summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c31
-rw-r--r--kernel/audit.h2
-rw-r--r--kernel/audit_tree.c2
-rw-r--r--kernel/audit_watch.c2
-rw-r--r--kernel/auditfilter.c10
-rw-r--r--kernel/cgroup.c60
-rw-r--r--kernel/cpuset.c10
-rw-r--r--kernel/events/core.c12
-rw-r--r--kernel/irq/irqdomain.c1
-rw-r--r--kernel/irq/manage.c3
-rw-r--r--kernel/power/console.c1
-rw-r--r--kernel/power/qos.c18
-rw-r--r--kernel/printk/printk.c2
-rw-r--r--kernel/profile.c4
-rw-r--r--kernel/sched/clock.c4
-rw-r--r--kernel/sched/core.c37
-rw-r--r--kernel/sched/cpudeadline.c6
-rw-r--r--kernel/sched/deadline.c20
-rw-r--r--kernel/sched/fair.c10
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/sched/sched.h1
-rw-r--r--kernel/stop_machine.c2
-rw-r--r--kernel/time/sched_clock.c46
-rw-r--r--kernel/trace/trace_events.c10
-rw-r--r--kernel/tracepoint.c7
-rw-r--r--kernel/user_namespace.c2
-rw-r--r--kernel/workqueue.c7
27 files changed, 191 insertions, 127 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 34c5a2310fbf..3392d3e0254a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -182,7 +182,7 @@ struct audit_buffer {
struct audit_reply {
__u32 portid;
- pid_t pid;
+ struct net *net;
struct sk_buff *skb;
};
@@ -500,7 +500,7 @@ int audit_send_list(void *_dest)
{
struct audit_netlink_list *dest = _dest;
struct sk_buff *skb;
- struct net *net = get_net_ns_by_pid(dest->pid);
+ struct net *net = dest->net;
struct audit_net *aunet = net_generic(net, audit_net_id);
/* wait for parent to finish and send an ACK */
@@ -510,6 +510,7 @@ int audit_send_list(void *_dest)
while ((skb = __skb_dequeue(&dest->q)) != NULL)
netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
+ put_net(net);
kfree(dest);
return 0;
@@ -543,7 +544,7 @@ out_kfree_skb:
static int audit_send_reply_thread(void *arg)
{
struct audit_reply *reply = (struct audit_reply *)arg;
- struct net *net = get_net_ns_by_pid(reply->pid);
+ struct net *net = reply->net;
struct audit_net *aunet = net_generic(net, audit_net_id);
mutex_lock(&audit_cmd_mutex);
@@ -552,12 +553,13 @@ static int audit_send_reply_thread(void *arg)
/* Ignore failure. It'll only happen if the sender goes away,
because our timeout is set to infinite. */
netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
+ put_net(net);
kfree(reply);
return 0;
}
/**
* audit_send_reply - send an audit reply message via netlink
- * @portid: netlink port to which to send reply
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: sequence number
* @type: audit message type
* @done: done (last) flag
@@ -568,9 +570,11 @@ static int audit_send_reply_thread(void *arg)
* Allocates an skb, builds the netlink message, and sends it to the port id.
* No failure notifications.
