r--r--kernel/time/timekeeping.c9
-rw-r--r--kernel/time/timer_list.c8
-rw-r--r--kernel/timer.c58
-rw-r--r--kernel/trace/Kconfig17
-rw-r--r--kernel/trace/blktrace.c4
-rw-r--r--kernel/trace/power-traces.c5
-rw-r--r--kernel/trace/ring_buffer.c344
-rw-r--r--kernel/trace/trace.c38
-rw-r--r--kernel/trace/trace_event_perf.c31
-rw-r--r--kernel/trace/trace_events.c6
-rw-r--r--kernel/trace/trace_export.c14
-rw-r--r--kernel/trace/trace_kdb.c1
-rw-r--r--kernel/trace/trace_kprobe.c3
-rw-r--r--kernel/trace/trace_selftest.c2
-rw-r--r--kernel/tsacct.c10
-rw-r--r--kernel/user.c2
-rw-r--r--kernel/wait.c6
-rw-r--r--kernel/watchdog.c16
-rw-r--r--kernel/workqueue.c323
97 files changed, 4831 insertions, 2479 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index d96045789b5..77770a034d5 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -467,23 +467,16 @@ static int audit_prepare_user_tty(pid_t pid, uid_t loginuid, u32 sessionid)
struct task_struct *tsk;
int err;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
tsk = find_task_by_vpid(pid);
- err = -ESRCH;
- if (!tsk)
- goto out;
- err = 0;
-
- spin_lock_irq(&tsk->sighand->siglock);
- if (!tsk->signal->audit_tty)
- err = -EPERM;
- spin_unlock_irq(&tsk->sighand->siglock);
- if (err)
- goto out;
-
- tty_audit_push_task(tsk, loginuid, sessionid);
-out:
- read_unlock(&tasklist_lock);
+ if (!tsk) {
+ rcu_read_unlock();
+ return -ESRCH;
+ }
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ err = tty_audit_push_task(tsk, loginuid, sessionid);
+ put_task_struct(tsk);
return err;
}
@@ -506,7 +499,7 @@ int audit_send_list(void *_dest)
}
struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
- int multi, void *payload, int size)
+ int multi, const void *payload, int size)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
@@ -555,8 +548,8 @@ static int audit_send_reply_thread(void *arg)
* Allocates an skb, builds the netlink message, and sends it to the pid.
* No failure notifications.
*/
-void audit_send_reply(int pid, int seq, int type, int done, int multi,
- void *payload, int size)
+static void audit_send_reply(int pid, int seq, int type, int done, int multi,
+ const void *payload, int size)
{
struct sk_buff *skb;
struct task_struct *tsk;
@@ -880,40 +873,40 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
case AUDIT_TTY_GET: {
struct audit_tty_status s;
struct task_struct *tsk;
+ unsigned long flags;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
tsk = find_task_by_vpid(pid);
- if (!tsk)
- err = -ESRCH;
- else {
- spin_lock_irq(&tsk->sighand->siglock);
+ if (tsk && lock_task_sighand(tsk, &flags)) {
s.enabled = tsk->signal->audit_tty != 0;
- spin_unlock_irq(&tsk->sighand->siglock);
- }
- read_unlock(&tasklist_lock);
- audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_TTY_GET, 0, 0,
- &s, sizeof(s));
+ unlock_task_sighand(tsk, &flags);
+ } else
+ err = -ESRCH;
+ rcu_read_unlock();
+
+ if (!err)
+ audit_send_reply(NETLINK_CB(skb).pid, seq,
+ AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_TTY_SET: {
struct audit_tty_status *s;
struct task_struct *tsk;
+ unsigned long flags;
if (nlh->nlmsg_len < sizeof(struct audit_tty_status))
return -EINVAL;
s = data;
if (s->enabled != 0 && s->enabled != 1)
return -EINVAL;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
tsk = find_task_by_vpid(pid);
- if (!tsk)
- err = -ESRCH;
- else {
- spin_lock_irq(&tsk->sighand->siglock);
+ if (tsk && lock_task_sighand(tsk, &flags)) {
tsk->signal->audit_tty = s->enabled != 0;
- spin_unlock_irq(&tsk->sighand->siglock);
- }
- read_unlock(&tasklist_lock);
+ unlock_task_sighand(tsk, &flags);
+ } else
+ err = -ESRCH;
+ rcu_read_unlock();
break;
}
default:
diff --git a/kernel/audit.h b/kernel/audit.h
index f7206db4e13..91e7071c4d2 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -84,10 +84,7 @@ extern int audit_compare_dname_path(const char *dname, const char *path,
int *dirlen);
extern struct sk_buff * audit_make_reply(int pid, int seq, int type,
int done, int multi,
- void *payload, int size);
-extern void audit_send_reply(int pid, int seq, int type,
- int done, int multi,
- void *payload, int size);
+ const void *payload, int size);
extern void audit_panic(const char *message);
struct audit_netlink_list {
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 7f18d3a4527..37b2bea170c 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -223,7 +223,7 @@ static void untag_chunk(struct node *p)
{
struct audit_chunk *chunk = find_chunk(p);
struct fsnotify_mark *entry = &chunk->mark;
- struct audit_chunk *new;
+ struct audit_chunk *new = NULL;
struct audit_tree *owner;
int size = chunk->count - 1;
int i, j;
@@ -232,9 +232,14 @@ static void untag_chunk(struct node *p)
spin_unlock(&hash_lock);
+ if (size)
+ new = alloc_chunk(size);
+
spin_lock(&entry->lock);
if (chunk->dead || !entry->i.inode) {
spin_unlock(&entry->lock);
+ if (new)
+ free_chunk(new);
goto out;
}
@@ -255,9 +260,9 @@ static void untag_chunk(struct node *p)
goto out;
}
- new = alloc_chunk(size);
if (!new)
goto Fallback;
+
fsnotify_duplicate_mark(&new->mark, entry);
if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) {
free_chunk(new);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index f0c9b2e7542..d2e3c786646 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -60,7 +60,7 @@ struct audit_parent {
};
/* fsnotify handle. */
-struct fsnotify_group *audit_watch_group;
+static struct fsnotify_group *audit_watch_group;
/* fsnotify events we care about. */
#define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
@@ -123,7 +123,7 @@ void audit_put_watch(struct audit_watch *watch)
}
}
-void audit_remove_watch(struct audit_watch *watch)
+static void audit_remove_watch(struct audit_watch *watch)
{
list_del(&watch->wlist);
audit_put_parent(watch->parent);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index eb7675499fb..add2819af71 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1252,6 +1252,18 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
case AUDIT_LOGINUID:
result = audit_comparator(cb->loginuid, f->op, f->val);
break;
+ case AUDIT_SUBJ_USER:
+ case AUDIT_SUBJ_ROLE:
+ case AUDIT_SUBJ_TYPE:
+ case AUDIT_SUBJ_SEN:
+ case AUDIT_SUBJ_CLR:
+ if (f->lsm_rule)
+ result = security_audit_rule_match(cb->sid,
+ f->type,
+ f->op,
+ f->lsm_rule,
+ NULL);
+ break;
}
if (!result)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 1b31c130d03..f49a0318c2e 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -241,6 +241,10 @@ struct audit_context {
pid_t pid;
struct audit_cap_data cap;
} capset;
+ struct {
+ int fd;
+ int flags;
+ } mmap;
};
int fds[2];
@@ -1305,6 +1309,10 @@ static void show_special(struct audit_context *context, int *call_panic)
audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted);
audit_log_cap(ab, "cap_pe", &context->capset.cap.effective);
break; }
+ case AUDIT_MMAP: {
+ audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
+ context->mmap.flags);
+ break; }
}
audit_log_end(ab);
}
@@ -2476,6 +2484,14 @@ void __audit_log_capset(pid_t pid,
context->type = AUDIT_CAPSET;
}
+void __audit_mmap_fd(int fd, int flags)
+{
+ struct audit_context *context = current->audit_context;
+ context->mmap.fd = fd;
+ context->mmap.flags = flags;
+ context->type = AUDIT_MMAP;
+}
+
/**
* audit_core_dumps - record information about processes that end abnormally
* @signr: signal value
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7b69b8d0313..66a416b42c1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -243,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp)
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}
+static int clone_children(const struct cgroup *cgrp)
+{
+ return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
/*
* for_each_subsys() allows you to iterate on each subsystem attached to
* an active hierarchy
@@ -777,6 +782,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
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();
@@ -1039,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",noprefix");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+ if (clone_children(&root->top_cgroup))
+ seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
mutex_unlock(&cgroup_mutex);
@@ -1049,6 +1057,7 @@ struct cgroup_sb_opts {
unsigned long subsys_bits;
unsigned long flags;
char *release_agent;
+ bool clone_children;
char *name;
/* User explicitly requested empty subsystem */
bool none;
@@ -1065,7 +1074,8 @@ struct cgroup_sb_opts {
*/
static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
{
- char *token, *o = data ?: "all";
+ char *token, *o = data;
+ bool all_ss = false, one_ss = false;
unsigned long mask = (unsigned long)-1;
int i;
bool module_pin_failed = false;
@@ -1081,22 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
while ((token = strsep(&o, ",")) != NULL) {
if (!*token)
return -EINVAL;
- if (!strcmp(token, "all")) {
- /* Add all non-disabled subsystems */
- opts->subsys_bits = 0;
- for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- struct cgroup_subsys *ss = subsys[i];
- if (ss == NULL)
- continue;
- if (!ss->disabled)
- opts->subsys_bits |= 1ul << i;
- }
- } else if (!strcmp(token, "none")) {
+ if (!strcmp(token, "none")) {
/* Explicitly have no subsystems */
opts->none = true;
- } else if (!strcmp(token, "noprefix")) {
+ continue;
+ }
+ if (!strcmp(token, "all")) {
+ /* Mutually exclusive option 'all' + subsystem name */
+ if (one_ss)
+ return -EINVAL;
+ all_ss = true;
+ continue;
+ }
+ if (!strcmp(token, "noprefix")) {
set_bit(ROOT_NOPREFIX, &opts->flags);
- } else if (!strncmp(token, "release_agent=", 14)) {
+ continue;
+ }
+ if (!strcmp(token, "clone_children")) {
+ opts->clone_children = true;
+ continue;
+ }
+ if (!strncmp(token, "release_agent=", 14)) {
/* Specifying two release agents is forbidden */
if (opts->release_agent)
return -EINVAL;
@@ -1104,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
if (!opts->release_agent)
return -ENOMEM;
- } else if (!strncmp(token, "name=", 5)) {
+ continue;
+ }
+ if (!strncmp(token, "name=", 5)) {
const char *name = token + 5;
/* Can't specify an empty name */
if (!strlen(name))
@@ -1126,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
GFP_KERNEL);
if (!opts->name)
return -ENOMEM;
- } else {
- struct cgroup_subsys *ss;
- for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
- ss = subsys[i];
- if (ss == NULL)
- continue;
- if (!strcmp(token, ss->name)) {
- if (!ss->disabled)
- set_bit(i, &opts->subsys_bits);
- break;
- }
- }
- if (i == CGROUP_SUBSYS_COUNT)
- return -ENOENT;
+
+ continue;
+ }
+
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss == NULL)
+ continue;
+ if (strcmp(token, ss->name))
+ continue;
+ if (ss->disabled)
+ continue;
+
+ /* Mutually exclusive option 'all' + subsystem name */
+ if (all_ss)
+ return -EINVAL;
+ set_bit(i, &opts->subsys_bits);
+ one_ss = true;
+
+ break;
+ }
+ if (i == CGROUP_SUBSYS_COUNT)
+ return -ENOENT;
+ }
+
+ /*
+ * If the 'all' option was specified select all the subsystems,
+ * otherwise 'all, 'none' and a subsystem name options were not
+ * specified, let's default to 'all'
+ */
+ if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss == NULL)
+ continue;
+ if (ss->disabled)
+ continue;
+ set_bit(i, &opts->subsys_bits);
}
}
@@ -1354,6 +1395,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
strcpy(root->release_agent_path, opts->release_agent);
if (opts->name)
strcpy(root->name, opts->name);
+ if (opts->clone_children)
+ set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
return root;
}
@@ -1417,9 +1460,9 @@ static int cgroup_get_rootdir(struct super_block *sb)
return 0;
}
-static int cgroup_get_sb(struct file_system_type *fs_type,
+static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
- void *data, struct vfsmount *mnt)
+ void *data)
{
struct cgroup_sb_opts opts;
struct cgroupfs_root *root;
@@ -1553,10 +1596,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
drop_parsed_module_refcounts(opts.subsys_bits);
}
- simple_set_mnt(mnt, sb);
kfree(opts.release_agent);
kfree(opts.name);
- return 0;
+ return dget(sb->s_root);
drop_new_super:
deactivate_locked_super(sb);
@@ -1565,7 +1607,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
out_err:
kfree(opts.release_agent);
kfree(opts.name);
- return ret;
+ return ERR_PTR(ret);
}
static void cgroup_kill_sb(struct super_block *sb) {
@@ -1615,7 +1657,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
static struct file_system_type cgroup_fs_type = {
.name = "cgroup",
- .get_sb = cgroup_get_sb,
+ .mount = cgroup_mount,
.kill_sb = cgroup_kill_sb,
};
@@ -1879,6 +1921,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
const char *buffer)
{
BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+ if (strlen(buffer) >= PATH_MAX)
+ return -EINVAL;
if (!cgroup_lock_live_group(cgrp))
return -ENODEV;
strcpy(cgrp->root->release_agent_path, buffer);
@@ -3172,6 +3216,23 @@ fail:
return ret;
}
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+ struct cftype *cft)
+{
+ return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+ struct cftype *cft,
+ u64 val)
+{
+ if (val)
+ set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+ else
+ clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+ return 0;
+}
+
/*
* for the common functions, 'private' gives the type of file
*/
@@ -3202,6 +3263,11 @@ static struct cftype files[] = {
.write_string = cgroup_write_event_control,
.mode = S_IWUGO,
},
+ {
+ .name = "cgroup.clone_children",
+ .read_u64 = cgroup_clone_children_read,
+ .write_u64 = cgroup_clone_children_write,
+ },
};
static struct cftype cft_release_agent = {
@@ -3331,6 +3397,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
if (notify_on_release(parent))
set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+ if (clone_children(parent))
+ set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
for_each_subsys(root, ss) {
struct cgroup_subsys_state *css = ss->create(ss, cgrp);
@@ -3345,6 +3414,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
goto err_destroy;
}
/* At error, ->destroy() callback has to free assigned ID. */
+ if (clone_children(parent) && ss->post_clone)
+ ss->post_clone(ss, cgrp);
}
cgroup_lock_hierarchy(root);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ce71ed53e88..e7bebb7c6c3 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -48,20 +48,19 @@ static inline struct freezer *task_freezer(struct task_struct *task)
struct freezer, css);
}
-int cgroup_freezing_or_frozen(struct task_struct *task)
+static inline int __cgroup_freezing_or_frozen(struct task_struct *task)
{
- struct freezer *freezer;
- enum freezer_state state;
+ enum freezer_state state = task_freezer(task)->state;
+ return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+}
+int cgroup_freezing_or_frozen(struct task_struct *task)
+{
+ int result;
task_lock(task);
- freezer = task_freezer(task);
- if (!freezer->css.cgroup->parent)
- state = CGROUP_THAWED; /* root cgroup can't be frozen */
- else
- state = freezer->state;
+ result = __cgroup_freezing_or_frozen(task);
task_unlock(task);
-
- return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+ return result;
}
/*
@@ -154,13 +153,6 @@ static void freezer_destroy(struct cgroup_subsys *ss,
kfree(cgroup_freezer(cgroup));
}
-/* Task is frozen or will freeze immediately when next it gets woken */
-static bool is_task_frozen_enough(struct task_struct *task)
-{
- return frozen(task) ||
- (task_is_stopped_or_traced(task) && freezing(task));
-}
-
/*
* The call to cgroup_lock() in the freezer.state write method prevents
* a write to that file racing against an attach, and hence the
@@ -174,24 +166,25 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
/*
* Anything frozen can't move or be moved to/from.
- *
- * Since orig_freezer->state == FROZEN means that @task has been
- * frozen, so it's sufficient to check the latter condition.
*/
- if (is_task_frozen_enough(task))
+ freezer = cgroup_freezer(new_cgroup);
+ if (freezer->state != CGROUP_THAWED)
return -EBUSY;
- freezer = cgroup_freezer(new_cgroup);
- if (freezer->state == CGROUP_FROZEN)
+ rcu_read_lock();
+ if (__cgroup_freezing_or_frozen(task)) {
+ rcu_read_unlock();
return -EBUSY;
+ }
+ rcu_read_unlock();
if (threadgroup) {
struct task_struct *c;
rcu_read_lock();
list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
- if (is_task_frozen_enough(c)) {
+ if (__cgroup_freezing_or_frozen(c)) {
rcu_read_unlock();
return -EBUSY;
}
@@ -236,31 +229,30 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
/*
* caller must hold freezer->lock
*/
-static void update_freezer_state(struct cgroup *cgroup,
+static void update_if_frozen(struct cgroup *cgroup,
struct freezer *freezer)
{
struct cgroup_iter it;
struct task_struct *task;
unsigned int nfrozen = 0, ntotal = 0;
+ enum freezer_state old_state = freezer->state;
cgroup_iter_start(cgroup, &it);
while ((task = cgroup_iter_next(cgroup, &it))) {
ntotal++;
- if (is_task_frozen_enough(task))
+ if (frozen(task))
nfrozen++;
}
- /*
- * Transition to FROZEN when no new tasks can be added ensures
- * that we never exist in the FROZEN state while there are unfrozen
- * tasks.
- */
- if (nfrozen == ntotal)
- freezer->state = CGROUP_FROZEN;
- else if (nfrozen > 0)
- freezer->state = CGROUP_FREEZING;
- else
- freezer->state = CGROUP_THAWED;
+ if (old_state == CGROUP_THAWED) {
+ BUG_ON(nfrozen > 0);
+ } else if (old_state == CGROUP_FREEZING) {
+ if (nfrozen == ntotal)
+ freezer->state = CGROUP_FROZEN;
+ } else { /* old_state == CGROUP_FROZEN */
+ BUG_ON(nfrozen != ntotal);
+ }
+
cgroup_iter_end(cgroup, &it);
}
@@ -279,7 +271,7 @@ static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
if (state == CGROUP_FREEZING) {
/* We change from FREEZING to FROZEN lazily if the cgroup was
* only partially frozen when we exitted write. */
- update_freezer_state(cgroup, freezer);
+ update_if_frozen(cgroup, freezer);
state = freezer->state;
}
spin_unlock_irq(&freezer->lock);
@@ -301,7 +293,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
while ((task = cgroup_iter_next(cgroup, &it))) {
if (!freeze_task(task, true))
continue;
- if (is_task_frozen_enough(task))
+ if (frozen(task))
continue;
if (!freezing(task) && !freezer_should_skip(task))
num_cant_freeze_now++;
@@ -335,7 +327,7 @@ static int freezer_change_state(struct cgroup *cgroup,
spin_lock_irq(&freezer->lock);
- update_freezer_state(cgroup, freezer);
+ update_if_frozen(cgroup, freezer);
if (goal_state == freezer->state)
goto out;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f6e726f1849..156cc555614 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -189,7 +189,6 @@ static inline void check_for_tasks(int cpu)
}
struct take_cpu_down_param {
- struct task_struct *caller;
unsigned long mod;
void *hcpu;
};
@@ -198,7 +197,6 @@ struct take_cpu_down_param {
static int __ref take_cpu_down(void *_param)
{
struct take_cpu_down_param *param = _param;
- unsigned int cpu = (unsigned long)param->hcpu;
int err;
/* Ensure this CPU doesn't handle any more interrupts. */
@@ -208,11 +206,6 @@ static int __ref take_cpu_down(void *_param)
cpu_notify(CPU_DYING | param->mod, param->hcpu);
- if (task_cpu(param->caller) == cpu)
- move_task_off_dead_cpu(cpu, param->caller);
- /* Force idle task to run as soon as we yield: it should
- immediately notice cpu is offline and die quickly. */
- sched_idle_next();
return 0;
}
@@ -223,7 +216,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
void *hcpu = (void *)(long)cpu;
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
struct take_cpu_down_param tcd_param = {
- .caller = current,
.mod = mod,
.hcpu = hcpu,
};
@@ -253,9 +245,15 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
}
BUG_ON(cpu_online(cpu));
- /* Wait for it to sleep (leaving idle task). */
+ /*
+ * The migration_call() CPU_DYING callback will have removed all
+ * runnable tasks from the cpu, there's only the idle task left now
+ * that the migration thread is done doing the stop_machine thing.
+ *
+ * Wait for the stop thread to go away.
+ */
while (!idle_cpu(cpu))
- yield();
+ cpu_relax();
/* This actually kills the CPU. */
__cpu_die(cpu);
@@ -386,6 +384,14 @@ out:
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
+void __weak arch_disable_nonboot_cpus_begin(void)
+{
+}
+
+void __weak arch_disable_nonboot_cpus_end(void)
+{
+}
+
int disable_nonboot_cpus(void)
{
int cpu, first_cpu, error = 0;
@@ -397,6 +403,7 @@ int disable_nonboot_cpus(void)
* with the userspace trying to use the CPU hotplug at the same time
*/
cpumask_clear(frozen_cpus);
+ arch_disable_nonboot_cpus_begin();
printk("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
@@ -412,6 +419,8 @@ int disable_nonboot_cpus(void)
}
}
+ arch_disable_nonboot_cpus_end();
+
if (!error) {
BUG_ON(num_online_cpus() > 1);
/* Make sure the CPUs won't be enabled by someone else */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 51b143e2a07..4349935c2ad 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -231,18 +231,17 @@ static DEFINE_SPINLOCK(cpuset_buffer_lock);
* users. If someone tries to mount the "cpuset" filesystem, we
* silently switch it to mount "cgroup" instead
*/
-static int cpuset_get_sb(struct file_system_type *fs_type,
- int flags, const char *unused_dev_name,
- void *data, struct vfsmount *mnt)
+static struct dentry *cpuset_mount(struct file_system_type *fs_type,
+ int flags, const char *unused_dev_name, void *data)
{
struct file_system_type *cgroup_fs = get_fs_type("cgroup");
- int ret = -ENODEV;
+ struct dentry *ret = ERR_PTR(-ENODEV);
if (cgroup_fs) {
char mountopts[] =
"cpuset,noprefix,"
"release_agent=/sbin/cpuset_release_agent";
- ret = cgroup_fs->get_sb(cgroup_fs, flags,
- unused_dev_name, mountopts, mnt);
+ ret = cgroup_fs->mount(cgroup_fs, flags,
+ unused_dev_name, mountopts);
put_filesystem(cgroup_fs);
}
return ret;
@@ -250,7 +249,7 @@ static int cpuset_get_sb(struct file_system_type *fs_type,
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
- .get_sb = cpuset_get_sb,
+ .mount = cpuset_mount,
};
/*
diff --git a/kernel/cred.c b/kernel/cred.c
index 9a3e22641fe..6a1aa004e37 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -325,7 +325,7 @@ EXPORT_SYMBOL(prepare_creds);
/*
* Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_guard_mutex
+ * - The caller must hold ->cred_guard_mutex
*/
struct cred *prepare_exec_creds(void)
{
@@ -384,8 +384,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
struct cred *new;
int ret;
- mutex_init(&p->cred_guard_mutex);
-
if (
#ifdef CONFIG_KEYS
!p->cred->thread_keyring &&
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index de407c78178..cefd4a11f6d 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -47,6 +47,7 @@
#include <linux/pid.h>
#include <linux/smp.h>
#include <linux/mm.h>
+#include <linux/rcupdate.h>
#include <asm/cacheflush.h>
#include <asm/byteorder.h>
@@ -109,13 +110,15 @@ static struct kgdb_bkpt kgdb_break[KGDB_MAX_BREAKPOINTS] = {
*/
atomic_t kgdb_active = ATOMIC_INIT(-1);
EXPORT_SYMBOL_GPL(kgdb_active);
+static DEFINE_RAW_SPINLOCK(dbg_master_lock);
+static DEFINE_RAW_SPINLOCK(dbg_slave_lock);
/*
* We use NR_CPUs not PERCPU, in case kgdb is used to debug early
* bootup code (which might not have percpu set up yet):
*/
-static atomic_t passive_cpu_wait[NR_CPUS];
-static atomic_t cpu_in_kgdb[NR_CPUS];
+static atomic_t masters_in_kgdb;
+static atomic_t slaves_in_kgdb;
static atomic_t kgdb_break_tasklet_var;
atomic_t kgdb_setting_breakpoint;
@@ -206,18 +209,6 @@ int __weak kgdb_skipexception(int exception, struct pt_regs *regs)
return 0;
}
-/**
- * kgdb_disable_hw_debug - Disable hardware debugging while we in kgdb.
- * @regs: Current &struct pt_regs.
- *
- * This function will be called if the particular architecture must
- * disable hardware debugging while it is processing gdb packets or
- * handling exception.
- */
-void __weak kgdb_disable_hw_debug(struct pt_regs *regs)
-{
-}
-
/*
* Some architectures need cache flushes when we set/clear a
* breakpoint:
@@ -457,26 +448,34 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
return 1;
}
-static void dbg_cpu_switch(int cpu, int next_cpu)
+static void dbg_touch_watchdogs(void)
{
- /* Mark the cpu we are switching away from as a slave when it
- * holds the kgdb_active token. This must be done so that the
- * that all the cpus wait in for the debug core will not enter
- * again as the master. */
- if (cpu == atomic_read(&kgdb_active)) {
- kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
- kgdb_info[cpu].exception_state &= ~DCPU_WANT_MASTER;
- }
- kgdb_info[next_cpu].exception_state |= DCPU_NEXT_MASTER;
+ touch_softlockup_watchdog_sync();
+ clocksource_touch_watchdog();
+ rcu_cpu_stall_reset();
}
-static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
+ int exception_state)
{
unsigned long flags;
int sstep_tries = 100;
int error;
- int i, cpu;
+ int cpu;
int trace_on = 0;
+ int online_cpus = num_online_cpus();
+
+ kgdb_info[ks->cpu].enter_kgdb++;
+ kgdb_info[ks->cpu].exception_state |= exception_state;
+
+ if (exception_state == DCPU_WANT_MASTER)
+ atomic_inc(&masters_in_kgdb);
+ else
+ atomic_inc(&slaves_in_kgdb);
+
+ if (arch_kgdb_ops.disable_hw_break)
+ arch_kgdb_ops.disable_hw_break(regs);
+
acquirelock:
/*
* Interrupts will be restored by the 'trap return' code, except when
@@ -489,14 +488,15 @@ acquirelock:
kgdb_info[cpu].task = current;
kgdb_info[cpu].ret_state = 0;
kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT;
- /*
- * Make sure the above info reaches the primary CPU before
- * our cpu_in_kgdb[] flag setting does:
- */
- atomic_inc(&cpu_in_kgdb[cpu]);
- if (exception_level == 1)
+ /* Make sure the above info reaches the primary CPU */
+ smp_mb();
+
+ if (exception_level == 1) {
+ if (raw_spin_trylock(&dbg_master_lock))
+ atomic_xchg(&kgdb_active, cpu);
goto cpu_master_loop;
+ }
/*
* CPU will loop if it is a slave or request to become a kgdb
@@ -508,10 +508,12 @@ cpu_loop:
kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER;
goto cpu_master_loop;
} else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
- if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+ if (raw_spin_trylock(&dbg_master_lock)) {
+ atomic_xchg(&kgdb_active, cpu);
break;
+ }
} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
- if (!atomic_read(&passive_cpu_wait[cpu]))
+ if (!raw_spin_is_locked(&dbg_slave_lock))
goto return_normal;
} else {
return_normal:
@@ -522,9 +524,12 @@ return_normal:
arch_kgdb_ops.correct_hw_break();
if (trace_on)
tracing_on();
- atomic_dec(&cpu_in_kgdb[cpu]);
- touch_softlockup_watchdog_sync();
- clocksource_touch_watchdog();
+ kgdb_info[cpu].exception_state &=
+ ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
+ kgdb_info[cpu].enter_kgdb--;
+ smp_mb__before_atomic_dec();
+ atomic_dec(&slaves_in_kgdb);
+ dbg_touch_watchdogs();
local_irq_restore(flags);
return 0;
}
@@ -541,8 +546,8 @@ return_normal:
(kgdb_info[cpu].task &&
kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
atomic_set(&kgdb_active, -1);
- touch_softlockup_watchdog_sync();
- clocksource_touch_watchdog();
+ raw_spin_unlock(&dbg_master_lock);
+ dbg_touch_watchdogs();
local_irq_restore(flags);
goto acquirelock;
@@ -563,16 +568,12 @@ return_normal:
if (dbg_io_ops->pre_exception)
dbg_io_ops->pre_exception();
- kgdb_disable_hw_debug(ks->linux_regs);
-
/*
* Get the passive CPU lock which will hold all the non-primary
* CPU in a spin state while the debugger is active
*/
- if (!kgdb_single_step) {
- for (i = 0; i < NR_CPUS; i++)
- atomic_inc(&passive_cpu_wait[i]);
- }
+ if (!kgdb_single_step)
+ raw_spin_lock(&dbg_slave_lock);
#ifdef CONFIG_SMP
/* Signal the other CPUs to enter kgdb_wait() */
@@ -583,10 +584,9 @@ return_normal:
/*
* Wait for the other CPUs to be notified and be waiting for us:
*/
- for_each_online_cpu(i) {
- while (kgdb_do_roundup && !atomic_read(&cpu_in_kgdb[i]))
- cpu_relax();
- }
+ while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
+ atomic_read(&slaves_in_kgdb)) != online_cpus)
+ cpu_relax();
/*
* At this point the primary processor is completely
@@ -615,7 +615,8 @@ cpu_master_loop:
if (error == DBG_PASS_EVENT) {
dbg_kdb_mode = !dbg_kdb_mode;
} else if (error == DBG_SWITCH_CPU_EVENT) {
- dbg_cpu_switch(cpu, dbg_switch_cpu);
+ kgdb_info[dbg_switch_cpu].exception_state |=
+ DCPU_NEXT_MASTER;
goto cpu_loop;
} else {
kgdb_info[cpu].ret_state = error;
@@ -627,24 +628,11 @@ cpu_master_loop:
if (dbg_io_ops->post_exception)
dbg_io_ops->post_exception();
- atomic_dec(&cpu_in_kgdb[ks->cpu]);
-
if (!kgdb_single_step) {
- for (i = NR_CPUS-1; i >= 0; i--)
- atomic_dec(&passive_cpu_wait[i]);
- /*
- * Wait till all the CPUs have quit from the debugger,
- * but allow a CPU that hit an exception and is
- * waiting to become the master to remain in the debug
- * core.
- */
- for_each_online_cpu(i) {
- while (kgdb_do_roundup &&
- atomic_read(&cpu_in_kgdb[i]) &&
- !(kgdb_info[i].exception_state &
- DCPU_WANT_MASTER))
- cpu_relax();
- }
+ raw_spin_unlock(&dbg_slave_lock);
+ /* Wait till all the CPUs have quit from the debugger. */
+ while (kgdb_do_roundup && atomic_read(&slaves_in_kgdb))
+ cpu_relax();
}
kgdb_restore:
@@ -655,12 +643,20 @@ kgdb_restore:
else
kgdb_sstep_pid = 0;
}
+ if (arch_kgdb_ops.correct_hw_break)
+ arch_kgdb_ops.correct_hw_break();
if (trace_on)
tracing_on();
+
+ kgdb_info[cpu].exception_state &=
+ ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
+ kgdb_info[cpu].enter_kgdb--;
+ smp_mb__before_atomic_dec();
+ atomic_dec(&masters_in_kgdb);
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
- touch_softlockup_watchdog_sync();
- clocksource_touch_watchdog();
+ raw_spin_unlock(&dbg_master_lock);
+ dbg_touch_watchdogs();
local_irq_restore(flags);
return kgdb_info[cpu].ret_state;
@@ -678,7 +674,6 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
{
struct kgdb_state kgdb_var;
struct kgdb_state *ks = &kgdb_var;
- int ret;
ks->cpu = raw_smp_processor_id();
ks->ex_vector = evector;
@@ -689,11 +684,10 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
if (kgdb_reenter_check(ks))
return 0; /* Ouch, double exception ! */
- kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
- ret = kgdb_cpu_enter(ks, regs);
- kgdb_info[ks->cpu].exception_state &= ~(DCPU_WANT_MASTER |
- DCPU_IS_SLAVE);
- return ret;
+ if (kgdb_info[ks->cpu].enter_kgdb != 0)
+ return 0;
+
+ return kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
}
int kgdb_nmicallback(int cpu, void *regs)
@@ -706,12 +700,9 @@ int kgdb_nmicallback(int cpu, void *regs)
ks->cpu = cpu;
ks->linux_regs = regs;
- if (!atomic_read(&cpu_in_kgdb[cpu]) &&
- atomic_read(&kgdb_active) != -1 &&
- atomic_read(&kgdb_active) != cpu) {
- kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
- kgdb_cpu_enter(ks, regs);
- kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
+ if (kgdb_info[ks->cpu].enter_kgdb == 0 &&
+ raw_spin_is_locked(&dbg_master_lock)) {
+ kgdb_cpu_enter(ks, regs, DCPU_IS_SLAVE);
return 0;
}
#endif
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index c5d753d80f6..3494c28a7e7 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -40,6 +40,7 @@ struct debuggerinfo_struct {
int exception_state;
int ret_state;
int irq_depth;
+ int enter_kgdb;
};
extern struct debuggerinfo_struct kgdb_info[];
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index bf6e8270e95..dd0b1b7dd02 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -86,7 +86,7 @@ int kdb_stub(struct kgdb_state *ks)
}
/* Set initial kdb state variables */
KDB_STATE_CLEAR(KGDB_TRANS);
- kdb_initial_cpu = ks->cpu;
+ kdb_initial_cpu = atomic_read(&kgdb_active);
kdb_current_task = kgdb_info[ks->cpu].task;
kdb_current_regs = kgdb_info[ks->cpu].debuggerinfo;
/* Remove any breakpoints as needed by kdb and clear single step */
@@ -105,7 +105,6 @@ int kdb_stub(struct kgdb_state *ks)
ks->pass_exception = 1;
KDB_FLAG_SET(CATASTROPHIC);
}
- kdb_initial_cpu = ks->cpu;
if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
KDB_STATE_CLEAR(SSBPT);
KDB_STATE_CLEAR(DOING_SS);
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index c9b7f4f90bb..96fdaac46a8 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -823,4 +823,4 @@ int kdb_printf(const char *fmt, ...)
return r;
}
-
+EXPORT_SYMBOL_GPL(kdb_printf);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index caf057a3de0..a6e72976682 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -82,7 +82,7 @@ static kdbtab_t kdb_base_commands[50];
#define for_each_kdbcmd(cmd, num) \
for ((cmd) = kdb_base_commands, (num) = 0; \
num < kdb_max_commands; \
- num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++, num++)
+ num++, num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++)
typedef struct _kdbmsg {
int km_diag; /* kdb diagnostic */
@@ -646,7 +646,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
}
if (!s->usable)
return KDB_NOTIMP;
- s->command = kmalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
+ s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
if (!s->command) {
kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
cmdstr);
@@ -1127,7 +1127,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
/* special case below */
} else {
kdb_printf("\nEntering kdb (current=0x%p, pid %d) ",
- kdb_current, kdb_current->pid);
+ kdb_current, kdb_current ? kdb_current->pid : 0);
#if defined(CONFIG_SMP)
kdb_printf("on processor %d ", raw_smp_processor_id());
#endif
@@ -1749,13 +1749,13 @@ static int kdb_go(int argc, const char **argv)
int nextarg;
long offset;
+ if (raw_smp_processor_id() != kdb_initial_cpu) {
+ kdb_printf("go must execute on the entry cpu, "
+ "please use \"cpu %d\" and then execute go\n",
+ kdb_initial_cpu);
+ return KDB_BADCPUNUM;
+ }
if (argc == 1) {
- if (raw_smp_processor_id() != kdb_initial_cpu) {
- kdb_printf("go <address> must be issued from the "
- "initial cpu, do cpu %d first\n",
- kdb_initial_cpu);
- return KDB_ARGCOUNT;
- }
nextarg = 1;
diag = kdbgetaddrarg(argc, argv, &nextarg,
&addr, &offset, NULL);
@@ -2361,7 +2361,7 @@ static int kdb_pid(int argc, const char **argv)
*/
static int kdb_ll(int argc, const char **argv)
{
- int diag;
+ int diag = 0;
unsigned long addr;
long offset = 0;
unsigned long va;
@@ -2400,20 +2400,21 @@ static int kdb_ll(int argc, const char **argv)
char buf[80];
if (KDB_FLAG(CMD_INTERRUPT))
- return 0;
+ goto out;
sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
diag = kdb_parse(buf);
if (diag)
- return diag;
+ goto out;
addr = va + linkoffset;
if (kdb_getword(&va, addr, sizeof(va)))
- return 0;
+ goto out;
}
- kfree(command);
- return 0;
+out:
+ kfree(command);
+ return diag;
}
static int kdb_kgdb(int argc, const char **argv)
@@ -2603,20 +2604,17 @@ static int kdb_summary(int argc, const char **argv)
*/
static int kdb_per_cpu(int argc, const char **argv)
{
- char buf[256], fmtstr[64];
- kdb_symtab_t symtab;
- cpumask_t suppress = CPU_MASK_NONE;
- int cpu, diag;
- unsigned long addr, val, bytesperword = 0, whichcpu = ~0UL;
+ char fmtstr[64];
+ int cpu, diag, nextarg = 1;
+ unsigned long addr, symaddr, val, bytesperword = 0, whichcpu = ~0UL;
if (argc < 1 || argc > 3)
return KDB_ARGCOUNT;
- snprintf(buf, sizeof(buf), "per_cpu__%s", argv[1]);
- if (!kdbgetsymval(buf, &symtab)) {
- kdb_printf("%s is not a per_cpu variable\n", argv[1]);
- return KDB_BADADDR;
- }
+ diag = kdbgetaddrarg(argc, argv, &nextarg, &symaddr, NULL, NULL);
+ if (diag)
+ return diag;
+
if (argc >= 2) {
diag = kdbgetularg(argv[2], &bytesperword);
if (diag)
@@ -2649,46 +2647,25 @@ static int kdb_per_cpu(int argc, const char **argv)
#define KDB_PCU(cpu) 0
#endif
#endif
-
for_each_online_cpu(cpu) {
+ if (KDB_FLAG(CMD_INTERRUPT))
+ return 0;
+
if (whichcpu != ~0UL && whichcpu != cpu)
continue;
- addr = symtab.sym_start + KDB_PCU(cpu);
+ addr = symaddr + KDB_PCU(cpu);
diag = kdb_getword(&val, addr, bytesperword);
if (diag) {
kdb_printf("%5d " kdb_bfd_vma_fmt0 " - unable to "
"read, diag=%d\n", cpu, addr, diag);
continue;
}
-#ifdef CONFIG_SMP
- if (!val) {
- cpu_set(cpu, suppress);
- continue;
- }
-#endif /* CONFIG_SMP */
kdb_printf("%5d ", cpu);
kdb_md_line(fmtstr, addr,
bytesperword == KDB_WORD_SIZE,
1, bytesperword, 1, 1, 0);
}
- if (cpus_weight(suppress) == 0)
- return 0;
- kdb_printf("Zero suppressed cpu(s):");
- for (cpu = first_cpu(suppress); cpu < num_possible_cpus();
- cpu = next_cpu(cpu, suppress)) {
- kdb_printf(" %d", cpu);
- if (cpu == num_possible_cpus() - 1 ||
- next_cpu(cpu, suppress) != cpu + 1)
- continue;
- while (cpu < num_possible_cpus() &&
- next_cpu(cpu, suppress) == cpu + 1)
- ++cpu;
- kdb_printf("-%d", cpu);
- }
- kdb_printf("\n");
-
#undef KDB_PCU
-
return 0;
}
@@ -2763,13 +2740,13 @@ int kdb_register_repeat(char *cmd,
}
if (kdb_commands) {
memcpy(new, kdb_commands,
- kdb_max_commands * sizeof(*new));
+ (kdb_max_commands - KDB_BASE_CMD_MAX) * sizeof(*new));
kfree(kdb_commands);
}
memset(new + kdb_max_commands, 0,
kdb_command_extend * sizeof(*new));
kdb_commands = new;
- kp = kdb_commands + kdb_max_commands;
+ kp = kdb_commands + kdb_max_commands - KDB_BASE_CMD_MAX;
kdb_max_commands += kdb_command_extend;
}
@@ -2783,6 +2760,8 @@ int kdb_register_repeat(char *cmd,
return 0;
}
+EXPORT_SYMBOL_GPL(kdb_register_repeat);
+
/*
* kdb_register - Compatibility register function for commands that do
@@ -2805,6 +2784,7 @@ int kdb_register(char *cmd,
return kdb_register_repeat(cmd, func, usage, help, minlen,
KDB_REPEAT_NONE);
}
+EXPORT_SYMBOL_GPL(kdb_register);
/*
* kdb_unregister - This function is used to unregister a kernel
@@ -2823,7 +2803,7 @@ int kdb_unregister(char *cmd)
/*
* find the command.
*/
- for (i = 0, kp = kdb_commands; i < kdb_max_commands; i++, kp++) {
+ for_each_kdbcmd(kp, i) {
if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
kp->cmd_name = NULL;
return 0;
@@ -2833,6 +2813,7 @@ int kdb_unregister(char *cmd)
/* Couldn't find it. */
return 1;
}
+EXPORT_SYMBOL_GPL(kdb_unregister);
/* Initialize the kdb command table. */
static void __init kdb_inittab(void)
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index be775f7e81e..35d69ed1dfb 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -15,29 +15,6 @@
#include <linux/kgdb.h>
#include "../debug_core.h"
-/* Kernel Debugger Error codes. Must not overlap with command codes. */
-#define KDB_NOTFOUND (-1)
-#define KDB_ARGCOUNT (-2)
-#define KDB_BADWIDTH (-3)
-#define KDB_BADRADIX (-4)
-#define KDB_NOTENV (-5)
-#define KDB_NOENVVALUE (-6)
-#define KDB_NOTIMP (-7)
-#define KDB_ENVFULL (-8)
-#define KDB_ENVBUFFULL (-9)
-#define KDB_TOOMANYBPT (-10)
-#define KDB_TOOMANYDBREGS (-11)
-#define KDB_DUPBPT (-12)
-#define KDB_BPTNOTFOUND (-13)
-#define KDB_BADMODE (-14)
-#define KDB_BADINT (-15)
-#define KDB_INVADDRFMT (-16)
-#define KDB_BADREG (-17)
-#define KDB_BADCPUNUM (-18)
-#define KDB_BADLENGTH (-19)
-#define KDB_NOBP (-20)
-#define KDB_BADADDR (-21)
-
/* Kernel Debugger Command codes. Must not overlap with error codes. */
#define KDB_CMD_GO (-1001)
#define KDB_CMD_CPU (-1002)
@@ -93,17 +70,6 @@
*/
#define KDB_MAXBPT 16
-/* Maximum number of arguments to a function */
-#define KDB_MAXARGS 16
-
-typedef enum {
- KDB_REPEAT_NONE = 0, /* Do not repeat this command */
- KDB_REPEAT_NO_ARGS, /* Repeat the command without arguments */
- KDB_REPEAT_WITH_ARGS, /* Repeat the command including its arguments */
-} kdb_repeat_t;
-
-typedef int (*kdb_func_t)(int, const char **);
-
/* Symbol table format returned by kallsyms. */
typedef struct __ksymtab {
unsigned long value; /* Address of symbol */
@@ -123,11 +89,6 @@ extern int kallsyms_symbol_next(char *prefix_name, int flag);
extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
/* Exported Symbols for kernel loadable modules to use. */
-extern int kdb_register(char *, kdb_func_t, char *, char *, short);
-extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
- short, kdb_repeat_t);
-extern int kdb_unregister(char *);
-
extern int kdb_getarea_size(void *, unsigned long, size_t);
extern int kdb_putarea_size(unsigned long, void *, size_t);
@@ -144,6 +105,7 @@ extern int kdb_getword(unsigned long *, unsigned long, size_t);
extern int kdb_putword(unsigned long, unsigned long, size_t);
extern int kdbgetularg(const char *, unsigned long *);
+extern int kdbgetu64arg(const char *, u64 *);
extern char *kdbgetenv(const char *);
extern int kdbgetaddrarg(int, const char **, int*, unsigned long *,
long *, char **);
@@ -255,14 +217,6 @@ extern void kdb_ps1(const struct task_struct *p);
extern void kdb_print_nameval(const char *name, unsigned long val);
extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
extern void kdb_meminfo_proc_show(void);
-#ifdef CONFIG_KALLSYMS
-extern const char *kdb_walk_kallsyms(loff_t *pos);
-#else /* ! CONFIG_KALLSYMS */
-static inline const char *kdb_walk_kallsyms(loff_t *pos)
-{
- return NULL;
-}
-#endif /* ! CONFIG_KALLSYMS */
extern char *kdb_getstr(char *, size_t, char *);
/* Defines for kdb_symbol_print */
diff --git a/kernel/exit.c b/kernel/exit.c
index e2bdf37f9fd..676149a4ac5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -50,6 +50,7 @@
#include <linux/perf_event.h>
#include <trace/events/sched.h>
#include <linux/hw_breakpoint.h>
+#include <linux/oom.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -95,6 +96,14 @@ static void __exit_signal(struct task_struct *tsk)
sig->tty = NULL;
} else {
/*
+ * This can only happen if the caller is de_thread().
+ * FIXME: this is the temporary hack, we should teach
+ * posix-cpu-timers to handle this case correctly.
+ */
+ if (unlikely(has_group_leader_pid(tsk)))
+ posix_cpu_timers_exit_group(tsk);
+
+ /*
* If there is any task waiting for the group exit
* then notify it:
*/
@@ -687,6 +696,8 @@ static void exit_mm(struct task_struct * tsk)
enter_lazy_tlb(mm, current);
/* We don't want this task to be frozen prematurely */
clear_freeze_flag(tsk);
+ if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ atomic_dec(&mm->oom_disable_count);
task_unlock(tsk);
mm_update_next_owner(mm);
mmput(mm);
@@ -700,6 +711,8 @@ static void exit_mm(struct task_struct * tsk)
* space.
*/
static struct task_struct *find_new_reaper(struct task_struct *father)
+ __releases(&tasklist_lock)
+ __acquires(&tasklist_lock)
{
struct pid_namespace *pid_ns = task_active_pid_ns(father);
struct task_struct *thread;
@@ -901,6 +914,15 @@ NORET_TYPE void do_exit(long code)
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
+ /*
+ * If do_exit is called because this processes oopsed, it's possible
+ * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
+ * continuing. Amongst other possible reasons, this is to prevent
+ * mm_release()->clear_child_tid() from writing to a user-controlled
+ * kernel address.
+ */
+ set_fs(USER_DS);
+
tracehook_report_exit(&code);
validate_creds_for_do_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index c445f8cc408..7d164e25b0f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -65,6 +65,7 @@
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
+#include <linux/oom.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -173,8 +174,10 @@ static inline void free_signal_struct(struct signal_struct *sig)
static inline void put_signal_struct(struct signal_struct *sig)
{
- if (atomic_dec_and_test(&sig->sigcnt))
+ if (atomic_dec_and_test(&sig->sigcnt)) {
+ sched_autogroup_exit(sig);
free_signal_struct(sig);
+ }
}
void __put_task_struct(struct task_struct *tsk)
@@ -272,6 +275,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
+ clear_tsk_need_resched(tsk);
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
@@ -488,6 +492,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
mm->cached_hole_size = ~0UL;
mm_init_aio(mm);
mm_init_owner(mm, p);
+ atomic_set(&mm->oom_disable_count, 0);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
@@ -741,6 +746,8 @@ good_mm:
/* Initializing for Swap token stuff */
mm->token_priority = 0;
mm->last_interval = 0;
+ if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ atomic_inc(&mm->oom_disable_count);
tsk->mm = mm;
tsk->active_mm = mm;
@@ -900,10 +907,13 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
posix_cpu_timers_init_group(sig);
tty_audit_fork(sig);
+ sched_autogroup_fork(sig);
sig->oom_adj = current->signal->oom_adj;
sig->oom_score_adj = current->signal->oom_score_adj;
+ mutex_init(&sig->cred_guard_mutex);
+
return 0;
}
@@ -1299,11 +1309,16 @@ bad_fork_cleanup_io:
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
- if (p->mm)
+ if (p->mm) {
+ task_lock(p);
+ if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ atomic_dec(&p->mm->oom_disable_count);
+ task_unlock(p);
mmput(p->mm);
+ }
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
- free_signal_struct(p->signal);
+ put_signal_struct(p->signal);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
@@ -1693,6 +1708,10 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
active_mm = current->active_mm;
current->mm = new_mm;
current->active_mm = new_mm;
+ if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+ atomic_dec(&mm->oom_disable_count);
+ atomic_inc(&new_mm->oom_disable_count);
+ }
activate_mm(active_mm, new_mm);
new_mm = mm;
}
diff --git a/kernel/futex.c b/kernel/futex.c
index a118bf160e0..3019b92e691 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -69,6 +69,14 @@ int __read_mostly futex_cmpxchg_enabled;
#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
/*
+ * Futex flags used to encode options to functions and preserve them across
+ * restarts.
+ */
+#define FLAGS_SHARED 0x01
+#define FLAGS_CLOCKRT 0x02
+#define FLAGS_HAS_TIMEOUT 0x04
+
+/*
* Priority Inheritance state:
*/
struct futex_pi_state {
@@ -123,6 +131,12 @@ struct futex_q {
u32 bitset;
};
+static const struct futex_q futex_q_init = {
+ /* list gets initialized in queue_me()*/
+ .key = FUTEX_KEY_INIT,
+ .bitset = FUTEX_BITSET_MATCH_ANY
+};
+
/*
* Hash buckets are shared by all the futex_keys that hash to the same
* location. Each key may have multiple futex_q structures, one for each task
@@ -169,7 +183,7 @@ static void get_futex_key_refs(union futex_key *key)
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- atomic_inc(&key->shared.inode->i_count);
+ ihold(key->shared.inode);
break;
case FUT_OFF_MMSHARED:
atomic_inc(&key->private.mm->mm_count);
@@ -283,8 +297,7 @@ again:
return 0;
}
-static inline
-void put_futex_key(int fshared, union futex_key *key)
+static inline void put_futex_key(union futex_key *key)
{
drop_futex_key_refs(key);
}
@@ -870,7 +883,8 @@ double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
/*
* Wake up waiters matching bitset queued on this futex (uaddr).
*/
-static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
+static int
+futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
@@ -881,7 +895,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
if (!bitset)
return -EINVAL;
- ret = get_futex_key(uaddr, fshared, &key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
if (unlikely(ret != 0))
goto out;
@@ -907,7 +921,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
}
spin_unlock(&hb->lock);
- put_futex_key(fshared, &key);
+ put_futex_key(&key);
out:
return ret;
}
@@ -917,7 +931,7 @@ out:
* to this virtual address:
*/
static int
-futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
+futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
int nr_wake, int nr_wake2, int op)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
@@ -927,10 +941,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
int ret, op_ret;
retry:
- ret = get_futex_key(uaddr1, fshared, &key1);
+ ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, fshared, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
if (unlikely(ret != 0))
goto out_put_key1;
@@ -962,11 +976,11 @@ retry_private:
if (ret)
goto out_put_keys;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
goto retry;
}
@@ -996,9 +1010,9 @@ retry_private:
double_unlock_hb(hb1, hb2);
out_put_keys:
- put_futex_key(fshared, &key2);
+ put_futex_key(&key2);
out_put_key1:
- put_futex_key(fshared, &key1);
+ put_futex_key(&key1);
out:
return ret;
}
@@ -1133,13 +1147,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
/**
* futex_requeue() - Requeue waiters from uaddr1 to uaddr2
* @uaddr1: source futex user address
- * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @flags: futex flags (FLAGS_SHARED, etc.)
* @uaddr2: target futex user address
* @nr_wake: number of waiters to wake (must be 1 for requeue_pi)
* @nr_requeue: number of waiters to requeue (0-INT_MAX)
* @cmpval: @uaddr1 expected value (or %NULL)
* @requeue_pi: if we are attempting to requeue from a non-pi futex to a
- * pi futex (pi to pi requeue is not supported)
+ * pi futex (pi to pi requeue is not supported)
*
* Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
* uaddr2 atomically on behalf of the top waiter.
@@ -1148,9 +1162,9 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
* >=0 - on success, the number of tasks requeued or woken
* <0 - on error
*/
-static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
- int nr_wake, int nr_requeue, u32 *cmpval,
- int requeue_pi)
+static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
+ u32 __user *uaddr2, int nr_wake, int nr_requeue,
+ u32 *cmpval, int requeue_pi)
{
union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
int drop_count = 0, task_count = 0, ret;
@@ -1191,10 +1205,10 @@ retry:
pi_state = NULL;
}
- ret = get_futex_key(uaddr1, fshared, &key1);
+ ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
if (unlikely(ret != 0))
goto out;
- ret = get_futex_key(uaddr2, fshared, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
if (unlikely(ret != 0))
goto out_put_key1;
@@ -1216,11 +1230,11 @@ retry_private:
if (ret)
goto out_put_keys;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
goto retry;
}
if (curval != *cmpval) {
@@ -1260,8 +1274,8 @@ retry_private:
break;
case -EFAULT:
double_unlock_hb(hb1, hb2);
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
ret = fault_in_user_writeable(uaddr2);
if (!ret)
goto retry;
@@ -1269,8 +1283,8 @@ retry_private:
case -EAGAIN:
/* The owner was exiting, try again. */
double_unlock_hb(hb1, hb2);
- put_futex_key(fshared, &key2);
- put_futex_key(fshared, &key1);
+ put_futex_key(&key2);
+ put_futex_key(&key1);
cond_resched();
goto retry;
default:
@@ -1352,9 +1366,9 @@ out_unlock:
drop_futex_key_refs(&key1);
out_put_keys:
- put_futex_key(fshared, &key2);
+ put_futex_key(&key2);
out_put_key1:
- put_futex_key(fshared, &key1);
+ put_futex_key(&key1);
out:
if (pi_state != NULL)
free_pi_state(pi_state);
@@ -1494,7 +1508,7 @@ static void unqueue_me_pi(struct futex_q *q)
* private futexes.
*/
static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
- struct task_struct *newowner, int fshared)
+ struct task_struct *newowner)
{
u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
struct futex_pi_state *pi_state = q->pi_state;
@@ -1587,20 +1601,11 @@ handle_fault:
goto retry;
}
-/*
- * In case we must use restart_block to restart a futex_wait,
- * we encode in the 'flags' shared capability
- */
-#define FLAGS_SHARED 0x01
-#define FLAGS_CLOCKRT 0x02
-#define FLAGS_HAS_TIMEOUT 0x04
-
static long futex_wait_restart(struct restart_block *restart);
/**
* fixup_owner() - Post lock pi_state and corner case management
* @uaddr: user address of the futex
- * @fshared: whether the futex is shared (1) or not (0)
* @q: futex_q (contains pi_state and access to the rt_mutex)
* @locked: if the attempt to take the rt_mutex succeeded (1) or not (0)
*
@@ -1613,8 +1618,7 @@ static long futex_wait_restart(struct restart_block *restart);
* 0 - success, lock not taken
* <0 - on error (-EFAULT)
*/
-static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
- int locked)
+static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
{
struct task_struct *owner;
int ret = 0;
@@ -1625,7 +1629,7 @@ static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
* did a lock-steal - fix up the PI-state in that case:
*/
if (q->pi_state->owner != current)
- ret = fixup_pi_state_owner(uaddr, q, current, fshared);
+ ret = fixup_pi_state_owner(uaddr, q, current);
goto out;
}
@@ -1652,7 +1656,7 @@ static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
* lock. Fix the state up.
*/
owner = rt_mutex_owner(&q->pi_state->pi_mutex);
- ret = fixup_pi_state_owner(uaddr, q, owner, fshared);
+ ret = fixup_pi_state_owner(uaddr, q, owner);
goto out;
}
@@ -1715,7 +1719,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
* futex_wait_setup() - Prepare to wait on a futex
* @uaddr: the futex userspace address
* @val: the expected value
- * @fshared: whether the futex is shared (1) or not (0)
+ * @flags: futex flags (FLAGS_SHARED, etc.)
* @q: the associated futex_q
* @hb: storage for hash_bucket pointer to be returned to caller
*
@@ -1728,7 +1732,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
* 0 - uaddr contains val and hb has been locked
* <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
*/
-static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
+static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
struct futex_q *q, struct futex_hash_bucket **hb)
{
u32 uval;
@@ -1752,8 +1756,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
* rare, but normal.
*/
retry:
- q->key = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr, fshared, &q->key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
if (unlikely(ret != 0))
return ret;
@@ -1769,10 +1772,10 @@ retry_private:
if (ret)
goto out;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &q->key);
+ put_futex_key(&q->key);
goto retry;
}
@@ -1783,32 +1786,29 @@ retry_private:
out:
if (ret)
- put_futex_key(fshared, &q->key);
+ put_futex_key(&q->key);
return ret;
}
-static int futex_wait(u32 __user *uaddr, int fshared,
- u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+ ktime_t *abs_time, u32 bitset)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct restart_block *restart;
struct futex_hash_bucket *hb;
- struct futex_q q;
+ struct futex_q q = futex_q_init;
int ret;
if (!bitset)
return -EINVAL;
-
- q.pi_state = NULL;
q.bitset = bitset;
- q.rt_waiter = NULL;
- q.requeue_pi_key = NULL;
if (abs_time) {
to = &timeout;
- hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
+ CLOCK_REALTIME : CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS);
hrtimer_init_sleeper(to, current);
hrtimer_set_expires_range_ns(&to->timer, *abs_time,
current->timer_slack_ns);
@@ -1819,7 +1819,7 @@ retry:
* Prepare to wait on uaddr. On success, holds hb lock and increments
* q.key refs.
*/
- ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+ ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
if (ret)
goto out;
@@ -1852,12 +1852,7 @@ retry:
restart->futex.val = val;
restart->futex.time = abs_time->tv64;
restart->futex.bitset = bitset;
- restart->futex.flags = FLAGS_HAS_TIMEOUT;
-
- if (fshared)
- restart->futex.flags |= FLAGS_SHARED;
- if (clockrt)
- restart->futex.flags |= FLAGS_CLOCKRT;
+ restart->futex.flags = flags;
ret = -ERESTART_RESTARTBLOCK;
@@ -1873,7 +1868,6 @@ out:
static long futex_wait_restart(struct restart_block *restart)
{
u32 __user *uaddr = restart->futex.uaddr;
- int fshared = 0;
ktime_t t, *tp = NULL;
if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
@@ -1881,11 +1875,9 @@ static long futex_wait_restart(struct restart_block *restart)
tp = &t;
}
restart->fn = do_no_restart_syscall;
- if (restart->futex.flags & FLAGS_SHARED)
- fshared = 1;
- return (long)futex_wait(uaddr, fshared, restart->futex.val, tp,
- restart->futex.bitset,
- restart->futex.flags & FLAGS_CLOCKRT);
+
+ return (long)futex_wait(uaddr, restart->futex.flags,
+ restart->futex.val, tp, restart->futex.bitset);
}
@@ -1895,12 +1887,12 @@ static long futex_wait_restart(struct restart_block *restart)
* if there are waiters then it will block, it does PI, etc. (Due to
* races the kernel might see a 0 value of the futex too.)
*/
-static int futex_lock_pi(u32 __user *uaddr, int fshared,
- int detect, ktime_t *time, int trylock)
+static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, int detect,
+ ktime_t *time, int trylock)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct futex_hash_bucket *hb;
- struct futex_q q;
+ struct futex_q q = futex_q_init;
int res, ret;
if (refill_pi_state_cache())
@@ -1914,12 +1906,8 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
hrtimer_set_expires(&to->timer, *time);
}
- q.pi_state = NULL;
- q.rt_waiter = NULL;
- q.requeue_pi_key = NULL;
retry:
- q.key = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr, fshared, &q.key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key);
if (unlikely(ret != 0))
goto out;
@@ -1941,7 +1929,7 @@ retry_private:
* exit to complete.
*/
queue_unlock(&q, hb);
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
cond_resched();
goto retry;
default:
@@ -1971,7 +1959,7 @@ retry_private:
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
*/
- res = fixup_owner(uaddr, fshared, &q, !ret);
+ res = fixup_owner(uaddr, &q, !ret);
/*
* If fixup_owner() returned an error, proprogate that. If it acquired
* the lock, clear our -ETIMEDOUT or -EINTR.
@@ -1995,7 +1983,7 @@ out_unlock_put_key:
queue_unlock(&q, hb);
out_put_key:
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
out:
if (to)
destroy_hrtimer_on_stack(&to->timer);
@@ -2008,10 +1996,10 @@ uaddr_faulted:
if (ret)
goto out_put_key;
- if (!fshared)
+ if (!(flags & FLAGS_SHARED))
goto retry_private;
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
goto retry;
}
@@ -2020,7 +2008,7 @@ uaddr_faulted:
* This is the in-kernel slowpath: we look up the PI state (if any),
* and do the rt-mutex unlock.
*/
-static int futex_unlock_pi(u32 __user *uaddr, int fshared)
+static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
struct futex_hash_bucket *hb;
struct futex_q *this, *next;
@@ -2038,7 +2026,7 @@ retry:
if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
return -EPERM;
- ret = get_futex_key(uaddr, fshared, &key);
+ ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
if (unlikely(ret != 0))
goto out;
@@ -2093,14 +2081,14 @@ retry:
out_unlock:
spin_unlock(&hb->lock);
- put_futex_key(fshared, &key);
+ put_futex_key(&key);
out:
return ret;
pi_faulted:
spin_unlock(&hb->lock);
- put_futex_key(fshared, &key);
+ put_futex_key(&key);
ret = fault_in_user_writeable(uaddr);
if (!ret)
@@ -2160,7 +2148,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
/**
* futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
* @uaddr: the futex we initially wait on (non-pi)
- * @fshared: whether the futexes are shared (1) or not (0). They must be
+ * @flags: futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), they must be
* the same type, no requeueing from private to shared, etc.
* @val: the expected value of uaddr
* @abs_time: absolute timeout
@@ -2198,16 +2186,16 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
* 0 - On success
* <0 - On error
*/
-static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
+static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
u32 val, ktime_t *abs_time, u32 bitset,
- int clockrt, u32 __user *uaddr2)
+ u32 __user *uaddr2)
{
struct hrtimer_sleeper timeout, *to = NULL;
struct rt_mutex_waiter rt_waiter;
struct rt_mutex *pi_mutex = NULL;
struct futex_hash_bucket *hb;
- union futex_key key2;
- struct futex_q q;
+ union futex_key key2 = FUTEX_KEY_INIT;
+ struct futex_q q = futex_q_init;
int res, ret;
if (!bitset)
@@ -2215,8 +2203,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
if (abs_time) {
to = &timeout;
- hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
+ CLOCK_REALTIME : CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS);
hrtimer_init_sleeper(to, current);
hrtimer_set_expires_range_ns(&to->timer, *abs_time,
current->timer_slack_ns);
@@ -2229,12 +2218,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
debug_rt_mutex_init_waiter(&rt_waiter);
rt_waiter.task = NULL;
- key2 = FUTEX_KEY_INIT;
- ret = get_futex_key(uaddr2, fshared, &key2);
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
if (unlikely(ret != 0))
goto out;
- q.pi_state = NULL;
q.bitset = bitset;
q.rt_waiter = &rt_waiter;
q.requeue_pi_key = &key2;
@@ -2243,7 +2230,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
* Prepare to wait on uaddr. On success, increments q.key (key1) ref
* count.
*/
- ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+ ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
if (ret)
goto out_key2;
@@ -2273,8 +2260,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
*/
if (q.pi_state && (q.pi_state->owner != current)) {
spin_lock(q.lock_ptr);
- ret = fixup_pi_state_owner(uaddr2, &q, current,
- fshared);
+ ret = fixup_pi_state_owner(uaddr2, &q, current);
spin_unlock(q.lock_ptr);
}
} else {
@@ -2293,7 +2279,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
*/
- res = fixup_owner(uaddr2, fshared, &q, !ret);
+ res = fixup_owner(uaddr2, &q, !ret);
/*
* If fixup_owner() returned an error, proprogate that. If it
* acquired the lock, clear -ETIMEDOUT or -EINTR.
@@ -2324,9 +2310,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
}
out_put_keys:
- put_futex_key(fshared, &q.key);
+ put_futex_key(&q.key);
out_key2:
- put_futex_key(fshared, &key2);
+ put_futex_key(&key2);
out:
if (to) {
@@ -2489,7 +2475,8 @@ void exit_robust_list(struct task_struct *curr)
{
struct robust_list_head __user *head = curr->robust_list;
struct robust_list __user *entry, *next_entry, *pending;
- unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+ unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+ unsigned int uninitialized_var(next_pi);
unsigned long futex_offset;
int rc;
@@ -2550,58 +2537,57 @@ void exit_robust_list(struct task_struct *curr)
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
- int clockrt, ret = -ENOSYS;
- int cmd = op & FUTEX_CMD_MASK;
- int fshared = 0;
+ int ret = -ENOSYS, cmd = op & FUTEX_CMD_MASK;
+ unsigned int flags = 0;
if (!(op & FUTEX_PRIVATE_FLAG))
- fshared = 1;
+ flags |= FLAGS_SHARED;
- clockrt = op & FUTEX_CLOCK_REALTIME;
- if (clockrt && cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
- return -ENOSYS;
+ if (op & FUTEX_CLOCK_REALTIME) {
+ flags |= FLAGS_CLOCKRT;
+ if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
+ return -ENOSYS;
+ }
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAIT_BITSET:
- ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
+ ret = futex_wait(uaddr, flags, val, timeout, val3);
break;
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAKE_BITSET:
- ret = futex_wake(uaddr, fshared, val, val3);
+ ret = futex_wake(uaddr, flags, val, val3);
break;
case FUTEX_REQUEUE:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL, 0);
+ ret = futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0);
break;
case FUTEX_CMP_REQUEUE:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
- 0);
+ ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0);
break;
case FUTEX_WAKE_OP:
- ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3);
+ ret = futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
break;
case FUTEX_LOCK_PI:
if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, fshared, val, timeout, 0);
+ ret = futex_lock_pi(uaddr, flags, val, timeout, 0);
break;
case FUTEX_UNLOCK_PI:
if (futex_cmpxchg_enabled)
- ret = futex_unlock_pi(uaddr, fshared);
+ ret = futex_unlock_pi(uaddr, flags);
break;
case FUTEX_TRYLOCK_PI:
if (futex_cmpxchg_enabled)
- ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1);
+ ret = futex_lock_pi(uaddr, flags, 0, timeout, 1);
break;
case FUTEX_WAIT_REQUEUE_PI:
val3 = FUTEX_BITSET_MATCH_ANY;
- ret = futex_wait_requeue_pi(uaddr, fshared, val, timeout, val3,
- clockrt, uaddr2);
+ ret = futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
+ uaddr2);
break;
case FUTEX_CMP_REQUEUE_PI:
- ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
- 1);
+ ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
break;
default:
ret = -ENOSYS;
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 06da4dfc339..a7934ac75e5 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -49,7 +49,8 @@ void compat_exit_robust_list(struct task_struct *curr)
{
struct compat_robust_list_head __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
- unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+ unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+ unsigned int uninitialized_var(next_pi);
compat_uptr_t uentry, next_uentry, upending;
compat_long_t futex_offset;
int rc;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 72206cf5c6c..f2429fc3438 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -516,10 +516,13 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
struct hrtimer *timer;
+ struct timerqueue_node *next;
- if (!base->first)
+ next = timerqueue_getnext(&base->active);
+ if (!next)
continue;
- timer = rb_entry(base->first, struct hrtimer, node);
+ timer = container_of(next, struct hrtimer, node);
+
expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
/*
* clock_was_set() has changed base->offset so the
@@ -840,48 +843,17 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
static int enqueue_hrtimer(struct hrtimer *timer,
struct hrtimer_clock_base *base)
{
- struct rb_node **link = &base->active.rb_node;
- struct rb_node *parent = NULL;
- struct hrtimer *entry;
- int leftmost = 1;
-
debug_activate(timer);
- /*
- * Find the right place in the rbtree:
- */
- while (*link) {
- parent = *link;
- entry = rb_entry(parent, struct hrtimer, node);
- /*
- * We dont care about collisions. Nodes with
- * the same expiry time stay together.
- */
- if (hrtimer_get_expires_tv64(timer) <
- hrtimer_get_expires_tv64(entry)) {
- link = &(*link)->rb_left;
- } else {
- link = &(*link)->rb_right;
- leftmost = 0;
- }
- }
-
- /*
- * Insert the timer to the rbtree and check whether it
- * replaces the first pending timer
- */
- if (leftmost)
- base->first = &timer->node;
+ timerqueue_add(&base->active, &timer->node);
- rb_link_node(&timer->node, parent, link);
- rb_insert_color(&timer->node, &base->active);
/*
* HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
* state of a possibly running callback.
*/
timer->state |= HRTIMER_STATE_ENQUEUED;
- return leftmost;
+ return (&timer->node == base->active.next);
}
/*
@@ -901,12 +873,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
if (!(timer->state & HRTIMER_STATE_ENQUEUED))
goto out;
- /*
- * Remove the timer from the rbtree and replace the first
- * entry pointer if necessary.
- */
- if (base->first == &timer->node) {
- base->first = rb_next(&timer->node);
+ if (&timer->node == timerqueue_getnext(&base->active)) {
#ifdef CONFIG_HIGH_RES_TIMERS
/* Reprogram the clock event device. if enabled */
if (reprogram && hrtimer_hres_active()) {
@@ -919,7 +886,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
}
#endif
}
- rb_erase(&timer->node, &base->active);
+ timerqueue_del(&base->active, &timer->node);
out:
timer->state = newstate;
}
@@ -1128,11 +1095,13 @@ ktime_t hrtimer_get_next_event(void)
if (!hrtimer_hres_active()) {
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
struct hrtimer *timer;
+ struct timerqueue_node *next;
- if (!base->first)
+ next = timerqueue_getnext(&base->active);
+ if (!next)
continue;
- timer = rb_entry(base->first, struct hrtimer, node);
+ timer = container_of(next, struct hrtimer, node);
delta.tv64 = hrtimer_get_expires_tv64(timer);
delta = ktime_sub(delta, base->get_time());
if (delta.tv64 < mindelta.tv64)
@@ -1162,6 +1131,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
timer->base = &cpu_base->clock_base[clock_id];
hrtimer_init_timer_hres(timer);
+ timerqueue_init(&timer->node);
#ifdef CONFIG_TIMER_STATS
timer->start_site = NULL;
@@ -1278,14 +1248,14 @@ retry:
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
- struct rb_node *node;
+ struct timerqueue_node *node;
basenow = ktime_add(now, base->offset);
- while ((node = base->first)) {
+ while ((node = timerqueue_getnext(&base->active))) {
struct hrtimer *timer;
- timer = rb_entry(node, struct hrtimer, node);
+ timer = container_of(node, struct hrtimer, node);
/*
* The immediate goal for using the softexpires is
@@ -1441,7 +1411,7 @@ void hrtimer_run_pending(void)
*/
void hrtimer_run_queues(void)
{
- struct rb_node *node;
+ struct timerqueue_node *node;
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
struct hrtimer_clock_base *base;
int index, gettime = 1;
@@ -1451,8 +1421,7 @@ void hrtimer_run_queues(void)
for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
base = &cpu_base->clock_base[index];
-
- if (!base->first)
+ if (!timerqueue_getnext(&base->active))
continue;
if (gettime) {
@@ -1462,10 +1431,10 @@ void hrtimer_run_queues(void)
raw_spin_lock(&cpu_base->lock);
- while ((node = base->first)) {
+ while ((node = timerqueue_getnext(&base->active))) {
struct hrtimer *timer;
- timer = rb_entry(node, struct hrtimer, node);
+ timer = container_of(node, struct hrtimer, node);
if (base->softirq_time.tv64 <=
hrtimer_get_expires_tv64(timer))
break;
@@ -1630,8 +1599,10 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
raw_spin_lock_init(&cpu_base->lock);
- for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
cpu_base->clock_base[i].cpu_base = cpu_base;
+ timerqueue_init_head(&cpu_base->clock_base[i].active);
+ }
hrtimer_init_hres(cpu_base);
}
@@ -1642,10 +1613,10 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
struct hrtimer_clock_base *new_base)
{
struct hrtimer *timer;
- struct rb_node *node;
+ struct timerqueue_node *node;
- while ((node = rb_first(&old_base->active))) {
- timer = rb_entry(node, struct hrtimer, node);
+ while ((node = timerqueue_getnext(&old_base->active))) {
+ timer = container_of(node, struct hrtimer, node);
BUG_ON(hrtimer_callback_running(timer));
debug_deactivate(timer);
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 2c9120f0afc..086adf25a55 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -620,7 +620,7 @@ static struct pmu perf_breakpoint = {
.read = hw_breakpoint_pmu_read,
};
-static int __init init_hw_breakpoint(void)
+int __init init_hw_breakpoint(void)
{
unsigned int **task_bp_pinned;
int cpu, err_cpu;
@@ -641,7 +641,7 @@ static int __init init_hw_breakpoint(void)
constraints_initialized = 1;
- perf_pmu_register(&perf_breakpoint);
+ perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
return register_die_notifier(&hw_breakpoint_exceptions_nb);
@@ -655,6 +655,5 @@ static int __init init_hw_breakpoint(void)
return -ENOMEM;
}
-core_initcall(init_hw_breakpoint);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 9d917ff7267..9988d03797f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -393,3 +393,18 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
struct irq_desc *desc = irq_to_desc(irq);
return desc ? desc->kstat_irqs[cpu] : 0;
}
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+unsigned int kstat_irqs(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ int cpu;
+ int sum = 0;
+
+ if (!desc)
+ return 0;
+ for_each_possible_cpu(cpu)
+ sum += desc->kstat_irqs[cpu];
+ return sum;
+}
+#endif /* CONFIG_GENERIC_HARDIRQS */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 644e8d5fa36..91a5fa25054 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -324,6 +324,10 @@ void enable_irq(unsigned int irq)
if (!desc)
return;
+ if (WARN(!desc->irq_data.chip || !desc->irq_data.chip->irq_enable,
+ KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
+ return;
+
chip_bus_lock(desc);
raw_spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, false);
@@ -573,7 +577,9 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
*/
static int irq_thread(void *data)
{
- struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
+ static struct sched_param param = {
+ .sched_priority = MAX_USER_RT_PRIO/2,
+ };
struct irqaction *action = data;
struct irq_desc *desc = irq_to_desc(action->irq);
int wake, oneshot = desc->status & IRQ_ONESHOT;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 01b1d3a8898..6c8a2a9f8a7 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -214,7 +214,7 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
static int irq_spurious_proc_open(struct inode *inode, struct file *file)
{
- return single_open(file, irq_spurious_proc_show, NULL);
+ return single_open(file, irq_spurious_proc_show, PDE(inode)->data);
}
static const struct file_operations irq_spurious_proc_fops = {
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f16763ff848..90f881904bb 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -145,7 +145,9 @@ void irq_work_run(void)
* Clear the BUSY bit and return to the free state if
* no-one else claimed it meanwhile.
*/
- cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+ (void)cmpxchg(&entry->next,
+ next_flags(NULL, IRQ_WORK_BUSY),
+ NULL);
}
}
EXPORT_SYMBOL_GPL(irq_work_run);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 7be868bf25c..3b79bd93833 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -39,6 +39,16 @@ struct jump_label_module_entry {
struct module *mod;
};
+void jump_label_lock(void)
+{
+ mutex_lock(&jump_label_mutex);
+}
+
+void jump_label_unlock(void)
+{
+ mutex_unlock(&jump_label_mutex);
+}
+
static int jump_label_cmp(const void *a, const void *b)
{
const struct jump_entry *jea = a;
@@ -152,7 +162,7 @@ void jump_label_update(unsigned long key, enum jump_label_type type)
struct jump_label_module_entry *e_module;
int count;
- mutex_lock(&jump_label_mutex);
+ jump_label_lock();
entry = get_jump_label_entry((jump_label_t)key);
if (entry) {
count = entry->nr_entries;
@@ -168,13 +178,14 @@ void jump_label_update(unsigned long key, enum jump_label_type type)
count = e_module->nr_entries;
iter = e_module->table;
while (count--) {
- if (kernel_text_address(iter->code))
+ if (iter->key &&
+ kernel_text_address(iter->code))
arch_jump_label_transform(iter, type);
iter++;
}
}
}
- mutex_unlock(&jump_label_mutex);
+ jump_label_unlock();
}
static int addr_conflict(struct jump_entry *entry, void *start, void *end)
@@ -231,6 +242,7 @@ out:
* overlaps with any of the jump label patch addresses. Code
* that wants to modify kernel text should first verify that
* it does not overlap with any of the jump label addresses.
+ * Caller must hold jump_label_mutex.
*
* returns 1 if there is an overlap, 0 otherwise
*/
@@ -241,7 +253,6 @@ int jump_label_text_reserved(void *start, void *end)
struct jump_entry *iter_stop = __start___jump_table;
int conflict = 0;
- mutex_lock(&jump_label_mutex);
iter = iter_start;
while (iter < iter_stop) {
if (addr_conflict(iter, start, end)) {
@@ -256,10 +267,16 @@ int jump_label_text_reserved(void *start, void *end)
conflict = module_conflict(start, end);
#endif
out:
- mutex_unlock(&jump_label_mutex);
return conflict;
}
+/*
+ * Not all archs need this.
+ */
+void __weak arch_jump_label_text_poke_early(jump_label_t addr)
+{
+}
+
static __init int init_jump_label(void)
{
int ret;
@@ -267,7 +284,7 @@ static __init int init_jump_label(void)
struct jump_entry *iter_stop = __stop___jump_table;
struct jump_entry *iter;
- mutex_lock(&jump_label_mutex);
+ jump_label_lock();
ret = build_jump_label_hashtable(__start___jump_table,
__stop___jump_table);
iter = iter_start;
@@ -275,7 +292,7 @@ static __init int init_jump_label(void)
arch_jump_label_text_poke_early(iter->code);
iter++;
}
- mutex_unlock(&jump_label_mutex);
+ jump_label_unlock();
return ret;
}
early_initcall(init_jump_label);
@@ -366,6 +383,39 @@ static void remove_jump_label_module(struct module *mod)
}
}
+static void remove_jump_label_module_init(struct module *mod)
+{
+ struct hlist_head *head;
+ struct hlist_node *node, *node_next, *module_node, *module_node_next;
+ struct jump_label_entry *e;
+ struct jump_label_module_entry *e_module;
+ struct jump_entry *iter;
+ int i, count;
+
+ /* if the module doesn't have jump label entries, just return */
+ if (!mod->num_jump_entries)
+ return;
+
+ for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+ head = &jump_label_table[i];
+ hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+ hlist_for_each_entry_safe(e_module, module_node,
+ module_node_next,
+ &(e->modules), hlist) {
+ if (e_module->mod != mod)
+ continue;
+ count = e_module->nr_entries;
+ iter = e_module->table;
+ while (count--) {
+ if (within_module_init(iter->code, mod))
+ iter->key = 0;
+ iter++;
+ }
+ }
+ }
+ }
+}
+
static int
jump_label_module_notify(struct notifier_block *self, unsigned long val,
void *data)
@@ -375,16 +425,21 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
switch (val) {
case MODULE_STATE_COMING:
- mutex_lock(&jump_label_mutex);
+ jump_label_lock();
ret = add_jump_label_module(mod);
if (ret)
remove_jump_label_module(mod);
- mutex_unlock(&jump_label_mutex);
+ jump_label_unlock();
break;
case MODULE_STATE_GOING:
- mutex_lock(&jump_label_mutex);
+ jump_label_lock();
remove_jump_label_module(mod);
- mutex_unlock(&jump_label_mutex);
+ jump_label_unlock();
+ break;
+ case MODULE_STATE_LIVE:
+ jump_label_lock();
+ remove_jump_label_module_init(mod);
+ jump_label_unlock();
break;
}
return ret;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index c0613f7d673..b55045bc756 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -816,7 +816,7 @@ static int kimage_load_normal_segment(struct kimage *image,
ptr = kmap(page);
/* Start with a clear page */
- memset(ptr, 0, PAGE_SIZE);
+ clear_page(ptr);
ptr += maddr & ~PAGE_MASK;
mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK);
if (mchunk > mbytes)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 56a89191427..7663e5df0e6 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -74,7 +74,8 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
/* NOTE: change this value only with kprobe_mutex held */
static bool kprobes_all_disarmed;
-static DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */
+/* This protects kprobe_table and optimizing_list */
+static DEFINE_MUTEX(kprobe_mutex);
static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
static struct {
spinlock_t lock ____cacheline_aligned_in_smp;
@@ -353,13 +354,20 @@ static inline int kprobe_aggrprobe(struct kprobe *p)
return p->pre_handler == aggr_pre_handler;
}
+/* Return true(!0) if the kprobe is unused */
+static inline int kprobe_unused(struct kprobe *p)
+{
+ return kprobe_aggrprobe(p) && kprobe_disabled(p) &&
+ list_empty(&p->list);
+}
+
/*
* Keep all fields in the kprobe consistent
*/
-static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p)
{
- memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
- memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+ memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t));
+ memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn));
}
#ifdef CONFIG_OPTPROBES
@@ -383,6 +391,17 @@ void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
}
}
+/* Free optimized instructions and optimized_kprobe */
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ arch_remove_optimized_kprobe(op);
+ arch_remove_kprobe(p);
+ kfree(op);
+}
+
/* Return true(!0) if the kprobe is ready for optimization. */
static inline int kprobe_optready(struct kprobe *p)
{
@@ -396,6 +415,33 @@ static inline int kprobe_optready(struct kprobe *p)
return 0;
}
+/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */
+static inline int kprobe_disarmed(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ /* If kprobe is not aggr/opt probe, just return kprobe is disabled */
+ if (!kprobe_aggrprobe(p))
+ return kprobe_disabled(p);
+
+ op = container_of(p, struct optimized_kprobe, kp);
+
+ return kprobe_disabled(p) && list_empty(&op->list);
+}
+
+/* Return true(!0) if the probe is queued on (un)optimizing lists */
+static int __kprobes kprobe_queued(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ if (kprobe_aggrprobe(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!list_empty(&op->list))
+ return 1;
+ }
+ return 0;
+}
+
/*
* Return an optimized kprobe whose optimizing code replaces
* instructions including addr (exclude breakpoint).
@@ -421,30 +467,23 @@ static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
/* Optimization staging list, protected by kprobe_mutex */
static LIST_HEAD(optimizing_list);
+static LIST_HEAD(unoptimizing_list);
static void kprobe_optimizer(struct work_struct *work);
static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
+static DECLARE_COMPLETION(optimizer_comp);
#define OPTIMIZE_DELAY 5
-/* Kprobe jump optimizer */
-static __kprobes void kprobe_optimizer(struct work_struct *work)
+/*
+ * Optimize (replace a breakpoint with a jump) kprobes listed on
+ * optimizing_list.
+ */
+static __kprobes void do_optimize_kprobes(void)
{
- struct optimized_kprobe *op, *tmp;
-
- /* Lock modules while optimizing kprobes */
- mutex_lock(&module_mutex);
- mutex_lock(&kprobe_mutex);
- if (kprobes_all_disarmed || !kprobes_allow_optimization)
- goto end;
-
- /*
- * Wait for quiesence period to ensure all running interrupts
- * are done. Because optprobe may modify multiple instructions
- * there is a chance that Nth instruction is interrupted. In that
- * case, running interrupt can return to 2nd-Nth byte of jump
- * instruction. This wait is for avoiding it.
- */
- synchronize_sched();
+ /* Optimization never be done when disarmed */
+ if (kprobes_all_disarmed || !kprobes_allow_optimization ||
+ list_empty(&optimizing_list))
+ return;
/*
* The optimization/unoptimization refers online_cpus via
@@ -458,17 +497,111 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
*/
get_online_cpus();
mutex_lock(&text_mutex);
- list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
- WARN_ON(kprobe_disabled(&op->kp));
- if (arch_optimize_kprobe(op) < 0)
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
- list_del_init(&op->list);
+ arch_optimize_kprobes(&optimizing_list);
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+}
+
+/*
+ * Unoptimize (replace a jump with a breakpoint and remove the breakpoint
+ * if need) kprobes listed on unoptimizing_list.
+ */
+static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
+{
+ struct optimized_kprobe *op, *tmp;
+
+ /* Unoptimization must be done anytime */
+ if (list_empty(&unoptimizing_list))
+ return;
+
+ /* Ditto to do_optimize_kprobes */
+ get_online_cpus();
+ mutex_lock(&text_mutex);
+ arch_unoptimize_kprobes(&unoptimizing_list, free_list);
+ /* Loop free_list for disarming */
+ list_for_each_entry_safe(op, tmp, free_list, list) {
+ /* Disarm probes if marked disabled */
+ if (kprobe_disabled(&op->kp))
+ arch_disarm_kprobe(&op->kp);
+ if (kprobe_unused(&op->kp)) {
+ /*
+ * Remove unused probes from hash list. After waiting
+ * for synchronization, these probes are reclaimed.
+ * (reclaiming is done by do_free_cleaned_kprobes.)
+ */
+ hlist_del_rcu(&op->kp.hlist);
+ } else
+ list_del_init(&op->list);
}
mutex_unlock(&text_mutex);
put_online_cpus();
-end:
+}
+
+/* Reclaim all kprobes on the free_list */
+static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list)
+{
+ struct optimized_kprobe *op, *tmp;
+
+ list_for_each_entry_safe(op, tmp, free_list, list) {
+ BUG_ON(!kprobe_unused(&op->kp));
+ list_del_init(&op->list);
+ free_aggr_kprobe(&op->kp);
+ }
+}
+
+/* Start optimizer after OPTIMIZE_DELAY passed */
+static __kprobes void kick_kprobe_optimizer(void)
+{
+ if (!delayed_work_pending(&optimizing_work))
+ schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+}
+
+/* Kprobe jump optimizer */
+static __kprobes void kprobe_optimizer(struct work_struct *work)
+{
+ LIST_HEAD(free_list);
+
+ /* Lock modules while optimizing kprobes */
+ mutex_lock(&module_mutex);
+ mutex_lock(&kprobe_mutex);
+
+ /*
+ * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
+ * kprobes before waiting for quiesence period.
+ */
+ do_unoptimize_kprobes(&free_list);
+
+ /*
+ * Step 2: Wait for quiesence period to ensure all running interrupts
+ * are done. Because optprobe may modify multiple instructions
+ * there is a chance that Nth instruction is interrupted. In that
+ * case, running interrupt can return to 2nd-Nth byte of jump
+ * instruction. This wait is for avoiding it.
+ */
+ synchronize_sched();
+
+ /* Step 3: Optimize kprobes after quiesence period */
+ do_optimize_kprobes();
+
+ /* Step 4: Free cleaned kprobes after quiesence period */
+ do_free_cleaned_kprobes(&free_list);
+
mutex_unlock(&kprobe_mutex);
mutex_unlock(&module_mutex);
+
+ /* Step 5: Kick optimizer again if needed */
+ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
+ kick_kprobe_optimizer();
+ else
+ /* Wake up all waiters */
+ complete_all(&optimizer_comp);
+}
+
+/* Wait for completing optimization and unoptimization */
+static __kprobes void wait_for_kprobe_optimizer(void)
+{
+ if (delayed_work_pending(&optimizing_work))
+ wait_for_completion(&optimizer_comp);
}
/* Optimize kprobe if p is ready to be optimized */
@@ -494,42 +627,99 @@ static __kprobes void optimize_kprobe(struct kprobe *p)
/* Check if it is already optimized. */
if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
return;
-
op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
- list_add(&op->list, &optimizing_list);
- if (!delayed_work_pending(&optimizing_work))
- schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+
+ if (!list_empty(&op->list))
+ /* This is under unoptimizing. Just dequeue the probe */
+ list_del_init(&op->list);
+ else {
+ list_add(&op->list, &optimizing_list);
+ kick_kprobe_optimizer();
+ }
+}
+
+/* Short cut to direct unoptimizing */
+static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+ get_online_cpus();
+ arch_unoptimize_kprobe(op);
+ put_online_cpus();
+ if (kprobe_disabled(&op->kp))
+ arch_disarm_kprobe(&op->kp);
}
/* Unoptimize a kprobe if p is optimized */
-static __kprobes void unoptimize_kprobe(struct kprobe *p)
+static __kprobes void unoptimize_kprobe(struct kprobe *p, bool force)
{
struct optimized_kprobe *op;
- if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
- op = container_of(p, struct optimized_kprobe, kp);
- if (!list_empty(&op->list))
- /* Dequeue from the optimization queue */
+ if (!kprobe_aggrprobe(p) || kprobe_disarmed(p))
+ return; /* This is not an optprobe nor optimized */
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!kprobe_optimized(p)) {
+ /* Unoptimized or unoptimizing case */
+ if (force && !list_empty(&op->list)) {
+ /*
+ * Only if this is unoptimizing kprobe and forced,
+ * forcibly unoptimize it. (No need to unoptimize
+ * unoptimized kprobe again :)
+ */
list_del_init(&op->list);
- else
- /* Replace jump with break */
- arch_unoptimize_kprobe(op);
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ force_unoptimize_kprobe(op);
+ }
+ return;
+ }
+
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ if (!list_empty(&op->list)) {
+ /* Dequeue from the optimization queue */
+ list_del_init(&op->list);
+ return;
+ }
+ /* Optimized kprobe case */
+ if (force)
+ /* Forcibly update the code: this is a special case */
+ force_unoptimize_kprobe(op);
+ else {
+ list_add(&op->list, &unoptimizing_list);
+ kick_kprobe_optimizer();
}
}
+/* Cancel unoptimizing for reusing */
+static void reuse_unused_kprobe(struct kprobe *ap)
+{
+ struct optimized_kprobe *op;
+
+ BUG_ON(!kprobe_unused(ap));
+ /*
+ * Unused kprobe MUST be on the way of delayed unoptimizing (means
+ * there is still a relative jump) and disabled.