*/
-static void audit_send_reply(__u32 portid, int seq, int type, int done,
+static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
int multi, const void *payload, int size)
{
+ u32 portid = NETLINK_CB(request_skb).portid;
+ struct net *net = sock_net(NETLINK_CB(request_skb).sk);
struct sk_buff *skb;
struct task_struct *tsk;
struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
@@ -583,8 +587,8 @@ static void audit_send_reply(__u32 portid, int seq, int type, int done,
if (!skb)
goto out;
+ reply->net = get_net(net);
reply->portid = portid;
- reply->pid = task_pid_vnr(current);
reply->skb = skb;
tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
@@ -673,8 +677,7 @@ static int audit_get_feature(struct sk_buff *skb)
seq = nlmsg_hdr(skb)->nlmsg_seq;
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
- &af, sizeof(af));
+ audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
return 0;
}
@@ -794,8 +797,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.backlog = skb_queue_len(&audit_skb_queue);
s.version = AUDIT_VERSION_LATEST;
s.backlog_wait_time = audit_backlog_wait_time;
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
- &s, sizeof(s));
+ audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_SET: {
@@ -905,7 +907,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
seq, data, nlmsg_len(nlh));
break;
case AUDIT_LIST_RULES:
- err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+ err = audit_list_rules_send(skb, seq);
break;
case AUDIT_TRIM:
audit_trim_trees();
@@ -970,8 +972,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
memcpy(sig_data->ctx, ctx, len);
security_release_secctx(ctx, len);
}
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO,
- 0, 0, sig_data, sizeof(*sig_data) + len);
+ audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
+ sig_data, sizeof(*sig_data) + len);
kfree(sig_data);
break;
case AUDIT_TTY_GET: {
@@ -983,8 +985,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.log_passwd = tsk->signal->audit_tty_log_passwd;
spin_unlock(&tsk->sighand->siglock);
- audit_send_reply(NETLINK_CB(skb).portid, seq,
- AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
+ audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_TTY_SET: {
diff --git a/kernel/audit.h b/kernel/audit.h
index 57cc64d67718..8df132214606 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -247,7 +247,7 @@ extern void audit_panic(const char *message);
struct audit_netlink_list {
__u32 portid;
- pid_t pid;
+ struct net *net;
struct sk_buff_head q;
};
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 67ccf0e7cca9..135944a7b28a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -916,7 +916,7 @@ static int audit_tree_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
return 0;
}
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 2596fac5dcb4..70b4554d2fbe 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -471,7 +471,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *dname)
+ const unsigned char *dname, u32 cookie)
{
struct inode *inode;
struct audit_parent *parent;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 14a78cca384e..92062fd6cc8c 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -29,6 +29,8 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
#include "audit.h"
/*
@@ -1065,11 +1067,13 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data,
/**
* audit_list_rules_send - list the audit rules
- * @portid: target portid for netlink audit messages
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: netlink audit message sequence (serial) number
*/
-int audit_list_rules_send(__u32 portid, int seq)
+int audit_list_rules_send(struct sk_buff *request_skb, int seq)
{
+ u32 portid = NETLINK_CB(request_skb).portid;
+ struct net *net = sock_net(NETLINK_CB(request_skb).sk);
struct task_struct *tsk;
struct audit_netlink_list *dest;
int err = 0;
@@ -1083,8 +1087,8 @@ int audit_list_rules_send(__u32 portid, int seq)
dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
if (!dest)
return -ENOMEM;
+ dest->net = get_net(net);
dest->portid = portid;
- dest->pid = task_pid_vnr(current);
skb_queue_head_init(&dest->q);
mutex_lock(&audit_filter_mutex);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2f46ba37f72..105f273b6f86 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -886,7 +886,9 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
* per-subsystem and moved to css->id so that lookups are
* successful until the target css is released.
*/
+ mutex_lock(&cgroup_mutex);
idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ mutex_unlock(&cgroup_mutex);
cgrp->id = -1;
call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
@@ -1566,10 +1568,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
mutex_lock(&cgroup_mutex);
mutex_lock(&cgroup_root_mutex);
- root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
- 0, 1, GFP_KERNEL);
- if (root_cgrp->id < 0)
+ ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+ if (ret < 0)
goto unlock_drop;
+ root_cgrp->id = ret;
/* Check for name clashes with existing mounts */
ret = -EBUSY;
@@ -2763,10 +2765,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
*/
update_before = cgroup_serial_nr_next;
- mutex_unlock(&cgroup_mutex);
-
/* add/rm files for all cgroups created before */
- rcu_read_lock();
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
@@ -2775,23 +2774,19 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
inode = cgrp->dentry->d_inode;
dget(cgrp->dentry);
- rcu_read_unlock();
-
dput(prev);
prev = cgrp->dentry;
+ mutex_unlock(&cgroup_mutex);
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
ret = cgroup_addrm_files(cgrp, cfts, is_add);
- mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
-
- rcu_read_lock();
if (ret)
break;
}
- rcu_read_unlock();
+ mutex_unlock(&cgroup_mutex);
dput(prev);
deactivate_super(sb);
return ret;
@@ -2910,9 +2905,14 @@ static void cgroup_enable_task_cg_lists(void)
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
+ * Do it while holding siglock so that we don't end up
+ * racing against cgroup_exit().
*/
+ spin_lock_irq(&p->sighand->siglock);
if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
list_add(&p->cg_list, &task_css_set(p)->tasks);
+ spin_unlock_irq(&p->sighand->siglock);
+
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
@@ -4158,7 +4158,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
struct cgroup *cgrp;
struct cgroup_name *name;
struct cgroupfs_root *root = parent->root;
- int ssid, err = 0;
+ int ssid, err;
struct cgroup_subsys *ss;
struct super_block *sb = root->sb;
@@ -4168,19 +4168,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
return -ENOMEM;
name = cgroup_alloc_name(dentry);
- if (!name)
+ if (!name) {
+ err = -ENOMEM;
goto err_free_cgrp;
+ }
rcu_assign_pointer(cgrp->name, name);
/*
- * Temporarily set the pointer to NULL, so idr_find() won't return
- * a half-baked cgroup.
- */
- cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
- if (cgrp->id < 0)
- goto err_free_name;
-
- /*
* Only live parents can have children. Note that the liveliness
* check isn't strictly necessary because cgroup_mkdir() and
* cgroup_rmdir() are fully synchronized by i_mutex; however, do it
@@ -4189,7 +4183,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
*/
if (!cgroup_lock_live_group(parent)) {
err = -ENODEV;
- goto err_free_id;
+ goto err_free_name;
+ }
+
+ /*
+ * Temporarily set the pointer to NULL, so idr_find() won't return
+ * a half-baked cgroup.
+ */
+ cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+ if (cgrp->id < 0) {
+ err = -ENOMEM;
+ goto err_unlock;
}
/* Grab a reference on the superblock so the hierarchy doesn't
@@ -4221,7 +4225,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
*/
err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
if (err < 0)
- goto err_unlock;
+ goto err_free_id;
lockdep_assert_held(&dentry->d_inode->i_mutex);
cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4257,12 +4261,12 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
return 0;
-err_unlock:
- mutex_unlock(&cgroup_mutex);
- /* Release the reference count that we took on the superblock */
- deactivate_super(sb);
err_free_id:
idr_remove(&root->cgroup_idr, cgrp->id);
+ /* Release the reference count that we took on the superblock */
+ deactivate_super(sb);
+err_unlock:
+ mutex_unlock(&cgroup_mutex);
err_free_name:
kfree(rcu_dereference_raw(cgrp->name));
err_free_cgrp:
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4410ac6a55f1..e6b1b66afe52 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -974,12 +974,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
* Temporarilly set tasks mems_allowed to target nodes of migration,
* so that the migration code can allocate pages on these nodes.
*
- * Call holding cpuset_mutex, so current's cpuset won't change
- * during this call, as manage_mutex holds off any cpuset_attach()
- * calls. Therefore we don't need to take task_lock around the
- * call to guarantee_online_mems(), as we know no one is changing
- * our task's cpuset.
- *
* While the mm_struct we are migrating is typically from some
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
@@ -996,8 +990,10 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+ rcu_read_lock();
mems_cs = effective_nodemask_cpuset(task_cs(tsk));
guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+ rcu_read_unlock();
}
/*
@@ -2486,9 +2482,9 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
task_lock(current);
cs = nearest_hardwall_ancestor(task_cs(current));
+ allowed = node_isset(node, cs->mems_allowed);
task_unlock(current);
- allowed = node_isset(node, cs->mems_allowed);
mutex_unlock(&callback_mutex);
return allowed;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6edfd3..fa0b2d4ad83c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7856,14 +7856,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
static void __perf_event_exit_context(void *__info)
{
struct perf_event_context *ctx = __info;
- struct perf_event *event, *tmp;
+ struct perf_event *event;
perf_pmu_rotate_stop(ctx->pmu);
- list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
- __perf_remove_from_context(event);
- list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
+ rcu_read_lock();
+ list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
__perf_remove_from_context(event);
+ rcu_read_unlock();
}
static void perf_event_exit_cpu_context(int cpu)
@@ -7887,11 +7887,11 @@ static void perf_event_exit_cpu(int cpu)
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
+ perf_event_exit_cpu_context(cpu);
+
mutex_lock(&swhash->hlist_mutex);
swevent_hlist_release(swhash);
mutex_unlock(&swhash->hlist_mutex);
-
- perf_event_exit_cpu_context(cpu);
}
#else
static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf68bb36fe58..f14033700c25 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_irq.h>
#include <linux/topology.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 481a13c43b17..d3bf660cb57f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -802,8 +802,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