+ */
+ op = container_of(ap, struct optimized_kprobe, kp);
+ if (unlikely(list_empty(&op->list)))
+ printk(KERN_WARNING "Warning: found a stray unused "
+ "aggrprobe@%p\n", ap->addr);
+ /* Enable the probe again */
+ ap->flags &= ~KPROBE_FLAG_DISABLED;
+ /* Optimize it again (remove from op->list) */
+ BUG_ON(!kprobe_optready(ap));
+ optimize_kprobe(ap);
+}
+
/* Remove optimized instructions */
static void __kprobes kill_optimized_kprobe(struct kprobe *p)
{
struct optimized_kprobe *op;
op = container_of(p, struct optimized_kprobe, kp);
- if (!list_empty(&op->list)) {
- /* Dequeue from the optimization queue */
+ if (!list_empty(&op->list))
+ /* Dequeue from the (un)optimization queue */
list_del_init(&op->list);
- op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
- }
- /* Don't unoptimize, because the target code will be freed. */
+
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ /* Don't touch the code, because it is already freed. */
arch_remove_optimized_kprobe(op);
}
@@ -542,16 +732,6 @@ static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
arch_prepare_optimized_kprobe(op);
}
-/* Free optimized instructions and optimized_kprobe */
-static __kprobes void free_aggr_kprobe(struct kprobe *p)
-{
- struct optimized_kprobe *op;
-
- op = container_of(p, struct optimized_kprobe, kp);
- arch_remove_optimized_kprobe(op);
- kfree(op);
-}
-
/* Allocate new optimized_kprobe and try to prepare optimized instructions */
static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
{
@@ -586,7 +766,8 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
op = container_of(ap, struct optimized_kprobe, kp);
if (!arch_prepared_optinsn(&op->optinsn)) {
/* If failed to setup optimizing, fallback to kprobe */
- free_aggr_kprobe(ap);
+ arch_remove_optimized_kprobe(op);
+ kfree(op);
return;
}
@@ -595,6 +776,7 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
}
#ifdef CONFIG_SYSCTL
+/* This should be called with kprobe_mutex locked */
static void __kprobes optimize_all_kprobes(void)
{
struct hlist_head *head;
@@ -607,17 +789,16 @@ static void __kprobes optimize_all_kprobes(void)
return;
kprobes_allow_optimization = true;
- mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist)
if (!kprobe_disabled(p))
optimize_kprobe(p);
}
- mutex_unlock(&text_mutex);
printk(KERN_INFO "Kprobes globally optimized\n");
}
+/* This should be called with kprobe_mutex locked */
static void __kprobes unoptimize_all_kprobes(void)
{
struct hlist_head *head;
@@ -630,21 +811,16 @@ static void __kprobes unoptimize_all_kprobes(void)
return;
kprobes_allow_optimization = false;
- printk(KERN_INFO "Kprobes globally unoptimized\n");
- get_online_cpus(); /* For avoiding text_mutex deadlock */
- mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!kprobe_disabled(p))
- unoptimize_kprobe(p);
+ unoptimize_kprobe(p, false);
}
}
-
- mutex_unlock(&text_mutex);
- put_online_cpus();
- /* Allow all currently running kprobes to complete */
- synchronize_sched();
+ /* Wait for unoptimizing completion */
+ wait_for_kprobe_optimizer();
+ printk(KERN_INFO "Kprobes globally unoptimized\n");
}
int sysctl_kprobes_optimization;
@@ -668,44 +844,60 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
}
#endif /* CONFIG_SYSCTL */
+/* Put a breakpoint for a probe. Must be called with text_mutex locked */
static void __kprobes __arm_kprobe(struct kprobe *p)
{
- struct kprobe *old_p;
+ struct kprobe *_p;
/* Check collision with other optimized kprobes */
- old_p = get_optimized_kprobe((unsigned long)p->addr);
- if (unlikely(old_p))
- unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
+ _p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(_p))
+ /* Fallback to unoptimized kprobe */
+ unoptimize_kprobe(_p, true);
arch_arm_kprobe(p);
optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */
}
-static void __kprobes __disarm_kprobe(struct kprobe *p)
+/* Remove the breakpoint of a probe. Must be called with text_mutex locked */
+static void __kprobes __disarm_kprobe(struct kprobe *p, bool reopt)
{
- struct kprobe *old_p;
+ struct kprobe *_p;
- unoptimize_kprobe(p); /* Try to unoptimize */
- arch_disarm_kprobe(p);
+ unoptimize_kprobe(p, false); /* Try to unoptimize */
- /* If another kprobe was blocked, optimize it. */
- old_p = get_optimized_kprobe((unsigned long)p->addr);
- if (unlikely(old_p))
- optimize_kprobe(old_p);
+ if (!kprobe_queued(p)) {
+ arch_disarm_kprobe(p);
+ /* If another kprobe was blocked, optimize it. */
+ _p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(_p) && reopt)
+ optimize_kprobe(_p);
+ }
+ /* TODO: reoptimize others after unoptimized this probe */
}
#else /* !CONFIG_OPTPROBES */
#define optimize_kprobe(p) do {} while (0)
-#define unoptimize_kprobe(p) do {} while (0)
+#define unoptimize_kprobe(p, f) do {} while (0)
#define kill_optimized_kprobe(p) do {} while (0)
#define prepare_optimized_kprobe(p) do {} while (0)
#define try_to_optimize_kprobe(p) do {} while (0)
#define __arm_kprobe(p) arch_arm_kprobe(p)
-#define __disarm_kprobe(p) arch_disarm_kprobe(p)
+#define __disarm_kprobe(p, o) arch_disarm_kprobe(p)
+#define kprobe_disarmed(p) kprobe_disabled(p)
+#define wait_for_kprobe_optimizer() do {} while (0)
+
+/* There should be no unused kprobes can be reused without optimization */
+static void reuse_unused_kprobe(struct kprobe *ap)
+{
+ printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
+ BUG_ON(kprobe_unused(ap));
+}
static __kprobes void free_aggr_kprobe(struct kprobe *p)
{
+ arch_remove_kprobe(p);
kfree(p);
}
@@ -731,11 +923,10 @@ static void __kprobes arm_kprobe(struct kprobe *kp)
/* Disarm a kprobe with text_mutex */
static void __kprobes disarm_kprobe(struct kprobe *kp)
{
- get_online_cpus(); /* For avoiding text_mutex deadlock */
+ /* Ditto */
mutex_lock(&text_mutex);
- __disarm_kprobe(kp);
+ __disarm_kprobe(kp, true);
mutex_unlock(&text_mutex);
- put_online_cpus();
}
/*
@@ -941,7 +1132,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
if (p->break_handler || p->post_handler)
- unoptimize_kprobe(ap); /* Fall back to normal kprobe */
+ unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */
if (p->break_handler) {
if (ap->break_handler)
@@ -992,19 +1183,21 @@ static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
* This is the second or subsequent kprobe at the address - handle
* the intricacies
*/
-static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
+static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
struct kprobe *p)
{
int ret = 0;
- struct kprobe *ap = old_p;
+ struct kprobe *ap = orig_p;
- if (!kprobe_aggrprobe(old_p)) {
- /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */
- ap = alloc_aggr_kprobe(old_p);
+ if (!kprobe_aggrprobe(orig_p)) {
+ /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */
+ ap = alloc_aggr_kprobe(orig_p);
if (!ap)
return -ENOMEM;
- init_aggr_kprobe(ap, old_p);
- }
+ init_aggr_kprobe(ap, orig_p);
+ } else if (kprobe_unused(ap))
+ /* This probe is going to die. Rescue it */
+ reuse_unused_kprobe(ap);
if (kprobe_gone(ap)) {
/*
@@ -1038,23 +1231,6 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
return add_new_kprobe(ap, p);
}
-/* Try to disable aggr_kprobe, and return 1 if succeeded.*/
-static int __kprobes try_to_disable_aggr_kprobe(struct kprobe *p)
-{
- struct kprobe *kp;
-
- list_for_each_entry_rcu(kp, &p->list, list) {
- if (!kprobe_disabled(kp))
- /*
- * There is an active probe on the list.
- * We can't disable aggr_kprobe.
- */
- return 0;
- }
- p->flags |= KPROBE_FLAG_DISABLED;
- return 1;
-}
-
static int __kprobes in_kprobes_functions(unsigned long addr)
{
struct kprobe_blackpoint *kb;
@@ -1097,34 +1273,33 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
/* Check passed kprobe is valid and return kprobe in kprobe_table. */
static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
{
- struct kprobe *old_p, *list_p;
+ struct kprobe *ap, *list_p;
- old_p = get_kprobe(p->addr);
- if (unlikely(!old_p))
+ ap = get_kprobe(p->addr);
+ if (unlikely(!ap))
return NULL;
- if (p != old_p) {
- list_for_each_entry_rcu(list_p, &old_p->list, list)
+ if (p != ap) {
+ list_for_each_entry_rcu(list_p, &ap->list, list)
if (list_p == p)
/* kprobe p is a valid probe */
goto valid;
return NULL;
}
valid:
- return old_p;
+ return ap;
}
/* Return error if the kprobe is being re-registered */
static inline int check_kprobe_rereg(struct kprobe *p)
{
int ret = 0;
- struct kprobe *old_p;
mutex_lock(&kprobe_mutex);
- old_p = __get_valid_kprobe(p);
- if (old_p)
+ if (__get_valid_kprobe(p))
ret = -EINVAL;
mutex_unlock(&kprobe_mutex);
+
return ret;
}
@@ -1144,14 +1319,13 @@ int __kprobes register_kprobe(struct kprobe *p)
if (ret)
return ret;
+ jump_label_lock();
preempt_disable();
if (!kernel_text_address((unsigned long) p->addr) ||
in_kprobes_functions((unsigned long) p->addr) ||
ftrace_text_reserved(p->addr, p->addr) ||
- jump_label_text_reserved(p->addr, p->addr)) {
- preempt_enable();
- return -EINVAL;
- }
+ jump_label_text_reserved(p->addr, p->addr))
+ goto fail_with_jump_label;
/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
p->flags &= KPROBE_FLAG_DISABLED;
@@ -1165,10 +1339,9 @@ int __kprobes register_kprobe(struct kprobe *p)
* We must hold a refcount of the probed module while updating
* its code to prohibit unexpected unloading.
*/
- if (unlikely(!try_module_get(probed_mod))) {
- preempt_enable();
- return -EINVAL;
- }
+ if (unlikely(!try_module_get(probed_mod)))
+ goto fail_with_jump_label;
+
/*
* If the module freed .init.text, we couldn't insert
* kprobes in there.
@@ -1176,16 +1349,18 @@ int __kprobes register_kprobe(struct kprobe *p)
if (within_module_init((unsigned long)p->addr, probed_mod) &&
probed_mod->state != MODULE_STATE_COMING) {
module_put(probed_mod);
- preempt_enable();
- return -EINVAL;
+ goto fail_with_jump_label;
}
}
preempt_enable();
+ jump_label_unlock();
p->nmissed = 0;
INIT_LIST_HEAD(&p->list);
mutex_lock(&kprobe_mutex);
+ jump_label_lock(); /* needed to call jump_label_text_reserved() */
+
get_online_cpus(); /* For avoiding text_mutex deadlock. */
mutex_lock(&text_mutex);
@@ -1213,76 +1388,136 @@ int __kprobes register_kprobe(struct kprobe *p)
out:
mutex_unlock(&text_mutex);
put_online_cpus();
+ jump_label_unlock();
mutex_unlock(&kprobe_mutex);
if (probed_mod)
module_put(probed_mod);
return ret;
+
+fail_with_jump_label:
+ preempt_enable();
+ jump_label_unlock();
+ return -EINVAL;
}
EXPORT_SYMBOL_GPL(register_kprobe);
+/* Check if all probes on the aggrprobe are disabled */
+static int __kprobes aggr_kprobe_disabled(struct kprobe *ap)
+{
+ struct kprobe *kp;
+
+ list_for_each_entry_rcu(kp, &ap->list, list)
+ if (!kprobe_disabled(kp))
+ /*
+ * There is an active probe on the list.
+ * We can't disable this ap.
+ */
+ return 0;
+
+ return 1;
+}
+
+/* Disable one kprobe: Make sure called under kprobe_mutex is locked */
+static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p)
+{
+ struct kprobe *orig_p;
+
+ /* Get an original kprobe for return */
+ orig_p = __get_valid_kprobe(p);
+ if (unlikely(orig_p == NULL))
+ return NULL;
+
+ if (!kprobe_disabled(p)) {
+ /* Disable probe if it is a child probe */
+ if (p != orig_p)
+ p->flags |= KPROBE_FLAG_DISABLED;
+
+ /* Try to disarm and disable this/parent probe */
+ if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
+ disarm_kprobe(orig_p);
+ orig_p->flags |= KPROBE_FLAG_DISABLED;
+ }
+ }
+
+ return orig_p;
+}
+
/*
* Unregister a kprobe without a scheduler synchronization.
*/
static int __kprobes __unregister_kprobe_top(struct kprobe *p)
{
- struct kprobe *old_p, *list_p;
+ struct kprobe *ap, *list_p;
- old_p = __get_valid_kprobe(p);
- if (old_p == NULL)
+ /* Disable kprobe. This will disarm it if needed. */
+ ap = __disable_kprobe(p);
+ if (ap == NULL)
return -EINVAL;
- if (old_p == p ||
- (kprobe_aggrprobe(old_p) &&
- list_is_singular(&old_p->list))) {
+ if (ap == p)
/*
- * Only probe on the hash list. Disarm only if kprobes are
- * enabled and not gone - otherwise, the breakpoint would
- * already have been removed. We save on flushing icache.
+ * This probe is an independent(and non-optimized) kprobe
+ * (not an aggrprobe). Remove from the hash list.
*/
- if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
- disarm_kprobe(old_p);
- hlist_del_rcu(&old_p->hlist);
- } else {
+ goto disarmed;
+
+ /* Following process expects this probe is an aggrprobe */
+ WARN_ON(!kprobe_aggrprobe(ap));
+
+ if (list_is_singular(&ap->list) && kprobe_disarmed(ap))
+ /*
+ * !disarmed could be happen if the probe is under delayed
+ * unoptimizing.
+ */
+ goto disarmed;
+ else {
+ /* If disabling probe has special handlers, update aggrprobe */
if (p->break_handler && !kprobe_gone(p))
- old_p->break_handler = NULL;
+ ap->break_handler = NULL;
if (p->post_handler && !kprobe_gone(p)) {
- list_for_each_entry_rcu(list_p, &old_p->list, list) {
+ list_for_each_entry_rcu(list_p, &ap->list, list) {
if ((list_p != p) && (list_p->post_handler))
goto noclean;
}
- old_p->post_handler = NULL;
+ ap->post_handler = NULL;
}
noclean:
+ /*
+ * Remove from the aggrprobe: this path will do nothing in
+ * __unregister_kprobe_bottom().
+ */
list_del_rcu(&p->list);
- if (!kprobe_disabled(old_p)) {
- try_to_disable_aggr_kprobe(old_p);
- if (!kprobes_all_disarmed) {
- if (kprobe_disabled(old_p))
- disarm_kprobe(old_p);
- else
- /* Try to optimize this probe again */
- optimize_kprobe(old_p);
- }
- }
+ if (!kprobe_disabled(ap) && !kprobes_all_disarmed)
+ /*
+ * Try to optimize this probe again, because post
+ * handler may have been changed.
+ */
+ optimize_kprobe(ap);
}
return 0;
+
+disarmed:
+ BUG_ON(!kprobe_disarmed(ap));
+ hlist_del_rcu(&ap->hlist);
+ return 0;
}
static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
{
- struct kprobe *old_p;
+ struct kprobe *ap;
if (list_empty(&p->list))
+ /* This is an independent kprobe */
arch_remove_kprobe(p);
else if (list_is_singular(&p->list)) {
- /* "p" is the last child of an aggr_kprobe */
- old_p = list_entry(p->list.next, struct kprobe, list);
+ /* This is the last child of an aggrprobe */
+ ap = list_entry(p->list.next, struct kprobe, list);
list_del(&p->list);
- arch_remove_kprobe(old_p);
- free_aggr_kprobe(old_p);
+ free_aggr_kprobe(ap);
}
+ /* Otherwise, do nothing. */
}
int __kprobes register_kprobes(struct kprobe **kps, int num)
@@ -1600,29 +1835,13 @@ static void __kprobes kill_kprobe(struct kprobe *p)
int __kprobes disable_kprobe(struct kprobe *kp)
{
int ret = 0;
- struct kprobe *p;
mutex_lock(&kprobe_mutex);
- /* Check whether specified probe is valid. */
- p = __get_valid_kprobe(kp);
- if (unlikely(p == NULL)) {
+ /* Disable this kprobe */
+ if (__disable_kprobe(kp) == NULL)
ret = -EINVAL;
- goto out;
- }
- /* If the probe is already disabled (or gone), just return */
- if (kprobe_disabled(kp))
- goto out;
-
- kp->flags |= KPROBE_FLAG_DISABLED;
- if (p != kp)
- /* When kp != p, p is always enabled. */
- try_to_disable_aggr_kprobe(p);
-
- if (!kprobes_all_disarmed && kprobe_disabled(p))
- disarm_kprobe(p);
-out:
mutex_unlock(&kprobe_mutex);
return ret;
}
@@ -1920,36 +2139,27 @@ static void __kprobes disarm_all_kprobes(void)
mutex_lock(&kprobe_mutex);
/* If kprobes are already disarmed, just return */
- if (kprobes_all_disarmed)
- goto already_disabled;
+ if (kprobes_all_disarmed) {
+ mutex_unlock(&kprobe_mutex);
+ return;
+ }
kprobes_all_disarmed = true;
printk(KERN_INFO "Kprobes globally disabled\n");
- /*
- * Here we call get_online_cpus() for avoiding text_mutex deadlock,
- * because disarming may also unoptimize kprobes.
- */
- get_online_cpus();
mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
- __disarm_kprobe(p);
+ __disarm_kprobe(p, false);
}
}
-
mutex_unlock(&text_mutex);
- put_online_cpus();
mutex_unlock(&kprobe_mutex);
- /* Allow all currently running kprobes to complete */
- synchronize_sched();
- return;
-already_disabled:
- mutex_unlock(&kprobe_mutex);
- return;
+ /* Wait for disarming all kprobes by optimizer */
+ wait_for_kprobe_optimizer();
}
/*
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2dc3786349d..5355cfd44a3 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -148,7 +148,7 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
wait_for_completion(&create.done);
if (!IS_ERR(create.result)) {
- struct sched_param param = { .sched_priority = 0 };
+ static struct sched_param param = { .sched_priority = 0 };
va_list args;
va_start(args, namefmt);
@@ -265,6 +265,17 @@ int kthreadd(void *unused)
return 0;
}
+void __init_kthread_worker(struct kthread_worker *worker,
+ const char *name,
+ struct lock_class_key *key)
+{
+ spin_lock_init(&worker->lock);
+ lockdep_set_class_and_name(&worker->lock, key, name);
+ INIT_LIST_HEAD(&worker->work_list);
+ worker->task = NULL;
+}
+EXPORT_SYMBOL_GPL(__init_kthread_worker);
+
/**
* kthread_worker_fn - kthread function to process kthread_worker
* @worker_ptr: pointer to initialized kthread_worker
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 877fb306d41..17110a4a4fc 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -194,14 +194,7 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
account_global_scheduler_latency(tsk, &lat);
- /*
- * short term hack; if we're > 32 we stop; future we recycle:
- */
- tsk->latency_record_count++;
- if (tsk->latency_record_count >= LT_SAVECOUNT)
- goto out_unlock;
-
- for (i = 0; i < LT_SAVECOUNT; i++) {
+ for (i = 0; i < tsk->latency_record_count; i++) {
struct latency_record *mylat;
int same = 1;
@@ -227,8 +220,14 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
}
}
+ /*
+ * short term hack; if we're > 32 we stop; future we recycle:
+ */
+ if (tsk->latency_record_count >= LT_SAVECOUNT)
+ goto out_unlock;
+
/* Allocated a new one: */
- i = tsk->latency_record_count;
+ i = tsk->latency_record_count++;
memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record));
out_unlock:
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 59b76c8ce9d..1969d2fc4b3 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -494,7 +494,6 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
namelen += 2;
for (i = 0; i < LOCKSTAT_POINTS; i++) {
- char sym[KSYM_SYMBOL_LEN];
char ip[32];
if (class->contention_point[i] == 0)
@@ -503,15 +502,13 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
if (!i)
seq_line(m, '-', 40-namelen, namelen);
- sprint_symbol(sym, class->contention_point[i]);
snprintf(ip, sizeof(ip), "[<%p>]",
(void *)class->contention_point[i]);
- seq_printf(m, "%40s %14lu %29s %s\n", name,
- stats->contention_point[i],
- ip, sym);
+ seq_printf(m, "%40s %14lu %29s %pS\n",
+ name, stats->contention_point[i],
+ ip, (void *)class->contention_point[i]);
}
for (i = 0; i < LOCKSTAT_POINTS; i++) {
- char sym[KSYM_SYMBOL_LEN];
char ip[32];
if (class->contending_point[i] == 0)
@@ -520,12 +517,11 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
if (!i)
seq_line(m, '-', 40-namelen, namelen);
- sprint_symbol(sym, class->contending_point[i]);
snprintf(ip, sizeof(ip), "[<%p>]",
(void *)class->contending_point[i]);
- seq_printf(m, "%40s %14lu %29s %s\n", name,
- stats->contending_point[i],
- ip, sym);
+ seq_printf(m, "%40s %14lu %29s %pS\n",
+ name, stats->contending_point[i],
+ ip, (void *)class->contending_point[i]);
}
if (i) {
seq_puts(m, "\n");
diff --git a/kernel/module.c b/kernel/module.c
index 2df46301a7a..34e00b708fa 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -56,6 +56,7 @@
#include <linux/percpu.h>
#include <linux/kmemleak.h>
#include <linux/jump_label.h>
+#include <linux/pfn.h>
#define CREATE_TRACE_POINTS
#include <trace/events/module.h>
@@ -70,6 +71,26 @@
#define ARCH_SHF_SMALL 0
#endif
+/*
+ * Modules' sections will be aligned on page boundaries
+ * to ensure complete separation of code and data, but
+ * only when CONFIG_DEBUG_SET_MODULE_RONX=y
+ */
+#ifdef CONFIG_DEBUG_SET_MODULE_RONX
+# define debug_align(X) ALIGN(X, PAGE_SIZE)
+#else
+# define debug_align(X) (X)
+#endif
+
+/*
+ * Given BASE and SIZE this macro calculates the number of pages the
+ * memory regions occupies
+ */
+#define MOD_NUMBER_OF_PAGES(BASE, SIZE) (((SIZE) > 0) ? \
+ (PFN_DOWN((unsigned long)(BASE) + (SIZE) - 1) - \
+ PFN_DOWN((unsigned long)BASE) + 1) \
+ : (0UL))
+
/* If this is set, the section belongs in the init part of the module */
#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1))
@@ -1542,6 +1563,115 @@ static int __unlink_module(void *_mod)
return 0;
}
+#ifdef CONFIG_DEBUG_SET_MODULE_RONX
+/*
+ * LKM RO/NX protection: protect module's text/ro-data
+ * from modification and any data from execution.
+ */
+void set_page_attributes(void *start, void *end, int (*set)(unsigned long start, int num_pages))
+{
+ unsigned long begin_pfn = PFN_DOWN((unsigned long)start);
+ unsigned long end_pfn = PFN_DOWN((unsigned long)end);
+
+ if (end_pfn > begin_pfn)
+ set(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn);
+}
+
+static void set_section_ro_nx(void *base,
+ unsigned long text_size,
+ unsigned long ro_size,
+ unsigned long total_size)
+{
+ /* begin and end PFNs of the current subsection */
+ unsigned long begin_pfn;
+ unsigned long end_pfn;
+
+ /*
+ * Set RO for module text and RO-data:
+ * - Always protect first page.
+ * - Do not protect last partial page.
+ */
+ if (ro_size > 0)
+ set_page_attributes(base, base + ro_size, set_memory_ro);
+
+ /*
+ * Set NX permissions for module data:
+ * - Do not protect first partial page.
+ * - Always protect last page.
+ */
+ if (total_size > text_size) {
+ begin_pfn = PFN_UP((unsigned long)base + text_size);
+ end_pfn = PFN_UP((unsigned long)base + total_size);
+ if (end_pfn > begin_pfn)
+ set_memory_nx(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn);
+ }
+}
+
+/* Setting memory back to RW+NX before releasing it */
+void unset_section_ro_nx(struct module *mod, void *module_region)
+{
+ unsigned long total_pages;
+
+ if (mod->module_core == module_region) {
+ /* Set core as NX+RW */
+ total_pages = MOD_NUMBER_OF_PAGES(mod->module_core, mod->core_size);
+ set_memory_nx((unsigned long)mod->module_core, total_pages);
+ set_memory_rw((unsigned long)mod->module_core, total_pages);
+
+ } else if (mod->module_init == module_region) {
+ /* Set init as NX+RW */
+ total_pages = MOD_NUMBER_OF_PAGES(mod->module_init, mod->init_size);
+ set_memory_nx((unsigned long)mod->module_init, total_pages);
+ set_memory_rw((unsigned long)mod->module_init, total_pages);
+ }
+}
+
+/* Iterate through all modules and set each module's text as RW */
+void set_all_modules_text_rw()
+{
+ struct module *mod;
+
+ mutex_lock(&module_mutex);
+ list_for_each_entry_rcu(mod, &modules, list) {
+ if ((mod->module_core) && (mod->core_text_size)) {
+ set_page_attributes(mod->module_core,
+ mod->module_core + mod->core_text_size,
+ set_memory_rw);
+ }
+ if ((mod->module_init) && (mod->init_text_size)) {
+ set_page_attributes(mod->module_init,
+ mod->module_init + mod->init_text_size,
+ set_memory_rw);
+ }
+ }
+ mutex_unlock(&module_mutex);
+}
+
+/* Iterate through all modules and set each module's text as RO */
+void set_all_modules_text_ro()
+{
+ struct module *mod;
+
+ mutex_lock(&module_mutex);
+ list_for_each_entry_rcu(mod, &modules, list) {
+ if ((mod->module_core) && (mod->core_text_size)) {
+ set_page_attributes(mod->module_core,
+ mod->module_core + mod->core_text_size,
+ set_memory_ro);
+ }
+ if ((mod->module_init) && (mod->init_text_size)) {
+ set_page_attributes(mod->module_init,
+ mod->module_init + mod->init_text_size,
+ set_memory_ro);
+ }
+ }
+ mutex_unlock(&module_mutex);
+}
+#else
+static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { }
+static inline void unset_section_ro_nx(struct module *mod, void *module_region) { }
+#endif
+
/* Free a module, remove from lists, etc. */
static void free_module(struct module *mod)
{
@@ -1566,6 +1696,7 @@ static void free_module(struct module *mod)
destroy_params(mod->kp, mod->num_kp);
/* This may be NULL, but that's OK */
+ unset_section_ro_nx(mod, mod->module_init);
module_free(mod, mod->module_init);
kfree(mod->args);
percpu_modfree(mod);
@@ -1574,6 +1705,7 @@ static void free_module(struct module *mod)
lockdep_free_key_range(mod->module_core, mod->core_size);
/* Finally, free the core (containing the module structure) */
+ unset_section_ro_nx(mod, mod->module_core);
module_free(mod, mod->module_core);
#ifdef CONFIG_MPU
@@ -1777,8 +1909,19 @@ static void layout_sections(struct module *mod, struct load_info *info)
s->sh_entsize = get_offset(mod, &mod->core_size, s, i);
DEBUGP("\t%s\n", name);
}
- if (m == 0)
+ switch (m) {
+ case 0: /* executable */
+ mod->core_size = debug_align(mod->core_size);
mod->core_text_size = mod->core_size;
+ break;
+ case 1: /* RO: text and ro-data */
+ mod->core_size = debug_align(mod->core_size);
+ mod->core_ro_size = mod->core_size;
+ break;
+ case 3: /* whole core */
+ mod->core_size = debug_align(mod->core_size);
+ break;
+ }
}
DEBUGP("Init section allocation order:\n");
@@ -1796,8 +1939,19 @@ static void layout_sections(struct module *mod, struct load_info *info)
| INIT_OFFSET_MASK);
DEBUGP("\t%s\n", sname);
}
- if (m == 0)
+ switch (m) {
+ case 0: /* executable */
+ mod->init_size = debug_align(mod->init_size);
mod->init_text_size = mod->init_size;
+ break;
+ case 1: /* RO: text and ro-data */
+ mod->init_size = debug_align(mod->init_size);
+ mod->init_ro_size = mod->init_size;
+ break;
+ case 3: /* whole init */
+ mod->init_size = debug_align(mod->init_size);
+ break;
+ }
}
}
@@ -2037,7 +2191,7 @@ static inline void layout_symtab(struct module *mod, struct load_info *info)
{
}
-static void add_kallsyms(struct module *mod, struct load_info *info)
+static void add_kallsyms(struct module *mod, const struct load_info *info)
{
}
#endif /* CONFIG_KALLSYMS */
@@ -2326,6 +2480,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
mod->num_trace_events, GFP_KERNEL);
#endif
+#ifdef CONFIG_TRACING
+ mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
+ sizeof(*mod->trace_bprintk_fmt_start),
+ &mod->num_trace_bprintk_fmt);
+ /*
+ * This section contains pointers to allocated objects in the trace
+ * code and not scanning it leads to false positives.
+ */
+ kmemleak_scan_area(mod->trace_bprintk_fmt_start,
+ sizeof(*mod->trace_bprintk_fmt_start) *
+ mod->num_trace_bprintk_fmt, GFP_KERNEL);
+#endif
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
/* sechdrs[0].sh_size is always zero */
mod->ftrace_callsites = section_objs(info, "__mcount_loc",
@@ -2710,6 +2876,18 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
blocking_notifier_call_chain(&module_notify_list,
MODULE_STATE_COMING, mod);
+ /* Set RO and NX regions for core */
+ set_section_ro_nx(mod->module_core,
+ mod->core_text_size,
+ mod->core_ro_size,
+ mod->core_size);
+
+ /* Set RO and NX regions for init */
+ set_section_ro_nx(mod->module_init,
+ mod->init_text_size,
+ mod->init_ro_size,
+ mod->init_size);
+
do_mod_ctors(mod);
/* Start the module */
if (mod->init != NULL)
@@ -2753,6 +2931,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
mod->symtab = mod->core_symtab;
mod->strtab = mod->core_strtab;
#endif
+ unset_section_ro_nx(mod, mod->module_init);
module_free(mod, mod->module_init);
mod->module_init = NULL;
mod->init_size = 0;
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 200407c1502..a5889fb28ec 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -199,7 +199,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* memory barriers as we'll eventually observe the right
* values at the cost of a few extra spins.
*/
- cpu_relax();
+ arch_mutex_cpu_relax();
}
#endif
spin_lock_mutex(&lock->wait_lock, flags);
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 2a5dfec8efe..2c98ad94ba0 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -85,6 +85,14 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
return ERR_PTR(-EPERM);
if (!cgroup_is_descendant(cgroup, current))
return ERR_PTR(-EPERM);
+ if (test_bit(CGRP_CLONE_CHILDREN, &cgroup->flags)) {
+ printk("ns_cgroup can't be created with parent "
+ "'clone_children' set.\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ printk_once("ns_cgroup deprecated: consider using the "
+ "'clone_children' flag without the ns_cgroup.\n");
ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
if (!ns_cgroup)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index f309e8014c7..11847bf1e8c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -13,6 +13,7 @@
#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/smp.h>
+#include <linux/idr.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
@@ -21,7 +22,9 @@
#include <linux/dcache.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
+#include <linux/reboot.h>
#include <linux/vmstat.h>
+#include <linux/device.h>
#include <linux/vmalloc.h>
#include <linux/hardirq.h>
#include <linux/rculist.h>
@@ -31,6 +34,7 @@
#include <linux/kernel_stat.h>
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
#include <asm/irq_regs.h>
@@ -132,6 +136,28 @@ static void unclone_ctx(struct perf_event_context *ctx)
}
}
+static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
+{
+ /*
+ * only top level events have the pid namespace they were created in
+ */
+ if (event->parent)
+ event = event->parent;
+
+ return task_tgid_nr_ns(p, event->ns);
+}
+
+static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
+{
+ /*
+ * only top level events have the pid namespace they were created in
+ */
+ if (event->parent)
+ event = event->parent;
+
+ return task_pid_nr_ns(p, event->ns);
+}
+
/*
* If we inherit events we want to return the parent event id
* to userspace.
@@ -311,9 +337,84 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
ctx->nr_stat++;
}
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__read_size(struct perf_event *event)
+{
+ int entry = sizeof(u64); /* value */
+ int size = 0;
+ int nr = 1;
+
+ if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+ size += sizeof(u64);
+
+ if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+ size += sizeof(u64);
+
+ if (event->attr.read_format & PERF_FORMAT_ID)
+ entry += sizeof(u64);
+
+ if (event->attr.read_format & PERF_FORMAT_GROUP) {
+ nr += event->group_leader->nr_siblings;
+ size += sizeof(u64);
+ }
+
+ size += entry * nr;
+ event->read_size = size;
+}
+
+static void perf_event__header_size(struct perf_event *event)
+{
+ struct perf_sample_data *data;
+ u64 sample_type = event->attr.sample_type;
+ u16 size = 0;
+
+ perf_event__read_size(event);
+
+ if (sample_type & PERF_SAMPLE_IP)
+ size += sizeof(data->ip);
+
+ if (sample_type & PERF_SAMPLE_ADDR)
+ size += sizeof(data->addr);
+
+ if (sample_type & PERF_SAMPLE_PERIOD)
+ size += sizeof(data->period);
+
+ if (sample_type & PERF_SAMPLE_READ)
+ size += event->read_size;
+
+ event->header_size = size;
+}
+
+static void perf_event__id_header_size(struct perf_event *event)
+{
+ struct perf_sample_data *data;
+ u64 sample_type = event->attr.sample_type;
+ u16 size = 0;
+
+ if (sample_type & PERF_SAMPLE_TID)
+ size += sizeof(data->tid_entry);
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ size += sizeof(data->time);
+
+ if (sample_type & PERF_SAMPLE_ID)
+ size += sizeof(data->id);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ size += sizeof(data->stream_id);
+
+ if (sample_type & PERF_SAMPLE_CPU)
+ size += sizeof(data->cpu_entry);
+
+ event->id_header_size = size;
+}
+
static void perf_group_attach(struct perf_event *event)
{
- struct perf_event *group_leader = event->group_leader;
+ struct perf_event *group_leader = event->group_leader, *pos;
/*
* We can have double attach due to group movement in perf_event_open.
@@ -332,6 +433,11 @@ static void perf_group_attach(struct perf_event *event)
list_add_tail(&event->group_entry, &group_leader->sibling_list);
group_leader->nr_siblings++;
+
+ perf_event__header_size(group_leader);
+
+ list_for_each_entry(pos, &group_leader->sibling_list, group_entry)
+ perf_event__header_size(pos);
}
/*
@@ -390,7 +496,7 @@ static void perf_group_detach(struct perf_event *event)
if (event->group_leader != event) {
list_del_init(&event->group_entry);
event->group_leader->nr_siblings--;
- return;
+ goto out;
}
if (!list_empty(&event->group_entry))
@@ -409,6 +515,12 @@ static void perf_group_detach(struct perf_event *event)
/* Inherit group flags from the previous leader */
sibling->group_flags = event->group_flags;
}
+
+out:
+ perf_event__header_size(event->group_leader);
+
+ list_for_each_entry(tmp, &event->group_leader->sibling_list, group_entry)
+ perf_event__header_size(tmp);
}
static inline int
@@ -417,8 +529,8 @@ event_filter_match(struct perf_event *event)
return event->cpu == -1 || event->cpu == smp_processor_id();
}
-static int
-__event_sched_out(struct perf_event *event,
+static void
+event_sched_out(struct perf_event *event,
struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx)
{
@@ -437,13 +549,14 @@ __event_sched_out(struct perf_event *event,
}
if (event->state != PERF_EVENT_STATE_ACTIVE)
- return 0;
+ return;
event->state = PERF_EVENT_STATE_INACTIVE;
if (event->pending_disable) {
event->pending_disable = 0;
event->state = PERF_EVENT_STATE_OFF;
}
+ event->tstamp_stopped = ctx->time;
event->pmu->del(event, 0);
event->oncpu = -1;
@@ -452,19 +565,6 @@ __event_sched_out(struct perf_event *event,
ctx->nr_active--;
if (event->attr.exclusive || !cpuctx->active_oncpu)
cpuctx->exclusive = 0;
- return 1;
-}
-
-static void
-event_sched_out(struct perf_event *event,
- struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- int ret;
-
- ret = __event_sched_out(event, cpuctx, ctx);
- if (ret)
- event->tstamp_stopped = ctx->time;
}
static void
@@ -664,7 +764,7 @@ retry:
}
static int
-__event_sched_in(struct perf_event *event,
+event_sched_in(struct perf_event *event,
struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx)
{
@@ -684,6 +784,10 @@ __event_sched_in(struct perf_event *event,
return -EAGAIN;
}
+ event->tstamp_running += ctx->time - event->tstamp_stopped;
+
+ event->shadow_ctx_time = ctx->time - ctx->timestamp;
+
if (!is_software_event(event))
cpuctx->active_oncpu++;
ctx->nr_active++;
@@ -694,35 +798,6 @@ __event_sched_in(struct perf_event *event,
return 0;
}
-static inline int
-event_sched_in(struct perf_event *event,
- struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- int ret = __event_sched_in(event, cpuctx, ctx);
- if (ret)
- return ret;
- event->tstamp_running += ctx->time - event->tstamp_stopped;
- return 0;
-}
-
-static void
-group_commit_event_sched_in(struct perf_event *group_event,
- struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- struct perf_event *event;
- u64 now = ctx->time;
-
- group_event->tstamp_running += now - group_event->tstamp_stopped;
- /*
- * Schedule in siblings as one group (if any):
- */
- list_for_each_entry(event, &group_event->sibling_list, group_entry) {
- event->tstamp_running += now - event->tstamp_stopped;
- }
-}
-
static int
group_sched_in(struct perf_event *group_event,
struct perf_cpu_context *cpuctx,
@@ -730,19 +805,15 @@ group_sched_in(struct perf_event *group_event,
{
struct perf_event *event, *partial_group = NULL;
struct pmu *pmu = group_event->pmu;
+ u64 now = ctx->time;
+ bool simulate = false;
if (group_event->state == PERF_EVENT_STATE_OFF)
return 0;
pmu->start_txn(pmu);
- /*
- * use __event_sched_in() to delay updating tstamp_running
- * until the transaction is committed. In case of failure
- * we will keep an unmodified tstamp_running which is a
- * requirement to get correct timing information
- */
- if (__event_sched_in(group_event, cpuctx, ctx)) {
+ if (event_sched_in(group_event, cpuctx, ctx)) {
pmu->cancel_txn(pmu);
return -EAGAIN;
}
@@ -751,31 +822,42 @@ group_sched_in(struct perf_event *group_event,
* Schedule in siblings as one group (if any):
*/
list_for_each_entry(event, &group_event->sibling_list, group_entry) {
- if (__event_sched_in(event, cpuctx, ctx)) {
+ if (event_sched_in(event, cpuctx, ctx)) {
partial_group = event;
goto group_error;
}
}
- if (!pmu->commit_txn(pmu)) {
- /* commit tstamp_running */
- group_commit_event_sched_in(group_event, cpuctx, ctx);
+ if (!pmu->commit_txn(pmu))
return 0;
- }
+
group_error:
/*
* Groups can be scheduled in as one unit only, so undo any
* partial group before returning:
+ * The events up to the failed event are scheduled out normally,
+ * tstamp_stopped will be updated.
*
- * use __event_sched_out() to avoid updating tstamp_stopped
- * because the event never actually ran
+ * The failed events and the remaining siblings need to have
+ * their timings updated as if they had gone thru event_sched_in()
+ * and event_sched_out(). This is required to get consistent timings
+ * across the group. This also takes care of the case where the group
+ * could never be scheduled by ensuring tstamp_stopped is set to mark
+ * the time the event was actually stopped, such that time delta
+ * calculation in update_event_times() is correct.
*/
list_for_each_entry(event, &group_event->sibling_list, group_entry) {
if (event == partial_group)
- break;
- __event_sched_out(event, cpuctx, ctx);
+ simulate = true;
+
+ if (simulate) {
+ event->tstamp_running += now - event->tstamp_stopped;
+ event->tstamp_stopped = now;
+ } else {
+ event_sched_out(event, cpuctx, ctx);
+ }
}
- __event_sched_out(group_event, cpuctx, ctx);
+ event_sched_out(group_event, cpuctx, ctx);
pmu->cancel_txn(pmu);
@@ -1102,7 +1184,7 @@ static int perf_event_refresh(struct perf_event *event, int refresh)
/*
* not supported on inherited events
*/
- if (event->attr.inherit)
+ if (event->attr.inherit || !is_sampling_event(event))
return -EINVAL;
atomic_add(refresh, &event->event_limit);
@@ -1316,8 +1398,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
{
int ctxn;
- perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
for_each_task_context_nr(ctxn)
perf_event_context_sched_out(task, ctxn, next);
}
@@ -1651,8 +1731,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
{
raw_spin_lock(&ctx->lock);
- /* Rotate the first entry last of non-pinned groups */
- list_rotate_left(&ctx->flexible_groups);
+ /*
+ * Rotate the first entry last of non-pinned groups. Rotation might be
+ * disabled by the inheritance code.
+ */
+ if (!ctx->rotate_disable)
+ list_rotate_left(&ctx->flexible_groups);
raw_spin_unlock(&ctx->lock);
}
@@ -2264,11 +2348,6 @@ int perf_event_release_kernel(struct perf_event *event)
raw_spin_unlock_irq(&ctx->lock);
mutex_unlock(&ctx->mutex);
- mutex_lock(&event->owner->perf_event_mutex);
- list_del_init(&event->owner_entry);
- mutex_unlock(&event->owner->perf_event_mutex);
- put_task_struct(event->owner);
-
free_event(event);
return 0;
@@ -2281,35 +2360,44 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
static int perf_release(struct inode *inode, struct file *file)
{
struct perf_event *event = file->private_data;
+ struct task_struct *owner;
file->private_data = NULL;
- return perf_event_release_kernel(event);
-}
-
-static int perf_event_read_size(struct perf_event *event)
-{
- int entry = sizeof(u64); /* value */
- int size = 0;
- int nr = 1;
-
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
- size += sizeof(u64);
-
- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
- size += sizeof(u64);
-
- if (event->attr.read_format & PERF_FORMAT_ID)
- entry += sizeof(u64);
-
- if (event->attr.read_format & PERF_FORMAT_GROUP) {
- nr += event->group_leader->nr_siblings;
- size += sizeof(u64);
+ rcu_read_lock();
+ owner = ACCESS_ONCE(event->owner);
+ /*
+ * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+ * !owner it means the list deletion is complete and we can indeed
+ * free this event, otherwise we need to serialize on
+ * owner->perf_event_mutex.
+ */
+ smp_read_barrier_depends();
+ if (owner) {
+ /*
+ * Since delayed_put_task_struct() also drops the last
+ * task reference we can safely take a new reference
+ * while holding the rcu_read_lock().
+ */
+ get_task_struct(owner);
}
+ rcu_read_unlock();
- size += entry * nr;
+ if (owner) {
+ mutex_lock(&owner->perf_event_mutex);
+ /*
+ * We have to re-check the event->owner field, if it is cleared
+ * we raced with perf_event_exit_task(), acquiring the mutex
+ * ensured they're done, and we can proceed with freeing the
+ * event.
+ */
+ if (event->owner)
+ list_del_init(&event->owner_entry);
+ mutex_unlock(&owner->perf_event_mutex);
+ put_task_struct(owner);
+ }
- return size;
+ return perf_event_release_kernel(event);
}
u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
@@ -2426,7 +2514,7 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
if (event->state == PERF_EVENT_STATE_ERROR)
return 0;
- if (count < perf_event_read_size(event))
+ if (count < event->read_size)
return -ENOSPC;
WARN_ON_ONCE(event->ctx->parent_ctx);
@@ -2512,7 +2600,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
int ret = 0;
u64 value;
- if (!event->attr.sample_period)
+ if (!is_sampling_event(event))
return -EINVAL;
if (copy_from_user(&value, arg, sizeof(value)))
@@ -3303,6 +3391,73 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle,
} while (len);
}
+static void __perf_event_header__init_id(struct perf_event_header *header,
+ struct perf_sample_data *data,
+ struct perf_event *event)
+{
+ u64 sample_type = event->attr.sample_type;
+
+ data->type = sample_type;
+ header->size += event->id_header_size;
+
+ if (sample_type & PERF_SAMPLE_TID) {
+ /* namespace issues */
+ data->tid_entry.pid = perf_event_pid(event, current);
+ data->tid_entry.tid = perf_event_tid(event, current);
+ }
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ data->time = perf_clock();
+
+ if (sample_type & PERF_SAMPLE_ID)
+ data->id = primary_event_id(event);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ data->stream_id = event->id;
+
+ if (sample_type & PERF_SAMPLE_CPU) {
+ data->cpu_entry.cpu = raw_smp_processor_id();
+ data->cpu_entry.reserved = 0;
+ }
+}
+
+static void perf_event_header__init_id(struct perf_event_header *header,
+ struct perf_sample_data *data,
+ struct perf_event *event)
+{
+ if (event->attr.sample_id_all)
+ __perf_event_header__init_id(header, data, event);
+}
+
+static void __perf_event__output_id_sample(struct perf_output_handle *handle,
+ struct perf_sample_data *data)
+{
+ u64 sample_type = data->type;
+
+ if (sample_type & PERF_SAMPLE_TID)
+ perf_output_put(handle, data->tid_entry);
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ perf_output_put(handle, data->time);
+
+ if (sample_type & PERF_SAMPLE_ID)
+ perf_output_put(handle, data->id);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ perf_output_put(handle, data->stream_id);
+
+ if (sample_type & PERF_SAMPLE_CPU)
+ perf_output_put(handle, data->cpu_entry);
+}
+
+static void perf_event__output_id_sample(struct perf_event *event,
+ struct perf_output_handle *handle,
+ struct perf_sample_data *sample)
+{
+ if (event->attr.sample_id_all)
+ __perf_event__output_id_sample(handle, sample);
+}
+
int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
int nmi, int sample)
@@ -3310,6 +3465,7 @@ int perf_output_begin(struct perf_output_handle *handle,
struct perf_buffer *buffer;
unsigned long tail, offset, head;
int have_lost;
+ struct perf_sample_data sample_data;
struct {
struct perf_event_header header;
u64 id;
@@ -3336,8 +3492,12 @@ int perf_output_begin(struct perf_output_handle *handle,
goto out;
have_lost = local_read(&buffer->lost);
- if (have_lost)
- size += sizeof(lost_event);
+ if (have_lost) {
+ lost_event.header.size = sizeof(lost_event);
+ perf_event_header__init_id(&lost_event.header, &sample_data,
+ event);
+ size += lost_event.header.size;
+ }
perf_output_get_handle(handle);
@@ -3368,11 +3528,11 @@ int perf_output_begin(struct perf_output_handle *handle,
if (have_lost) {
lost_event.header.type = PERF_RECORD_LOST;
lost_event.header.misc = 0;
- lost_event.header.size = sizeof(lost_event);
lost_event.id = event->id;
lost_event.lost = local_xchg(&buffer->lost, 0);
perf_output_put(handle, lost_event);
+ perf_event__output_id_sample(event, handle, &sample_data);
}
return 0;
@@ -3405,30 +3565,9 @@ void perf_output_end(struct perf_output_handle *handle)
rcu_read_unlock();
}
-static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
-{
- /*
- * only top level events have the pid namespace they were created in
- */
- if (event->parent)
- event = event->parent;
-
- return task_tgid_nr_ns(p, event->ns);
-}
-
-static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
-{
- /*
- * only top level events have the pid namespace they were created in
- */
- if (event->parent)
- event = event->parent;
-
- return task_pid_nr_ns(p, event->ns);
-}
-
static void perf_output_read_one(struct perf_output_handle *handle,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 enabled, u64 running)
{
u64 read_format = event->attr.read_format;
u64 values[4];
@@ -3436,11 +3575,11 @@ static void perf_output_read_one(struct perf_output_handle *handle,
values[n++] = perf_event_count(event);
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
- values[n++] = event->total_time_enabled +
+ values[n++] = enabled +
atomic64_read(&event->child_total_time_enabled);
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
- values[n++] = event->total_time_running +
+ values[n++] = running +
atomic64_read(&event->child_total_time_running);
}
if (read_format & PERF_FORMAT_ID)
@@ -3453,7 +3592,8 @@ static void perf_output_read_one(struct perf_output_handle *handle,
* XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
*/
static void perf_output_read_group(struct perf_output_handle *handle,
- struct perf_event *event)
+ struct perf_event *event,
+ u64 enabled, u64 running)
{
struct perf_event *leader = event->group_leader, *sub;
u64 read_format = event->attr.read_format;
@@ -3463,10 +3603,10 @@ static void perf_output_read_group(struct perf_output_handle *handle,
values[n++] = 1 + leader->nr_siblings;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
- values[n++] = leader->total_time_enabled;
+ values[n++] = enabled;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
- values[n++] = leader->total_time_running;
+ values[n++] = running;
if (leader != event)
leader->pmu->read(leader);
@@ -3491,13 +3631,35 @@ static void perf_output_read_group(struct perf_output_handle *handle,
}
}
+#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
+ PERF_FORMAT_TOTAL_TIME_RUNNING)
+
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
+ u64 enabled = 0, running = 0, now, ctx_time;
+ u64 read_format = event->attr.read_format;
+
+ /*
+ * compute total_time_enabled, total_time_running
+ * based on snapshot values taken when the event
+ * was last scheduled in.