static void wake_threads_waitq(struct irq_desc *desc)
{
- if (atomic_dec_and_test(&desc->threads_active) &&
- waitqueue_active(&desc->wait_for_threads))
+ if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
diff --git a/kernel/power/console.c b/kernel/power/console.c
index eacb8bd8cab4..aba9c545a0e3 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -9,6 +9,7 @@
#include <linux/kbd_kern.h>
#include <linux/vt.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include "power.h"
#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 8dff9b48075a..884b77058864 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -66,6 +66,7 @@ static struct pm_qos_constraints cpu_dma_constraints = {
.list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
.type = PM_QOS_MIN,
.notifiers = &cpu_dma_lat_notifier,
};
@@ -79,6 +80,7 @@ static struct pm_qos_constraints network_lat_constraints = {
.list = PLIST_HEAD_INIT(network_lat_constraints.list),
.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
.type = PM_QOS_MIN,
.notifiers = &network_lat_notifier,
};
@@ -93,6 +95,7 @@ static struct pm_qos_constraints network_tput_constraints = {
.list = PLIST_HEAD_INIT(network_tput_constraints.list),
.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+ .no_constraint_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
.type = PM_QOS_MAX,
.notifiers = &network_throughput_notifier,
};
@@ -128,7 +131,7 @@ static const struct file_operations pm_qos_power_fops = {
static inline int pm_qos_get_value(struct pm_qos_constraints *c)
{
if (plist_head_empty(&c->list))
- return c->default_value;
+ return c->no_constraint_value;
switch (c->type) {
case PM_QOS_MIN:
@@ -170,6 +173,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
{
unsigned long flags;
int prev_value, curr_value, new_value;
+ int ret;
spin_lock_irqsave(&pm_qos_lock, flags);
prev_value = pm_qos_get_value(c);
@@ -205,13 +209,15 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
trace_pm_qos_update_target(action, prev_value, curr_value);
if (prev_value != curr_value) {
- blocking_notifier_call_chain(c->notifiers,
- (unsigned long)curr_value,
- NULL);
- return 1;
+ ret = 1;
+ if (c->notifiers)
+ blocking_notifier_call_chain(c->notifiers,
+ (unsigned long)curr_value,
+ NULL);
} else {
- return 0;
+ ret = 0;
}
+ return ret;
}
/**
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index b1d255f04135..4dae9cbe9259 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1076,7 +1076,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
next_seq = log_next_seq;
len = 0;
- prev = 0;
while (len >= 0 && seq < next_seq) {
struct printk_log *msg = log_from_idx(idx);
int textlen;
@@ -2788,7 +2787,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
next_idx = idx;
l = 0;
- prev = 0;
while (seq < dumper->next_seq) {
struct printk_log *msg = log_from_idx(idx);
diff --git a/kernel/profile.c b/kernel/profile.c
index 6631e1ef55ab..ebdd9c1a86b4 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -549,14 +549,14 @@ static int create_hash_tables(void)
struct page *page;
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 43c2bcc35761..b30a2924ef14 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu)
if (unlikely(!sched_clock_running))
return 0ull;
- preempt_disable();
+ preempt_disable_notrace();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
- preempt_enable();
+ preempt_enable_notrace();
return clock;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b46131ef6aab..f5c6635b806c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1952,7 +1952,7 @@ static int dl_overflow(struct task_struct *p, int policy,
{
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
- u64 period = attr->sched_period;
+ u64 period = attr->sched_period ?: attr->sched_deadline;
u64 runtime = attr->sched_runtime;
u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
int cpus, err = -1;
@@ -3338,6 +3338,15 @@ recheck:
return -EPERM;
}
+ /*
+ * Can't set/change SCHED_DEADLINE policy at all for now
+ * (safest behavior); in the future we would like to allow
+ * unprivileged DL tasks to increase their relative deadline
+ * or reduce their runtime (both ways reducing utilization)
+ */
+ if (dl_policy(policy))
+ return -EPERM;
+
/*
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
@@ -3661,13 +3670,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
*/
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, flags)
{
struct sched_attr attr;
struct task_struct *p;
int retval;
- if (!uattr || pid < 0)
+ if (!uattr || pid < 0 || flags)
return -EINVAL;
if (sched_copy_attr(uattr, &attr))
@@ -3786,7 +3796,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
attr->size = usize;
}
- ret = copy_to_user(uattr, attr, usize);
+ ret = copy_to_user(uattr, attr, attr->size);
if (ret)
return -EFAULT;
@@ -3804,8 +3814,8 @@ err_size:
* @uattr: structure containing the extended parameters.