+ *
+ * we cannot simply called update_context_time()
+ * because of locking issue as we are called in
+ * NMI context
+ */
+ if (read_format & PERF_FORMAT_TOTAL_TIMES) {
+ now = perf_clock();
+ ctx_time = event->shadow_ctx_time + now;
+ enabled = ctx_time - event->tstamp_enabled;
+ running = ctx_time - event->tstamp_running;
+ }
+
if (event->attr.read_format & PERF_FORMAT_GROUP)
- perf_output_read_group(handle, event);
+ perf_output_read_group(handle, event, enabled, running);
else
- perf_output_read_one(handle, event);
+ perf_output_read_one(handle, event, enabled, running);
}
void perf_output_sample(struct perf_output_handle *handle,
@@ -3577,61 +3739,16 @@ void perf_prepare_sample(struct perf_event_header *header,
{
u64 sample_type = event->attr.sample_type;
- data->type = sample_type;
-
header->type = PERF_RECORD_SAMPLE;
- header->size = sizeof(*header);
+ header->size = sizeof(*header) + event->header_size;
header->misc = 0;
header->misc |= perf_misc_flags(regs);
- if (sample_type & PERF_SAMPLE_IP) {
- data->ip = perf_instruction_pointer(regs);
-
- header->size += sizeof(data->ip);
- }
-
- if (sample_type & PERF_SAMPLE_TID) {
- /* namespace issues */
- data->tid_entry.pid = perf_event_pid(event, current);
- data->tid_entry.tid = perf_event_tid(event, current);
-
- header->size += sizeof(data->tid_entry);
- }
-
- if (sample_type & PERF_SAMPLE_TIME) {
- data->time = perf_clock();
-
- header->size += sizeof(data->time);
- }
-
- if (sample_type & PERF_SAMPLE_ADDR)
- header->size += sizeof(data->addr);
-
- if (sample_type & PERF_SAMPLE_ID) {
- data->id = primary_event_id(event);
-
- header->size += sizeof(data->id);
- }
-
- if (sample_type & PERF_SAMPLE_STREAM_ID) {
- data->stream_id = event->id;
+ __perf_event_header__init_id(header, data, event);
- header->size += sizeof(data->stream_id);
- }
-
- if (sample_type & PERF_SAMPLE_CPU) {
- data->cpu_entry.cpu = raw_smp_processor_id();
- data->cpu_entry.reserved = 0;
-
- header->size += sizeof(data->cpu_entry);
- }
-
- if (sample_type & PERF_SAMPLE_PERIOD)
- header->size += sizeof(data->period);
-
- if (sample_type & PERF_SAMPLE_READ)
- header->size += perf_event_read_size(event);
+ if (sample_type & PERF_SAMPLE_IP)
+ data->ip = perf_instruction_pointer(regs);
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
@@ -3696,23 +3813,26 @@ perf_event_read_event(struct perf_event *event,
struct task_struct *task)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
struct perf_read_event read_event = {
.header = {
.type = PERF_RECORD_READ,
.misc = 0,
- .size = sizeof(read_event) + perf_event_read_size(event),
+ .size = sizeof(read_event) + event->read_size,
},
.pid = perf_event_pid(event, task),
.tid = perf_event_tid(event, task),
};
int ret;
+ perf_event_header__init_id(&read_event.header, &sample, event);
ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);
if (ret)
return;
perf_output_put(&handle, read_event);
perf_output_read(&handle, event);
+ perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
@@ -3742,14 +3862,16 @@ static void perf_event_task_output(struct perf_event *event,
struct perf_task_event *task_event)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
struct task_struct *task = task_event->task;
- int size, ret;
+ int ret, size = task_event->event_id.header.size;
- size = task_event->event_id.header.size;
- ret = perf_output_begin(&handle, event, size, 0, 0);
+ perf_event_header__init_id(&task_event->event_id.header, &sample, event);
+ ret = perf_output_begin(&handle, event,
+ task_event->event_id.header.size, 0, 0);
if (ret)
- return;
+ goto out;
task_event->event_id.pid = perf_event_pid(event, task);
task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3759,7 +3881,11 @@ static void perf_event_task_output(struct perf_event *event,
perf_output_put(&handle, task_event->event_id);
+ perf_event__output_id_sample(event, &handle, &sample);
+
perf_output_end(&handle);
+out:
+ task_event->event_id.header.size = size;
}
static int perf_event_task_match(struct perf_event *event)
@@ -3798,6 +3924,8 @@ static void perf_event_task_event(struct perf_task_event *task_event)
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ if (cpuctx->active_pmu != pmu)
+ goto next;
perf_event_task_ctx(&cpuctx->ctx, task_event);
ctx = task_event->task_ctx;
@@ -3872,11 +4000,16 @@ static void perf_event_comm_output(struct perf_event *event,
struct perf_comm_event *comm_event)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
int size = comm_event->event_id.header.size;
- int ret = perf_output_begin(&handle, event, size, 0, 0);
+ int ret;
+
+ perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
+ ret = perf_output_begin(&handle, event,
+ comm_event->event_id.header.size, 0, 0);
if (ret)
- return;
+ goto out;
comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
@@ -3884,7 +4017,12 @@ static void perf_event_comm_output(struct perf_event *event,
perf_output_put(&handle, comm_event->event_id);
perf_output_copy(&handle, comm_event->comm,
comm_event->comm_size);
+
+ perf_event__output_id_sample(event, &handle, &sample);
+
perf_output_end(&handle);
+out:
+ comm_event->event_id.header.size = size;
}
static int perf_event_comm_match(struct perf_event *event)
@@ -3929,10 +4067,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
comm_event->comm_size = size;
comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
-
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ if (cpuctx->active_pmu != pmu)
+ goto next;
perf_event_comm_ctx(&cpuctx->ctx, comm_event);
ctxn = pmu->task_ctx_nr;
@@ -4008,11 +4147,15 @@ static void perf_event_mmap_output(struct perf_event *event,
struct perf_mmap_event *mmap_event)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
int size = mmap_event->event_id.header.size;
- int ret = perf_output_begin(&handle, event, size, 0, 0);
+ int ret;
+ perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
+ ret = perf_output_begin(&handle, event,
+ mmap_event->event_id.header.size, 0, 0);
if (ret)
- return;
+ goto out;
mmap_event->event_id.pid = perf_event_pid(event, current);
mmap_event->event_id.tid = perf_event_tid(event, current);
@@ -4020,7 +4163,12 @@ static void perf_event_mmap_output(struct perf_event *event,
perf_output_put(&handle, mmap_event->event_id);
perf_output_copy(&handle, mmap_event->file_name,
mmap_event->file_size);
+
+ perf_event__output_id_sample(event, &handle, &sample);
+
perf_output_end(&handle);
+out:
+ mmap_event->event_id.header.size = size;
}
static int perf_event_mmap_match(struct perf_event *event,
@@ -4118,6 +4266,8 @@ got_name:
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ if (cpuctx->active_pmu != pmu)
+ goto next;
perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
vma->vm_flags & VM_EXEC);
@@ -4173,6 +4323,7 @@ void perf_event_mmap(struct vm_area_struct *vma)
static void perf_log_throttle(struct perf_event *event, int enable)
{
struct perf_output_handle handle;
+ struct perf_sample_data sample;
int ret;
struct {
@@ -4194,11 +4345,15 @@ static void perf_log_throttle(struct perf_event *event, int enable)
if (enable)
throttle_event.header.type = PERF_RECORD_UNTHROTTLE;
- ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0);
+ perf_event_header__init_id(&throttle_event.header, &sample, event);
+
+ ret = perf_output_begin(&handle, event,
+ throttle_event.header.size, 1, 0);
if (ret)
return;
perf_output_put(&handle, throttle_event);
+ perf_event__output_id_sample(event, &handle, &sample);
perf_output_end(&handle);
}
@@ -4214,6 +4369,13 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
struct hw_perf_event *hwc = &event->hw;
int ret = 0;
+ /*
+ * Non-sampling counters might still use the PMI to fold short
+ * hardware counters, ignore those.
+ */
+ if (unlikely(!is_sampling_event(event)))
+ return 0;
+
if (!throttle) {
hwc->interrupts++;
} else {
@@ -4359,7 +4521,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
if (!regs)
return;
- if (!hwc->sample_period)
+ if (!is_sampling_event(event))
return;
if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
@@ -4522,7 +4684,7 @@ static int perf_swevent_add(struct perf_event *event, int flags)
struct hw_perf_event *hwc = &event->hw;
struct hlist_head *head;
- if (hwc->sample_period) {
+ if (is_sampling_event(event)) {
hwc->last_period = hwc->sample_period;
perf_swevent_set_period(event);
}
@@ -4687,7 +4849,7 @@ static int perf_swevent_init(struct perf_event *event)
break;
}
- if (event_id > PERF_COUNT_SW_MAX)
+ if (event_id >= PERF_COUNT_SW_MAX)
return -ENOENT;
if (!event->parent) {
@@ -4779,15 +4941,6 @@ static int perf_tp_event_init(struct perf_event *event)
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -ENOENT;
- /*
- * Raw tracepoint data is a severe data leak, only allow root to
- * have these.
- */
- if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
- perf_paranoid_tracepoint_raw() &&
- !capable(CAP_SYS_ADMIN))
- return -EPERM;
-
err = perf_trace_init(event);
if (err)
return err;
@@ -4810,7 +4963,7 @@ static struct pmu perf_tracepoint = {
static inline void perf_tp_register(void)
{
- perf_pmu_register(&perf_tracepoint);
+ perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
}
static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -4900,31 +5053,33 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
static void perf_swevent_start_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
+ s64 period;
+
+ if (!is_sampling_event(event))
+ return;
hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hwc->hrtimer.function = perf_swevent_hrtimer;
- if (hwc->sample_period) {
- s64 period = local64_read(&hwc->period_left);
- if (period) {
- if (period < 0)
- period = 10000;
+ period = local64_read(&hwc->period_left);
+ if (period) {
+ if (period < 0)
+ period = 10000;
- local64_set(&hwc->period_left, 0);
- } else {
- period = max_t(u64, 10000, hwc->sample_period);
- }
- __hrtimer_start_range_ns(&hwc->hrtimer,
+ local64_set(&hwc->period_left, 0);
+ } else {
+ period = max_t(u64, 10000, hwc->sample_period);
+ }
+ __hrtimer_start_range_ns(&hwc->hrtimer,
ns_to_ktime(period), 0,
HRTIMER_MODE_REL_PINNED, 0);
- }
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- if (hwc->sample_period) {
+ if (is_sampling_event(event)) {
ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
local64_set(&hwc->period_left, ktime_to_ns(remaining));
@@ -5119,25 +5274,94 @@ static void *find_pmu_context(int ctxn)
return NULL;
}
-static void free_pmu_context(void * __percpu cpu_context)
+static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
{
- struct pmu *pmu;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct perf_cpu_context *cpuctx;
+
+ cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+
+ if (cpuctx->active_pmu == old_pmu)
+ cpuctx->active_pmu = pmu;
+ }
+}
+
+static void free_pmu_context(struct pmu *pmu)
+{
+ struct pmu *i;
mutex_lock(&pmus_lock);
/*
* Like a real lame refcount.
*/
- list_for_each_entry(pmu, &pmus, entry) {
- if (pmu->pmu_cpu_context == cpu_context)
+ list_for_each_entry(i, &pmus, entry) {
+ if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
+ update_pmu_context(i, pmu);
goto out;
+ }
}
- free_percpu(cpu_context);
+ free_percpu(pmu->pmu_cpu_context);
out:
mutex_unlock(&pmus_lock);
}
+static struct idr pmu_idr;
-int perf_pmu_register(struct pmu *pmu)
+static ssize_t
+type_show(struct device *dev, struct device_attribute *attr, char *page)
+{
+ struct pmu *pmu = dev_get_drvdata(dev);
+
+ return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->type);
+}
+
+static struct device_attribute pmu_dev_attrs[] = {
+ __ATTR_RO(type),
+ __ATTR_NULL,
+};
+
+static int pmu_bus_running;
+static struct bus_type pmu_bus = {
+ .name = "event_source",
+ .dev_attrs = pmu_dev_attrs,
+};
+
+static void pmu_dev_release(struct device *dev)
+{
+ kfree(dev);
+}
+
+static int pmu_dev_alloc(struct pmu *pmu)
+{
+ int ret = -ENOMEM;
+
+ pmu->dev = kzalloc(sizeof(struct device), GFP_KERNEL);
+ if (!pmu->dev)
+ goto out;
+
+ device_initialize(pmu->dev);
+ ret = dev_set_name(pmu->dev, "%s", pmu->name);
+ if (ret)
+ goto free_dev;
+
+ dev_set_drvdata(pmu->dev, pmu);
+ pmu->dev->bus = &pmu_bus;
+ pmu->dev->release = pmu_dev_release;
+ ret = device_add(pmu->dev);
+ if (ret)
+ goto free_dev;
+
+out:
+ return ret;
+
+free_dev:
+ put_device(pmu->dev);
+ goto out;
+}
+
+int perf_pmu_register(struct pmu *pmu, char *name, int type)
{
int cpu, ret;
@@ -5147,13 +5371,38 @@ int perf_pmu_register(struct pmu *pmu)
if (!pmu->pmu_disable_count)
goto unlock;
+ pmu->type = -1;
+ if (!name)
+ goto skip_type;
+ pmu->name = name;
+
+ if (type < 0) {
+ int err = idr_pre_get(&pmu_idr, GFP_KERNEL);
+ if (!err)
+ goto free_pdc;
+
+ err = idr_get_new_above(&pmu_idr, pmu, PERF_TYPE_MAX, &type);
+ if (err) {
+ ret = err;
+ goto free_pdc;
+ }
+ }
+ pmu->type = type;
+
+ if (pmu_bus_running) {
+ ret = pmu_dev_alloc(pmu);
+ if (ret)
+ goto free_idr;
+ }
+
+skip_type:
pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
if (pmu->pmu_cpu_context)
goto got_cpu_context;
pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
if (!pmu->pmu_cpu_context)
- goto free_pdc;
+ goto free_dev;
for_each_possible_cpu(cpu) {
struct perf_cpu_context *cpuctx;
@@ -5164,6 +5413,7 @@ int perf_pmu_register(struct pmu *pmu)
cpuctx->ctx.pmu = pmu;
cpuctx->jiffies_interval = 1;
INIT_LIST_HEAD(&cpuctx->rotation_list);
+ cpuctx->active_pmu = pmu;
}
got_cpu_context:
@@ -5196,6 +5446,14 @@ unlock:
return ret;
+free_dev:
+ device_del(pmu->dev);
+ put_device(pmu->dev);
+
+free_idr:
+ if (pmu->type >= PERF_TYPE_MAX)
+ idr_remove(&pmu_idr, pmu->type);
+
free_pdc:
free_percpu(pmu->pmu_disable_count);
goto unlock;
@@ -5215,7 +5473,11 @@ void perf_pmu_unregister(struct pmu *pmu)
synchronize_rcu();
free_percpu(pmu->pmu_disable_count);
- free_pmu_context(pmu->pmu_cpu_context);
+ if (pmu->type >= PERF_TYPE_MAX)
+ idr_remove(&pmu_idr, pmu->type);
+ device_del(pmu->dev);
+ put_device(pmu->dev);
+ free_pmu_context(pmu);
}
struct pmu *perf_init_event(struct perf_event *event)
@@ -5224,6 +5486,13 @@ struct pmu *perf_init_event(struct perf_event *event)
int idx;
idx = srcu_read_lock(&pmus_srcu);
+
+ rcu_read_lock();
+ pmu = idr_find(&pmu_idr, event->attr.type);
+ rcu_read_unlock();
+ if (pmu)
+ goto unlock;
+
list_for_each_entry_rcu(pmu, &pmus, entry) {
int ret = pmu->event_init(event);
if (!ret)
@@ -5683,12 +5952,18 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_unlock(&ctx->mutex);
event->owner = current;
- get_task_struct(current);
+
mutex_lock(&current->perf_event_mutex);
list_add_tail(&event->owner_entry, &current->perf_event_list);
mutex_unlock(&current->perf_event_mutex);
/*
+ * Precalculate sample_data sizes
+ */
+ perf_event__header_size(event);
+ perf_event__id_header_size(event);
+
+ /*
* Drop the reference on the group_event after placing the
* new event on the sibling_list. This ensures destruction
* of the group leader will find the pointer to itself in
@@ -5751,12 +6026,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
++ctx->generation;
mutex_unlock(&ctx->mutex);
- event->owner = current;
- get_task_struct(current);
- mutex_lock(&current->perf_event_mutex);
- list_add_tail(&event->owner_entry, &current->perf_event_list);
- mutex_unlock(&current->perf_event_mutex);
-
return event;
err_free:
@@ -5907,8 +6176,24 @@ again:
*/
void perf_event_exit_task(struct task_struct *child)
{
+ struct perf_event *event, *tmp;
int ctxn;
+ mutex_lock(&child->perf_event_mutex);
+ list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+ owner_entry) {
+ list_del_init(&event->owner_entry);
+
+ /*
+ * Ensure the list deletion is visible before we clear
+ * the owner, closes a race against perf_release() where
+ * we need to serialize on the owner->perf_event_mutex.
+ */
+ smp_wmb();
+ event->owner = NULL;
+ }
+ mutex_unlock(&child->perf_event_mutex);
+
for_each_task_context_nr(ctxn)
perf_event_exit_task_context(child, ctxn);
}
@@ -6031,6 +6316,12 @@ inherit_event(struct perf_event *parent_event,
child_event->overflow_handler = parent_event->overflow_handler;
/*
+ * Precalculate sample_data sizes
+ */
+ perf_event__header_size(child_event);
+ perf_event__id_header_size(child_event);
+
+ /*
* Link it up in the child's context:
*/
raw_spin_lock_irqsave(&child_ctx->lock, flags);
@@ -6128,6 +6419,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
struct perf_event *event;
struct task_struct *parent = current;
int inherited_all = 1;
+ unsigned long flags;
int ret = 0;
child->perf_event_ctxp[ctxn] = NULL;
@@ -6168,6 +6460,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
break;
}
+ /*
+ * We can't hold ctx->lock when iterating the ->flexible_group list due
+ * to allocations, but we need to prevent rotation because
+ * rotate_ctx() will change the list from interrupt context.
+ */
+ raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+ parent_ctx->rotate_disable = 1;
+ raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
@@ -6175,6 +6476,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
break;
}
+ raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+ parent_ctx->rotate_disable = 0;
+ raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
child_ctx = child->perf_event_ctxp[ctxn];
if (child_ctx && inherited_all) {
@@ -6247,7 +6552,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
mutex_unlock(&swhash->hlist_mutex);
}
-#ifdef CONFIG_HOTPLUG_CPU
+#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
static void perf_pmu_rotate_stop(struct pmu *pmu)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
@@ -6301,6 +6606,26 @@ static void perf_event_exit_cpu(int cpu)
static inline void perf_event_exit_cpu(int cpu) { }
#endif
+static int
+perf_reboot(struct notifier_block *notifier, unsigned long val, void *v)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ perf_event_exit_cpu(cpu);
+
+ return NOTIFY_OK;
+}
+
+/*
+ * Run the perf reboot notifier at the very last possible moment so that
+ * the generic watchdog code runs as long as possible.
+ */
+static struct notifier_block perf_reboot_notifier = {
+ .notifier_call = perf_reboot,
+ .priority = INT_MIN,
+};
+
static int __cpuinit
perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
{
@@ -6327,11 +6652,47 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
void __init perf_event_init(void)
{
+ int ret;
+
+ idr_init(&pmu_idr);
+
perf_event_init_all_cpus();
init_srcu_struct(&pmus_srcu);
- perf_pmu_register(&perf_swevent);
- perf_pmu_register(&perf_cpu_clock);
- perf_pmu_register(&perf_task_clock);
+ perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE);
+ perf_pmu_register(&perf_cpu_clock, NULL, -1);
+ perf_pmu_register(&perf_task_clock, NULL, -1);
perf_tp_register();
perf_cpu_notifier(perf_cpu_notify);
+ register_reboot_notifier(&perf_reboot_notifier);
+
+ ret = init_hw_breakpoint();
+ WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
+}
+
+static int __init perf_event_sysfs_init(void)
+{
+ struct pmu *pmu;
+ int ret;
+
+ mutex_lock(&pmus_lock);
+
+ ret = bus_register(&pmu_bus);
+ if (ret)
+ goto unlock;
+
+ list_for_each_entry(pmu, &pmus, entry) {
+ if (!pmu->name || pmu->type < 0)
+ continue;
+
+ ret = pmu_dev_alloc(pmu);
+ WARN(ret, "Failed to register pmu: %s, reason %d\n", pmu->name, ret);
+ }
+ pmu_bus_running = 1;
+ ret = 0;
+
+unlock:
+ mutex_unlock(&pmus_lock);
+
+ return ret;
}
+device_initcall(perf_event_sysfs_init);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index a96b850ba08..aeaa7f84682 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -121,10 +121,10 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
switch (o->type) {
case PM_QOS_MIN:
- return plist_last(&o->requests)->prio;
+ return plist_first(&o->requests)->prio;
case PM_QOS_MAX:
- return plist_first(&o->requests)->prio;
+ return plist_last(&o->requests)->prio;
default:
/* runtime check for not using enum */
@@ -399,7 +399,7 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
} else
return -EINVAL;
- pm_qos_req = (struct pm_qos_request_list *)filp->private_data;
+ pm_qos_req = filp->private_data;
pm_qos_update_request(pm_qos_req, value);
return count;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 6842eeba587..05bb7173850 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -37,13 +37,13 @@ static int check_clock(const clockid_t which_clock)
if (pid == 0)
return 0;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
p = find_task_by_vpid(pid);
if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
- same_thread_group(p, current) : thread_group_leader(p))) {
+ same_thread_group(p, current) : has_group_leader_pid(p))) {
error = -EINVAL;
}
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return error;
}
@@ -390,7 +390,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
INIT_LIST_HEAD(&new_timer->it.cpu.entry);
- read_lock(&tasklist_lock);
+ rcu_read_lock();
if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
if (pid == 0) {
p = current;
@@ -404,7 +404,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
p = current->group_leader;
} else {
p = find_task_by_vpid(pid);
- if (p && !thread_group_leader(p))
+ if (p && !has_group_leader_pid(p))
p = NULL;
}
}
@@ -414,7 +414,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
} else {
ret = -EINVAL;
}
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return ret;
}
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 9ca4973f736..93bd2eb2bc5 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -145,7 +145,13 @@ static int common_timer_del(struct k_itimer *timer);
static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
-static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags);
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);
+
+#define lock_timer(tid, flags) \
+({ struct k_itimer *__timr; \
+ __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags)); \
+ __timr; \
+})
static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
{
@@ -619,7 +625,7 @@ out:
* the find to the timer lock. To avoid a dead lock, the timer id MUST
* be release with out holding the timer lock.
*/
-static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
{
struct k_itimer *timr;
/*
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 29bff6117ab..a5aff3ebad3 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -246,9 +246,13 @@ config PM_OPS
depends on PM_SLEEP || PM_RUNTIME
default y
+config ARCH_HAS_OPP
+ bool
+
config PM_OPP
bool "Operating Performance Point (OPP) Layer library"
depends on PM
+ depends on ARCH_HAS_OPP
---help---
SOCs have a standard set of tuples consisting of frequency and
voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 657272e91d0..048d0b51483 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -327,7 +327,6 @@ static int create_image(int platform_mode)
int hibernation_snapshot(int platform_mode)
{
int error;
- gfp_t saved_mask;
error = platform_begin(platform_mode);
if (error)
@@ -339,7 +338,7 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+ pm_restrict_gfp_mask();
error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Recover_platform;
@@ -348,7 +347,10 @@ int hibernation_snapshot(int platform_mode)
goto Recover_platform;
error = create_image(platform_mode);
- /* Control returns here after successful restore */
+ /*
+ * Control returns here (1) after the image has been created or the
+ * image creation has failed and (2) after a successful restore.
+ */
Resume_devices:
/* We may need to release the preallocated image pages here. */
@@ -357,7 +359,10 @@ int hibernation_snapshot(int platform_mode)
dpm_resume_end(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
- set_gfp_allowed_mask(saved_mask);
+
+ if (error || !in_suspend)
+ pm_restore_gfp_mask();
+
resume_console();
Close:
platform_end(platform_mode);
@@ -452,17 +457,16 @@ static int resume_target_kernel(bool platform_mode)
int hibernation_restore(int platform_mode)
{
int error;
- gfp_t saved_mask;
pm_prepare_console();
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+ pm_restrict_gfp_mask();
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
dpm_resume_end(PMSG_RECOVER);
}
- set_gfp_allowed_mask(saved_mask);
+ pm_restore_gfp_mask();
resume_console();
pm_restore_console();
return error;
@@ -476,7 +480,6 @@ int hibernation_restore(int platform_mode)
int hibernation_platform_enter(void)
{
int error;
- gfp_t saved_mask;
if (!hibernation_ops)
return -ENOSYS;
@@ -492,7 +495,6 @@ int hibernation_platform_enter(void)
entering_platform_hibernation = true;
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
@@ -536,7 +538,6 @@ int hibernation_platform_enter(void)
Resume_devices:
entering_platform_hibernation = false;
dpm_resume_end(PMSG_RESTORE);
- set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
@@ -646,6 +647,7 @@ int hibernate(void)
swsusp_free();
if (!error)
power_down();
+ pm_restore_gfp_mask();
} else {
pr_debug("PM: Image restored successfully.\n");
}
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ac7eb109f19..0dac75ea445 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -984,8 +984,8 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
src = kmap_atomic(s_page, KM_USER0);
dst = kmap_atomic(d_page, KM_USER1);
do_copy_page(dst, src);
- kunmap_atomic(src, KM_USER0);
kunmap_atomic(dst, KM_USER1);
+ kunmap_atomic(src, KM_USER0);
} else {
if (PageHighMem(d_page)) {
/* Page pointed to by src may contain some kernel
@@ -993,7 +993,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
*/
safe_copy_page(buffer, s_page);
dst = kmap_atomic(d_page, KM_USER0);
- memcpy(dst, buffer, PAGE_SIZE);
+ copy_page(dst, buffer);
kunmap_atomic(dst, KM_USER0);
} else {
safe_copy_page(page_address(d_page), s_page);
@@ -1687,7 +1687,7 @@ int snapshot_read_next(struct snapshot_handle *handle)
memory_bm_position_reset(&orig_bm);
memory_bm_position_reset(&copy_bm);
} else if (handle->cur <= nr_meta_pages) {
- memset(buffer, 0, PAGE_SIZE);
+ clear_page(buffer);
pack_pfns(buffer, &orig_bm);
} else {
struct page *page;
@@ -1701,7 +1701,7 @@ int snapshot_read_next(struct snapshot_handle *handle)
void *kaddr;
kaddr = kmap_atomic(page, KM_USER0);
- memcpy(buffer, kaddr, PAGE_SIZE);
+ copy_page(buffer, kaddr);
kunmap_atomic(kaddr, KM_USER0);
handle->buffer = buffer;
} else {
@@ -1984,7 +1984,7 @@ static void copy_last_highmem_page(void)
void *dst;
dst = kmap_atomic(last_highmem_page, KM_USER0);
- memcpy(dst, buffer, PAGE_SIZE);
+ copy_page(dst, buffer);
kunmap_atomic(dst, KM_USER0);
last_highmem_page = NULL;
}
@@ -2270,11 +2270,11 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf)
kaddr1 = kmap_atomic(p1, KM_USER0);
kaddr2 = kmap_atomic(p2, KM_USER1);
- memcpy(buf, kaddr1, PAGE_SIZE);
- memcpy(kaddr1, kaddr2, PAGE_SIZE);
- memcpy(kaddr2, buf, PAGE_SIZE);
- kunmap_atomic(kaddr1, KM_USER0);
+ copy_page(buf, kaddr1);
+ copy_page(kaddr1, kaddr2);
+ copy_page(kaddr2, buf);
kunmap_atomic(kaddr2, KM_USER1);
+ kunmap_atomic(kaddr1, KM_USER0);
}
/**
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 7335952ee47..031d5e3a619 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -22,6 +22,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/suspend.h>
+#include <trace/events/power.h>
#include "power.h"
@@ -197,18 +198,18 @@ static int suspend_enter(suspend_state_t state)
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
- gfp_t saved_mask;
if (!suspend_ops)
return -ENOSYS;
+ trace_machine_suspend(state);
if (suspend_ops->begin) {
error = suspend_ops->begin(state);
if (error)
goto Close;
}
suspend_console();
- saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+ pm_restrict_gfp_mask();
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
@@ -225,11 +226,12 @@ int suspend_devices_and_enter(suspend_state_t state)
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
- set_gfp_allowed_mask(saved_mask);
+ pm_restore_gfp_mask();
resume_console();
Close:
if (suspend_ops->end)
suspend_ops->end();
+ trace_machine_suspend(PWR_EVENT_EXIT);
return error;
Recover_platform:
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 916eaa79039..8c7e4832b9b 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -6,6 +6,7 @@
*
* Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
* Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
*
* This file is released under the GPLv2.
*
@@ -29,7 +30,7 @@
#include "power.h"
-#define HIBERNATE_SIG "LINHIB0001"
+#define HIBERNATE_SIG "S1SUSPEND"
/*
* The swap map is a data structure used for keeping track of each page
@@ -251,7 +252,7 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
if (bio_chain) {
src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
if (src) {
- memcpy(src, buf, PAGE_SIZE);
+ copy_page(src, buf);
} else {
WARN_ON_ONCE(1);
bio_chain = NULL; /* Go synchronous */
@@ -325,7 +326,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
error = write_page(handle->cur, handle->cur_swap, NULL);
if (error)
goto out;
- memset(handle->cur, 0, PAGE_SIZE);
+ clear_page(handle->cur);
handle->cur_swap = offset;
handle->k = 0;
}
@@ -753,30 +754,43 @@ static int load_image_lzo(struct swap_map_handle *handle,
{
unsigned int m;
int error = 0;
+ struct bio *bio;
struct timeval start;
struct timeval stop;
unsigned nr_pages;
- size_t off, unc_len, cmp_len;
- unsigned char *unc, *cmp, *page;
+ size_t i, off, unc_len, cmp_len;
+ unsigned char *unc, *cmp, *page[LZO_CMP_PAGES];
- page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
- if (!page) {
- printk(KERN_ERR "PM: Failed to allocate LZO page\n");
- return -ENOMEM;
+ for (i = 0; i < LZO_CMP_PAGES; i++) {
+ page[i] = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+ if (!page[i]) {
+ printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+
+ while (i)
+ free_page((unsigned long)page[--i]);
+
+ return -ENOMEM;
+ }
}
unc = vmalloc(LZO_UNC_SIZE);
if (!unc) {
printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
- free_page((unsigned long)page);
+
+ for (i = 0; i < LZO_CMP_PAGES; i++)
+ free_page((unsigned long)page[i]);
+
return -ENOMEM;
}
cmp = vmalloc(LZO_CMP_SIZE);
if (!cmp) {
printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
+
vfree(unc);
- free_page((unsigned long)page);
+ for (i = 0; i < LZO_CMP_PAGES; i++)
+ free_page((unsigned long)page[i]);
+
return -ENOMEM;
}
@@ -787,6 +801,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
if (!m)
m = 1;
nr_pages = 0;
+ bio = NULL;
do_gettimeofday(&start);
error = snapshot_write_next(snapshot);
@@ -794,11 +809,11 @@ static int load_image_lzo(struct swap_map_handle *handle,
goto out_finish;
for (;;) {
- error = swap_read_page(handle, page, NULL); /* sync */
+ error = swap_read_page(handle, page[0], NULL); /* sync */
if (error)
break;
- cmp_len = *(size_t *)page;
+ cmp_len = *(size_t *)page[0];
if (unlikely(!cmp_len ||
cmp_len > lzo1x_worst_compress(LZO_UNC_SIZE))) {
printk(KERN_ERR "PM: Invalid LZO compressed length\n");
@@ -806,13 +821,20 @@ static int load_image_lzo(struct swap_map_handle *handle,
break;
}
- memcpy(cmp, page, PAGE_SIZE);
- for (off = PAGE_SIZE; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) {
- error = swap_read_page(handle, page, NULL); /* sync */
+ for (off = PAGE_SIZE, i = 1;
+ off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
+ error = swap_read_page(handle, page[i], &bio);
if (error)
goto out_finish;
+ }
- memcpy(cmp + off, page, PAGE_SIZE);
+ error = hib_wait_on_bio_chain(&bio); /* need all data now */
+ if (error)
+ goto out_finish;
+
+ for (off = 0, i = 0;
+ off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
+ memcpy(cmp + off, page[i], PAGE_SIZE);
}
unc_len = LZO_UNC_SIZE;
@@ -857,7 +879,8 @@ out_finish:
vfree(cmp);
vfree(unc);
- free_page((unsigned long)page);
+ for (i = 0; i < LZO_CMP_PAGES; i++)
+ free_page((unsigned long)page[i]);
return error;
}
@@ -910,7 +933,7 @@ int swsusp_check(void)
hib_resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
if (!IS_ERR(hib_resume_bdev)) {
set_blocksize(hib_resume_bdev, PAGE_SIZE);
- memset(swsusp_header, 0, PAGE_SIZE);
+ clear_page(swsusp_header);
error = hib_bio_read_page(swsusp_resume_block,
swsusp_header, NULL);
if (error)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index e819e17877c..c36c3b9e8a8 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -137,7 +137,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
free_all_swap_pages(data->swap);
if (data->frozen)
thaw_processes();
- pm_notifier_call_chain(data->mode == O_WRONLY ?
+ pm_notifier_call_chain(data->mode == O_RDONLY ?
PM_POST_HIBERNATION : PM_POST_RESTORE);
atomic_inc(&snapshot_device_available);
@@ -263,6 +263,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
case SNAPSHOT_UNFREEZE:
if (!data->frozen || data->ready)
break;
+ pm_restore_gfp_mask();
thaw_processes();
usermodehelper_enable();
data->frozen = 0;
@@ -275,6 +276,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
error = -EPERM;
break;
}
+ pm_restore_gfp_mask();
error = hibernation_snapshot(data->platform_support);
if (!error)
error = put_user(in_suspend, (int __user *)arg);
diff --git a/kernel/printk.c b/kernel/printk.c
index 2531017795f..ab3ffc5b3b6 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -210,7 +210,7 @@ __setup("log_buf_len=", log_buf_len_setup);
#ifdef CONFIG_BOOT_PRINTK_DELAY
-static unsigned int boot_delay; /* msecs delay after each printk during bootup */
+static int boot_delay; /* msecs delay after each printk during bootup */
static unsigned long long loops_per_msec; /* based on boot_delay */
static int __init boot_delay_setup(char *str)
@@ -261,6 +261,12 @@ static inline void boot_delay_msec(void)
}
#endif
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
int do_syslog(int type, char __user *buf, int len, bool from_file)
{
unsigned i, j, limit, count;
@@ -268,7 +274,20 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
char c;
int error = 0;
- error = security_syslog(type, from_file);
+ /*
+ * If this is from /proc/kmsg we only do the capabilities checks
+ * at open time.
+ */
+ if (type == SYSLOG_ACTION_OPEN || !from_file) {
+ if (dmesg_restrict && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if ((type != SYSLOG_ACTION_READ_ALL &&
+ type != SYSLOG_ACTION_SIZE_BUFFER) &&
+ !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ }
+
+ error = security_syslog(type);
if (error)
return error;
@@ -647,6 +666,7 @@ static inline int can_use_console(unsigned int cpu)
* released but interrupts still disabled.
*/
static int acquire_console_semaphore_for_printk(unsigned int cpu)
+ __releases(&logbuf_lock)
{
int retval = 0;
@@ -1054,21 +1074,23 @@ static DEFINE_PER_CPU(int, printk_pending);
void printk_tick(void)
{
- if (__get_cpu_var(printk_pending)) {
- __get_cpu_var(printk_pending) = 0;
+ if (__this_cpu_read(printk_pending)) {
+ __this_cpu_write(printk_pending, 0);
wake_up_interruptible(&log_wait);
}
}
int printk_needs_cpu(int cpu)
{
- return per_cpu(printk_pending, cpu);
+ if (cpu_is_offline(cpu))
+ printk_tick();
+ return __this_cpu_read(printk_pending);
}
void wake_up_klogd(void)
{
if (waitqueue_active(&log_wait))
- __raw_get_cpu_var(printk_pending) = 1;
+ this_cpu_write(printk_pending, 1);
}
/**
@@ -1511,7 +1533,7 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper)
}
EXPORT_SYMBOL_GPL(kmsg_dump_unregister);
-static const char const *kmsg_reasons[] = {
+static const char * const kmsg_reasons[] = {
[KMSG_DUMP_OOPS] = "oops",
[KMSG_DUMP_PANIC] = "panic",
[KMSG_DUMP_KEXEC] = "kexec",
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index f34d798ef4a..99bbaa3e5b0 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -181,7 +181,7 @@ int ptrace_attach(struct task_struct *task)
* under ptrace.
*/
retval = -ERESTARTNOINTR;
- if (mutex_lock_interruptible(&task->cred_guard_mutex))
+ if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
goto out;
task_lock(task);
@@ -208,7 +208,7 @@ int ptrace_attach(struct task_struct *task)
unlock_tasklist:
write_unlock_irq(&tasklist_lock);
unlock_creds:
- mutex_unlock(&task->cred_guard_mutex);
+ mutex_unlock(&task->signal->cred_guard_mutex);
out:
return retval;
}
@@ -329,6 +329,8 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
* and reacquire the lock.
*/
void exit_ptrace(struct task_struct *tracer)
+ __releases(&tasklist_lock)
+ __acquires(&tasklist_lock)
{
struct task_struct *p, *n;
LIST_HEAD(ptrace_dead);
@@ -402,7 +404,7 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
return copied;
}
-static int ptrace_setoptions(struct task_struct *child, long data)
+static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
child->ptrace &= ~PT_TRACE_MASK;
@@ -481,7 +483,8 @@ static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
#define is_sysemu_singlestep(request) 0
#endif
-static int ptrace_resume(struct task_struct *child, long request, long data)
+static int ptrace_resume(struct task_struct *child, long request,
+ unsigned long data)
{
if (!valid_signal(data))
return -EIO;
@@ -558,10 +561,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
#endif
int ptrace_request(struct task_struct *child, long request,
- long addr, long data)
+ unsigned long addr, unsigned long data)
{
int ret = -EIO;
siginfo_t siginfo;
+ void __user *datavp = (void __user *) data;
+ unsigned long __user *datalp = datavp;
switch (request) {
case PTRACE_PEEKTEXT:
@@ -578,19 +583,17 @@ int ptrace_request(struct task_struct *child, long request,
ret = ptrace_setoptions(child, data);
break;
case PTRACE_GETEVENTMSG:
- ret = put_user(child->ptrace_message, (unsigned long __user *) data);
+ ret = put_user(child->ptrace_message, datalp);
break;
case PTRACE_GETSIGINFO:
ret = ptrace_getsiginfo(child, &siginfo);
if (!ret)
- ret = copy_siginfo_to_user((siginfo_t __user *) data,
- &siginfo);
+ ret = copy_siginfo_to_user(datavp, &siginfo);
break;
case PTRACE_SETSIGINFO:
- if (copy_from_user(&siginfo, (siginfo_t __user *) data,
- sizeof siginfo))
+ if (copy_from_user(&siginfo, datavp, sizeof siginfo))
ret = -EFAULT;
else
ret = ptrace_setsiginfo(child, &siginfo);
@@ -621,7 +624,7 @@ int ptrace_request(struct task_struct *child, long request,
}
mmput(mm);
- ret = put_user(tmp, (unsigned long __user *) data);
+ ret = put_user(tmp, datalp);
break;
}
#endif
@@ -650,7 +653,7 @@ int ptrace_request(struct task_struct *child, long request,
case PTRACE_SETREGSET:
{
struct iovec kiov;
- struct iovec __user *uiov = (struct iovec __user *) data;
+ struct iovec __user *uiov = datavp;
if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
return -EFAULT;
@@ -691,7 +694,8 @@ static struct task_struct *ptrace_get_task_struct(pid_t pid)
#define arch_ptrace_attach(child) do { } while (0)
#endif
-SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
+SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
+ unsigned long, data)
{
struct task_struct *child;
long ret;
@@ -732,7 +736,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
return ret;
}
-int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data)
+int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
+ unsigned long data)
{
unsigned long tmp;
int copied;
@@ -743,7 +748,8 @@ int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data)
return put_user(tmp, (unsigned long __user *)data);
}
-int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data)
+int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
+ unsigned long data)
{
int copied;
diff --git a/kernel/range.c b/kernel/range.c
index 471b66acabb..37fa9b99ad5 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -119,7 +119,7 @@ static int cmp_range(const void *x1, const void *x2)
int clean_sort_range(struct range *range, int az)
{
- int i, j, k = az - 1, nr_range = 0;
+ int i, j, k = az - 1, nr_range = az;
for (i = 0; i < k; i++) {
if (range[i].end)
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index d806735342a..03449372474 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -36,31 +36,16 @@
#include <linux/time.h>
#include <linux/cpu.h>
-/* Global control variables for rcupdate callback mechanism. */
-struct rcu_ctrlblk {
- struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
- struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
- struct rcu_head **curtail; /* ->next pointer of last CB. */
-};
-
-/* Definition for rcupdate control block. */
-static struct rcu_ctrlblk rcu_sched_ctrlblk = {
- .donetail = &rcu_sched_ctrlblk.rcucblist,
- .curtail = &rcu_sched_ctrlblk.rcucblist,
-};
-
-static struct rcu_ctrlblk rcu_bh_ctrlblk = {
- .donetail = &rcu_bh_ctrlblk.rcucblist,
- .curtail = &rcu_bh_ctrlblk.rcucblist,
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-int rcu_scheduler_active __read_mostly;
-EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+/* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */
+static struct task_struct *rcu_kthread_task;
+static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
+static unsigned long have_rcu_kthread_work;
+static void invoke_rcu_kthread(void);
/* Forward declarations for rcutiny_plugin.h. */
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+struct rcu_ctrlblk;
+static void rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+static int rcu_kthread(void *arg);
static void __call_rcu(struct rcu_head *head,
void (*func)(struct rcu_head *rcu),
struct rcu_ctrlblk *rcp);
@@ -123,7 +108,7 @@ void rcu_sched_qs(int cpu)
{
if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
rcu_qsctr_help(&rcu_bh_ctrlblk))
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -132,7 +117,7 @@ void rcu_sched_qs(int cpu)
void rcu_bh_qs(int cpu)
{
if (rcu_qsctr_help(&rcu_bh_ctrlblk))
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -152,13 +137,14 @@ void rcu_check_callbacks(int cpu, int user)
}
/*
- * Helper function for rcu_process_callbacks() that operates on the
- * specified rcu_ctrlkblk structure.
+ * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure
+ * whose grace period has elapsed.
*/
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
+static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
struct rcu_head *next, *list;
unsigned long flags;
+ RCU_TRACE(int cb_count = 0);
/* If no RCU callbacks ready to invoke, just return. */
if (&rcp->rcucblist == rcp->donetail)
@@ -180,19 +166,58 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
next = list->next;
prefetch(next);
debug_rcu_head_unqueue(list);
+ local_bh_disable();
list->func(list);
+ local_bh_enable();
list = next;
+ RCU_TRACE(cb_count++);
}
+ RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
}
/*
- * Invoke any callbacks whose grace period has completed.
+ * This kthread invokes RCU callbacks whose grace periods have
+ * elapsed. It is awakened as needed, and takes the place of the
+ * RCU_SOFTIRQ that was used previously for this purpose.
+ * This is a kthread, but it is never stopped, at least not until
+ * the system goes down.
*/
-static void rcu_process_callbacks(struct softirq_action *unused)
+static int rcu_kthread(void *arg)
{
- __rcu_process_callbacks(&rcu_sched_ctrlblk);
- __rcu_process_callbacks(&rcu_bh_ctrlblk);
- rcu_preempt_process_callbacks();
+ unsigned long work;
+ unsigned long morework;
+ unsigned long flags;
+
+ for (;;) {
+ wait_event(rcu_kthread_wq, have_rcu_kthread_work != 0);
+ morework = rcu_boost();
+ local_irq_save(flags);
+ work = have_rcu_kthread_work;
+ have_rcu_kthread_work = morework;
+ local_irq_restore(flags);
+ if (work) {
+ rcu_process_callbacks(&rcu_sched_ctrlblk);
+ rcu_process_callbacks(&rcu_bh_ctrlblk);
+ rcu_preempt_process_callbacks();
+ }
+ schedule_timeout_interruptible(1); /* Leave CPU for others. */
+ }
+
+ return 0; /* Not reached, but needed to shut gcc up. */
+}
+
+/*
+ * Wake up rcu_kthread() to process callbacks now eligible for invocation
+ * or to boost readers.
+ */
+static void invoke_rcu_kthread(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ have_rcu_kthread_work = 1;
+ wake_up(&rcu_kthread_wq);
+ local_irq_restore(flags);
}
/*
@@ -230,6 +255,7 @@ static void __call_rcu(struct rcu_head *head,
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
+ RCU_TRACE(rcp->qlen++);
local_irq_restore(flags);
}
@@ -282,7 +308,16 @@ void rcu_barrier_sched(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
-void __init rcu_init(void)
+/*
+ * Spawn the kthread that invokes RCU callbacks.
+ */
+static int __init rcu_spawn_kthreads(void)
{
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+ struct sched_param sp;
+
+ rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread");
+ sp.sched_priority = RCU_BOOST_PRIO;
+ sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp);
+ return 0;
}
+early_initcall(rcu_spawn_kthreads);
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 6ceca4f745f..015abaea962 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -22,6 +22,40 @@
* Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#ifdef CONFIG_RCU_TRACE
+#define RCU_TRACE(stmt) stmt
+#else /* #ifdef CONFIG_RCU_TRACE */
+#define RCU_TRACE(stmt)
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+ struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
+ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
+ struct rcu_head **curtail; /* ->next pointer of last CB. */
+ RCU_TRACE(long qlen); /* Number of pending CBs. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_sched_ctrlblk = {
+ .donetail = &rcu_sched_ctrlblk.rcucblist,
+ .curtail = &rcu_sched_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+ .donetail = &rcu_bh_ctrlblk.rcucblist,
+ .curtail = &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
#ifdef CONFIG_TINY_PREEMPT_RCU
#include <linux/delay.h>
@@ -46,17 +80,45 @@ struct rcu_preempt_ctrlblk {
struct list_head *gp_tasks;
/* Pointer to the first task blocking the */
/* current grace period, or NULL if there */
- /* is not such task. */
+ /* is no such task. */
struct list_head *exp_tasks;
/* Pointer to first task blocking the */
/* current expedited grace period, or NULL */
/* if there is no such task. If there */
/* is no current expedited grace period, */
/* then there cannot be any such task. */
+#ifdef CONFIG_RCU_BOOST
+ struct list_head *boost_tasks;
+ /* Pointer to first task that needs to be */
+ /* priority-boosted, or NULL if no priority */
+ /* boosting is needed. If there is no */
+ /* current or expedited grace period, there */
+ /* can be no such task. */
+#endif /* #ifdef CONFIG_RCU_BOOST */
u8 gpnum; /* Current grace period. */
u8 gpcpu; /* Last grace period blocked by the CPU. */
u8 completed; /* Last grace period completed. */
/* If all three are equal, RCU is idle. */
+#ifdef CONFIG_RCU_BOOST
+ s8 boosted_this_gp; /* Has boosting already happened? */
+ unsigned long boost_time; /* When to start boosting (jiffies) */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+#ifdef CONFIG_RCU_TRACE
+ unsigned long n_grace_periods;
+#ifdef CONFIG_RCU_BOOST
+ unsigned long n_tasks_boosted;
+ unsigned long n_exp_boosts;
+ unsigned long n_normal_boosts;
+ unsigned long n_normal_balk_blkd_tasks;
+ unsigned long n_normal_balk_gp_tasks;
+ unsigned long n_normal_balk_boost_tasks;
+ unsigned long n_normal_balk_boosted;
+ unsigned long n_normal_balk_notyet;
+ unsigned long n_normal_balk_nos;
+ unsigned long n_exp_balk_blkd_tasks;
+ unsigned long n_exp_balk_nos;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+#endif /* #ifdef CONFIG_RCU_TRACE */
};
static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
@@ -122,6 +184,210 @@ static int rcu_preempt_gp_in_progress(void)
}
/*
+ * Advance a ->blkd_tasks-list pointer to the next entry, instead
+ * returning NULL if at the end of the list.
+ */
+static struct list_head *rcu_next_node_entry(struct task_struct *t)
+{
+ struct list_head *np;
+
+ np = t->rcu_node_entry.next;
+ if (np == &rcu_preempt_ctrlblk.blkd_tasks)
+ np = NULL;
+ return np;
+}
+
+#ifdef CONFIG_RCU_TRACE
+
+#ifdef CONFIG_RCU_BOOST
+static void rcu_initiate_boost_trace(void);
+static void rcu_initiate_exp_boost_trace(void);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Dump additional statistice for TINY_PREEMPT_RCU.
+ */
+static void show_tiny_preempt_stats(struct seq_file *m)
+{
+ seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n",
+ rcu_preempt_ctrlblk.rcb.qlen,
+ rcu_preempt_ctrlblk.n_grace_periods,
+ rcu_preempt_ctrlblk.gpnum,
+ rcu_preempt_ctrlblk.gpcpu,
+ rcu_preempt_ctrlblk.completed,
+ "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)],
+ "N."[!rcu_preempt_ctrlblk.gp_tasks],
+ "E."[!rcu_preempt_ctrlblk.exp_tasks]);
+#ifdef CONFIG_RCU_BOOST
+ seq_printf(m, " ttb=%c btg=",
+ "B."[!rcu_preempt_ctrlblk.boost_tasks]);
+ switch (rcu_preempt_ctrlblk.boosted_this_gp) {
+ case -1:
+ seq_puts(m, "exp");
+ break;
+ case 0:
+ seq_puts(m, "no");
+ break;
+ case 1:
+ seq_puts(m, "begun");
+ break;
+ case 2:
+ seq_puts(m, "done");
+ break;
+ default:
+ seq_printf(m, "?%d?", rcu_preempt_ctrlblk.boosted_this_gp);
+ }
+ seq_printf(m, " ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
+ rcu_preempt_ctrlblk.n_tasks_boosted,
+ rcu_preempt_ctrlblk.n_exp_boosts,
+ rcu_preempt_ctrlblk.n_normal_boosts,
+ (int)(jiffies & 0xffff),
+ (int)(rcu_preempt_ctrlblk.boost_time & 0xffff));
+ seq_printf(m, " %s: nt=%lu gt=%lu bt=%lu b=%lu ny=%lu nos=%lu\n",
+ "normal balk",
+ rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_gp_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_boost_tasks,
+ rcu_preempt_ctrlblk.n_normal_balk_boosted,
+ rcu_preempt_ctrlblk.n_normal_balk_notyet,
+ rcu_preempt_ctrlblk.n_normal_balk_nos);
+ seq_printf(m, " exp balk: bt=%lu nos=%lu\n",
+ rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks,
+ rcu_preempt_ctrlblk.n_exp_balk_nos);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+#ifdef CONFIG_RCU_BOOST
+
+#include "rtmutex_common.h"
+
+/*
+ * Carry out RCU priority boosting on the task indicated by ->boost_tasks,
+ * and advance ->boost_tasks to the next task in the ->blkd_tasks list.
+ */
+static int rcu_boost(void)
+{
+ unsigned long flags;
+ struct rt_mutex mtx;
+ struct list_head *np;
+ struct task_struct *t;
+
+ if (rcu_preempt_ctrlblk.boost_tasks == NULL)
+ return 0; /* Nothing to boost. */
+ raw_local_irq_save(flags);
+ rcu_preempt_ctrlblk.boosted_this_gp++;
+ t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct,
+ rcu_node_entry);
+ np = rcu_next_node_entry(t);
+ rt_mutex_init_proxy_locked(&mtx, t);
+ t->rcu_boost_mutex = &mtx;
+ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
+ raw_local_irq_restore(flags);
+ rt_mutex_lock(&mtx);
+ RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
+ rcu_preempt_ctrlblk.boosted_this_gp++;
+ rt_mutex_unlock(&mtx);
+ return rcu_preempt_ctrlblk.boost_tasks != NULL;
+}
+
+/*
+ * Check to see if it is now time to start boosting RCU readers blocking
+ * the current grace period, and, if so, tell the rcu_kthread_task to
+ * start boosting them. If there is an expedited boost in progress,
+ * we wait for it to complete.
+ *
+ * If there are no blocked readers blocking the current grace period,
+ * return 0 to let the caller know, otherwise return 1. Note that this
+ * return value is independent of whether or not boosting was done.
+ */
+static int rcu_initiate_boost(void)
+{
+ if (!rcu_preempt_blocked_readers_cgp()) {
+ RCU_TRACE(rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks++);
+ return 0;
+ }
+ if (rcu_preempt_ctrlblk.gp_tasks != NULL &&
+ rcu_preempt_ctrlblk.boost_tasks == NULL &&
+ rcu_preempt_ctrlblk.boosted_this_gp == 0 &&
+ ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) {
+ rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks;
+ invoke_rcu_kthread();
+ RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
+ } else
+ RCU_TRACE(rcu_initiate_boost_trace());
+ return 1;
+}
+
+/*
+ * Initiate boosting for an expedited grace period.
+ */
+static void rcu_initiate_expedited_boost(void)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) {
+ rcu_preempt_ctrlblk.boost_tasks =
+ rcu_preempt_ctrlblk.blkd_tasks.next;
+ rcu_preempt_ctrlblk.boosted_this_gp = -1;
+ invoke_rcu_kthread();
+ RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
+ } else
+ RCU_TRACE(rcu_initiate_exp_boost_trace());
+ raw_local_irq_restore(flags);
+}
+
+#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000);
+
+/*
+ * Do priority-boost accounting for the start of a new grace period.
+ */
+static void rcu_preempt_boost_start_gp(void)
+{
+ rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
+ if (rcu_preempt_ctrlblk.boosted_this_gp > 0)
+ rcu_preempt_ctrlblk.boosted_this_gp = 0;
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * If there is no RCU priority boosting, we don't boost.
+ */
+static int rcu_boost(void)
+{
+ return 0;
+}
+
+/*
+ * If there is no RCU priority boosting, we don't initiate boosting,
+ * but we do indicate whether there are blocked readers blocking the
+ * current grace period.
+ */
+static int rcu_initiate_boost(void)
+{
+ return rcu_preempt_blocked_readers_cgp();
+}
+
+/*
+ * If there is no RCU priority boosting, we don't initiate expedited boosting.
+ */
+static void rcu_initiate_expedited_boost(void)
+{
+}
+
+/*
+ * If there is no RCU priority boosting, nothing to do at grace-period start.
+ */
+static void rcu_preempt_boost_start_gp(void)
+{
+}
+
+#endif /* else #ifdef CONFIG_RCU_BOOST */
+
+/*
* Record a preemptible-RCU quiescent state for the specified CPU. Note
* that this just means that the task currently running on the CPU is
* in a quiescent state. There might be any number of tasks blocked
@@ -148,11 +414,14 @@ static void rcu_preempt_cpu_qs(void)
rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ /* If there is no GP then there is nothing more to do. */
+ if (!rcu_preempt_gp_in_progress())
+ return;
/*
- * If there is no GP, or if blocked readers are still blocking GP,
- * then there is nothing more to do.
+ * Check up on boosting. If there are no readers blocking the
+ * current grace period, leave.
*/
- if (!rcu_preempt_gp_in_progress() || rcu_preempt_blocked_readers_cgp())
+ if (rcu_initiate_boost())
return;
/* Advance callbacks. */
@@ -164,9 +433,9 @@ static void rcu_preempt_cpu_qs(void)
if (!rcu_preempt_blocked_readers_any())
rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;
- /* If there are done callbacks, make RCU_SOFTIRQ process them. */
+ /* If there are done callbacks, cause them to be invoked. */
if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
}
/*
@@ -178,12 +447,16 @@ static void rcu_preempt_start_gp(void)
/* Official start of GP. */
rcu_preempt_ctrlblk.gpnum++;
+ RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++);
/* Any blocked RCU readers block new GP. */
if (rcu_preempt_blocked_readers_any())
rcu_preempt_ctrlblk.gp_tasks =
rcu_preempt_ctrlblk.blkd_tasks.next;
+ /* Set up for RCU priority boosting. */
+ rcu_preempt_boost_start_gp();
+
/* If there is no running reader, CPU is done with GP. */
if (!rcu_preempt_running_reader())
rcu_preempt_cpu_qs();
@@ -304,14 +577,16 @@ static void rcu_read_unlock_special(struct task_struct *t)
*/
empty = !rcu_preempt_blocked_readers_cgp();
empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
- np = t->rcu_node_entry.next;
- if (np == &rcu_preempt_ctrlblk.blkd_tasks)
- np = NULL;
+ np = rcu_next_node_entry(t);
list_del(&t->rcu_node_entry);
if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
rcu_preempt_ctrlblk.gp_tasks = np;
if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
rcu_preempt_ctrlblk.exp_tasks = np;
+#ifdef CONFIG_RCU_BOOST
+ if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks)
+ rcu_preempt_ctrlblk.boost_tasks = np;
+#endif /* #ifdef CONFIG_RCU_BOOST */
INIT_LIST_HEAD(&t->rcu_node_entry);
/*
@@ -331,6 +606,14 @@ static void rcu_read_unlock_special(struct task_struct *t)
if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
rcu_report_exp_done();
}
+#ifdef CONFIG_RCU_BOOST
+ /* Unboost self if was boosted. */
+ if (special & RCU_READ_UNLOCK_BOOSTED) {
+ t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
+ rt_mutex_unlock(t->rcu_boost_mutex);
+ t->rcu_boost_mutex = NULL;
+ }
+#endif /* #ifdef CONFIG_RCU_BOOST */
local_irq_restore(flags);
}
@@ -374,7 +657,7 @@ static void rcu_preempt_check_callbacks(void)
rcu_preempt_cpu_qs();
if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
rcu_preempt_ctrlblk.rcb.donetail)
- raise_softirq(RCU_SOFTIRQ);
+ invoke_rcu_kthread();
if (rcu_preempt_gp_in_progress() &&
rcu_cpu_blocking_cur_gp() &&
rcu_preempt_running_reader())
@@ -383,7 +666,7 @@ static void rcu_preempt_check_callbacks(void)
/*
* TINY_PREEMPT_RCU has an extra callback-list tail pointer to
- * update, so this is invoked from __rcu_process_callbacks() to
+ * update, so this is invoked from rcu_process_callbacks() to
* handle that case. Of course, it is invoked for all flavors of
* RCU, but RCU callbacks can appear only on one of the lists, and
* neither ->nexttail nor ->donetail can possibly be NULL, so there
@@ -400,7 +683,7 @@ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
*/
static void rcu_preempt_process_callbacks(void)
{
- __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
+ rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
}
/*
@@ -417,6 +700,7 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
local_irq_save(flags);
*rcu_preempt_ctrlblk.nexttail = head;
rcu_preempt_ctrlblk.nexttail = &head->next;
+ RCU_TRACE(rcu_preempt_ctrlblk.rcb.qlen++);
rcu_preempt_start_gp(); /* checks to see if GP needed. */
local_irq_restore(flags);
}
@@ -532,6 +816,7 @@ void synchronize_rcu_expedited(void)
/* Wait for tail of ->blkd_tasks list to drain. */
if (rcu_preempted_readers_exp())
+ rcu_initiate_expedited_boost();
wait_event(sync_rcu_preempt_exp_wq,
!rcu_preempted_readers_exp());
@@ -572,6 +857,27 @@ void exit_rcu(void)
#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+#ifdef CONFIG_RCU_TRACE
+
+/*
+ * Because preemptible RCU does not exist, it is not necessary to
+ * dump out its statistics.
+ */
+static void show_tiny_preempt_stats(struct seq_file *m)
+{
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+/*
+ * Because preemptible RCU does not exist, it is never necessary to
+ * boost preempted RCU readers.
+ */
+static int rcu_boost(void)
+{
+ return 0;
+}
+
/*
* Because preemptible RCU does not exist, it never has any callbacks
* to check.
@@ -599,17 +905,116 @@ static void rcu_preempt_process_callbacks(void)
#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-
#include <linux/kernel_stat.h>
/*
* During boot, we forgive RCU lockdep issues. After this function is
* invoked, we start taking RCU lockdep issues seriously.
*/
-void rcu_scheduler_starting(void)
+void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
rcu_scheduler_active = 1;
}
#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_RCU_BOOST
+#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
+#else /* #ifdef CONFIG_RCU_BOOST */
+#define RCU_BOOST_PRIO 1
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+#ifdef CONFIG_RCU_TRACE
+
+#ifdef CONFIG_RCU_BOOST
+
+static void rcu_initiate_boost_trace(void)
+{
+ if (rcu_preempt_ctrlblk.gp_tasks == NULL)
+ rcu_preempt_ctrlblk.n_normal_balk_gp_tasks++;
+ else if (rcu_preempt_ctrlblk.boost_tasks != NULL)
+ rcu_preempt_ctrlblk.n_normal_balk_boost_tasks++;
+ else if (rcu_preempt_ctrlblk.boosted_this_gp != 0)
+ rcu_preempt_ctrlblk.n_normal_balk_boosted++;
+ else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))
+ rcu_preempt_ctrlblk.n_normal_balk_notyet++;
+ else
+ rcu_preempt_ctrlblk.n_normal_balk_nos++;
+}
+
+static void rcu_initiate_exp_boost_trace(void)
+{
+ if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
+ rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks++;
+ else
+ rcu_preempt_ctrlblk.n_exp_balk_nos++;
+}
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
+{
+ unsigned long flags;
+
+ raw_local_irq_save(flags);
+ rcp->qlen -= n;
+ raw_local_irq_restore(flags);
+}
+
+/*
+ * Dump statistics for TINY_RCU, such as they are.
+ */
+static int show_tiny_stats(struct seq_file *m, void *unused)
+{
+ show_tiny_preempt_stats(m);
+ seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen);
+ seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen);
+ return 0;
+}
+
+static int show_tiny_stats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, show_tiny_stats, NULL);
+}
+
+static const struct file_operations show_tiny_stats_fops = {
+ .owner = THIS_MODULE,
+ .open = show_tiny_stats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static struct dentry *rcudir;
+
+static int __init rcutiny_trace_init(void)
+{
+ struct dentry *retval;
+
+ rcudir = debugfs_create_dir("rcu", NULL);
+ if (!rcudir)
+ goto free_out;
+ retval = debugfs_create_file("rcudata", 0444, rcudir,
+ NULL, &show_tiny_stats_fops);
+ if (!retval)
+ goto free_out;
+ return 0;
+free_out:
+ debugfs_remove_recursive(rcudir);
+ return 1;
+}
+
+static void __exit rcutiny_trace_cleanup(void)
+{
+ debugfs_remove_recursive(rcudir);
+}
+
+module_init(rcutiny_trace_init);
+module_exit(rcutiny_trace_cleanup);
+
+MODULE_AUTHOR("Paul E. McKenney");
+MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
+MODULE_LICENSE("GPL");
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 9d8e8fb2515..89613f97ff2 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -47,6 +47,7 @@
#include <linux/srcu.h>
#include <linux/slab.h>
#include <asm/byteorder.h>
+#include <linux/sched.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
@@ -64,6 +65,9 @@ static int irqreader = 1; /* RCU readers from irq (timers). */
static int fqs_duration = 0; /* Duration of bursts (us), 0 to disable. */
static int fqs_holdoff = 0; /* Hold time within burst (us). */
static int fqs_stutter = 3; /* Wait time between bursts (s). */
+static int test_boost = 1; /* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */
+static int test_boost_interval = 7; /* Interval between boost tests, seconds. */
+static int test_boost_duration = 4; /* Duration of each boost test, seconds. */
static char *torture_type = "rcu"; /* What RCU implementation to torture. */
module_param(nreaders, int, 0444);
@@ -88,6 +92,12 @@ module_param(fqs_holdoff, int, 0444);
MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
module_param(fqs_stutter, int, 0444);
MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+module_param(test_boost, int, 0444);
+MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
+module_param(test_boost_interval, int, 0444);
+MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+module_param(test_boost_duration, int, 0444);
+MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
@@ -109,6 +119,7 @@ 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];
#define RCU_TORTURE_PIPE_LEN 10
@@ -134,6 +145,12 @@ static atomic_t n_rcu_torture_alloc_fail;
static atomic_t n_rcu_torture_free;
static atomic_t n_rcu_torture_mberror;
static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_boost_ktrerror;
+static long n_rcu_torture_boost_rterror;
+static long n_rcu_torture_boost_allocerror;
+static long n_rcu_torture_boost_afferror;
+static long n_rcu_torture_boost_failure;
+static long n_rcu_torture_boosts;
static long n_rcu_torture_timers;
static struct list_head rcu_torture_removed;
static cpumask_var_t shuffle_tmp_mask;
@@ -147,6 +164,16 @@ static int stutter_pause_test;
#endif
int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+#ifdef CONFIG_RCU_BOOST
+#define rcu_can_boost() 1
+#else /* #ifdef CONFIG_RCU_BOOST */
+#define rcu_can_boost() 0
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+static unsigned long boost_starttime; /* jiffies of next boost test start. */
+DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */
+ /* and boost task create/destroy. */
+
/* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */
#define FULLSTOP_DONTSTOP 0 /* Normal operation. */
@@ -277,6 +304,7 @@ struct rcu_torture_ops {
void (*fqs)(void);
int (*stats)(char *page);
int irq_capable;
+ int can_boost;
char *name;
};
@@ -366,6 +394,7 @@ static struct rcu_torture_ops rcu_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu"
};
@@ -408,6 +437,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu_sync"
};
@@ -424,6 +454,7 @@ static struct rcu_torture_ops rcu_expedited_ops = {
.fqs = rcu_force_quiescent_state,
.stats = NULL,
.irq_capable = 1,
+ .can_boost = rcu_can_boost(),
.name = "rcu_expedited"
};
@@ -684,6 +715,110 @@ static struct rcu_torture_ops sched_expedited_ops = {
};
/*
+ * RCU torture priority-boost testing. Runs one real-time thread per
+ * CPU for moderate bursts, repeatedly registering RCU callbacks and
+ * spinning waiting for them to be invoked. If a given callback takes
+ * too long to be invoked, we assume that priority inversion has occurred.
+ */
+
+struct rcu_boost_inflight {
+ struct rcu_head rcu;
+ int inflight;
+};
+
+static void rcu_torture_boost_cb(struct rcu_head *head)
+{
+ struct rcu_boost_inflight *rbip =
+ container_of(head, struct rcu_boost_inflight, rcu);
+
+ smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
+ rbip->inflight = 0;
+}
+
+static int rcu_torture_boost(void *arg)
+{
+ unsigned long call_rcu_time;
+ unsigned long endtime;
+ unsigned long oldstarttime;
+ struct rcu_boost_inflight rbi = { .inflight = 0 };
+ struct sched_param sp;
+
+ VERBOSE_PRINTK_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!");
+ n_rcu_torture_boost_rterror++;
+ }
+
+ /* Each pass through the following loop does one boost-test cycle. */
+ do {
+ /* Wait for the next test interval. */
+ oldstarttime = boost_starttime;
+ while (jiffies - oldstarttime > ULONG_MAX / 2) {
+ schedule_timeout_uninterruptible(1);
+ rcu_stutter_wait("rcu_torture_boost");
+ if (kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP)
+ goto checkwait;
+ }
+
+ /* Do one boost-test interval. */
+ endtime = oldstarttime + test_boost_duration * HZ;
+ call_rcu_time = jiffies;
+ while (jiffies - endtime > ULONG_MAX / 2) {
+ /* If we don't have a callback in flight, post one. */
+ if (!rbi.inflight) {
+ smp_mb(); /* RCU core before ->inflight = 1. */
+ rbi.inflight = 1;
+ 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");
+ n_rcu_torture_boost_failure++;
+ }
+ call_rcu_time = jiffies;
+ }
+ cond_resched();
+ rcu_stutter_wait("rcu_torture_boost");
+ if (kthread_should_stop() ||
+ fullstop != FULLSTOP_DONTSTOP)
+ goto checkwait;
+ }
+
+ /*
+ * Set the start time of the next test interval.
+ * Yes, this is vulnerable to long delays, but such
+ * delays simply cause a false negative for the next
+ * interval. Besides, we are running at RT priority,
+ * so delays should be relatively rare.
+ */
+ while (oldstarttime == boost_starttime) {
+ if (mutex_trylock(&boost_mutex)) {
+ boost_starttime = jiffies +
+ test_boost_interval * HZ;
+ n_rcu_torture_boosts++;
+ mutex_unlock(&boost_mutex);
+ break;
+ }
+ schedule_timeout_uninterruptible(1);
+ }
+
+ /* Go do the stutter. */
+checkwait: rcu_stutter_wait("rcu_torture_boost");
+ } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+
+ /* Clean up and exit. */
+ VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
+ rcutorture_shutdown_absorb("rcu_torture_boost");
+ while (!kthread_should_stop() || rbi.inflight)
+ schedule_timeout_uninterruptible(1);
+ smp_mb(); /* order accesses to ->inflight before stack-frame death. */
+ return 0;
+}
+
+/*
* RCU torture force-quiescent-state kthread. Repeatedly induces
* bursts of calls to force_quiescent_state(), increasing the probability
* of occurrence of some important types of race conditions.
@@ -933,7 +1068,8 @@ rcu_torture_printk(char *page)
cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
cnt += sprintf(&page[cnt],
"rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d "
- "rtmbe: %d nt: %ld",
+ "rtmbe: %d rtbke: %ld rtbre: %ld rtbae: %ld rtbafe: %ld "
+ "rtbf: %ld rtb: %ld nt: %ld",
rcu_torture_current,
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
@@ -941,8 +1077,19 @@ rcu_torture_printk(char *page)
atomic_read(&n_rcu_torture_alloc_fail),
atomic_read(&n_rcu_torture_free),
atomic_read(&n_rcu_torture_mberror),
+ n_rcu_torture_boost_ktrerror,
+ n_rcu_torture_boost_rterror,
+ n_rcu_torture_boost_allocerror,
+ n_rcu_torture_boost_afferror,
+ n_rcu_torture_boost_failure,
+ n_rcu_torture_boosts,
n_rcu_torture_timers);
- if (atomic_read(&n_rcu_torture_mberror) != 0)
+ if (atomic_read(&n_rcu_torture_mberror) != 0 ||
+ n_rcu_torture_boost_ktrerror != 0 ||
+ n_rcu_torture_boost_rterror != 0 ||
+ n_rcu_torture_boost_allocerror != 0 ||
+ n_rcu_torture_boost_afferror != 0 ||
+ n_rcu_torture_boost_failure != 0)
cnt += sprintf(&page[cnt], " !!!");
cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
if (i > 1) {
@@ -1094,22 +1241,91 @@ rcu_torture_stutter(void *arg)
}
static inline void
-rcu_torture_print_module_parms(char *tag)
+rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
{
printk(KERN_ALERT "%s" TORTURE_FLAG
"--- %s: nreaders=%d nfakewriters=%d "
"stat_interval=%d verbose=%d test_no_idle_hz=%d "
"shuffle_interval=%d stutter=%d irqreader=%d "
- "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d\n",
+ "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
+ "test_boost=%d/%d test_boost_interval=%d "
+ "test_boost_duration=%d\n",
torture_type, tag, nrealreaders, nfakewriters,
stat_interval, verbose, test_no_idle_hz, shuffle_interval,
- stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter);
+ stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
+ test_boost, cur_ops->can_boost,
+ test_boost_interval, test_boost_duration);
}
-static struct notifier_block rcutorture_nb = {
+static struct notifier_block rcutorture_shutdown_nb = {
.notifier_call = rcutorture_shutdown_notify,
};
+static void rcutorture_booster_cleanup(int cpu)
+{
+ struct task_struct *t;
+
+ 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);
+}
+
+static int rcutorture_booster_init(int cpu)
+{
+ int retval;
+
+ if (boost_tasks[cpu] != NULL)
+ return 0; /* Already created, nothing more to do. */
+
+ /* Don't allow time recalculation while creating a new task. */
+ mutex_lock(&boost_mutex);
+ VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task");
+ boost_tasks[cpu] = kthread_create(rcu_torture_boost, NULL,
+ "rcu_torture_boost");
+ if (IS_ERR(boost_tasks[cpu])) {
+ retval = PTR_ERR(boost_tasks[cpu]);
+ VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed");
+ n_rcu_torture_boost_ktrerror++;
+ boost_tasks[cpu] = NULL;
+ mutex_unlock(&boost_mutex);
+ return retval;
+ }
+ kthread_bind(boost_tasks[cpu], cpu);
+ wake_up_process(boost_tasks[cpu]);
+ mutex_unlock(&boost_mutex);
+ return 0;
+}
+
+static int rcutorture_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_DOWN_FAILED:
+ (void)rcutorture_booster_init(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ rcutorture_booster_cleanup(cpu);
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcutorture_cpu_nb = {
+ .notifier_call = rcutorture_cpu_notify,
+};
+
static void
rcu_torture_cleanup(void)
{
@@ -1127,7 +1343,7 @@ rcu_torture_cleanup(void)
}
fullstop = FULLSTOP_RMMOD;
mutex_unlock(&fullstop_mutex);
- unregister_reboot_notifier(&rcutorture_nb);
+ unregister_reboot_notifier(&rcutorture_shutdown_nb);
if (stutter_task) {
VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
kthread_stop(stutter_task);
@@ -1184,6 +1400,12 @@ rcu_torture_cleanup(void)
kthread_stop(fqs_task);
}
fqs_task = NULL;
+ 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);
+ }
/* Wait for all RCU callbacks to fire. */
@@ -1195,9 +1417,9 @@ rcu_torture_cleanup(void)
if (cur_ops->cleanup)
cur_ops->cleanup();
if (atomic_read(&n_rcu_torture_error))
- rcu_torture_print_module_parms("End of test: FAILURE");
+ rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
else
- rcu_torture_print_module_parms("End of test: SUCCESS");
+ rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
}
static int __init
@@ -1242,7 +1464,7 @@ rcu_torture_init(void)
nrealreaders = nreaders;
else
nrealreaders = 2 * num_online_cpus();
- rcu_torture_print_module_parms("Start of test");
+ rcu_torture_print_module_parms(cur_ops, "Start of test");
fullstop = FULLSTOP_DONTSTOP;
/* Set up the freelist. */
@@ -1263,6 +1485,12 @@ rcu_torture_init(void)
atomic_set(&n_rcu_torture_free, 0);
atomic_set(&n_rcu_torture_mberror, 0);
atomic_set(&n_rcu_torture_error, 0);
+ n_rcu_torture_boost_ktrerror = 0;
+ n_rcu_torture_boost_rterror = 0;
+ n_rcu_torture_boost_allocerror = 0;
+ n_rcu_torture_boost_afferror = 0;
+ n_rcu_torture_boost_failure = 0;
+ n_rcu_torture_boosts = 0;
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
atomic_set(&rcu_torture_wcount[i], 0);
for_each_possible_cpu(cpu) {
@@ -1376,7 +1604,27 @@ rcu_torture_init(void)
goto unwind;
}
}
- register_reboot_notifier(&rcutorture_nb);
+ if (test_boost_interval < 1)
+ test_boost_interval = 1;
+ if (test_boost_duration < 2)
+ test_boost_duration = 2;
+ if ((test_boost == 1 && cur_ops->can_boost) ||
+ test_boost == 2) {
+ int retval;
+
+ boost_starttime = jiffies + test_boost_interval * HZ;
+ register_cpu_notifier(&rcutorture_cpu_nb);
+ 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;
+ goto unwind;
+ }
+ }
+ }
+ register_reboot_notifier(&rcutorture_shutdown_nb);
mutex_unlock(&fullstop_mutex);
return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ccdc04c4798..d0ddfea6579 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -67,9 +67,6 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
.gpnum = -300, \
.completed = -300, \
.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \
- .orphan_cbs_list = NULL, \
- .orphan_cbs_tail = &structname.orphan_cbs_list, \
- .orphan_qlen = 0, \
.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \
.n_force_qs = 0, \
.n_force_qs_ngp = 0, \
@@ -620,9 +617,17 @@ static void __init check_cpu_stall_init(void)
static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
if (rdp->gpnum != rnp->gpnum) {
- rdp->qs_pending = 1;
- rdp->passed_quiesc = 0;
+ /*
+ * If the current grace period is waiting for this CPU,
+ * set up to detect a quiescent state, otherwise don't
+ * go looking for one.
+ */
rdp->gpnum = rnp->gpnum;
+ if (rnp->qsmask & rdp->grpmask) {
+ rdp->qs_pending = 1;
+ rdp->passed_quiesc = 0;
+ } else
+ rdp->qs_pending = 0;
}
}
@@ -681,6 +686,24 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat
/* Remember that we saw this grace-period completion. */
rdp->completed = rnp->completed;
+
+ /*
+ * If we were in an extended quiescent state, we may have
+ * missed some grace periods that others CPUs handled on
+ * our behalf. Catch up with this state to avoid noting
+ * spurious new grace periods. If another grace period
+ * has started, then rnp->gpnum will have advanced, so
+ * we will detect this later on.
+ */
+ if (ULONG_CMP_LT(rdp->gpnum, rdp->completed))
+ rdp->gpnum = rdp->completed;
+
+ /*
+ * If RCU does not need a quiescent state from this CPU,
+ * then make sure that this CPU doesn't go looking for one.
+ */
+ if ((rnp->qsmask & rdp->grpmask) == 0)
+ rdp->qs_pending = 0;
}
}
@@ -984,53 +1007,31 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Move a dying CPU's RCU callbacks to the ->orphan_cbs_list for the
- * specified flavor of RCU. The callbacks will be adopted by the next
- * _rcu_barrier() invocation or by the CPU_DEAD notifier, whichever
- * comes first. Because this is invoked from the CPU_DYING notifier,
- * irqs are already disabled.
+ * Move a dying CPU's RCU callbacks to online CPU's callback list.
+ * Synchronization is not required because this function executes
+ * in stop_machine() context.
*/
-static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
+static void rcu_send_cbs_to_online(struct rcu_state *rsp)
{
int i;
+ /* current DYING CPU is cleared in the cpu_online_mask */
+ int receive_cpu = cpumask_any(cpu_online_mask);
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
+ struct rcu_data *receive_rdp = per_cpu_ptr(rsp->rda, receive_cpu);
if (rdp->nxtlist == NULL)
return; /* irqs disabled, so comparison is stable. */
- raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */
- *rsp->orphan_cbs_tail = rdp->nxtlist;
- rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
+
+ *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
+ receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+ receive_rdp->qlen += rdp->qlen;
+ receive_rdp->n_cbs_adopted += rdp->qlen;
+ rdp->n_cbs_orphaned += rdp->qlen;
+
rdp->nxtlist = NULL;
for (i = 0; i < RCU_NEXT_SIZE; i++)
rdp->nxttail[i] = &rdp->nxtlist;
- rsp->orphan_qlen += rdp->qlen;
- rdp->n_cbs_orphaned += rdp->qlen;
rdp->qlen = 0;
- raw_spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
-}
-
-/*
- * Adopt previously orphaned RCU callbacks.
- */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
-{
- unsigned long flags;
- struct rcu_data *rdp;
-
- raw_spin_lock_irqsave(&rsp->onofflock, flags);
- rdp = this_cpu_ptr(rsp->rda);
- if (rsp->orphan_cbs_list == NULL) {
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
- return;
- }
- *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
- rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
- rdp->qlen += rsp->orphan_qlen;
- rdp->n_cbs_adopted += rsp->orphan_qlen;
- rsp->orphan_cbs_list = NULL;
- rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
- rsp->orphan_qlen = 0;
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
}
/*
@@ -1081,8 +1082,6 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
raw_spin_unlock_irqrestore(&rnp->lock, flags);
if (need_report & RCU_OFL_TASKS_EXP_GP)
rcu_report_exp_rnp(rsp, rnp);
-
- rcu_adopt_orphan_cbs(rsp);
}
/*
@@ -1100,11 +1099,7 @@ static void rcu_offline_cpu(int cpu)
#else /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
-{
-}
-
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_send_cbs_to_online(struct rcu_state *rsp)
{
}
@@ -1440,22 +1435,11 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
*/
local_irq_save(flags);
rdp = this_cpu_ptr(rsp->rda);
- rcu_process_gp_end(rsp, rdp);
- check_for_new_grace_period(rsp, rdp);
/* Add the callback to our list. */
*rdp->nxttail[RCU_NEXT_TAIL] = head;
rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
- /* Start a new grace period if one not already started. */
- if (!rcu_gp_in_progress(rsp)) {
- unsigned long nestflag;
- struct rcu_node *rnp_root = rcu_get_root(rsp);
-
- raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
- rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */
- }
-
/*
* Force the grace period if too many callbacks or too long waiting.
* Enforce hysteresis, and don't invoke force_quiescent_state()
@@ -1464,12 +1448,27 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
* is the only one waiting for a grace period to complete.
*/
if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
- rdp->blimit = LONG_MAX;
- if (rsp->n_force_qs == rdp->n_force_qs_snap &&
- *rdp->nxttail[RCU_DONE_TAIL] != head)
- force_quiescent_state(rsp, 0);
- rdp->n_force_qs_snap = rsp->n_force_qs;
- rdp->qlen_last_fqs_check = rdp->qlen;
+
+ /* Are we ignoring a completed grace period? */
+ rcu_process_gp_end(rsp, rdp);
+ check_for_new_grace_period(rsp, rdp);
+
+ /* Start a new grace period if one not already started. */
+ if (!rcu_gp_in_progress(rsp)) {
+ unsigned long nestflag;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+
+ raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
+ rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */
+ } else {
+ /* Give the grace period a kick. */
+ rdp->blimit = LONG_MAX;
+ if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ *rdp->nxttail[RCU_DONE_TAIL] != head)
+ force_quiescent_state(rsp, 0);
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->qlen_last_fqs_check = rdp->qlen;
+ }
} else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
force_quiescent_state(rsp, 1);
local_irq_restore(flags);
@@ -1699,13 +1698,12 @@ static void _rcu_barrier(struct rcu_state *rsp,
* decrement rcu_barrier_cpu_count -- otherwise the first CPU
* might complete its grace period before all of the other CPUs
* did their increment, causing this function to return too
- * early.
+ * early. Note that on_each_cpu() disables irqs, which prevents
+ * any CPUs from coming online or going offline until each online
+ * CPU has queued its RCU-barrier callback.
*/
atomic_set(&rcu_barrier_cpu_count, 1);
- preempt_disable(); /* stop CPU_DYING from filling orphan_cbs_list */
- rcu_adopt_orphan_cbs(rsp);
on_each_cpu(rcu_barrier_func, (void *)call_rcu_func, 1);
- preempt_enable(); /* CPU_DYING can again fill orphan_cbs_list */
if (atomic_dec_and_test(&rcu_barrier_cpu_count))
complete(&rcu_barrier_completion);
wait_for_completion(&rcu_barrier_completion);
@@ -1831,18 +1829,13 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
case CPU_DYING:
case CPU_DYING_FROZEN:
/*
- * preempt_disable() in _rcu_barrier() prevents stop_machine(),
- * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
- * returns, all online cpus have queued rcu_barrier_func().
- * The dying CPU clears its cpu_online_mask bit and
- * moves all of its RCU callbacks to ->orphan_cbs_list
- * in the context of stop_machine(), so subsequent calls
- * to _rcu_barrier() will adopt these callbacks and only
- * then queue rcu_barrier_func() on all remaining CPUs.
+ * The whole machine is "stopped" except this CPU, so we can
+ * touch any data without introducing corruption. We send the
+ * dying CPU's callbacks to an arbitrarily chosen online CPU.
*/
- rcu_send_cbs_to_orphanage(&rcu_bh_state);
- rcu_send_cbs_to_orphanage(&rcu_sched_state);
- rcu_preempt_send_cbs_to_orphanage();
+ rcu_send_cbs_to_online(&rcu_bh_state);
+ rcu_send_cbs_to_online(&rcu_sched_state);
+ rcu_preempt_send_cbs_to_online();
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
@@ -1880,8 +1873,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
int i;
- for (i = NUM_RCU_LVLS - 1; i >= 0; i--)
+ for (i = NUM_RCU_LVLS - 1; 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)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 91d4170c5c1..e8f057e44e3 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -31,46 +31,51 @@
/*
* Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
* In theory, it should be possible to add more levels straightforwardly.
- * In practice, this has not been tested, so there is probably some
- * bug somewhere.
+ * In practice, this did work well going from three levels to four.
+ * Of course, your mileage may vary.
*/
#define MAX_RCU_LVLS 4
-#define RCU_FANOUT (CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
-#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
-#define RCU_FANOUT_FOURTH (RCU_FANOUT_CUBE * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT
+#if CONFIG_RCU_FANOUT > 16
+#define RCU_FANOUT_LEAF 16
+#else /* #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_LEAF (CONFIG_RCU_FANOUT)
+#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
+#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT_1
# define NUM_RCU_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_SQ
+#elif NR_CPUS <= RCU_FANOUT_2
# define NUM_RCU_LVLS 2
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_CUBE
+#elif NR_CPUS <= RCU_FANOUT_3
# define NUM_RCU_LVLS 3
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
-# define NUM_RCU_LVL_3 NR_CPUS
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_LVL_3 (NR_CPUS)
# define NUM_RCU_LVL_4 0
-#elif NR_CPUS <= RCU_FANOUT_FOURTH
+#elif NR_CPUS <= RCU_FANOUT_4
# define NUM_RCU_LVLS 4
# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
-# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
-# define NUM_RCU_LVL_4 NR_CPUS
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_LVL_4 (NR_CPUS)
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
@@ -203,8 +208,8 @@ struct rcu_data {
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
- unsigned long n_cbs_orphaned; /* RCU cbs sent to orphanage. */
- unsigned long n_cbs_adopted; /* RCU cbs adopted from orphanage. */
+ unsigned long n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */
+ unsigned long n_cbs_adopted; /* RCU cbs adopted from dying CPU */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
@@ -309,15 +314,7 @@ struct rcu_state {
/* End of fields guarded by root rcu_node's lock. */
raw_spinlock_t onofflock; /* exclude on/offline and */
- /* starting new GP. Also */
- /* protects the following */
- /* orphan_cbs fields. */
- struct rcu_head *orphan_cbs_list; /* list of rcu_head structs */
- /* orphaned by all CPUs in */
- /* a given leaf rcu_node */
- /* going offline. */
- struct rcu_head **orphan_cbs_tail; /* And tail pointer. */
- long orphan_qlen; /* Number of orphaned cbs. */
+ /* starting new GP. */
raw_spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
@@ -390,7 +387,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
static int rcu_preempt_pending(int cpu);
static int rcu_preempt_needs_cpu(int cpu);
static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
-static void rcu_preempt_send_cbs_to_orphanage(void);
+static void rcu_preempt_send_cbs_to_online(void);
static void __init __rcu_init_preempt(void);
static void rcu_needs_cpu_flush(void);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 71a4147473f..a3638710dc6 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -25,6 +25,7 @@
*/
#include <linux/delay.h>
+#include <linux/stop_machine.h>
/*
* Check the RCU kernel configuration parameters and print informative
@@ -773,11 +774,11 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
}
/*
- * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ * Move preemptable RCU's callbacks from dying CPU to other online CPU.
*/
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
{
- rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+ rcu_send_cbs_to_online(&rcu_preempt_state);
}
/*
@@ -1001,7 +1002,7 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
/*
* Because there is no preemptable RCU, there are no callbacks to move.
*/
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
{
}
@@ -1014,6 +1015,132 @@ static void __init __rcu_init_preempt(void)
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifndef CONFIG_SMP
+
+void synchronize_sched_expedited(void)
+{
+ cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0);
+static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0);
+
+static int synchronize_sched_expedited_cpu_stop(void *data)
+{
+ /*
+ * There must be a full memory barrier on each affected CPU
+ * between the time that try_stop_cpus() is called and the
+ * time that it returns.
+ *
+ * In the current initial implementation of cpu_stop, the
+ * above condition is already met when the control reaches
+ * this point and the following smp_mb() is not strictly
+ * necessary. Do smp_mb() anyway for documentation and
+ * robustness against future implementation changes.
+ */
+ smp_mb(); /* See above comment block. */
+ return 0;
+}
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly. This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier. Failing to
+ * observe this restriction will result in deadlock.