* @size: sizeof(attr) for fwd/bwd comp.
*/
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
- unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, size, unsigned int, flags)
{
struct sched_attr attr = {
.size = sizeof(struct sched_attr),
@@ -3814,7 +3824,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
int retval;
if (!uattr || pid < 0 || size > PAGE_SIZE ||
- size < SCHED_ATTR_SIZE_VER0)
+ size < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
@@ -7422,6 +7432,7 @@ static int sched_dl_global_constraints(void)
u64 period = global_rt_period();
u64 new_bw = to_ratio(period, runtime);
int cpu, ret = 0;
+ unsigned long flags;
/*
* Here we want to check the bandwidth not being set to some
@@ -7435,10 +7446,10 @@ static int sched_dl_global_constraints(void)
for_each_possible_cpu(cpu) {
struct dl_bw *dl_b = dl_bw_of(cpu);
- raw_spin_lock(&dl_b->lock);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
if (new_bw < dl_b->total_bw)
ret = -EBUSY;
- raw_spin_unlock(&dl_b->lock);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
if (ret)
break;
@@ -7451,6 +7462,7 @@ static void sched_dl_do_global(void)
{
u64 new_bw = -1;
int cpu;
+ unsigned long flags;
def_dl_bandwidth.dl_period = global_rt_period();
def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7464,9 +7476,9 @@ static void sched_dl_do_global(void)
for_each_possible_cpu(cpu) {
struct dl_bw *dl_b = dl_bw_of(cpu);
- raw_spin_lock(&dl_b->lock);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
dl_b->bw = new_bw;
- raw_spin_unlock(&dl_b->lock);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
}
}
@@ -7475,7 +7487,8 @@ static int sched_rt_global_validate(void)
if (sysctl_sched_rt_period <= 0)
return -EINVAL;
- if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+ if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+ (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
return -EINVAL;
return 0;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 045fc74e3f09..5b9bb42b2d47 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)
static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
{
- WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+ WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
if (dl_time_before(new_dl, cp->elements[idx].dl)) {
cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
}
out:
- WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+ WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
return best_cpu;
}
@@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
int old_idx, new_cpu;
unsigned long flags;
- WARN_ON(cpu > num_present_cpus());
+ WARN_ON(!cpu_present(cpu));
raw_spin_lock_irqsave(&cp->lock, flags);
old_idx = cp->cpu_to_idx[cpu];
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0dd5e0971a07..6e79b3faa4cd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq)
static void update_dl_migration(struct dl_rq *dl_rq)
{
- if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+ if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
if (!dl_rq->overloaded) {
dl_set_overload(rq_of_dl_rq(dl_rq));
dl_rq->overloaded = 1;
@@ -135,9 +135,7 @@ static void update_dl_migration(struct dl_rq *dl_rq)
static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
- dl_rq = &rq_of_dl_rq(dl_rq)->dl;
- dl_rq->dl_nr_total++;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory++;
@@ -147,9 +145,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
- dl_rq = &rq_of_dl_rq(dl_rq)->dl;
- dl_rq->dl_nr_total--;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory--;
@@ -566,6 +562,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
return 1;
}
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
/*
* Update the current task's runtime statistics (provided it is still
* a -deadline task and has not been removed from the dl_rq).
@@ -629,11 +627,13 @@ static void update_curr_dl(struct rq *rq)
struct rt_rq *rt_rq = &rq->rt;
raw_spin_lock(&rt_rq->rt_runtime_lock);
- rt_rq->rt_time += delta_exec;
/*
* We'll let actual RT tasks worry about the overflow here, we
- * have our own CBS to keep us inline -- see above.
+ * have our own CBS to keep us inline; only account when RT
+ * bandwidth is relevant.