+ *
+ * This implementation can be thought of as an application of ticket
+ * locking to RCU, with sync_sched_expedited_started and
+ * sync_sched_expedited_done taking on the roles of the halves
+ * of the ticket-lock word. Each task atomically increments
+ * sync_sched_expedited_started upon entry, snapshotting the old value,
+ * then attempts to stop all the CPUs. If this succeeds, then each
+ * CPU will have executed a context switch, resulting in an RCU-sched
+ * grace period. We are then done, so we use atomic_cmpxchg() to
+ * update sync_sched_expedited_done to match our snapshot -- but
+ * only if someone else has not already advanced past our snapshot.
+ *
+ * On the other hand, if try_stop_cpus() fails, we check the value
+ * of sync_sched_expedited_done. If it has advanced past our
+ * initial snapshot, then someone else must have forced a grace period
+ * some time after we took our snapshot. In this case, our work is
+ * done for us, and we can simply return. Otherwise, we try again,
+ * but keep our initial snapshot for purposes of checking for someone
+ * doing our work for us.
+ *
+ * If we fail too many times in a row, we fall back to synchronize_sched().
+ */
+void synchronize_sched_expedited(void)
+{
+ int firstsnap, s, snap, trycount = 0;
+
+ /* Note that atomic_inc_return() implies full memory barrier. */
+ firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started);
+ get_online_cpus();
+
+ /*
+ * Each pass through the following loop attempts to force a
+ * context switch on each CPU.
+ */
+ while (try_stop_cpus(cpu_online_mask,
+ synchronize_sched_expedited_cpu_stop,
+ NULL) == -EAGAIN) {
+ put_online_cpus();
+
+ /* No joy, try again later. Or just synchronize_sched(). */
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_sched();
+ return;
+ }
+
+ /* Check to see if someone else did our work for us. */
+ s = atomic_read(&sync_sched_expedited_done);
+ if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ return;
+ }
+
+ /*
+ * Refetching sync_sched_expedited_started allows later
+ * callers to piggyback on our grace period. We subtract
+ * 1 to get the same token that the last incrementer got.
+ * We retry after they started, so our grace period works
+ * for them, and they started after our first try, so their
+ * grace period works for us.
+ */
+ get_online_cpus();
+ snap = atomic_read(&sync_sched_expedited_started) - 1;
+ smp_mb(); /* ensure read is before try_stop_cpus(). */
+ }
+
+ /*
+ * Everyone up to our most recent fetch is covered by our grace
+ * period. Update the counter, but only if our work is still
+ * relevant -- which it won't be if someone who started later
+ * than we did beat us to the punch.
+ */
+ do {
+ s = atomic_read(&sync_sched_expedited_done);
+ if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ break;
+ }
+ } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s);
+
+ put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
+
#if !defined(CONFIG_RCU_FAST_NO_HZ)
/*
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index d15430b9d12..c8e97853b97 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -166,13 +166,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
gpnum = rsp->gpnum;
seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
- "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
+ "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
rsp->completed, gpnum, rsp->signaled,
(long)(rsp->jiffies_force_qs - jiffies),
(int)(jiffies & 0xffff),
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- rsp->n_force_qs_lh, rsp->orphan_qlen);
+ rsp->n_force_qs_lh);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
@@ -300,7 +300,7 @@ static const struct file_operations rcu_pending_fops = {
static struct dentry *rcudir;
-static int __init rcuclassic_trace_init(void)
+static int __init rcutree_trace_init(void)
{
struct dentry *retval;
@@ -337,14 +337,14 @@ free_out:
return 1;
}
-static void __exit rcuclassic_trace_cleanup(void)
+static void __exit rcutree_trace_cleanup(void)
{
debugfs_remove_recursive(rcudir);
}
-module_init(rcuclassic_trace_init);
-module_exit(rcuclassic_trace_cleanup);
+module_init(rcutree_trace_init);
+module_exit(rcutree_trace_cleanup);
MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
diff --git a/kernel/relay.c b/kernel/relay.c
index c7cf397fb92..859ea5a9605 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -70,17 +70,10 @@ static const struct vm_operations_struct relay_file_mmap_ops = {
*/
static struct page **relay_alloc_page_array(unsigned int n_pages)
{
- struct page **array;
- size_t pa_size = n_pages * sizeof(struct page *);
-
- if (pa_size > PAGE_SIZE) {
- array = vmalloc(pa_size);
- if (array)
- memset(array, 0, pa_size);
- } else {
- array = kzalloc(pa_size, GFP_KERNEL);
- }
- return array;
+ const size_t pa_size = n_pages * sizeof(struct page *);
+ if (pa_size > PAGE_SIZE)
+ return vzalloc(pa_size);
+ return kzalloc(pa_size, GFP_KERNEL);
}
/*
diff --git a/kernel/resource.c b/kernel/resource.c
index 7b36976e5de..798e2fae2a0 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -357,6 +357,32 @@ int __weak page_is_ram(unsigned long pfn)
return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
}
+void __weak arch_remove_reservations(struct resource *avail)
+{
+}
+
+static resource_size_t simple_align_resource(void *data,
+ const struct resource *avail,
+ resource_size_t size,
+ resource_size_t align)
+{
+ return avail->start;
+}
+
+static void resource_clip(struct resource *res, resource_size_t min,
+ resource_size_t max)
+{
+ if (res->start < min)
+ res->start = min;
+ if (res->end > max)
+ 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 given range and alignment.
*/
@@ -370,8 +396,9 @@ static int find_resource(struct resource *root, struct resource *new,
void *alignf_data)
{
struct resource *this = root->child;
- struct resource tmp = *new;
+ struct resource tmp = *new, avail, alloc;
+ tmp.flags = new->flags;
tmp.start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
@@ -386,17 +413,22 @@ static int find_resource(struct resource *root, struct resource *new,
tmp.end = this->start - 1;
else
tmp.end = root->end;
- if (tmp.start < min)
- tmp.start = min;
- if (tmp.end > max)
- tmp.end = max;
- tmp.start = ALIGN(tmp.start, align);
- if (alignf)
- tmp.start = alignf(alignf_data, &tmp, size, align);
- if (tmp.start < tmp.end && tmp.end - tmp.start >= size - 1) {
- new->start = tmp.start;
- new->end = tmp.start + size - 1;
- return 0;
+
+ resource_clip(&tmp, min, max);
+ arch_remove_reservations(&tmp);
+
+ /* Check for overflow after ALIGN() */
+ avail = *new;
+ avail.start = ALIGN(tmp.start, align);
+ avail.end = tmp.end;
+ if (avail.start >= tmp.start) {
+ alloc.start = alignf(alignf_data, &avail, size, align);
+ alloc.end = alloc.start + size - 1;
+ if (resource_contains(&avail, &alloc)) {
+ new->start = alloc.start;
+ new->end = alloc.end;
+ return 0;
+ }
}
if (!this)
break;
@@ -428,6 +460,9 @@ int allocate_resource(struct resource *root, struct resource *new,
{
int err;
+ if (!alignf)
+ alignf = simple_align_resource;
+
write_lock(&resource_lock);
err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
if (err >= 0 && __request_resource(root, new))
@@ -453,6 +488,8 @@ static struct resource * __insert_resource(struct resource *parent, struct resou
if (first == parent)
return first;
+ if (WARN_ON(first == new)) /* duplicated insertion */
+ return first;
if ((first->start > new->start) || (first->end < new->end))
break;
diff --git a/kernel/sched.c b/kernel/sched.c
index d42992bccdf..04949089e76 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,9 +75,11 @@
#include <asm/tlb.h>
#include <asm/irq_regs.h>
+#include <asm/mutex.h>
#include "sched_cpupri.h"
#include "workqueue_sched.h"
+#include "sched_autogroup.h"
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
@@ -253,6 +255,8 @@ struct task_group {
/* runqueue "owned" by this group on each cpu */
struct cfs_rq **cfs_rq;
unsigned long shares;
+
+ atomic_t load_weight;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
@@ -268,24 +272,19 @@ struct task_group {
struct task_group *parent;
struct list_head siblings;
struct list_head children;
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+ struct autogroup *autogroup;
+#endif
};
#define root_task_group init_task_group
-/* task_group_lock serializes add/remove of task groups and also changes to
- * a task group's cpu shares.
- */
+/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
#ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
-static int root_task_group_empty(void)
-{
- return list_empty(&root_task_group.children);
-}
-#endif
-
# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
/*
@@ -342,6 +341,7 @@ struct cfs_rq {
* leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
* list is used during load balance.
*/
+ int on_list;
struct list_head leaf_cfs_rq_list;
struct task_group *tg; /* group that "owns" this runqueue */
@@ -360,14 +360,17 @@ struct cfs_rq {
unsigned long h_load;
/*
- * this cpu's part of tg->shares
+ * Maintaining per-cpu shares distribution for group scheduling
+ *
+ * load_stamp is the last time we updated the load average
+ * load_last is the last time we updated the load average and saw load
+ * load_unacc_exec_time is currently unaccounted execution time
*/
- unsigned long shares;
+ u64 load_avg;
+ u64 load_period;
+ u64 load_stamp, load_last, load_unacc_exec_time;
- /*
- * load.weight at the time we set shares
- */
- unsigned long rq_weight;
+ unsigned long load_contribution;
#endif
#endif
};
@@ -560,18 +563,8 @@ struct rq {
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
- rq->curr->sched_class->check_preempt_curr(rq, p, flags);
- /*
- * A queue event has occurred, and we're going to schedule. In
- * this case, we can save a useless back to back clock update.
- */
- if (test_tsk_need_resched(p))
- rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
static inline int cpu_of(struct rq *rq)
{
@@ -615,11 +608,14 @@ static inline int cpu_of(struct rq *rq)
*/
static inline struct task_group *task_group(struct task_struct *p)
{
+ struct task_group *tg;
struct cgroup_subsys_state *css;
css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
lockdep_is_held(&task_rq(p)->lock));
- return container_of(css, struct task_group, css);
+ tg = container_of(css, struct task_group, css);
+
+ return autogroup_task_group(p, tg);
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -646,22 +642,18 @@ static inline struct task_group *task_group(struct task_struct *p)
#endif /* CONFIG_CGROUP_SCHED */
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
{
- if (!rq->skip_clock_update) {
- int cpu = cpu_of(rq);
- u64 irq_time;
+ s64 delta;
- rq->clock = sched_clock_cpu(cpu);
- irq_time = irq_time_cpu(cpu);
- if (rq->clock - irq_time > rq->clock_task)
- rq->clock_task = rq->clock - irq_time;
+ if (rq->skip_clock_update)
+ return;
- sched_irq_time_avg_update(rq, irq_time);
- }
+ delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+ rq->clock += delta;
+ update_rq_clock_task(rq, delta);
}
/*
@@ -807,20 +799,6 @@ late_initcall(sched_init_debug);
const_debug unsigned int sysctl_sched_nr_migrate = 32;
/*
- * ratelimit for updating the group shares.
- * default: 0.25ms
- */
-unsigned int sysctl_sched_shares_ratelimit = 250000;
-unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
-
-/*
- * Inject some fuzzyness into changing the per-cpu group shares
- * this avoids remote rq-locks at the expense of fairness.
- * default: 4
- */
-unsigned int sysctl_sched_shares_thresh = 4;
-
-/*
* period over which we average the RT time consumption, measured
* in ms.
*
@@ -1369,6 +1347,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
lw->inv_weight = 0;
}
+static inline void update_load_set(struct load_weight *lw, unsigned long w)
+{
+ lw->weight = w;
+ lw->inv_weight = 0;
+}
+
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
* of tasks with abnormal "nice" values across CPUs the contribution that
@@ -1557,101 +1541,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
#ifdef CONFIG_FAIR_GROUP_SCHED
-static __read_mostly unsigned long __percpu *update_shares_data;
-
-static void __set_se_shares(struct sched_entity *se, unsigned long shares);
-
-/*
- * Calculate and set the cpu's group shares.
- */
-static void update_group_shares_cpu(struct task_group *tg, int cpu,
- unsigned long sd_shares,
- unsigned long sd_rq_weight,
- unsigned long *usd_rq_weight)
-{
- unsigned long shares, rq_weight;
- int boost = 0;
-
- rq_weight = usd_rq_weight[cpu];
- if (!rq_weight) {
- boost = 1;
- rq_weight = NICE_0_LOAD;
- }
-
- /*
- * \Sum_j shares_j * rq_weight_i
- * shares_i = -----------------------------
- * \Sum_j rq_weight_j
- */
- shares = (sd_shares * rq_weight) / sd_rq_weight;
- shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
-
- if (abs(shares - tg->se[cpu]->load.weight) >
- sysctl_sched_shares_thresh) {
- struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
-
- raw_spin_lock_irqsave(&rq->lock, flags);
- tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
- tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
- __set_se_shares(tg->se[cpu], shares);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
- }
-}
-
-/*
- * Re-compute the task group their per cpu shares over the given domain.
- * This needs to be done in a bottom-up fashion because the rq weight of a
- * parent group depends on the shares of its child groups.
- */
-static int tg_shares_up(struct task_group *tg, void *data)
-{
- unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
- unsigned long *usd_rq_weight;
- struct sched_domain *sd = data;
- unsigned long flags;
- int i;
-
- if (!tg->se[0])
- return 0;
-
- local_irq_save(flags);
- usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
-
- for_each_cpu(i, sched_domain_span(sd)) {
- weight = tg->cfs_rq[i]->load.weight;
- usd_rq_weight[i] = weight;
-
- rq_weight += weight;
- /*
- * If there are currently no tasks on the cpu pretend there
- * is one of average load so that when a new task gets to
- * run here it will not get delayed by group starvation.
- */
- if (!weight)
- weight = NICE_0_LOAD;
-
- sum_weight += weight;
- shares += tg->cfs_rq[i]->shares;
- }
-
- if (!rq_weight)
- rq_weight = sum_weight;
-
- if ((!shares && rq_weight) || shares > tg->shares)
- shares = tg->shares;
-
- if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
- shares = tg->shares;
-
- for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
-
- local_irq_restore(flags);
-
- return 0;
-}
-
/*
* Compute the cpu's hierarchical load factor for each task group.
* This needs to be done in a top-down fashion because the load of a child
@@ -1666,7 +1555,7 @@ static int tg_load_down(struct task_group *tg, void *data)
load = cpu_rq(cpu)->load.weight;
} else {
load = tg->parent->cfs_rq[cpu]->h_load;
- load *= tg->cfs_rq[cpu]->shares;
+ load *= tg->se[cpu]->load.weight;
load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
}
@@ -1675,34 +1564,11 @@ static int tg_load_down(struct task_group *tg, void *data)
return 0;
}
-static void update_shares(struct sched_domain *sd)
-{
- s64 elapsed;
- u64 now;
-
- if (root_task_group_empty())
- return;
-
- now = local_clock();
- elapsed = now - sd->last_update;
-
- if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
- sd->last_update = now;
- walk_tg_tree(tg_nop, tg_shares_up, sd);
- }
-}
-
static void update_h_load(long cpu)
{
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}
-#else
-
-static inline void update_shares(struct sched_domain *sd)
-{
-}
-
#endif
#ifdef CONFIG_PREEMPT
@@ -1824,15 +1690,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
-{
-#ifdef CONFIG_SMP
- cfs_rq->shares = shares;
-#endif
-}
-#endif
-
static void calc_load_account_idle(struct rq *this_rq);
static void update_sysctl(void);
static int get_update_sysctl_factor(void);
@@ -1934,10 +1791,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
* They are read and saved off onto struct rq in update_rq_clock().
* This may result in other CPU reading this CPU's irq time and can
* race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
*/
static DEFINE_PER_CPU(u64, cpu_hardirq_time);
static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1955,19 +1811,58 @@ void disable_sched_clock_irqtime(void)
sched_clock_irqtime = 0;
}
-static u64 irq_time_cpu(int cpu)
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
{
- if (!sched_clock_irqtime)
- return 0;
+ __this_cpu_inc(irq_time_seq.sequence);
+ smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+ smp_wmb();
+ __this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+ u64 irq_time;
+ unsigned seq;
+ do {
+ seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+ irq_time = per_cpu(cpu_softirq_time, cpu) +
+ per_cpu(cpu_hardirq_time, cpu);
+ } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+ return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
}
+#endif /* CONFIG_64BIT */
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
void account_system_vtime(struct task_struct *curr)
{
unsigned long flags;
+ s64 delta;
int cpu;
- u64 now, delta;
if (!sched_clock_irqtime)
return;
@@ -1975,9 +1870,10 @@ void account_system_vtime(struct task_struct *curr)
local_irq_save(flags);
cpu = smp_processor_id();
- now = sched_clock_cpu(cpu);
- delta = now - per_cpu(irq_start_time, cpu);
- per_cpu(irq_start_time, cpu) = now;
+ delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+ __this_cpu_add(irq_start_time, delta);
+
+ irq_time_write_begin();
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
@@ -1985,37 +1881,60 @@ void account_system_vtime(struct task_struct *curr)
* that do not consume any time, but still wants to run.
*/
if (hardirq_count())
- per_cpu(cpu_hardirq_time, cpu) += delta;
+ __this_cpu_add(cpu_hardirq_time, delta);
else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
- per_cpu(cpu_softirq_time, cpu) += delta;
+ __this_cpu_add(cpu_softirq_time, delta);
+ irq_time_write_end();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(account_system_vtime);
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
{
- if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
- u64 delta_irq = curr_irq_time - rq->prev_irq_time;
- rq->prev_irq_time = curr_irq_time;
- sched_rt_avg_update(rq, delta_irq);
- }
+ s64 irq_delta;
+
+ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+ /*
+ * Since irq_time is only updated on {soft,}irq_exit, we might run into
+ * this case when a previous update_rq_clock() happened inside a
+ * {soft,}irq region.
+ *
+ * When this happens, we stop ->clock_task and only update the
+ * prev_irq_time stamp to account for the part that fit, so that a next
+ * update will consume the rest. This ensures ->clock_task is
+ * monotonic.
+ *
+ * It does however cause some slight miss-attribution of {soft,}irq
+ * time, a more accurate solution would be to update the irq_time using
+ * the current rq->clock timestamp, except that would require using
+ * atomic ops.
+ */
+ if (irq_delta > delta)
+ irq_delta = delta;
+
+ rq->prev_irq_time += irq_delta;
+ delta -= irq_delta;
+ rq->clock_task += delta;
+
+ if (irq_delta && sched_feat(NONIRQ_POWER))
+ sched_rt_avg_update(rq, irq_delta);
}
-#else
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static u64 irq_time_cpu(int cpu)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
{
- return 0;
+ rq->clock_task += delta;
}
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
-
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
+#include "sched_autogroup.c"
#include "sched_stoptask.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
@@ -2118,6 +2037,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
p->sched_class->prio_changed(rq, p, oldprio, running);
}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+ const struct sched_class *class;
+
+ if (p->sched_class == rq->curr->sched_class) {
+ rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+ } else {
+ for_each_class(class) {
+ if (class == rq->curr->sched_class)
+ break;
+ if (class == p->sched_class) {
+ resched_task(rq->curr);
+ break;
+ }
+ }
+ }
+
+ /*
+ * A queue event has occurred, and we're going to schedule. In
+ * this case, we can save a useless back to back clock update.
+ */
+ if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+ rq->skip_clock_update = 1;
+}
+
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
@@ -2183,10 +2127,8 @@ static int migration_cpu_stop(void *data);
* The task's runqueue lock must be held.
* Returns true if you have to wait for migration thread.
*/
-static bool migrate_task(struct task_struct *p, int dest_cpu)
+static bool migrate_task(struct task_struct *p, struct rq *rq)
{
- struct rq *rq = task_rq(p);
-
/*
* If the task is not on a runqueue (and not running), then
* the next wake-up will properly place the task.
@@ -2366,18 +2308,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
return dest_cpu;
/* No more Mr. Nice Guy. */
- if (unlikely(dest_cpu >= nr_cpu_ids)) {
- dest_cpu = cpuset_cpus_allowed_fallback(p);
- /*
- * Don't tell them about moving exiting tasks or
- * kernel threads (both mm NULL), since they never
- * leave kernel.
- */
- if (p->mm && printk_ratelimit()) {
- printk(KERN_INFO "process %d (%s) no "
- "longer affine to cpu%d\n",
- task_pid_nr(p), p->comm, cpu);
- }
+ dest_cpu = cpuset_cpus_allowed_fallback(p);
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (p->mm && printk_ratelimit()) {
+ printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
+ task_pid_nr(p), p->comm, cpu);
}
return dest_cpu;
@@ -2713,7 +2652,9 @@ void sched_fork(struct task_struct *p, int clone_flags)
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;
#endif
+#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
+#endif
put_cpu();
}
@@ -3104,6 +3045,15 @@ static long calc_load_fold_active(struct rq *this_rq)
return delta;
}
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+ load *= exp;
+ load += active * (FIXED_1 - exp);
+ load += 1UL << (FSHIFT - 1);
+ return load >> FSHIFT;
+}
+
#ifdef CONFIG_NO_HZ
/*
* For NO_HZ we delay the active fold to the next LOAD_FREQ update.
@@ -3133,6 +3083,128 @@ static long calc_load_fold_idle(void)
return delta;
}
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x: base of the power
+ * @frac_bits: fractional bits of @x
+ * @n: power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+ unsigned long result = 1UL << frac_bits;
+
+ if (n) for (;;) {
+ if (n & 1) {
+ result *= x;
+ result += 1UL << (frac_bits - 1);
+ result >>= frac_bits;
+ }
+ n >>= 1;
+ if (!n)
+ break;
+ x *= x;
+ x += 1UL << (frac_bits - 1);
+ x >>= frac_bits;
+ }
+
+ return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ * = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ * ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ * = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ * n 1 - x^(n+1)
+ * S_n := \Sum x^i = -------------
+ * i=0 1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n)
+{
+
+ return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(unsigned long ticks)
+{
+ long delta, active, n;
+
+ if (time_before(jiffies, calc_load_update))
+ return;
+
+ /*
+ * If we crossed a calc_load_update boundary, make sure to fold
+ * any pending idle changes, the respective CPUs might have
+ * missed the tick driven calc_load_account_active() update
+ * due to NO_HZ.
+ */
+ delta = calc_load_fold_idle();
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
+
+ /*
+ * If we were idle for multiple load cycles, apply them.
+ */
+ if (ticks >= LOAD_FREQ) {
+ n = ticks / LOAD_FREQ;
+
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
+
+ avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+ avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+ avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+ calc_load_update += n * LOAD_FREQ;
+ }
+
+ /*
+ * Its possible the remainder of the above division also crosses
+ * a LOAD_FREQ period, the regular check in calc_global_load()
+ * which comes after this will take care of that.
+ *
+ * Consider us being 11 ticks before a cycle completion, and us
+ * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+ * age us 4 cycles, and the test in calc_global_load() will
+ * pick up the final one.
+ */
+}
#else
static void calc_load_account_idle(struct rq *this_rq)
{
@@ -3142,6 +3214,10 @@ static inline long calc_load_fold_idle(void)
{
return 0;
}
+
+static void calc_global_nohz(unsigned long ticks)
+{
+}
#endif
/**
@@ -3159,24 +3235,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
loads[2] = (avenrun[2] + offset) << shift;
}
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
- load *= exp;
- load += active * (FIXED_1 - exp);
- return load >> FSHIFT;
-}
-
/*
* calc_load - update the avenrun load estimates 10 ticks after the
* CPUs have updated calc_load_tasks.
*/
-void calc_global_load(void)
+void calc_global_load(unsigned long ticks)
{
- unsigned long upd = calc_load_update + 10;
long active;
- if (time_before(jiffies, upd))
+ calc_global_nohz(ticks);
+
+ if (time_before(jiffies, calc_load_update + 10))
return;
active = atomic_long_read(&calc_load_tasks);
@@ -3349,7 +3418,7 @@ void sched_exec(void)
* select_task_rq() can race against ->cpus_allowed
*/
if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
- likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+ likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
struct migration_arg arg = { p, dest_cpu };
task_rq_unlock(rq, &flags);
@@ -3830,7 +3899,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
if (prev->se.on_rq)
update_rq_clock(rq);
- rq->skip_clock_update = 0;
prev->sched_class->put_prev_task(rq, prev);
}
@@ -3888,7 +3956,6 @@ need_resched_nonpreemptible:
hrtick_clear(rq);
raw_spin_lock_irq(&rq->lock);
- clear_tsk_need_resched(prev);
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3920,6 +3987,8 @@ need_resched_nonpreemptible:
put_prev_task(rq, prev);
next = pick_next_task(rq);
+ clear_tsk_need_resched(prev);
+ rq->skip_clock_update = 0;
if (likely(prev != next)) {
sched_info_switch(prev, next);
@@ -4014,7 +4083,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
if (task_thread_info(rq->curr) != owner || need_resched())
return 0;
- cpu_relax();
+ arch_mutex_cpu_relax();
}
return 1;
@@ -4326,7 +4395,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
* This waits for either a completion of a specific task to be signaled or for a
* specified timeout to expire. It is interruptible. The timeout is in jiffies.
*/
-unsigned long __sched
+long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
unsigned long timeout)
{
@@ -4359,7 +4428,7 @@ EXPORT_SYMBOL(wait_for_completion_killable);
* signaled or for a specified timeout to expire. It can be
* interrupted by a kill signal. The timeout is in jiffies.
*/
-unsigned long __sched
+long __sched
wait_for_completion_killable_timeout(struct completion *x,
unsigned long timeout)
{
@@ -4701,7 +4770,7 @@ static bool check_same_owner(struct task_struct *p)
}
static int __sched_setscheduler(struct task_struct *p, int policy,
- struct sched_param *param, bool user)
+ const struct sched_param *param, bool user)
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
unsigned long flags;
@@ -4856,7 +4925,7 @@ recheck:
* NOTE that the task may be already dead.
*/
int sched_setscheduler(struct task_struct *p, int policy,
- struct sched_param *param)
+ const struct sched_param *param)
{
return __sched_setscheduler(p, policy, param, true);
}
@@ -4874,7 +4943,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
* but our caller might not have that capability.
*/
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
- struct sched_param *param)
+ const struct sched_param *param)
{
return __sched_setscheduler(p, policy, param, false);
}
@@ -5390,7 +5459,7 @@ void sched_show_task(struct task_struct *p)
unsigned state;
state = p->state ? __ffs(p->state) + 1 : 0;
- printk(KERN_INFO "%-13.13s %c", p->comm,
+ printk(KERN_INFO "%-15.15s %c", p->comm,
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
if (state == TASK_RUNNING)
@@ -5554,7 +5623,6 @@ static void update_sysctl(void)
SET_SYSCTL(sched_min_granularity);
SET_SYSCTL(sched_latency);
SET_SYSCTL(sched_wakeup_granularity);
- SET_SYSCTL(sched_shares_ratelimit);
#undef SET_SYSCTL
}
@@ -5630,7 +5698,7 @@ again:
goto out;
dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
- if (migrate_task(p, dest_cpu)) {
+ if (migrate_task(p, rq)) {
struct migration_arg arg = { p, dest_cpu };
/* Need help from migration thread: drop lock and wait. */
task_rq_unlock(rq, &flags);
@@ -5712,29 +5780,20 @@ static int migration_cpu_stop(void *data)
}
#ifdef CONFIG_HOTPLUG_CPU
+
/*
- * Figure out where task on dead CPU should go, use force if necessary.
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
*/
-void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void idle_task_exit(void)
{
- struct rq *rq = cpu_rq(dead_cpu);
- int needs_cpu, uninitialized_var(dest_cpu);
- unsigned long flags;
+ struct mm_struct *mm = current->active_mm;
- local_irq_save(flags);
+ BUG_ON(cpu_online(smp_processor_id()));
- raw_spin_lock(&rq->lock);
- needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
- if (needs_cpu)
- dest_cpu = select_fallback_rq(dead_cpu, p);
- raw_spin_unlock(&rq->lock);
- /*
- * It can only fail if we race with set_cpus_allowed(),
- * in the racer should migrate the task anyway.
- */
- if (needs_cpu)
- __migrate_task(p, dead_cpu, dest_cpu);
- local_irq_restore(flags);
+ if (mm != &init_mm)
+ switch_mm(mm, &init_mm, current);
+ mmdrop(mm);
}
/*
@@ -5747,128 +5806,69 @@ void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
- unsigned long flags;
- local_irq_save(flags);
- double_rq_lock(rq_src, rq_dest);
rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
rq_src->nr_uninterruptible = 0;
- double_rq_unlock(rq_src, rq_dest);
- local_irq_restore(flags);
-}
-
-/* Run through task list and migrate tasks from the dead cpu. */
-static void migrate_live_tasks(int src_cpu)
-{
- struct task_struct *p, *t;
-
- read_lock(&tasklist_lock);
-
- do_each_thread(t, p) {
- if (p == current)
- continue;
-
- if (task_cpu(p) == src_cpu)
- move_task_off_dead_cpu(src_cpu, p);
- } while_each_thread(t, p);
-
- read_unlock(&tasklist_lock);
}
/*
- * Schedules idle task to be the next runnable task on current CPU.
- * It does so by boosting its priority to highest possible.
- * Used by CPU offline code.
+ * remove the tasks which were accounted by rq from calc_load_tasks.
*/
-void sched_idle_next(void)
+static void calc_global_load_remove(struct rq *rq)
{
- int this_cpu = smp_processor_id();
- struct rq *rq = cpu_rq(this_cpu);
- struct task_struct *p = rq->idle;
- unsigned long flags;
-
- /* cpu has to be offline */
- BUG_ON(cpu_online(this_cpu));
-
- /*
- * Strictly not necessary since rest of the CPUs are stopped by now
- * and interrupts disabled on the current cpu.
- */
- raw_spin_lock_irqsave(&rq->lock, flags);
-
- __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-
- activate_task(rq, p, 0);
-
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+ rq->calc_load_active = 0;
}
/*
- * Ensures that the idle task is using init_mm right before its cpu goes
- * offline.
+ * Migrate all tasks from the rq, sleeping tasks will be migrated by
+ * try_to_wake_up()->select_task_rq().
+ *
+ * Called with rq->lock held even though we'er in stop_machine() and
+ * there's no concurrency possible, we hold the required locks anyway
+ * because of lock validation efforts.
*/
-void idle_task_exit(void)
-{
- struct mm_struct *mm = current->active_mm;
-
- BUG_ON(cpu_online(smp_processor_id()));
-
- if (mm != &init_mm)
- switch_mm(mm, &init_mm, current);
- mmdrop(mm);
-}
-
-/* called under rq->lock with disabled interrupts */
-static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
+static void migrate_tasks(unsigned int dead_cpu)
{
struct rq *rq = cpu_rq(dead_cpu);
-
- /* Must be exiting, otherwise would be on tasklist. */
- BUG_ON(!p->exit_state);
-
- /* Cannot have done final schedule yet: would have vanished. */
- BUG_ON(p->state == TASK_DEAD);
-
- get_task_struct(p);
+ struct task_struct *next, *stop = rq->stop;
+ int dest_cpu;
/*
- * Drop lock around migration; if someone else moves it,
- * that's OK. No task can be added to this CPU, so iteration is
- * fine.
+ * Fudge the rq selection such that the below task selection loop
+ * doesn't get stuck on the currently eligible stop task.
+ *
+ * We're currently inside stop_machine() and the rq is either stuck
+ * in the stop_machine_cpu_stop() loop, or we're executing this code,
+ * either way we should never end up calling schedule() until we're
+ * done here.
*/
- raw_spin_unlock_irq(&rq->lock);
- move_task_off_dead_cpu(dead_cpu, p);
- raw_spin_lock_irq(&rq->lock);
-
- put_task_struct(p);
-}
-
-/* release_task() removes task from tasklist, so we won't find dead tasks. */
-static void migrate_dead_tasks(unsigned int dead_cpu)
-{
- struct rq *rq = cpu_rq(dead_cpu);
- struct task_struct *next;
+ rq->stop = NULL;
for ( ; ; ) {
- if (!rq->nr_running)
+ /*
+ * There's this thread running, bail when that's the only
+ * remaining thread.
+ */
+ if (rq->nr_running == 1)
break;
+
next = pick_next_task(rq);
- if (!next)
- break;
+ BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
- migrate_dead(dead_cpu, next);
+ /* Find suitable destination for @next, with force if needed. */
+ dest_cpu = select_fallback_rq(dead_cpu, next);
+ raw_spin_unlock(&rq->lock);
+
+ __migrate_task(next, dead_cpu, dest_cpu);
+
+ raw_spin_lock(&rq->lock);
}
-}
-/*
- * remove the tasks which were accounted by rq from calc_load_tasks.
- */
-static void calc_global_load_remove(struct rq *rq)
-{
- atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
- rq->calc_load_active = 0;
+ rq->stop = stop;
}
+
#endif /* CONFIG_HOTPLUG_CPU */
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -6078,15 +6078,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
unsigned long flags;
struct rq *rq = cpu_rq(cpu);
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
rq->calc_load_update = calc_load_update;
break;
case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
@@ -6098,30 +6096,19 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
break;
#ifdef CONFIG_HOTPLUG_CPU
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- migrate_live_tasks(cpu);
- /* Idle task back to normal (off runqueue, low prio) */
- raw_spin_lock_irq(&rq->lock);
- deactivate_task(rq, rq->idle, 0);
- __setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
- rq->idle->sched_class = &idle_sched_class;
- migrate_dead_tasks(cpu);
- raw_spin_unlock_irq(&rq->lock);
- migrate_nr_uninterruptible(rq);
- BUG_ON(rq->nr_running != 0);
- calc_global_load_remove(rq);
- break;
-
case CPU_DYING:
- case CPU_DYING_FROZEN:
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
+ migrate_tasks(cpu);
+ BUG_ON(rq->nr_running != 1); /* the migration thread */
raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+ migrate_nr_uninterruptible(rq);
+ calc_global_load_remove(rq);
break;
#endif
}
@@ -6960,6 +6947,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
if (cpu != group_first_cpu(sd->groups))
return;
+ sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+
child = sd->child;
sd->groups->cpu_power = 0;
@@ -7850,15 +7839,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
#ifdef CONFIG_FAIR_GROUP_SCHED
static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
- struct sched_entity *se, int cpu, int add,
+ struct sched_entity *se, int cpu,
struct sched_entity *parent)
{
struct rq *rq = cpu_rq(cpu);
tg->cfs_rq[cpu] = cfs_rq;
init_cfs_rq(cfs_rq, rq);
cfs_rq->tg = tg;
- if (add)
- list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
tg->se[cpu] = se;
/* se could be NULL for init_task_group */
@@ -7871,15 +7858,14 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
se->cfs_rq = parent->my_q;
se->my_q = cfs_rq;
- se->load.weight = tg->shares;
- se->load.inv_weight = 0;
+ update_load_set(&se->load, 0);
se->parent = parent;
}
#endif
#ifdef CONFIG_RT_GROUP_SCHED
static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
- struct sched_rt_entity *rt_se, int cpu, int add,
+ struct sched_rt_entity *rt_se, int cpu,
struct sched_rt_entity *parent)
{
struct rq *rq = cpu_rq(cpu);
@@ -7888,8 +7874,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
init_rt_rq(rt_rq, rq);
rt_rq->tg = tg;
rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
- if (add)
- list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
tg->rt_se[cpu] = rt_se;
if (!rt_se)
@@ -7962,13 +7946,9 @@ void __init sched_init(void)
#ifdef CONFIG_CGROUP_SCHED
list_add(&init_task_group.list, &task_groups);
INIT_LIST_HEAD(&init_task_group.children);
-
+ autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */
-#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
- update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
- __alignof__(unsigned long));
-#endif
for_each_possible_cpu(i) {
struct rq *rq;
@@ -7982,7 +7962,6 @@ void __init sched_init(void)
#ifdef CONFIG_FAIR_GROUP_SCHED
init_task_group.shares = init_task_group_load;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
/*
* How much cpu bandwidth does init_task_group get?
*
@@ -8002,16 +7981,13 @@ void __init sched_init(void)
* We achieve this by letting init_task_group's tasks sit
* directly in rq->cfs (i.e init_task_group->se[] = NULL).
*/
- init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
-#endif
+ init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
- init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
-#endif
+ init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, NULL);
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
@@ -8091,8 +8067,6 @@ void __init sched_init(void)
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
- perf_event_init();
-
scheduler_running = 1;
}
@@ -8286,7 +8260,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
if (!se)
goto err_free_rq;
- init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
+ init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
}
return 1;
@@ -8297,15 +8271,21 @@ err:
return 0;
}
-static inline void register_fair_sched_group(struct task_group *tg, int cpu)
-{
- list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list,
- &cpu_rq(cpu)->leaf_cfs_rq_list);
-}
-
static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
- list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ /*
+ * Only empty task groups can be destroyed; so we can speculatively
+ * check on_list without danger of it being re-added.
+ */
+ if (!tg->cfs_rq[cpu]->on_list)
+ return;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
#else /* !CONFG_FAIR_GROUP_SCHED */
static inline void free_fair_sched_group(struct task_group *tg)
@@ -8318,10 +8298,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
return 1;
}
-static inline void register_fair_sched_group(struct task_group *tg, int cpu)
-{
-}
-
static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
}
@@ -8376,7 +8352,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
if (!rt_se)
goto err_free_rq;
- init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
+ init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
}
return 1;
@@ -8386,17 +8362,6 @@ err_free_rq:
err:
return 0;
}
-
-static inline void register_rt_sched_group(struct task_group *tg, int cpu)
-{
- list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list,
- &cpu_rq(cpu)->leaf_rt_rq_list);
-}
-
-static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
-{
- list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
-}
#else /* !CONFIG_RT_GROUP_SCHED */
static inline void free_rt_sched_group(struct task_group *tg)
{
@@ -8407,14 +8372,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
return 1;
}
-
-static inline void register_rt_sched_group(struct task_group *tg, int cpu)
-{
-}
-
-static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
-{
-}
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_CGROUP_SCHED
@@ -8430,7 +8387,6 @@ struct task_group *sched_create_group(struct task_group *parent)
{
struct task_group *tg;
unsigned long flags;
- int i;
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
if (!tg)
@@ -8443,10 +8399,6 @@ struct task_group *sched_create_group(struct task_group *parent)
goto err;
spin_lock_irqsave(&task_group_lock, flags);
- for_each_possible_cpu(i) {
- register_fair_sched_group(tg, i);
- register_rt_sched_group(tg, i);
- }
list_add_rcu(&tg->list, &task_groups);
WARN_ON(!parent); /* root should already exist */
@@ -8476,11 +8428,11 @@ void sched_destroy_group(struct task_group *tg)
unsigned long flags;
int i;
- spin_lock_irqsave(&task_group_lock, flags);
- for_each_possible_cpu(i) {
+ /* end participation in shares distribution */
+ for_each_possible_cpu(i)
unregister_fair_sched_group(tg, i);
- unregister_rt_sched_group(tg, i);
- }
+
+ spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
list_del_rcu(&tg->siblings);
spin_unlock_irqrestore(&task_group_lock, flags);
@@ -8510,12 +8462,12 @@ void sched_move_task(struct task_struct *tsk)
if (unlikely(running))
tsk->sched_class->put_prev_task(rq, tsk);
- set_task_rq(tsk, task_cpu(tsk));
-
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (tsk->sched_class->moved_group)
- tsk->sched_class->moved_group(tsk, on_rq);
+ if (tsk->sched_class->task_move_group)
+ tsk->sched_class->task_move_group(tsk, on_rq);
+ else
#endif
+ set_task_rq(tsk, task_cpu(tsk));
if (unlikely(running))
tsk->sched_class->set_curr_task(rq);
@@ -8527,33 +8479,6 @@ void sched_move_task(struct task_struct *tsk)
#endif /* CONFIG_CGROUP_SCHED */
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void __set_se_shares(struct sched_entity *se, unsigned long shares)
-{
- struct cfs_rq *cfs_rq = se->cfs_rq;
- int on_rq;
-
- on_rq = se->on_rq;
- if (on_rq)
- dequeue_entity(cfs_rq, se, 0);
-
- se->load.weight = shares;
- se->load.inv_weight = 0;
-
- if (on_rq)
- enqueue_entity(cfs_rq, se, 0);
-}
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares)
-{
- struct cfs_rq *cfs_rq = se->cfs_rq;
- struct rq *rq = cfs_rq->rq;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&rq->lock, flags);
- __set_se_shares(se, shares);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
static DEFINE_MUTEX(shares_mutex);
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
@@ -8576,37 +8501,19 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
if (tg->shares == shares)
goto done;
- spin_lock_irqsave(&task_group_lock, flags);
- for_each_possible_cpu(i)
- unregister_fair_sched_group(tg, i);
- list_del_rcu(&tg->siblings);
- spin_unlock_irqrestore(&task_group_lock, flags);
-
- /* wait for any ongoing reference to this group to finish */
- synchronize_sched();
-
- /*
- * Now we are free to modify the group's share on each cpu
- * w/o tripping rebalance_share or load_balance_fair.
- */
tg->shares = shares;
for_each_possible_cpu(i) {
- /*
- * force a rebalance
- */
- cfs_rq_set_shares(tg->cfs_rq[i], 0);
- set_se_shares(tg->se[i], shares);
+ struct rq *rq = cpu_rq(i);
+ struct sched_entity *se;
+
+ se = tg->se[i];
+ /* Propagate contribution to hierarchy */
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ for_each_sched_entity(se)
+ update_cfs_shares(group_cfs_rq(se), 0);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
- /*
- * Enable load balance activity on this group, by inserting it back on
- * each cpu's rq->leaf_cfs_rq_list.
- */
- spin_lock_irqsave(&task_group_lock, flags);
- for_each_possible_cpu(i)
- register_fair_sched_group(tg, i);
- list_add_rcu(&tg->siblings, &tg->parent->children);
- spin_unlock_irqrestore(&task_group_lock, flags);
done:
mutex_unlock(&shares_mutex);
return 0;
@@ -9332,72 +9239,3 @@ struct cgroup_subsys cpuacct_subsys = {
};
#endif /* CONFIG_CGROUP_CPUACCT */
-#ifndef CONFIG_SMP
-
-void synchronize_sched_expedited(void)
-{
- barrier();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#else /* #ifndef CONFIG_SMP */
-
-static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
-
-static int synchronize_sched_expedited_cpu_stop(void *data)
-{
- /*
- * There must be a full memory barrier on each affected CPU
- * between the time that try_stop_cpus() is called and the
- * time that it returns.
- *
- * In the current initial implementation of cpu_stop, the
- * above condition is already met when the control reaches
- * this point and the following smp_mb() is not strictly
- * necessary. Do smp_mb() anyway for documentation and
- * robustness against future implementation changes.
- */
- smp_mb(); /* See above comment block. */
- return 0;
-}
-
-/*
- * Wait for an rcu-sched grace period to elapse, but use "big hammer"
- * approach to force grace period to end quickly. This consumes
- * significant time on all CPUs, and is thus not recommended for
- * any sort of common-case code.
- *
- * Note that it is illegal to call this function while holding any
- * lock that is acquired by a CPU-hotplug notifier. Failing to
- * observe this restriction will result in deadlock.
- */
-void synchronize_sched_expedited(void)
-{
- int snap, trycount = 0;
-
- smp_mb(); /* ensure prior mod happens before capturing snap. */
- snap = atomic_read(&synchronize_sched_expedited_count) + 1;
- get_online_cpus();
- while (try_stop_cpus(cpu_online_mask,
- synchronize_sched_expedited_cpu_stop,
- NULL) == -EAGAIN) {
- put_online_cpus();
- if (trycount++ < 10)
- udelay(trycount * num_online_cpus());
- else {
- synchronize_sched();
- return;
- }
- if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
- smp_mb(); /* ensure test happens before caller kfree */
- return;
- }
- get_online_cpus();
- }
- atomic_inc(&synchronize_sched_expedited_count);
- smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
- put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#endif /* #else #ifndef CONFIG_SMP */
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
new file mode 100644
index 00000000000..c80fedcd476
--- /dev/null
+++ b/kernel/sched_autogroup.c
@@ -0,0 +1,238 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/utsname.h>
+
+unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
+static struct autogroup autogroup_default;
+static atomic_t autogroup_seq_nr;
+
+static void autogroup_init(struct task_struct *init_task)
+{
+ autogroup_default.tg = &init_task_group;
+ init_task_group.autogroup = &autogroup_default;
+ kref_init(&autogroup_default.kref);
+ init_rwsem(&autogroup_default.lock);
+ init_task->signal->autogroup = &autogroup_default;
+}
+
+static inline void autogroup_free(struct task_group *tg)
+{
+ kfree(tg->autogroup);
+}
+
+static inline void autogroup_destroy(struct kref *kref)
+{
+ struct autogroup *ag = container_of(kref, struct autogroup, kref);
+
+ sched_destroy_group(ag->tg);
+}
+
+static inline void autogroup_kref_put(struct autogroup *ag)
+{
+ kref_put(&ag->kref, autogroup_destroy);
+}
+
+static inline struct autogroup *autogroup_kref_get(struct autogroup *ag)
+{
+ kref_get(&ag->kref);
+ return ag;
+}
+
+static inline struct autogroup *autogroup_task_get(struct task_struct *p)
+{
+ struct autogroup *ag;
+ unsigned long flags;
+
+ if (!lock_task_sighand(p, &flags))
+ return autogroup_kref_get(&autogroup_default);
+
+ ag = autogroup_kref_get(p->signal->autogroup);
+ unlock_task_sighand(p, &flags);
+
+ return ag;
+}
+
+static inline struct autogroup *autogroup_create(void)
+{
+ struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
+ struct task_group *tg;
+
+ if (!ag)
+ goto out_fail;
+
+ tg = sched_create_group(&init_task_group);
+
+ if (IS_ERR(tg))
+ goto out_free;
+
+ kref_init(&ag->kref);
+ init_rwsem(&ag->lock);
+ ag->id = atomic_inc_return(&autogroup_seq_nr);
+ ag->tg = tg;
+ tg->autogroup = ag;
+
+ return ag;
+
+out_free:
+ kfree(ag);
+out_fail:
+ if (printk_ratelimit()) {
+ printk(KERN_WARNING "autogroup_create: %s failure.\n",
+ ag ? "sched_create_group()" : "kmalloc()");
+ }
+
+ return autogroup_kref_get(&autogroup_default);
+}
+
+static inline bool
+task_wants_autogroup(struct task_struct *p, struct task_group *tg)
+{
+ if (tg != &root_task_group)
+ return false;
+
+ if (p->sched_class != &fair_sched_class)
+ return false;
+
+ /*
+ * We can only assume the task group can't go away on us if
+ * autogroup_move_group() can see us on ->thread_group list.
+ */
+ if (p->flags & PF_EXITING)
+ return false;
+
+ return true;
+}
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+ int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+ if (enabled && task_wants_autogroup(p, tg))
+ return p->signal->autogroup->tg;
+
+ return tg;
+}
+
+static void
+autogroup_move_group(struct task_struct *p, struct autogroup *ag)
+{
+ struct autogroup *prev;
+ struct task_struct *t;
+ unsigned long flags;
+
+ BUG_ON(!lock_task_sighand(p, &flags));
+
+ prev = p->signal->autogroup;
+ if (prev == ag) {
+ unlock_task_sighand(p, &flags);
+ return;
+ }
+
+ p->signal->autogroup = autogroup_kref_get(ag);
+
+ t = p;
+ do {
+ sched_move_task(t);
+ } while_each_thread(p, t);
+
+ unlock_task_sighand(p, &flags);
+ autogroup_kref_put(prev);
+}
+
+/* Allocates GFP_KERNEL, cannot be called under any spinlock */
+void sched_autogroup_create_attach(struct task_struct *p)
+{
+ struct autogroup *ag = autogroup_create();
+
+ autogroup_move_group(p, ag);
+ /* drop extra refrence added by autogroup_create() */
+ autogroup_kref_put(ag);
+}
+EXPORT_SYMBOL(sched_autogroup_create_attach);
+
+/* Cannot be called under siglock. Currently has no users */
+void sched_autogroup_detach(struct task_struct *p)
+{
+ autogroup_move_group(p, &autogroup_default);
+}
+EXPORT_SYMBOL(sched_autogroup_detach);
+
+void sched_autogroup_fork(struct signal_struct *sig)
+{
+ sig->autogroup = autogroup_task_get(current);
+}
+
+void sched_autogroup_exit(struct signal_struct *sig)
+{
+ autogroup_kref_put(sig->autogroup);
+}
+
+static int __init setup_autogroup(char *str)
+{
+ sysctl_sched_autogroup_enabled = 0;
+
+ return 1;
+}
+
+__setup("noautogroup", setup_autogroup);
+
+#ifdef CONFIG_PROC_FS
+
+int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice)
+{
+ static unsigned long next = INITIAL_JIFFIES;
+ struct autogroup *ag;
+ int err;
+
+ if (*nice < -20 || *nice > 19)
+ return -EINVAL;
+
+ err = security_task_setnice(current, *nice);
+ if (err)
+ return err;
+
+ if (*nice < 0 && !can_nice(current, *nice))
+ return -EPERM;
+
+ /* this is a heavy operation taking global locks.. */
+ if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
+ return -EAGAIN;
+
+ next = HZ / 10 + jiffies;
+ ag = autogroup_task_get(p);
+
+ down_write(&ag->lock);
+ err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]);
+ if (!err)
+ ag->nice = *nice;
+ up_write(&ag->lock);
+
+ autogroup_kref_put(ag);
+
+ return err;
+}
+
+void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
+{
+ struct autogroup *ag = autogroup_task_get(p);
+
+ down_read(&ag->lock);
+ seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
+ up_read(&ag->lock);
+
+ autogroup_kref_put(ag);
+}
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_SCHED_DEBUG
+static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+ return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
new file mode 100644
index 00000000000..5358e241cb2
--- /dev/null
+++ b/kernel/sched_autogroup.h
@@ -0,0 +1,32 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+struct autogroup {
+ struct kref kref;
+ struct task_group *tg;
+ struct rw_semaphore lock;
+ unsigned long id;
+ int nice;
+};
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg);
+
+#else /* !CONFIG_SCHED_AUTOGROUP */
+
+static inline void autogroup_init(struct task_struct *init_task) { }
+static inline void autogroup_free(struct task_group *tg) { }
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+ return tg;
+}
+
+#ifdef CONFIG_SCHED_DEBUG
+static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+ return 0;
+}
+#endif
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 52f1a149bfb..9d8af0b3fb6 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -79,7 +79,7 @@ unsigned long long __attribute__((weak)) sched_clock(void)
}
EXPORT_SYMBOL_GPL(sched_clock);
-static __read_mostly int sched_clock_running;
+__read_mostly int sched_clock_running;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
__read_mostly int sched_clock_stable;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 2e1b0d17dd9..1dfae3d014b 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -54,8 +54,7 @@ static unsigned long nsec_low(unsigned long long nsec)
#define SPLIT_NS(x) nsec_high(x), nsec_low(x)
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void print_cfs_group_stats(struct seq_file *m, int cpu,
- struct task_group *tg)
+static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
{
struct sched_entity *se = tg->se[cpu];
if (!se)
@@ -110,16 +109,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
#endif
-#ifdef CONFIG_CGROUP_SCHED
- {
- char path[64];
-
- rcu_read_lock();
- cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
- rcu_read_unlock();
- SEQ_printf(m, " %s", path);
- }
-#endif
SEQ_printf(m, "\n");
}
@@ -147,19 +136,6 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
read_unlock_irqrestore(&tasklist_lock, flags);
}
-#if defined(CONFIG_CGROUP_SCHED) && \
- (defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED))
-static void task_group_path(struct task_group *tg, char *buf, int buflen)
-{
- /* may be NULL if the underlying cgroup isn't fully-created yet */
- if (!tg->css.cgroup) {
- buf[0] = '\0';
- return;
- }
- cgroup_path(tg->css.cgroup, buf, buflen);
-}
-#endif
-
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
@@ -168,16 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
struct sched_entity *last;
unsigned long flags;
-#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
- char path[128];
- struct task_group *tg = cfs_rq->tg;
-
- task_group_path(tg, path, sizeof(path));
-
- SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
-#else
SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
-#endif
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock",
SPLIT_NS(cfs_rq->exec_clock));
@@ -202,32 +169,29 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
spread0 = min_vruntime - rq0_min_vruntime;
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0",
SPLIT_NS(spread0));
- SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
- SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
-
SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over",
cfs_rq->nr_spread_over);
+ SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
+ SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_SMP
- SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares);
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_avg",
+ SPLIT_NS(cfs_rq->load_avg));
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_period",
+ SPLIT_NS(cfs_rq->load_period));
+ SEQ_printf(m, " .%-30s: %ld\n", "load_contrib",
+ cfs_rq->load_contribution);
+ SEQ_printf(m, " .%-30s: %d\n", "load_tg",
+ atomic_read(&cfs_rq->tg->load_weight));
#endif
+
print_cfs_group_stats(m, cpu, cfs_rq->tg);
#endif
}
void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
{
-#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
- char path[128];
- struct task_group *tg = rt_rq->tg;
-
- task_group_path(tg, path, sizeof(path));
-
- SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
-#else
SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
-#endif
-
#define P(x) \
SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
@@ -243,6 +207,8 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
#undef P
}
+extern __read_mostly int sched_clock_running;
+
static void print_cpu(struct seq_file *m, int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -314,21 +280,42 @@ static const char *sched_tunable_scaling_names[] = {
static int sched_debug_show(struct seq_file *m, void *v)
{
- u64 now = ktime_to_ns(ktime_get());
+ u64 ktime, sched_clk, cpu_clk;
+ unsigned long flags;
int cpu;
- SEQ_printf(m, "Sched Debug Version: v0.09, %s %.*s\n",
+ local_irq_save(flags);
+ ktime = ktime_to_ns(ktime_get());
+ sched_clk = sched_clock();
+ cpu_clk = local_clock();
+ local_irq_restore(flags);
+
+ SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
- SEQ_printf(m, "now at %Lu.%06ld msecs\n", SPLIT_NS(now));
+#define P(x) \
+ SEQ_printf(m, "%-40s: %Ld\n", #x, (long long)(x))
+#define PN(x) \
+ SEQ_printf(m, "%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
+ PN(ktime);
+ PN(sched_clk);
+ PN(cpu_clk);
+ P(jiffies);
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+ P(sched_clock_stable);
+#endif
+#undef PN
+#undef P
+
+ SEQ_printf(m, "\n");
+ SEQ_printf(m, "sysctl_sched\n");
#define P(x) \
SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x))
#define PN(x) \
SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
- P(jiffies);
PN(sysctl_sched_latency);
PN(sysctl_sched_min_granularity);
PN(sysctl_sched_wakeup_granularity);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 933f3d1b62e..c62ebae65cf 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -89,6 +89,13 @@ unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
+/*
+ * The exponential sliding window over which load is averaged for shares
+ * distribution.
+ * (default: 10msec)
+ */
+unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
+
static const struct sched_class fair_sched_class;
/**************************************************************
@@ -143,6 +150,36 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
return cfs_rq->tg->cfs_rq[this_cpu];
}
+static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+ if (!cfs_rq->on_list) {
+ /*
+ * Ensure we either appear before our parent (if already
+ * enqueued) or force our parent to appear after us when it is
+ * enqueued. The fact that we always enqueue bottom-up
+ * reduces this to two cases.
+ */
+ if (cfs_rq->tg->parent &&
+ cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+ &rq_of(cfs_rq)->leaf_cfs_rq_list);
+ } else {
+ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+ &rq_of(cfs_rq)->leaf_cfs_rq_list);
+ }
+
+ cfs_rq->on_list = 1;
+ }
+}
+
+static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+ if (cfs_rq->on_list) {
+ list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+ cfs_rq->on_list = 0;
+ }
+}
+
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
@@ -246,6 +283,14 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
return &cpu_rq(this_cpu)->cfs;
}
+static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+}
+
+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)
@@ -417,7 +462,6 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
WRT_SYSCTL(sched_min_granularity);
WRT_SYSCTL(sched_latency);
WRT_SYSCTL(sched_wakeup_granularity);
- WRT_SYSCTL(sched_shares_ratelimit);
#undef WRT_SYSCTL
return 0;
@@ -495,6 +539,9 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
return calc_delta_fair(sched_slice(cfs_rq, se), se);
}
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
+static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+
/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
@@ -514,6 +561,10 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
curr->vruntime += delta_exec_weighted;
update_min_vruntime(cfs_rq);
+
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+ cfs_rq->load_unacc_exec_time += delta_exec;
+#endif
}
static void update_curr(struct cfs_rq *cfs_rq)
@@ -633,7 +684,6 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
list_add(&se->group_node, &cfs_rq->tasks);
}
cfs_rq->nr_running++;
- se->on_rq = 1;
}
static void
@@ -647,9 +697,140 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
list_del_init(&se->group_node);
}
cfs_rq->nr_running--;
- se->on_rq = 0;
}
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
+ int global_update)
+{
+ struct task_group *tg = cfs_rq->tg;
+ long load_avg;
+
+ load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1);
+ load_avg -= cfs_rq->load_contribution;
+
+ if (global_update || abs(load_avg) > cfs_rq->load_contribution / 8) {
+ atomic_add(load_avg, &tg->load_weight);
+ cfs_rq->load_contribution += load_avg;
+ }
+}
+
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+{
+ u64 period = sysctl_sched_shares_window;
+ u64 now, delta;
+ unsigned long load = cfs_rq->load.weight;
+
+ if (!cfs_rq)
+ return;
+
+ now = rq_of(cfs_rq)->clock;
+ delta = now - cfs_rq->load_stamp;
+
+ /* truncate load history at 4 idle periods */
+ if (cfs_rq->load_stamp > cfs_rq->load_last &&
+ now - cfs_rq->load_last > 4 * period) {
+ cfs_rq->load_period = 0;
+ cfs_rq->load_avg = 0;
+ }
+
+ cfs_rq->load_stamp = now;
+ cfs_rq->load_unacc_exec_time = 0;
+ cfs_rq->load_period += delta;
+ if (load) {
+ cfs_rq->load_last = now;
+ cfs_rq->load_avg += delta * load;
+ }
+
+ /* consider updating load contribution on each fold or truncate */
+ if (global_update || cfs_rq->load_period > period
+ || !cfs_rq->load_period)
+ update_cfs_rq_load_contribution(cfs_rq, global_update);
+
+ while (cfs_rq->load_period > period) {
+ /*
+ * Inline assembly required to prevent the compiler
+ * optimising this loop into a divmod call.
+ * See __iter_div_u64_rem() for another example of this.
+ */
+ asm("" : "+rm" (cfs_rq->load_period));
+ cfs_rq->load_period /= 2;
+ cfs_rq->load_avg /= 2;
+ }
+
+ if (!cfs_rq->curr && !cfs_rq->nr_running && !cfs_rq->load_avg)
+ list_del_leaf_cfs_rq(cfs_rq);
+}
+
+static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
+ unsigned long weight)
+{
+ if (se->on_rq) {
+ /* commit outstanding execution time */
+ if (cfs_rq->curr == se)
+ update_curr(cfs_rq);
+ account_entity_dequeue(cfs_rq, se);
+ }
+
+ update_load_set(&se->load, weight);
+
+ if (se->on_rq)
+ account_entity_enqueue(cfs_rq, se);
+}
+
+static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+{
+ struct task_group *tg;
+ struct sched_entity *se;
+ long load_weight, load, shares;
+
+ if (!cfs_rq)
+ return;
+
+ tg = cfs_rq->tg;
+ se = tg->se[cpu_of(rq_of(cfs_rq))];
+ if (!se)
+ return;
+
+ load = cfs_rq->load.weight + weight_delta;
+
+ load_weight = atomic_read(&tg->load_weight);
+ load_weight -= cfs_rq->load_contribution;
+ load_weight += load;
+
+ shares = (tg->shares * load);
+ if (load_weight)
+ shares /= load_weight;
+
+ if (shares < MIN_SHARES)
+ shares = MIN_SHARES;
+ if (shares > tg->shares)
+ shares = tg->shares;
+
+ reweight_entity(cfs_rq_of(se), se, shares);
+}
+
+static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+ if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
+ update_cfs_load(cfs_rq, 0);
+ update_cfs_shares(cfs_rq, 0);
+ }
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+{
+}
+
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+{
+}
+
+static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
@@ -771,6 +952,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+ update_cfs_load(cfs_rq, 0);
+ update_cfs_shares(cfs_rq, se->load.weight);
account_entity_enqueue(cfs_rq, se);
if (flags & ENQUEUE_WAKEUP) {
@@ -782,6 +965,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
+ se->on_rq = 1;
+
+ if (cfs_rq->nr_running == 1)
+ list_add_leaf_cfs_rq(cfs_rq);
}
static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -825,8 +1012,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
+ se->on_rq = 0;
+ update_cfs_load(cfs_rq, 0);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
+ update_cfs_shares(cfs_rq, 0);
/*
* Normalize the entity after updating the min_vruntime because the
@@ -955,6 +1145,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
*/
update_curr(cfs_rq);
+ /*
+ * Update share accounting for long-running entities.
+ */
+ update_entity_shares_tick(cfs_rq);
+
#ifdef CONFIG_SCHED_HRTICK
/*
* queued ticks are scheduled to match the slice, so don't bother
@@ -1055,6 +1250,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
flags = ENQUEUE_WAKEUP;
}
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ update_cfs_load(cfs_rq, 0);
+ update_cfs_shares(cfs_rq, 0);
+ }
+
hrtick_update(rq);
}
@@ -1071,12 +1273,20 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, flags);
+
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight)
break;
flags |= DEQUEUE_SLEEP;
}
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ update_cfs_load(cfs_rq, 0);
+ update_cfs_shares(cfs_rq, 0);
+ }
+
hrtick_update(rq);
}
@@ -1143,51 +1353,20 @@ static void task_waking_fair(struct rq *rq, struct task_struct *p)
* Adding load to a group doesn't make a group heavier, but can cause movement
* of group shares between cpus. Assuming the shares were perfectly aligned one
* can calculate the shift in shares.
- *
- * The problem is that perfectly aligning the shares is rather expensive, hence
- * we try to avoid doing that too often - see update_shares(), which ratelimits
- * this change.
- *
- * We compensate this by not only taking the current delta into account, but
- * also considering the delta between when the shares were last adjusted and
- * now.
- *
- * We still saw a performance dip, some tracing learned us that between
- * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
- * significantly. Therefore try to bias the error in direction of failing
- * the affine wakeup.
- *
*/
-static long effective_load(struct task_group *tg, int cpu,
- long wl, long wg)
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
if (!tg->parent)
return wl;
- /*
- * By not taking the decrease of shares on the other cpu into
- * account our error leans towards reducing the affine wakeups.
- */
- if (!wl && sched_feat(ASYM_EFF_LOAD))
- return wl;
-
for_each_sched_entity(se) {
long S, rw, s, a, b;
- long more_w;
-
- /*
- * Instead of using this increment, also add the difference
- * between when the shares were last updated and now.
- */
- more_w = se->my_q->load.weight - se->my_q->rq_weight;
- wl += more_w;
- wg += more_w;
S = se->my_q->tg->shares;
- s = se->my_q->shares;
- rw = se->my_q->rq_weight;
+ s = se->load.weight;
+ rw = se->my_q->load.weight;
a = S*(rw + wl);
b = S*rw + s*wg;
@@ -1508,23 +1687,6 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
sd = tmp;
}
-#ifdef CONFIG_FAIR_GROUP_SCHED
- if (sched_feat(LB_SHARES_UPDATE)) {
- /*
- * Pick the largest domain to update shares over
- */
- tmp = sd;
- if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight))
- tmp = affine_sd;
-
- if (tmp) {
- raw_spin_unlock(&rq->lock);
- update_shares(tmp);
- raw_spin_lock(&rq->lock);
- }
- }
-#endif
-
if (affine_sd) {
if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
return select_idle_sibling(p, cpu);
@@ -1654,12 +1816,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int scale = cfs_rq->nr_running >= sched_nr_latency;
- if (unlikely(rt_prio(p->prio)))
- goto preempt;
-
- if (unlikely(p->sched_class != &fair_sched_class))
- return;
-
if (unlikely(se == pse))
return;
@@ -1764,10 +1920,6 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
check_preempt_curr(this_rq, p, 0);
-
- /* re-arm NEWIDLE balancing when moving tasks */
- src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
- this_rq->idle_stamp = 0;
}
/*
@@ -1919,6 +2071,48 @@ out:
}
#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * update tg->load_weight by folding this cpu's load_avg
+ */
+static int update_shares_cpu(struct task_group *tg, int cpu)
+{
+ struct cfs_rq *cfs_rq;
+ unsigned long flags;
+ struct rq *rq;
+
+ if (!tg->se[cpu])
+ return 0;
+
+ rq = cpu_rq(cpu);
+ cfs_rq = tg->cfs_rq[cpu];
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+
+ update_rq_clock(rq);
+ update_cfs_load(cfs_rq, 1);
+
+ /*
+ * We need to update shares after updating tg->load_weight in
+ * order to adjust the weight of groups with long running tasks.
+ */
+ update_cfs_shares(cfs_rq, 0);
+
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+ return 0;
+}
+
+static void update_shares(int cpu)
+{
+ struct cfs_rq *cfs_rq;
+ struct rq *rq = cpu_rq(cpu);
+
+ rcu_read_lock();
+ for_each_leaf_cfs_rq(rq, cfs_rq)
+ update_shares_cpu(cfs_rq->tg, cpu);
+ rcu_read_unlock();
+}
+
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
@@ -1966,6 +2160,10 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
return max_load_move - rem_load_move;
}
#else
+static inline void update_shares(int cpu)
+{
+}
+
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
@@ -2035,13 +2233,16 @@ struct sd_lb_stats {
unsigned long this_load_per_task;
unsigned long this_nr_running;
unsigned long this_has_capacity;
+ unsigned int this_idle_cpus;
/* Statistics of the busiest group */
+ unsigned int busiest_idle_cpus;
unsigned long max_load;
unsigned long busiest_load_per_task;
unsigned long busiest_nr_running;
unsigned long busiest_group_capacity;
unsigned long busiest_has_capacity;
+ unsigned int busiest_group_weight;
int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2063,6 +2264,8 @@ struct sg_lb_stats {
unsigned long sum_nr_running; /* Nr tasks running in the group */
unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long group_capacity;
+ unsigned long idle_cpus;
+ unsigned long group_weight;
int group_imb; /* Is there an imbalance in the group ? */
int group_has_capacity; /* Is there extra capacity in the group? */
};
@@ -2431,7 +2634,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
sgs->group_load += load;
sgs->sum_nr_running += rq->nr_running;
sgs->sum_weighted_load += weighted_cpuload(i);
-
+ if (idle_cpu(i))
+ sgs->idle_cpus++;
}
/*
@@ -2469,6 +2673,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
if (!sgs->group_capacity)
sgs->group_capacity = fix_small_capacity(sd, group);
+ sgs->group_weight = group->group_weight;
if (sgs->group_capacity > sgs->sum_nr_running)
sgs->group_has_capacity = 1;
@@ -2576,13 +2781,16 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
sds->this_nr_running = sgs.sum_nr_running;
sds->this_load_per_task = sgs.sum_weighted_load;
sds->this_has_capacity = sgs.group_has_capacity;
+ sds->this_idle_cpus = sgs.idle_cpus;
} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
sds->max_load = sgs.avg_load;
sds->busiest = sg;
sds->busiest_nr_running = sgs.sum_nr_running;
+ sds->busiest_idle_cpus = sgs.idle_cpus;
sds->busiest_group_capacity = sgs.group_capacity;
sds->busiest_load_per_task = sgs.sum_weighted_load;
sds->busiest_has_capacity = sgs.group_has_capacity;
+ sds->busiest_group_weight = sgs.group_weight;
sds->group_imb = sgs.group_imb;
}
@@ -2860,8 +3068,26 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
if (sds.this_load >= sds.avg_load)
goto out_balanced;
- if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
- goto out_balanced;
+ /*
+ * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
+ * And to check for busy balance use !idle_cpu instead of
+ * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
+ * even when they are idle.
+ */
+ if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
+ } else {
+ /*
+ * This cpu is idle. If the busiest group load doesn't
+ * have more tasks than the number of available cpu's and
+ * there is no imbalance between this and busiest group
+ * wrt to idle cpu's, it is balanced.
+ */
+ if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
+ sds.busiest_nr_running <= sds.busiest_group_weight)
+ goto out_balanced;
+ }
force_balance:
/* Looks like there is an imbalance. Compute it */
@@ -3014,7 +3240,6 @@ static int load_balance(int this_cpu, struct rq *this_rq,
schedstat_inc(sd, lb_count[idle]);
redo:
- update_shares(sd);
group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
cpus, balance);
@@ -3156,8 +3381,6 @@ out_one_pinned:
else
ld_moved = 0;
out:
- if (ld_moved)
- update_shares(sd);
return ld_moved;
}
@@ -3181,6 +3404,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
*/
raw_spin_unlock(&this_rq->lock);
+ update_shares(this_cpu);
for_each_domain(this_cpu, sd) {
unsigned long interval;
int balance = 1;
@@ -3197,8 +3421,10 @@ static 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)
+ if (pulled_task) {
+ this_rq->idle_stamp = 0;
break;
+ }
}
raw_spin_lock(&this_rq->lock);
@@ -3549,6 +3775,8 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
int update_next_balance = 0;
int need_serialize;
+ update_shares(cpu);
+
for_each_domain(cpu, sd) {
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
@@ -3869,13 +4097,26 @@ static void set_curr_task_fair(struct rq *rq)
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void moved_group_fair(struct task_struct *p, int on_rq)
+static void task_move_group_fair(struct task_struct *p, int on_rq)
{
- struct cfs_rq *cfs_rq = task_cfs_rq(p);
-
- update_curr(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
+ * absolute on their old rq until wakeup (needed for the fair sleeper
+ * bonus in place_entity()).
+ *
+ * If it was on the rq, we've just 'preempted' it, which does convert
+ * ->vruntime to a relative base.
+ *
+ * Make sure both cases convert their relative position when migrating
+ * to another cgroup's rq. This does somewhat interfere with the
+ * fair sleeper stuff for the first placement, but who cares.
+ */
+ if (!on_rq)
+ p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+ set_task_rq(p, task_cpu(p));
if (!on_rq)
- place_entity(cfs_rq, &p->se, 1);
+ p->se.vruntime += cfs_rq_of(&p->se)->min_vruntime;
}
#endif
@@ -3927,7 +4168,7 @@ static const struct sched_class fair_sched_class = {
.get_rr_interval = get_rr_interval_fair,
#ifdef CONFIG_FAIR_GROUP_SCHED
- .moved_group = moved_group_fair,
+ .task_move_group = task_move_group_fair,
#endif
};
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 185f920ec1a..68e69acc29b 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -52,8 +52,6 @@ SCHED_FEAT(ARCH_POWER, 0)
SCHED_FEAT(HRTICK, 0)
SCHED_FEAT(DOUBLE_TICK, 0)
SCHED_FEAT(LB_BIAS, 1)
-SCHED_FEAT(LB_SHARES_UPDATE, 1)
-SCHED_FEAT(ASYM_EFF_LOAD, 1)
/*
* Spin-wait on mutex acquisition when the mutex owner is running on
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index bea7d79f7e9..c914ec747ca 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -183,6 +183,17 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
}
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+ list_add_rcu(&rt_rq->leaf_rt_rq_list,
+ &rq_of_rt_rq(rt_rq)->leaf_rt_rq_list);
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+ list_del_rcu(&rt_rq->leaf_rt_rq_list);
+}
+
#define for_each_leaf_rt_rq(rt_rq, rq) \
list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
@@ -276,6 +287,14 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
return ktime_to_ns(def_rt_bandwidth.rt_period);
}
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
#define for_each_leaf_rt_rq(rt_rq, rq) \
for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
@@ -825,6 +844,9 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
return;
+ if (!rt_rq->rt_nr_running)
+ list_add_leaf_rt_rq(rt_rq);
+
if (head)
list_add(&rt_se->run_list, queue);
else
@@ -844,6 +866,8 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
__clear_bit(rt_se_prio(rt_se), array->bitmap);
dec_rt_tasks(rt_se, rt_rq);
+ if (!rt_rq->rt_nr_running)
+ list_del_leaf_rt_rq(rt_rq);
}
/*
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 25c2f962f6f..48ddf431db0 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -157,15 +157,7 @@ static inline void sched_info_reset_dequeued(struct task_struct *t)
}
/*
- * Called when a process is dequeued from the active array and given
- * the cpu. We should note that with the exception of interactive
- * tasks, the expired queue will become the active queue after the active
- * queue is empty, without explicitly dequeuing and requeuing tasks in the
- * expired queue. (Interactive tasks may be requeued directly to the
- * active queue, thus delaying tasks in the expired queue from running;
- * see scheduler_tick()).
- *
- * Though we are interested in knowing how long it was from the *first* time a
+ * We are interested in knowing how long it was from the *first* time a
* task was queued to the time that it finally hit a cpu, we call this routine
* from dequeue_task() to account for possible rq->clock skew across cpus. The
* delta taken on each cpu would annul the skew.
@@ -203,16 +195,6 @@ static void sched_info_arrive(struct task_struct *t)
}
/*
- * Called when a process is queued into either the active or expired
- * array. The time is noted and later used to determine how long we
- * had to wait for us to reach the cpu. Since the expired queue will
- * become the active queue after active queue is empty, without dequeuing
- * and requeuing any tasks, we are interested in queuing to either. It
- * is unusual but not impossible for tasks to be dequeued and immediately
- * requeued in the same or another array: this can happen in sched_yield(),
- * set_user_nice(), and even load_balance() as it moves tasks from runqueue
- * to runqueue.
- *
* This function is only called from enqueue_task(), but also only updates
* the timestamp if it is already not set. It's assumed that
* sched_info_dequeued() will clear that stamp when appropriate.
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 45bddc0c104..2bf6b47058c 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -19,14 +19,14 @@ select_task_rq_stop(struct rq *rq, struct task_struct *p,
static void
check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
{
- resched_task(rq->curr); /* we preempt everything */
+ /* we're never preempted */
}
static struct task_struct *pick_next_task_stop(struct rq *rq)
{
struct task_struct *stop = rq->stop;
- if (stop && stop->state == TASK_RUNNING)
+ if (stop && stop->se.on_rq)
return stop;
return NULL;
diff --git a/kernel/signal.c b/kernel/signal.c
index 919562c3d6b..4e3cff10fdc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1105,7 +1105,8 @@ int zap_other_threads(struct task_struct *p)
return count;
}
-struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
+struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
+ unsigned long *flags)
{
struct sighand_struct *sighand;
@@ -1617,6 +1618,8 @@ static int sigkill_pending(struct task_struct *tsk)
* is gone, we keep current->exit_code unless clear_code.
*/
static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
+ __releases(&current->sighand->siglock)
+ __acquires(&current->sighand->siglock)
{
if (arch_ptrace_stop_needed(exit_code, info)) {
/*
diff --git a/kernel/smp.c b/kernel/smp.c
index ed6aacfcb7e..12ed8b013e2 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -267,7 +267,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
*
* Returns 0 on success, else a negative status code.
*/
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
int wait)
{
struct call_single_data d = {
@@ -336,7 +336,7 @@ EXPORT_SYMBOL(smp_call_function_single);
* 3) any other online cpu in @mask
*/
int smp_call_function_any(const struct cpumask *mask,
- void (*func)(void *info), void *info, int wait)
+ smp_call_func_t func, void *info, int wait)
{
unsigned int cpu;
const struct cpumask *nodemask;
@@ -416,7 +416,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
* must be disabled when calling this function.
*/
void smp_call_function_many(const struct cpumask *mask,
- void (*func)(void *), void *info, bool wait)
+ smp_call_func_t func, void *info, bool wait)
{
struct call_function_data *data;
unsigned long flags;
@@ -500,7 +500,7 @@ EXPORT_SYMBOL(smp_call_function_many);
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
-int smp_call_function(void (*func)(void *), void *info, int wait)
+int smp_call_function(smp_call_func_t func, void *info, int wait)
{
preempt_disable();
smp_call_function_many(cpu_online_mask, func, info, wait);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index fc978889b19..d4d918a9188 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -67,7 +67,7 @@ char *softirq_to_name[NR_SOFTIRQS] = {
* to the pending events, so lets the scheduler to balance
* the softirq load for us.
*/
-void wakeup_softirqd(void)
+static void wakeup_softirqd(void)
{
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
@@ -229,18 +229,20 @@ restart:
do {
if (pending & 1) {
+ unsigned int vec_nr = h - softirq_vec;
int prev_count = preempt_count();
- kstat_incr_softirqs_this_cpu(h - softirq_vec);
- trace_softirq_entry(h, softirq_vec);
+ kstat_incr_softirqs_this_cpu(vec_nr);
+
+ trace_softirq_entry(vec_nr);
h->action(h);
- trace_softirq_exit(h, softirq_vec);
+ trace_softirq_exit(vec_nr);
if (unlikely(prev_count != preempt_count())) {
- printk(KERN_ERR "huh, entered softirq %td %s %p"
+ printk(KERN_ERR "huh, entered softirq %u %s %p"
"with preempt_count %08x,"
- " exited with %08x?\n", h - softirq_vec,
- softirq_to_name[h - softirq_vec],
- h->action, prev_count, preempt_count());
+ " exited with %08x?\n", vec_nr,
+ softirq_to_name[vec_nr], h->action,
+ prev_count, preempt_count());
preempt_count() = prev_count;
}
@@ -851,7 +853,9 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
cpumask_any(cpu_online_mask));
case CPU_DEAD:
case CPU_DEAD_FROZEN: {
- struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+ static struct sched_param param = {
+ .sched_priority = MAX_RT_PRIO-1
+ };
p = per_cpu(ksoftirqd, hotcpu);
per_cpu(ksoftirqd, hotcpu) = NULL;
diff --git a/kernel/srcu.c b/kernel/srcu.c
index c71e0750053..98d8c1e80ed 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -31,6 +31,7 @@
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/smp.h>
+#include <linux/delay.h>
#include <linux/srcu.h>
static int init_srcu_struct_fields(struct srcu_struct *sp)
@@ -203,9 +204,14 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
* all srcu_read_lock() calls using the old counters have completed.
* Their corresponding critical sections might well be still
* executing, but the srcu_read_lock() primitives themselves
- * will have finished executing.
+ * will have finished executing. We initially give readers
+ * an arbitrarily chosen 10 microseconds to get out of their
+ * SRCU read-side critical sections, then loop waiting 1/HZ
+ * seconds per iteration.
*/
+ if (srcu_readers_active_idx(sp, idx))
+ udelay(CONFIG_SRCU_SYNCHRONIZE_DELAY);
while (srcu_readers_active_idx(sp, idx))
schedule_timeout_interruptible(1);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 090c28812ce..2df820b03be 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -262,7 +262,7 @@ repeat:
cpu_stop_fn_t fn = work->fn;
void *arg = work->arg;
struct cpu_stop_done *done = work->done;
- char ksym_buf[KSYM_NAME_LEN];
+ char ksym_buf[KSYM_NAME_LEN] __maybe_unused;
__set_current_state(TASK_RUNNING);
@@ -304,7 +304,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
p = kthread_create(cpu_stopper_thread, stopper, "migration/%d",
cpu);
if (IS_ERR(p))
- return NOTIFY_BAD;
+ return notifier_from_errno(PTR_ERR(p));
get_task_struct(p);
kthread_bind(p, cpu);
sched_set_stop_task(cpu, p);
@@ -372,7 +372,7 @@ static int __init cpu_stop_init(void)
/* start one for the boot cpu */
err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE,
bcpu);
- BUG_ON(err == NOTIFY_BAD);
+ BUG_ON(err != NOTIFY_OK);
cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu);
register_cpu_notifier(&cpu_stop_cpu_notifier);
diff --git a/kernel/sys.c b/kernel/sys.c
index 7f5a0cd296a..2745dcdb6c6 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1080,8 +1080,10 @@ SYSCALL_DEFINE0(setsid)
err = session;
out:
write_unlock_irq(&tasklist_lock);
- if (err > 0)
+ if (err > 0) {
proc_sid_connector(group_leader);
+ sched_autogroup_create_attach(group_leader);
+ }
return err;
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3a45c224770..ae5cbb1e3ce 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -161,8 +161,6 @@ extern int no_unaligned_warning;
extern int unaligned_dump_stack;
#endif
-extern struct ratelimit_state printk_ratelimit_state;
-
#ifdef CONFIG_PROC_SYSCTL
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -261,8 +259,6 @@ static int min_wakeup_granularity_ns; /* 0 usecs */
static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */
static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-static int min_sched_shares_ratelimit = 100000; /* 100 usec */
-static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */
#endif
#ifdef CONFIG_COMPACTION
@@ -307,15 +303,6 @@ static struct ctl_table kern_table[] = {
.extra2 = &max_wakeup_granularity_ns,
},
{
- .procname = "sched_shares_ratelimit",
- .data = &sysctl_sched_shares_ratelimit,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_proc_update_handler,
- .extra1 = &min_sched_shares_ratelimit,
- .extra2 = &max_sched_shares_ratelimit,
- },
- {
.procname = "sched_tunable_scaling",
.data = &sysctl_sched_tunable_scaling,
.maxlen = sizeof(enum sched_tunable_scaling),
@@ -325,14 +312,6 @@ static struct ctl_table kern_table[] = {
.extra2 = &max_sched_tunable_scaling,
},
{
- .procname = "sched_shares_thresh",
- .data = &sysctl_sched_shares_thresh,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- },
- {
.procname = "sched_migration_cost",
.data = &sysctl_sched_migration_cost,
.maxlen = sizeof(unsigned int),
@@ -354,6 +333,13 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "sched_shares_window",
+ .data = &sysctl_sched_shares_window,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "timer_migration",
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
@@ -384,6 +370,17 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#ifdef CONFIG_SCHED_AUTOGROUP
+ {
+ .procname = "sched_autogroup_enabled",
+ .data = &sysctl_sched_autogroup_enabled,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
@@ -704,6 +701,15 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &ten_thousand,
},
+ {
+ .procname = "dmesg_restrict",
+ .data = &dmesg_restrict,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#endif
{
.procname = "ngroups_max",
@@ -738,21 +744,21 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
-#endif
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
{
- .procname = "unknown_nmi_panic",
- .data = &unknown_nmi_panic,
+ .procname = "nmi_watchdog",
+ .data = &watchdog_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dowatchdog_enabled,
},
+#endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
{
- .procname = "nmi_watchdog",
- .data = &nmi_watchdog_enabled,
+ .procname = "unknown_nmi_panic",
+ .data = &unknown_nmi_panic,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = proc_nmi_enabled,
+ .proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_X86)
@@ -1340,28 +1346,28 @@ static struct ctl_table fs_table[] = {
.data = &inodes_stat,
.maxlen = 2*sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_nr_inodes,
},
{
.procname = "inode-state",
.data = &inodes_stat,
.maxlen = 7*sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_nr_inodes,
},
{
.procname = "file-nr",
.data = &files_stat,
- .maxlen = 3*sizeof(int),
+ .maxlen = sizeof(files_stat),
.mode = 0444,
.proc_handler = proc_nr_files,
},
{
.procname = "file-max",
.data = &files_stat.max_files,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(files_stat.max_files),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_doulongvec_minmax,
},
{
.procname = "nr_open",
@@ -1377,7 +1383,7 @@ static struct ctl_table fs_table[] = {
.data = &dentry_stat,
.maxlen = 6*sizeof(int),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_nr_dentry,
},
{
.procname = "overflowuid",
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 1357c578606..4b2545a136f 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -136,7 +136,6 @@ static const struct bin_table bin_kern_table[] = {
{ CTL_INT, KERN_IA64_UNALIGNED, "ignore-unaligned-usertrap" },
{ CTL_INT, KERN_COMPAT_LOG, "compat-log" },
{ CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" },
- { CTL_INT, KERN_NMI_WATCHDOG, "nmi_watchdog" },
{ CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" },
{}
};
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 11281d5792b..3308fd7f1b5 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -175,22 +175,8 @@ static void send_cpu_listeners(struct sk_buff *skb,
up_write(&listeners->sem);
}
-static int fill_pid(pid_t pid, struct task_struct *tsk,
- struct taskstats *stats)
+static void fill_stats(struct task_struct *tsk, struct taskstats *stats)
{
- int rc = 0;
-
- if (!tsk) {
- rcu_read_lock();
- tsk = find_task_by_vpid(pid);
- if (tsk)
- get_task_struct(tsk);
- rcu_read_unlock();
- if (!tsk)
- return -ESRCH;
- } else
- get_task_struct(tsk);
-
memset(stats, 0, sizeof(*stats));
/*
* Each accounting subsystem adds calls to its functions to
@@ -209,17 +195,27 @@ static int fill_pid(pid_t pid, struct task_struct *tsk,
/* fill in extended acct fields */
xacct_add_tsk(stats, tsk);
+}
- /* Define err: label here if needed */
- put_task_struct(tsk);
- return rc;
+static int fill_stats_for_pid(pid_t pid, struct taskstats *stats)
+{
+ struct task_struct *tsk;
+ rcu_read_lock();
+ tsk = find_task_by_vpid(pid);
+ if (tsk)
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ if (!tsk)
+ return -ESRCH;
+ fill_stats(tsk, stats);
+ put_task_struct(tsk);
+ return 0;
}
-static int fill_tgid(pid_t tgid, struct task_struct *first,
- struct taskstats *stats)
+static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
{
- struct task_struct *tsk;
+ struct task_struct *tsk, *first;
unsigned long flags;
int rc = -ESRCH;
@@ -228,8 +224,7 @@ static int fill_tgid(pid_t tgid, struct task_struct *first,
* leaders who are already counted with the dead tasks
*/
rcu_read_lock();
- if (!first)
- first = find_task_by_vpid(tgid);
+ first = find_task_by_vpid(tgid);
if (!first || !lock_task_sighand(first, &flags))
goto out;
@@ -268,7 +263,6 @@ out:
return rc;
}
-
static void fill_tgid_exit(struct task_struct *tsk)
{
unsigned long flags;
@@ -355,6 +349,10 @@ static int parse(struct nlattr *na, struct cpumask *mask)
return ret;
}
+#ifdef CONFIG_IA64
+#define TASKSTATS_NEEDS_PADDING 1
+#endif
+
static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
{
struct nlattr *na, *ret;
@@ -364,9 +362,33 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
? TASKSTATS_TYPE_AGGR_PID
: TASKSTATS_TYPE_AGGR_TGID;
+ /*
+ * The taskstats structure is internally aligned on 8 byte
+ * boundaries but the layout of the aggregrate reply, with
+ * two NLA headers and the pid (each 4 bytes), actually
+ * force the entire structure to be unaligned. This causes
+ * the kernel to issue unaligned access warnings on some
+ * architectures like ia64. Unfortunately, some software out there
+ * doesn't properly unroll the NLA packet and assumes that the start
+ * of the taskstats structure will always be 20 bytes from the start
+ * of the netlink payload. Aligning the start of the taskstats
+ * structure breaks this software, which we don't want. So, for now
+ * the alignment only happens on architectures that require it
+ * and those users will have to update to fixed versions of those
+ * packages. Space is reserved in the packet only when needed.
+ * This ifdef should be removed in several years e.g. 2012 once
+ * we can be confident that fixed versions are installed on most
+ * systems. We add the padding before the aggregate since the
+ * aggregate is already a defined type.
+ */
+#ifdef TASKSTATS_NEEDS_PADDING
+ if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0)
+ goto err;
+#endif
na = nla_nest_start(skb, aggr);
if (!na)
goto err;
+
if (nla_put(skb, type, sizeof(pid), &pid) < 0)
goto err;
ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
@@ -424,74 +446,122 @@ err:
return rc;
}
-static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
+static int cmd_attr_register_cpumask(struct genl_info *info)
{
- int rc;
- struct sk_buff *rep_skb;
- struct taskstats *stats;
- size_t size;
cpumask_var_t mask;
+ int rc;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
-
rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
if (rc < 0)
- goto free_return_rc;
- if (rc == 0) {
- rc = add_del_listener(info->snd_pid, mask, REGISTER);
- goto free_return_rc;
- }
+ goto out;
+ rc = add_del_listener(info->snd_pid, mask, REGISTER);
+out:
+ free_cpumask_var(mask);
+ return rc;
+}
+
+static int cmd_attr_deregister_cpumask(struct genl_info *info)
+{
+ cpumask_var_t mask;
+ int rc;
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
if (rc < 0)
- goto free_return_rc;
- if (rc == 0) {
- rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
-free_return_rc:
- free_cpumask_var(mask);
- return rc;
- }
+ goto out;
+ rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
+out:
free_cpumask_var(mask);
+ return rc;
+}
+
+static size_t taskstats_packet_size(void)
+{
+ size_t size;
- /*
- * Size includes space for nested attributes
- */
size = nla_total_size(sizeof(u32)) +
nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+#ifdef TASKSTATS_NEEDS_PADDING
+ size += nla_total_size(0); /* Padding for alignment */
+#endif
+ return size;
+}
+
+static int cmd_attr_pid(struct genl_info *info)
+{
+ struct taskstats *stats;
+ struct sk_buff *rep_skb;
+ size_t size;
+ u32 pid;
+ int rc;
+
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
return rc;
rc = -EINVAL;
- if (info->attrs[TASKSTATS_CMD_ATTR_PID]) {
- u32 pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
- stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
- if (!stats)
- goto err;
-
- rc = fill_pid(pid, NULL, stats);
- if (rc < 0)
- goto err;
- } else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) {
- u32 tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]);
- stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
- if (!stats)
- goto err;
-
- rc = fill_tgid(tgid, NULL, stats);
- if (rc < 0)
- goto err;
- } else
+ pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
+ if (!stats)
goto err;
+ rc = fill_stats_for_pid(pid, stats);
+ if (rc < 0)
+ goto err;
return send_reply(rep_skb, info);
err:
nlmsg_free(rep_skb);
return rc;
}
+static int cmd_attr_tgid(struct genl_info *info)
+{
+ struct taskstats *stats;
+ struct sk_buff *rep_skb;
+ size_t size;
+ u32 tgid;
+ int rc;
+
+ size = taskstats_packet_size();
+
+ rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
+ if (rc < 0)
+ return rc;
+
+ rc = -EINVAL;
+ tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]);
+ stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
+ if (!stats)
+ goto err;
+
+ rc = fill_stats_for_tgid(tgid, stats);
+ if (rc < 0)
+ goto err;
+ return send_reply(rep_skb, info);
+err:
+ nlmsg_free(rep_skb);
+ return rc;
+}
+
+static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+ if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK])
+ return cmd_attr_register_cpumask(info);
+ else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK])
+ return cmd_attr_deregister_cpumask(info);
+ else if (info->attrs[TASKSTATS_CMD_ATTR_PID])
+ return cmd_attr_pid(info);
+ else if (info->attrs[TASKSTATS_CMD_ATTR_TGID])
+ return cmd_attr_tgid(info);
+ else
+ return -EINVAL;
+}
+
static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
@@ -532,8 +602,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
/*
* Size includes space for nested attributes
*/
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
is_thread_group = !!taskstats_tgid_alloc(tsk);
if (is_thread_group) {
@@ -555,9 +624,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
if (!stats)
goto err;
- rc = fill_pid(-1, tsk, stats);
- if (rc < 0)
- goto err;
+ fill_stats(tsk, stats);
/*
* Doesn't matter if tsk is the leader or the last group member leaving
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index ac38fbb176c..a9ae369925c 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -21,6 +21,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/math64.h>
+#include <linux/kernel.h>
/*
* fixed point arithmetic scale factor for skew
@@ -57,11 +58,11 @@ int timecompare_offset(struct timecompare *sync,
int index;
int num_samples = sync->num_samples;
- if (num_samples > sizeof(buffer)/sizeof(buffer[0])) {
+ if (num_samples > ARRAY_SIZE(buffer)) {
samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
if (!samples) {
samples = buffer;
- num_samples = sizeof(buffer)/sizeof(buffer[0]);
+ num_samples = ARRAY_SIZE(buffer);
}
} else {
samples = buffer;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 49010d822f7..5bb86da8200 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -32,6 +32,8 @@ struct timekeeper {
cycle_t cycle_interval;
/* Number of clock shifted nano seconds in one NTP interval. */
u64 xtime_interval;
+ /* shifted nano seconds left over when rounding cycle_interval */
+ s64 xtime_remainder;
/* Raw nano seconds accumulated per NTP interval. */
u32 raw_interval;
@@ -62,7 +64,7 @@ struct timekeeper timekeeper;
static void timekeeper_setup_internals(struct clocksource *clock)
{
cycle_t interval;
- u64 tmp;
+ u64 tmp, ntpinterval;
timekeeper.clock = clock;
clock->cycle_last = clock->read(clock);
@@ -70,6 +72,7 @@ static void timekeeper_setup_internals(struct clocksource *clock)
/* Do the ns -> cycle conversion first, using original mult */
tmp = NTP_INTERVAL_LENGTH;
tmp <<= clock->shift;
+ ntpinterval = tmp;
tmp += clock->mult/2;
do_div(tmp, clock->mult);
if (tmp == 0)
@@ -80,6 +83,7 @@ static void timekeeper_setup_internals(struct clocksource *clock)
/* Go back from cycles -> shifted ns */
timekeeper.xtime_interval = (u64) interval * clock->mult;
+ timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval;
timekeeper.raw_interval =
((u64) interval * clock->mult) >> clock->shift;
@@ -719,7 +723,8 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
/* Accumulate error between NTP and clock interval */
timekeeper.ntp_error += tick_length << shift;
- timekeeper.ntp_error -= timekeeper.xtime_interval <<
+ timekeeper.ntp_error -=
+ (timekeeper.xtime_interval + timekeeper.xtime_remainder) <<
(timekeeper.ntp_error_shift + shift);
return offset;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ab8f5e33fa9..32a19f9397f 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -79,26 +79,26 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
{
struct hrtimer *timer, tmp;
unsigned long next = 0, i;
- struct rb_node *curr;
+ struct timerqueue_node *curr;
unsigned long flags;
next_one:
i = 0;
raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
- curr = base->first;
+ curr = timerqueue_getnext(&base->active);
/*
* Crude but we have to do this O(N*N) thing, because
* we have to unlock the base when printing:
*/
while (curr && i < next) {
- curr = rb_next(curr);
+ curr = timerqueue_iterate_next(curr);
i++;
}
if (curr) {
- timer = rb_entry(curr, struct hrtimer, node);
+ timer = container_of(curr, struct hrtimer, node);
tmp = *timer;
raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
diff --git a/kernel/timer.c b/kernel/timer.c
index 68a9ae7679b..43ca9936f2d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -88,18 +88,6 @@ struct tvec_base boot_tvec_bases;
EXPORT_SYMBOL(boot_tvec_bases);
static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
-/*
- * Note that all tvec_bases are 2 byte aligned and lower bit of
- * base in timer_list is guaranteed to be zero. Use the LSB to
- * indicate whether the timer is deferrable.
- *
- * A deferrable timer will work normally when the system is busy, but
- * will not cause a CPU to come out of idle just to service it; instead,
- * the timer will be serviced when the CPU eventually wakes up with a
- * subsequent non-deferrable timer.
- */
-#define TBASE_DEFERRABLE_FLAG (0x1)
-
/* Functions below help us manage 'deferrable' flag */
static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
{
@@ -113,8 +101,7 @@ static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
static inline void timer_set_deferrable(struct timer_list *timer)
{
- timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
- TBASE_DEFERRABLE_FLAG));
+ timer->base = TBASE_MAKE_DEFERRED(timer->base);
}
static inline void
@@ -343,15 +330,6 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
}
EXPORT_SYMBOL_GPL(set_timer_slack);
-
-static inline void set_running_timer(struct tvec_base *base,
- struct timer_list *timer)
-{
-#ifdef CONFIG_SMP
- base->running_timer = timer;
-#endif
-}
-
static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
{
unsigned long expires = timer->expires;
@@ -936,15 +914,12 @@ int del_timer(struct timer_list *timer)
}
EXPORT_SYMBOL(del_timer);
-#ifdef CONFIG_SMP
/**
* try_to_del_timer_sync - Try to deactivate a timer
* @timer: timer do del
*
* This function tries to deactivate a timer. Upon successful (ret >= 0)
* exit the timer is not queued and the handler is not running on any CPU.
- *
- * It must not be called from interrupt contexts.
*/
int try_to_del_timer_sync(struct timer_list *timer)
{
@@ -973,6 +948,7 @@ out:
}
EXPORT_SYMBOL(try_to_del_timer_sync);
+#ifdef CONFIG_SMP
/**
* del_timer_sync - deactivate a timer and wait for the handler to finish.
* @timer: the timer to be deactivated
@@ -983,7 +959,7 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
*
* Synchronization rules: Callers must prevent restarting of the timer,
* otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which would prevent
+ * hardirq contexts. The caller must not hold locks which would prevent
* completion of the timer's handler. The timer's handler must not call
* add_timer_on(). Upon exit the timer is not queued and the handler is
* not running on any CPU.
@@ -993,14 +969,16 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
int del_timer_sync(struct timer_list *timer)
{
#ifdef CONFIG_LOCKDEP
- unsigned long flags;
-
- local_irq_save(flags);
+ local_bh_disable();
lock_map_acquire(&timer->lockdep_map);
lock_map_release(&timer->lockdep_map);
- local_irq_restore(flags);
+ local_bh_enable();
#endif
-
+ /*
+ * don't use it in hardirq context, because it
+ * could lead to deadlock.
+ */
+ WARN_ON(in_irq());
for (;;) {
int ret = try_to_del_timer_sync(timer);
if (ret >= 0)
@@ -1111,7 +1089,7 @@ static inline void __run_timers(struct tvec_base *base)
timer_stats_account_timer(timer);
- set_running_timer(base, timer);
+ base->running_timer = timer;
detach_timer(timer, 1);
spin_unlock_irq(&base->lock);
@@ -1119,7 +1097,7 @@ static inline void __run_timers(struct tvec_base *base)
spin_lock_irq(&base->lock);
}
}
- set_running_timer(base, NULL);
+ base->running_timer = NULL;
spin_unlock_irq(&base->lock);
}
@@ -1249,9 +1227,15 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now,
*/
unsigned long get_next_timer_interrupt(unsigned long now)
{
- struct tvec_base *base = __get_cpu_var(tvec_bases);
+ struct tvec_base *base = __this_cpu_read(tvec_bases);
unsigned long expires;
+ /*
+ * Pretend that there is no timer pending if the cpu is offline.
+ * Possible pending timers will be migrated later to an active cpu.
+ */
+ if (cpu_is_offline(smp_processor_id()))
+ return now + NEXT_TIMER_MAX_DELTA;
spin_lock(&base->lock);
if (time_before_eq(base->next_timer, base->timer_jiffies))
base->next_timer = __next_timer_interrupt(base);
@@ -1292,7 +1276,7 @@ void update_process_times(int user_tick)
*/
static void run_timer_softirq(struct softirq_action *h)
{
- struct tvec_base *base = __get_cpu_var(tvec_bases);
+ struct tvec_base *base = __this_cpu_read(tvec_bases);
hrtimer_run_pending();
@@ -1319,7 +1303,7 @@ void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
update_wall_time();
- calc_global_load();
+ calc_global_load(ticks);
}
#ifdef __ARCH_WANT_SYS_ALARM
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bcdef8..14674dce77a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -69,6 +69,21 @@ config EVENT_TRACING
select CONTEXT_SWITCH_TRACER
bool
+config EVENT_POWER_TRACING_DEPRECATED
+ depends on EVENT_TRACING
+ bool "Deprecated power event trace API, to be removed"
+ default y
+ help
+ Provides old power event types:
+ C-state/idle accounting events:
+ power:power_start
+ power:power_end
+ and old cpufreq accounting event:
+ power:power_frequency
+ This is for userspace compatibility
+ and will vanish after 5 kernel iterations,
+ namely 2.6.41.
+
config CONTEXT_SWITCH_TRACER
bool
@@ -126,7 +141,7 @@ if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
depends on HAVE_FUNCTION_TRACER
- select FRAME_POINTER if (!ARM_UNWIND)
+ select FRAME_POINTER if !ARM_UNWIND && !S390
select KALLSYMS
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index bc251ed6672..7b8ec028154 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -168,7 +168,6 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
BLK_TC_ACT(BLK_TC_WRITE) };
-#define BLK_TC_HARDBARRIER BLK_TC_BARRIER
#define BLK_TC_RAHEAD BLK_TC_AHEAD
/* The ilog2() calls fall out because they're constant */
@@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
return;
what |= ddir_act[rw & WRITE];
- what |= MASK_TC_BIT(rw, HARDBARRIER);
what |= MASK_TC_BIT(rw, SYNC);
what |= MASK_TC_BIT(rw, RAHEAD);
what |= MASK_TC_BIT(rw, META);
@@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
if (rw & REQ_RAHEAD)
rwbs[i++] = 'A';
- if (rw & REQ_HARDBARRIER)
- rwbs[i++] = 'B';
if (rw & REQ_SYNC)
rwbs[i++] = 'S';
if (rw & REQ_META)
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index a22582a0616..f55fcf61b22 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -13,5 +13,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/power.h>
-EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+#ifdef EVENT_POWER_TRACING_DEPRECATED
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c3dab054d18..bd1c35a4fbc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -224,6 +224,9 @@ enum {
RB_LEN_TIME_STAMP = 16,
};
+#define skip_time_extend(event) \
+ ((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND))
+
static inline int rb_null_event(struct ring_buffer_event *event)
{
return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
@@ -248,8 +251,12 @@ rb_event_data_length(struct ring_buffer_event *event)
return length + RB_EVNT_HDR_SIZE;
}
-/* inline for ring buffer fast paths */
-static unsigned
+/*
+ * Return the length of the given event. Will return
+ * the length of the time extend if the event is a
+ * time extend.
+ */
+static inline unsigned
rb_event_length(struct ring_buffer_event *event)
{
switch (event->type_len) {
@@ -274,13 +281,41 @@ rb_event_length(struct ring_buffer_event *event)
return 0;
}
+/*
+ * Return total length of time extend and data,
+ * or just the event length for all other events.
+ */
+static inline unsigned
+rb_event_ts_length(struct ring_buffer_event *event)
+{
+ unsigned len = 0;
+
+ if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+ /* time extends include the data event after it */
+ len = RB_LEN_TIME_EXTEND;
+ event = skip_time_extend(event);
+ }
+ return len + rb_event_length(event);
+}
+
/**
* ring_buffer_event_length - return the length of the event
* @event: the event to get the length of
+ *
+ * Returns the size of the data load of a data event.
+ * If the event is something other than a data event, it
+ * returns the size of the event itself. With the exception
+ * of a TIME EXTEND, where it still returns the size of the
+ * data load of the data event after it.
*/
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
- unsigned length = rb_event_length(event);
+ unsigned length;
+
+ if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ event = skip_time_extend(event);
+
+ length = rb_event_length(event);
if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
return length;
length -= RB_EVNT_HDR_SIZE;
@@ -294,6 +329,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length);
static void *
rb_event_data(struct ring_buffer_event *event)
{
+ if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ event = skip_time_extend(event);
BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
if (event->type_len)
@@ -404,9 +441,6 @@ static inline int test_time_stamp(u64 delta)
/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
-/* Max number of timestamps that can fit on a page */
-#define RB_TIMESTAMPS_PER_PAGE (BUF_PAGE_SIZE / RB_LEN_TIME_EXTEND)
-
int ring_buffer_print_page_header(struct trace_seq *s)
{
struct buffer_data_page field;
@@ -1546,6 +1580,25 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
iter->head = 0;
}
+/* Slow path, do not inline */
+static noinline struct ring_buffer_event *
+rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
+{
+ event->type_len = RINGBUF_TYPE_TIME_EXTEND;
+
+ /* Not the first event on the page? */
+ if (rb_event_index(event)) {
+ event->time_delta = delta & TS_MASK;
+ event->array[0] = delta >> TS_SHIFT;
+ } else {
+ /* nope, just zero it */
+ event->time_delta = 0;
+ event->array[0] = 0;
+ }
+
+ return skip_time_extend(event);
+}
+
/**
* ring_buffer_update_event - update event type and data
* @event: the even to update
@@ -1558,28 +1611,31 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
* data field.
*/
static void
-rb_update_event(struct ring_buffer_event *event,
- unsigned type, unsigned length)
+rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event, unsigned length,
+ int add_timestamp, u64 delta)
{
- event->type_len = type;
-
- switch (type) {
-
- case RINGBUF_TYPE_PADDING:
- case RINGBUF_TYPE_TIME_EXTEND:
- case RINGBUF_TYPE_TIME_STAMP:
- break;
+ /* Only a commit updates the timestamp */
+ if (unlikely(!rb_event_is_commit(cpu_buffer, event)))
+ delta = 0;
- case 0:
- length -= RB_EVNT_HDR_SIZE;
- if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
- event->array[0] = length;
- else
- event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
- break;
- default:
- BUG();
+ /*
+ * If we need to add a timestamp, then we
+ * add it to the start of the resevered space.
+ */
+ if (unlikely(add_timestamp)) {
+ event = rb_add_time_stamp(event, delta);
+ length -= RB_LEN_TIME_EXTEND;
+ delta = 0;
}
+
+ event->time_delta = delta;
+ length -= RB_EVNT_HDR_SIZE;
+ if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) {
+ event->type_len = 0;
+ event->array[0] = length;
+ } else
+ event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
}
/*
@@ -1823,10 +1879,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
local_sub(length, &tail_page->write);
}
-static struct ring_buffer_event *
+/*
+ * This is the slow path, force gcc not to inline it.
+ */
+static noinline struct ring_buffer_event *
rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long length, unsigned long tail,
- struct buffer_page *tail_page, u64 *ts)
+ struct buffer_page *tail_page, u64 ts)
{
struct buffer_page *commit_page = cpu_buffer->commit_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
@@ -1909,8 +1968,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
* Nested commits always have zero deltas, so
* just reread the time stamp
*/
- *ts = rb_time_stamp(buffer);
- next_page->page->time_stamp = *ts;
+ ts = rb_time_stamp(buffer);
+ next_page->page->time_stamp = ts;
}
out_again:
@@ -1929,12 +1988,21 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
static struct ring_buffer_event *
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length, u64 *ts)
+ unsigned long length, u64 ts,
+ u64 delta, int add_timestamp)
{
struct buffer_page *tail_page;
struct ring_buffer_event *event;
unsigned long tail, write;
+ /*
+ * If the time delta since the last event is too big to
+ * hold in the time field of the event, then we append a
+ * TIME EXTEND event ahead of the data event.
+ */
+ if (unlikely(add_timestamp))
+ length += RB_LEN_TIME_EXTEND;
+
tail_page = cpu_buffer->tail_page;
write = local_add_return(length, &tail_page->write);
@@ -1943,7 +2011,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
tail = write - length;
/* See if we shot pass the end of this buffer page */
- if (write > BUF_PAGE_SIZE)
+ if (unlikely(write > BUF_PAGE_SIZE))
return rb_move_tail(cpu_buffer, length, tail,
tail_page, ts);
@@ -1951,18 +2019,16 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
event = __rb_page_index(tail_page, tail);
kmemcheck_annotate_bitfield(event, bitfield);
- rb_update_event(event, type, length);
+ rb_update_event(cpu_buffer, event, length, add_timestamp, delta);
- /* The passed in type is zero for DATA */
- if (likely(!type))
- local_inc(&tail_page->entries);
+ local_inc(&tail_page->entries);
/*
* If this is the first commit on the page, then update
* its timestamp.
*/
if (!tail)
- tail_page->page->time_stamp = *ts;
+ tail_page->page->time_stamp = ts;
return event;
}
@@ -1977,7 +2043,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long addr;
new_index = rb_event_index(event);
- old_index = new_index + rb_event_length(event);
+ old_index = new_index + rb_event_ts_length(event);
addr = (unsigned long)event;
addr &= PAGE_MASK;
@@ -2003,76 +2069,13 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
return 0;
}
-static int
-rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
- u64 *ts, u64 *delta)
-{
- struct ring_buffer_event *event;
- int ret;
-
- WARN_ONCE(*delta > (1ULL << 59),
- KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
- (unsigned long long)*delta,
- (unsigned long long)*ts,
- (unsigned long long)cpu_buffer->write_stamp);
-
- /*
- * The delta is too big, we to add a
- * new timestamp.
- */
- event = __rb_reserve_next(cpu_buffer,
- RINGBUF_TYPE_TIME_EXTEND,
- RB_LEN_TIME_EXTEND,
- ts);
- if (!event)
- return -EBUSY;
-
- if (PTR_ERR(event) == -EAGAIN)
- return -EAGAIN;
-
- /* Only a commited time event can update the write stamp */
- if (rb_event_is_commit(cpu_buffer, event)) {
- /*
- * If this is the first on the page, then it was
- * updated with the page itself. Try to discard it
- * and if we can't just make it zero.
- */
- if (rb_event_index(event)) {
- event->time_delta = *delta & TS_MASK;
- event->array[0] = *delta >> TS_SHIFT;
- } else {
- /* try to discard, since we do not need this */
- if (!rb_try_to_discard(cpu_buffer, event)) {
- /* nope, just zero it */
- event->time_delta = 0;
- event->array[0] = 0;
- }
- }
- cpu_buffer->write_stamp = *ts;
- /* let the caller know this was the commit */
- ret = 1;
- } else {
- /* Try to discard the event */
- if (!rb_try_to_discard(cpu_buffer, event)) {
- /* Darn, this is just wasted space */
- event->time_delta = 0;
- event->array[0] = 0;
- }
- ret = 0;
- }
-
- *delta = 0;
-
- return ret;
-}
-
static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
{
local_inc(&cpu_buffer->committing);
local_inc(&cpu_buffer->commits);
}
-static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
+static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
{
unsigned long commits;
@@ -2110,9 +2113,10 @@ rb_reserve_next_event(struct ring_buffer *buffer,
unsigned long length)
{
struct ring_buffer_event *event;
- u64 ts, delta = 0;
- int commit = 0;
+ u64 ts, delta;
int nr_loops = 0;
+ int add_timestamp;
+ u64 diff;
rb_start_commit(cpu_buffer);
@@ -2133,6 +2137,9 @@ rb_reserve_next_event(struct ring_buffer *buffer,
length = rb_calculate_event_length(length);
again:
+ add_timestamp = 0;
+ delta = 0;
+
/*
* We allow for interrupts to reenter here and do a trace.
* If one does, it will cause this original code to loop
@@ -2146,56 +2153,32 @@ rb_reserve_next_event(struct ring_buffer *buffer,
goto out_fail;
ts = rb_time_stamp(cpu_buffer->buffer);
+ diff = ts - cpu_buffer->write_stamp;
- /*
- * Only the first commit can update the timestamp.
- * Yes there is a race here. If an interrupt comes in
- * just after the conditional and it traces too, then it
- * will also check the deltas. More than one timestamp may
- * also be made. But only the entry that did the actual
- * commit will be something other than zero.
- */
- if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page &&
- rb_page_write(cpu_buffer->tail_page) ==
- rb_commit_index(cpu_buffer))) {
- u64 diff;
-
- diff = ts - cpu_buffer->write_stamp;
-
- /* make sure this diff is calculated here */
- barrier();
-
- /* Did the write stamp get updated already? */
- if (unlikely(ts < cpu_buffer->write_stamp))
- goto get_event;
+ /* make sure this diff is calculated here */
+ barrier();
+ /* Did the write stamp get updated already? */
+ if (likely(ts >= cpu_buffer->write_stamp)) {
delta = diff;
if (unlikely(test_time_stamp(delta))) {
-
- commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
- if (commit == -EBUSY)
- goto out_fail;
-
- if (commit == -EAGAIN)
- goto again;
-
- RB_WARN_ON(cpu_buffer, commit < 0);
+ WARN_ONCE(delta > (1ULL << 59),
+ KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+ (unsigned long long)delta,
+ (unsigned long long)ts,
+ (unsigned long long)cpu_buffer->write_stamp);
+ add_timestamp = 1;
}
}
- get_event:
- event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
+ event = __rb_reserve_next(cpu_buffer, length, ts,
+ delta, add_timestamp);
if (unlikely(PTR_ERR(event) == -EAGAIN))
goto again;
if (!event)
goto out_fail;
- if (!rb_event_is_commit(cpu_buffer, event))
- delta = 0;
-
- event->time_delta = delta;
-
return event;
out_fail:
@@ -2207,13 +2190,9 @@ rb_reserve_next_event(struct ring_buffer *buffer,
#define TRACE_RECURSIVE_DEPTH 16
-static int trace_recursive_lock(void)
+/* Keep this code out of the fast path cache */
+static noinline void trace_recursive_fail(void)
{
- current->trace_recursion++;
-
- if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
- return 0;
-
/* Disable all tracing before we do anything else */
tracing_off_permanent();
@@ -2225,10 +2204,21 @@ static int trace_recursive_lock(void)
in_nmi());
WARN_ON_ONCE(1);
+}
+
+static inline int trace_recursive_lock(void)
+{
+ current->trace_recursion++;
+
+ if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+ return 0;
+
+ trace_recursive_fail();
+
return -1;
}
-static void trace_recursive_unlock(void)
+static inline void trace_recursive_unlock(void)
{
WARN_ON_ONCE(!current->trace_recursion);
@@ -2308,12 +2298,28 @@ static void
rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
+ u64 delta;
+
/*
* The event first in the commit queue updates the
* time stamp.
*/
- if (rb_event_is_commit(cpu_buffer, event))
- cpu_buffer->write_stamp += event->time_delta;
+ if (rb_event_is_commit(cpu_buffer, event)) {
+ /*
+ * A commit event that is first on a page
+ * updates the write timestamp with the page stamp
+ */
+ if (!rb_event_index(event))
+ cpu_buffer->write_stamp =
+ cpu_buffer->commit_page->page->time_stamp;
+ else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+ delta = event->array[0];
+ delta <<= TS_SHIFT;
+ delta += event->time_delta;
+ cpu_buffer->write_stamp += delta;
+ } else
+ cpu_buffer->write_stamp += event->time_delta;
+ }
}
static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
@@ -2353,6 +2359,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
static inline void rb_event_discard(struct ring_buffer_event *event)
{
+ if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+ event = skip_time_extend(event);
+
/* array[0] holds the actual length for the discarded event */
event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
event->type_len = RINGBUF_TYPE_PADDING;
@@ -3049,12 +3058,12 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
again:
/*
- * We repeat when a timestamp is encountered. It is possible
- * to get multiple timestamps from an interrupt entering just
- * as one timestamp is about to be written, or from discarded
- * commits. The most that we can have is the number on a single page.
+ * We repeat when a time extend is encountered.
+ * Since the time extend is always attached to a data event,
+ * we should never loop more than once.
+ * (We never hit the following condition more than twice).
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
return NULL;
reader = rb_get_reader_page(cpu_buffer);
@@ -3130,14 +3139,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
return NULL;
/*
- * We repeat when a timestamp is encountered.
- * We can get multiple timestamps by nested interrupts or also
- * if filtering is on (discarding commits). Since discarding
- * commits can be frequent we can get a lot of timestamps.
- * But we limit them by not adding timestamps if they begin
- * at the start of a page.
+ * We repeat when a time extend is encountered.
+ * Since the time extend is always attached to a data event,
+ * we should never loop more than once.
+ * (We never hit the following condition more than twice).
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
return NULL;
if (rb_per_cpu_empty(cpu_buffer))
@@ -3835,7 +3842,8 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
if (len > (commit - read))
len = (commit - read);
- size = rb_event_length(event);
+ /* Always keep the time extend and data together */
+ size = rb_event_ts_length(event);
if (len < size)
goto out_unlock;
@@ -3845,6 +3853,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
/* Need to copy one event at a time */
do {
+ /* We need the size of one event, because
+ * rb_advance_reader only advances by one event,
+ * whereas rb_event_ts_length may include the size of
+ * one or two events.
+ * We have already ensured there's enough space if this
+ * is a time extend. */
+ size = rb_event_length(event);
memcpy(bpage->data + pos, rpage->data + rpos, size);
len -= size;
@@ -3857,8 +3872,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
break;
event = rb_reader_event(cpu_buffer);
- size = rb_event_length(event);
- } while (len > size);
+ /* Always keep the time extend and data together */
+ size = rb_event_ts_length(event);
+ } while (len >= size);
/* update bpage */
local_set(&bpage->commit, pos);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 001bcd2ccf4..f8cf959bad4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
-#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
@@ -1284,6 +1283,8 @@ void trace_dump_stack(void)
__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
}
+static DEFINE_PER_CPU(int, user_stack_count);
+
void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
@@ -1302,6 +1303,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
if (unlikely(in_nmi()))
return;
+ /*
+ * prevent recursion, since the user stack tracing may
+ * trigger other kernel events.
+ */
+ preempt_disable();
+ if (__this_cpu_read(user_stack_count))
+ goto out;
+
+ __this_cpu_inc(user_stack_count);
+
+
+
event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
sizeof(*entry), flags, pc);
if (!event)
@@ -1319,6 +1332,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
save_stack_trace_user(&trace);
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
+
+ __this_cpu_dec(user_stack_count);
+
+ out:
+ preempt_enable();
}
#ifdef UNUSED
@@ -2320,11 +2338,19 @@ 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)
+{
+ if (file->f_mode & FMODE_READ)
+ return seq_lseek(file, offset, origin);
+ else
+ return 0;
+}
+
static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.write = tracing_write_stub,
- .llseek = seq_lseek,
+ .llseek = tracing_seek,
.release = tracing_release,
};
@@ -3996,13 +4022,9 @@ static void tracing_init_debugfs_percpu(long cpu)
{
struct dentry *d_percpu = tracing_dentry_percpu();
struct dentry *d_cpu;
- /* strlen(cpu) + MAX(log10(cpu)) + '\0' */
- char cpu_dir[7];
-
- if (cpu > 999 || cpu < 0)
- return;
+ char cpu_dir[30]; /* 30 characters should be more than enough */
- sprintf(cpu_dir, "cpu%ld", cpu);
+ snprintf(cpu_dir, 30, "cpu%ld", cpu);
d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
if (!d_cpu) {
pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 39c059ca670..19a359d5e6d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
/* Count the events in use (per event id, not per instance) */
static int total_ref_count;
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
+{
+ /* No tracing, just counting, so no obvious leak */
+ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+ return 0;
+
+ /* Some events are ok to be traced by non-root users... */
+ if (p_event->attach_state == PERF_ATTACH_TASK) {
+ if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+ return 0;
+ }
+
+ /*
+ * ...otherwise raw tracepoint data can be a severe data leak,
+ * only allow root to have these.
+ */
+ if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return 0;
+}
+
static int perf_trace_event_init(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
struct hlist_head __percpu *list;
- int ret = -ENOMEM;
+ int ret;
int cpu;
+ ret = perf_trace_event_perm(tp_event, p_event);
+ if (ret)
+ return ret;
+
p_event->tp_event = tp_event;
if (tp_event->perf_refcount++ > 0)
return 0;
+ ret = -ENOMEM;
+
list = alloc_percpu(struct hlist_head);
if (!list)
goto fail;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0725eeab193..35fde09b81d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,6 +27,12 @@
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);
LIST_HEAD(ftrace_common_fields);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4ba44deaac2..4b74d71705c 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -83,13 +83,19 @@ static void __always_unused ____ftrace_check_##name(void) \
#undef __array
#define __array(type, item, len) \
- BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ do { \
+ 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, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
- if (ret) \
- return ret;
+ mutex_unlock(&event_storage_mutex); \
+ if (ret) \
+ return ret; \
+ } while (0);
#undef __array_desc
#define __array_desc(type, container, item, len) \
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 7b8ecd751d9..3c5c5dfea0b 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -13,7 +13,6 @@
#include <linux/kdb.h>
#include <linux/ftrace.h>
-#include "../debug/kdb/kdb_private.h"
#include "trace.h"
#include "trace_output.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 544301d29de..2dec9bcde8b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -31,7 +31,6 @@
#include <linux/perf_event.h>
#include <linux/stringify.h>
#include <linux/limits.h>
-#include <linux/uaccess.h>
#include <asm/bitsperlong.h>
#include "trace.h"
@@ -648,7 +647,7 @@ static int register_trace_probe(struct trace_probe *tp)
}
ret = register_probe_event(tp);
if (ret) {
- pr_warning("Faild to register probe event(%d)\n", ret);
+ pr_warning("Failed to register probe event(%d)\n", ret);
goto end;
}
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 155a415b320..562c56e048f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -558,7 +558,7 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
static int trace_wakeup_test_thread(void *data)
{
/* Make this a RT thread, doesn't need to be too high */
- struct sched_param param = { .sched_priority = 5 };
+ static struct sched_param param = { .sched_priority = 5 };
struct completion *x = data;
sched_setscheduler(current, SCHED_FIFO, &param);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 0a67e041edf..24dc60d9fa1 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -63,12 +63,10 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
stats->ac_ppid = pid_alive(tsk) ?
rcu_dereference(tsk->real_parent)->tgid : 0;
rcu_read_unlock();
- stats->ac_utime = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC;
- stats->ac_stime = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC;
- stats->ac_utimescaled =
- cputime_to_msecs(tsk->utimescaled) * USEC_PER_MSEC;
- stats->ac_stimescaled =
- cputime_to_msecs(tsk->stimescaled) * USEC_PER_MSEC;
+ stats->ac_utime = cputime_to_usecs(tsk->utime);
+ stats->ac_stime = cputime_to_usecs(tsk->stime);
+ stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled);
+ stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled);
stats->ac_minflt = tsk->min_flt;
stats->ac_majflt = tsk->maj_flt;
diff --git a/kernel/user.c b/kernel/user.c
index 7e72614b736..5c598ca781d 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -91,6 +91,7 @@ static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
* upon function exit.
*/
static void free_user(struct user_struct *up, unsigned long flags)
+ __releases(&uidhash_lock)
{
uid_hash_remove(up);
spin_unlock_irqrestore(&uidhash_lock, flags);
@@ -157,6 +158,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
if (up) {
+ put_user_ns(ns);
key_put(new->uid_keyring);
key_put(new->session_keyring);
kmem_cache_free(uid_cachep, new);
diff --git a/kernel/wait.c b/kernel/wait.c
index c4bd3d825f3..b0310eb6cc1 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -92,7 +92,7 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
}
EXPORT_SYMBOL(prepare_to_wait_exclusive);
-/*
+/**
* finish_wait - clean up after waiting in a queue
* @q: waitqueue waited on
* @wait: wait descriptor
@@ -127,11 +127,11 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
}
EXPORT_SYMBOL(finish_wait);
-/*
+/**
* abort_exclusive_wait - abort exclusive waiting in a queue
* @q: waitqueue waited on
* @wait: wait descriptor
- * @state: runstate of the waiter to be woken
+ * @mode: runstate of the waiter to be woken
* @key: key to identify a wait bit queue or %NULL
*
* Sets current thread back to running state and removes
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index bafba687a6d..6e7b575ac33 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -43,7 +43,7 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
-static int __initdata no_watchdog;
+static int no_watchdog;
/* boot commands */
@@ -57,6 +57,8 @@ static int __init hardlockup_panic_setup(char *str)
{
if (!strncmp(str, "panic", 5))
hardlockup_panic = 1;
+ else if (!strncmp(str, "0", 1))
+ no_watchdog = 1;
return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -307,7 +309,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
*/
static int watchdog(void *unused)
{
- struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+ static struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
sched_setscheduler(current, SCHED_FIFO, &param);
@@ -364,7 +366,8 @@ static int watchdog_nmi_enable(int cpu)
goto out_save;
}
- printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
+ printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
+ cpu, PTR_ERR(event));
return PTR_ERR(event);
/* success path */
@@ -547,13 +550,13 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
.notifier_call = cpu_callback
};
-static int __init spawn_watchdog_task(void)
+void __init lockup_detector_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
if (no_watchdog)
- return 0;
+ return;
err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
WARN_ON(notifier_to_errno(err));
@@ -561,6 +564,5 @@ static int __init spawn_watchdog_task(void)
cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
- return 0;
+ return;
}
-early_initcall(spawn_watchdog_task);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f77afd93922..e785b0f2aea 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -42,9 +42,6 @@
#include <linux/lockdep.h>
#include <linux/idr.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
-
#include "workqueue_sched.h"
enum {
@@ -257,6 +254,9 @@ EXPORT_SYMBOL_GPL(system_long_wq);
EXPORT_SYMBOL_GPL(system_nrt_wq);
EXPORT_SYMBOL_GPL(system_unbound_wq);
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
#define for_each_busy_worker(worker, i, pos, gcwq) \
for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \
hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
@@ -310,21 +310,6 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
(cpu) < WORK_CPU_NONE; \
(cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))
-#ifdef CONFIG_LOCKDEP
-/**
- * in_workqueue_context() - in context of specified workqueue?
- * @wq: the workqueue of interest
- *
- * Checks lockdep state to see if the current task is executing from
- * within a workqueue item. This function exists only if lockdep is
- * enabled.
- */
-int in_workqueue_context(struct workqueue_struct *wq)
-{
- return lock_is_held(&wq->lockdep_map);
-}
-#endif
-
#ifdef CONFIG_DEBUG_OBJECTS_WORK
static struct debug_obj_descr work_debug_descr;
@@ -604,7 +589,9 @@ static bool keep_working(struct global_cwq *gcwq)
{
atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu);
- return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1;
+ return !list_empty(&gcwq->worklist) &&
+ (atomic_read(nr_running) <= 1 ||
+ gcwq->flags & GCWQ_HIGHPRI_PENDING);
}
/* Do we need a new worker? Called from manager. */
@@ -674,7 +661,7 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
{
struct worker *worker = kthread_data(task);
- if (likely(!(worker->flags & WORKER_NOT_RUNNING)))
+ if (!(worker->flags & WORKER_NOT_RUNNING))
atomic_inc(get_gcwq_nr_running(cpu));
}
@@ -700,7 +687,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task,
struct global_cwq *gcwq = get_gcwq(cpu);
atomic_t *nr_running = get_gcwq_nr_running(cpu);
- if (unlikely(worker->flags & WORKER_NOT_RUNNING))
+ if (worker->flags & WORKER_NOT_RUNNING)
return NULL;
/* this can only happen on the local cpu */
@@ -997,6 +984,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
/* gcwq determined, get cwq and queue */
cwq = get_cwq(gcwq->cpu, wq);
+ trace_workqueue_queue_work(cpu, cwq, work);
BUG_ON(!list_empty(&work->entry));
@@ -1004,6 +992,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
work_flags = work_color_to_flags(cwq->work_color);
if (likely(cwq->nr_active < cwq->max_active)) {
+ trace_workqueue_activate_work(work);
cwq->nr_active++;
worklist = gcwq_determine_ins_pos(gcwq, cwq);
} else {
@@ -1679,6 +1668,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
struct work_struct, entry);
struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
+ trace_workqueue_activate_work(work);
move_linked_works(work, pos, NULL);
__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
cwq->nr_active++;
@@ -2074,7 +2064,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
* checks and call back into the fixup functions where we
* might deadlock.
*/
- INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
+ INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
init_completion(&barr->done);
@@ -2326,27 +2316,17 @@ out_unlock:
}
EXPORT_SYMBOL_GPL(flush_workqueue);
-/**
- * flush_work - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns false if @work has already terminated.
- *
- * It is expected that, prior to calling flush_work(), the caller has
- * arranged for the work to not be requeued, otherwise it doesn't make
- * sense to use this function.
- */
-int flush_work(struct work_struct *work)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+ bool wait_executing)
{
struct worker *worker = NULL;
struct global_cwq *gcwq;
struct cpu_workqueue_struct *cwq;
- struct wq_barrier barr;
might_sleep();
gcwq = get_work_gcwq(work);
if (!gcwq)
- return 0;
+ return false;
spin_lock_irq(&gcwq->lock);
if (!list_empty(&work->entry)) {
@@ -2359,28 +2339,127 @@ int flush_work(struct work_struct *work)
cwq = get_work_cwq(work);
if (unlikely(!cwq || gcwq != cwq->gcwq))
goto already_gone;
- } else {
+ } else if (wait_executing) {
worker = find_worker_executing_work(gcwq, work);
if (!worker)
goto already_gone;
cwq = worker->current_cwq;
- }
+ } else
+ goto already_gone;
- insert_wq_barrier(cwq, &barr, work, worker);
+ insert_wq_barrier(cwq, barr, work, worker);
spin_unlock_irq(&gcwq->lock);
lock_map_acquire(&cwq->wq->lockdep_map);
lock_map_release(&cwq->wq->lockdep_map);
-
- wait_for_completion(&barr.done);
- destroy_work_on_stack(&barr.work);
- return 1;
+ return true;
already_gone:
spin_unlock_irq(&gcwq->lock);
- return 0;
+ return false;
+}
+
+/**
+ * flush_work - wait for a work to finish executing the last queueing instance
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution. This function considers
+ * only the last queueing instance of @work. If @work has been
+ * enqueued across different CPUs on a non-reentrant workqueue or on
+ * multiple workqueues, @work might still be executing on return on
+ * some of the CPUs from earlier queueing.
+ *
+ * If @work was queued only on a non-reentrant, ordered or unbound
+ * workqueue, @work is guaranteed to be idle on return if it hasn't
+ * been requeued since flush started.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work(struct work_struct *work)
+{
+ struct wq_barrier barr;
+
+ if (start_flush_work(work, &barr, true)) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ return true;
+ } else
+ return false;
}
EXPORT_SYMBOL_GPL(flush_work);
+static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
+{
+ struct wq_barrier barr;
+ struct worker *worker;
+
+ spin_lock_irq(&gcwq->lock);
+
+ worker = find_worker_executing_work(gcwq, work);
+ if (unlikely(worker))
+ insert_wq_barrier(worker->current_cwq, &barr, work, worker);
+
+ spin_unlock_irq(&gcwq->lock);
+
+ if (unlikely(worker)) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ return true;
+ } else
+ return false;
+}
+
+static bool wait_on_work(struct work_struct *work)
+{
+ bool ret = false;
+ int cpu;
+
+ might_sleep();
+
+ lock_map_acquire(&work->lockdep_map);
+ lock_map_release(&work->lockdep_map);
+
+ for_each_gcwq_cpu(cpu)
+ ret |= wait_on_cpu_work(get_gcwq(cpu), work);
+ return ret;
+}
+
+/**
+ * flush_work_sync - wait until a work has finished execution
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution. On return, it's
+ * guaranteed that all queueing instances of @work which happened
+ * before this function is called are finished. In other words, if
+ * @work hasn't been requeued since this function was called, @work is
+ * guaranteed to be idle on return.
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work_sync(struct work_struct *work)
+{
+ struct wq_barrier barr;
+ bool pending, waited;
+
+ /* we'll wait for executions separately, queue barr only if pending */
+ pending = start_flush_work(work, &barr, false);
+
+ /* wait for executions to finish */
+ waited = wait_on_work(work);
+
+ /* wait for the pending one */
+ if (pending) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
+
+ return pending || waited;
+}
+EXPORT_SYMBOL_GPL(flush_work_sync);
+
/*
* Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
* so this work can't be re-armed in any way.
@@ -2423,39 +2502,7 @@ static int try_to_grab_pending(struct work_struct *work)
return ret;
}
-static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
-{
- struct wq_barrier barr;
- struct worker *worker;
-
- spin_lock_irq(&gcwq->lock);
-
- worker = find_worker_executing_work(gcwq, work);
- if (unlikely(worker))
- insert_wq_barrier(worker->current_cwq, &barr, work, worker);
-
- spin_unlock_irq(&gcwq->lock);
-
- if (unlikely(worker)) {
- wait_for_completion(&barr.done);
- destroy_work_on_stack(&barr.work);
- }
-}
-
-static void wait_on_work(struct work_struct *work)
-{
- int cpu;
-
- might_sleep();
-
- lock_map_acquire(&work->lockdep_map);
- lock_map_release(&work->lockdep_map);
-
- for_each_gcwq_cpu(cpu)
- wait_on_cpu_work(get_gcwq(cpu), work);
-}
-
-static int __cancel_work_timer(struct work_struct *work,
+static bool __cancel_work_timer(struct work_struct *work,
struct timer_list* timer)
{
int ret;
@@ -2472,42 +2519,81 @@ static int __cancel_work_timer(struct work_struct *work,
}
/**
- * cancel_work_sync - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns true if @work was pending.
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
*
- * cancel_work_sync() will cancel the work if it is queued. If the work's
- * callback appears to be running, cancel_work_sync() will block until it
- * has completed.
+ * Cancel @work and wait for its execution to finish. This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue. On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
*
- * It is possible to use this function if the work re-queues itself. It can
- * cancel the work even if it migrates to another workqueue, however in that
- * case it only guarantees that work->func() has completed on the last queued
- * workqueue.
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's. Use cancel_delayed_work_sync() instead.
*
- * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
- * pending, otherwise it goes into a busy-wait loop until the timer expires.
- *
- * The caller must ensure that workqueue_struct on which this work was last
+ * The caller must ensure that the workqueue on which @work was last
* queued can't be destroyed before this function returns.
+ *
+ * RETURNS:
+ * %true if @work was pending, %false otherwise.
*/
-int cancel_work_sync(struct work_struct *work)
+bool cancel_work_sync(struct work_struct *work)
{
return __cancel_work_timer(work, NULL);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);
/**
- * cancel_delayed_work_sync - reliably kill off a delayed work.
- * @dwork: the delayed work struct
+ * flush_delayed_work - wait for a dwork to finish executing the last queueing
+ * @dwork: the delayed work to flush
+ *
+ * Delayed timer is cancelled and the pending work is queued for
+ * immediate execution. Like flush_work(), this function only
+ * considers the last queueing instance of @dwork.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_delayed_work(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer))
+ __queue_work(raw_smp_processor_id(),
+ get_work_cwq(&dwork->work)->wq, &dwork->work);
+ return flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
+ * flush_delayed_work_sync - wait for a dwork to finish
+ * @dwork: the delayed work to flush
*
- * Returns true if @dwork was pending.
+ * Delayed timer is cancelled and the pending work is queued for
+ * execution immediately. Other than timer handling, its behavior
+ * is identical to flush_work_sync().
*
- * It is possible to use this function if @dwork rearms itself via queue_work()
- * or queue_delayed_work(). See also the comment for cancel_work_sync().
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
*/
-int cancel_delayed_work_sync(struct delayed_work *dwork)
+bool flush_delayed_work_sync(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer))
+ __queue_work(raw_smp_processor_id(),
+ get_work_cwq(&dwork->work)->wq, &dwork->work);
+ return flush_work_sync(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work_sync);
+
+/**
+ * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
+ * @dwork: the delayed work cancel
+ *
+ * This is cancel_work_sync() for delayed works.
+ *
+ * RETURNS:
+ * %true if @dwork was pending, %false otherwise.
+ */
+bool cancel_delayed_work_sync(struct delayed_work *dwork)
{
return __cancel_work_timer(&dwork->work, &dwork->timer);
}
@@ -2559,23 +2645,6 @@ int schedule_delayed_work(struct delayed_work *dwork,
EXPORT_SYMBOL(schedule_delayed_work);
/**
- * flush_delayed_work - block until a dwork_struct's callback has terminated
- * @dwork: the delayed work which is to be flushed
- *
- * Any timeout is cancelled, and any pending work is run immediately.
- */
-void flush_delayed_work(struct delayed_work *dwork)
-{
- if (del_timer_sync(&dwork->timer)) {
- __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq,
- &dwork->work);
- put_cpu();
- }
- flush_work(&dwork->work);
-}
-EXPORT_SYMBOL(flush_delayed_work);
-
-/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
@@ -2592,13 +2661,15 @@ int schedule_delayed_work_on(int cpu,
EXPORT_SYMBOL(schedule_delayed_work_on);
/**
- * schedule_on_each_cpu - call a function on each online CPU from keventd
+ * schedule_on_each_cpu - execute a function synchronously on each online CPU
* @func: the function to call
*
- * Returns zero on success.
- * Returns -ve errno on failure.
- *
+ * schedule_on_each_cpu() executes @func on each online CPU using the
+ * system workqueue and blocks until all CPUs have completed.
* schedule_on_each_cpu() is very slow.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
*/
int schedule_on_each_cpu(work_func_t func)
{
@@ -2720,7 +2791,9 @@ static int alloc_cwqs(struct workqueue_struct *wq)
}
}
- /* just in case, make sure it's actually aligned */
+ /* just in case, make sure it's actually aligned
+ * - this is affected by PERCPU() alignment in vmlinux.lds.S
+ */
BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align));
return wq->cpu_wq.v ? 0 : -ENOMEM;
}
@@ -2764,6 +2837,13 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
unsigned int cpu;
/*
+ * Workqueues which may be used during memory reclaim should
+ * have a rescuer to guarantee forward progress.
+ */
+ if (flags & WQ_MEM_RECLAIM)
+ flags |= WQ_RESCUER;
+
+ /*
* Unbound workqueues aren't concurrency managed and should be
* dispatched to workers immediately.
*/
@@ -3612,7 +3692,8 @@ static int __init init_workqueues(void)
system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0);
system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
WQ_UNBOUND_MAX_ACTIVE);
- BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq);
+ BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq ||
+ !system_unbound_wq);
return 0;
}
early_initcall(init_workqueues);