*/
+ if (sched_rt_bandwidth_account(rt_rq))
+ rt_rq->rt_time += delta_exec;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
}
@@ -717,6 +717,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_prio(prio));
dl_rq->dl_nr_running++;
+ inc_nr_running(rq_of_dl_rq(dl_rq));
inc_dl_deadline(dl_rq, deadline);
inc_dl_migration(dl_se, dl_rq);
@@ -730,6 +731,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_prio(prio));
WARN_ON(!dl_rq->dl_nr_running);
dl_rq->dl_nr_running--;
+ dec_nr_running(rq_of_dl_rq(dl_rq));
dec_dl_deadline(dl_rq, dl_se->deadline);
dec_dl_migration(dl_se, dl_rq);
@@ -836,8 +838,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
-
- inc_nr_running(rq);
}
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -850,8 +850,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
update_curr_dl(rq);
__dequeue_task_dl(rq, p, flags);
-
- dec_nr_running(rq);
}
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 966cc2bfcb77..9b4c4f320130 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1757,6 +1757,8 @@ void task_numa_work(struct callback_head *work)
start = end;
if (pages <= 0)
goto out;
+
+ cond_resched();
} while (end != vma->vm_end);
}
@@ -6999,15 +7001,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when its
+ * Ensure the task's vruntime is normalized, so that when it's
* switched back to the fair class the enqueue_entity(.flags=0) will
* do the right thing.
*
- * If it was on_rq, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it was !on_rq, then only when
+ * If it's on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it's !on_rq, then only when
* the task is sleeping will it still have non-normalized vruntime.
*/
- if (!se->on_rq && p->state != TASK_RUNNING) {
+ if (!p->on_rq && p->state != TASK_RUNNING) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b775b45..1999021042c7 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -538,6 +538,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
#endif /* CONFIG_RT_GROUP_SCHED */
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+ return (hrtimer_active(&rt_b->rt_period_timer) ||
+ rt_rq->rt_time < rt_b->rt_runtime);
+}
+
#ifdef CONFIG_SMP
/*
* We ran out of runtime, see if we can borrow some from our neighbours.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2119fd20f8b..f964add50f38 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -462,7 +462,6 @@ struct dl_rq {
} earliest_dl;
unsigned long dl_nr_migratory;
- unsigned long dl_nr_total;
int overloaded;
/*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 84571e09c907..01fbae5b97b7 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
*/
smp_call_function_single(min(cpu1, cpu2),
&irq_cpu_stop_queue_work,
- &call_args, 0);
+ &call_args, 1);
lg_local_unlock(&stop_cpus_lock);
preempt_enable();
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0abb36464281..4d23dc4d8139 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -116,20 +116,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
void __init sched_clock_register(u64 (*read)(void), int bits,
unsigned long rate)
{
+ u64 res, wrap, new_mask, new_epoch, cyc, ns;
+ u32 new_mult, new_shift;
+ ktime_t new_wrap_kt;
unsigned long r;
- u64 res, wrap;
char r_unit;
if (cd.rate > rate)
return;
WARN_ON(!irqs_disabled());
- read_sched_clock = read;
- sched_clock_mask = CLOCKSOURCE_MASK(bits);
- cd.rate = rate;
/* calculate the mult/shift to convert counter ticks to ns. */
- clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+ new_mask = CLOCKSOURCE_MASK(bits);
+
+ /* calculate how many ns until we wrap */
+ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+ new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+ /* update epoch for new counter and update epoch_ns from old counter*/
+ new_epoch = read();
+ cyc = read_sched_clock();
+ ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+ cd.mult, cd.shift);
+
+ raw_write_seqcount_begin(&cd.seq);
+ read_sched_clock = read;
+ sched_clock_mask = new_mask;
+ cd.rate = rate;
+ cd.wrap_kt = new_wrap_kt;
+ cd.mult = new_mult;
+ cd.shift = new_shift;
+ cd.epoch_cyc = new_epoch;
+ cd.epoch_ns = ns;
+ raw_write_seqcount_end(&cd.seq);
r = rate;
if (r >= 4000000) {
@@ -141,22 +163,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
} else
r_unit = ' ';
- /* calculate how many ns until we wrap */
- wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
- cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
/* calculate the ns resolution of this counter */
- res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+ res = cyc_to_ns(1ULL, new_mult, new_shift);
+
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
- update_sched_clock();
-
- /*
- * Ensure that sched_clock() starts off at 0ns
- */
- cd.epoch_ns = 0;
-
/* Enable IRQ time accounting if we have a fast enough sched_clock */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4eccb5..f3989ceb5cd5 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1777,6 +1777,16 @@ static void trace_module_add_events(struct module *mod)
{
struct ftrace_event_call **call, **start, **end;
+ if (!mod->num_trace_events)
+ return;
+
+ /* Don't add infrastructure for mods without tracepoints */
+ if (trace_module_has_bad_taint(mod)) {
+ pr_err("%s: module has bad taint, not creating trace events\n",
+ mod->name);
+ return;
+ }
+
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f26540e9c9..031cc5655a51 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,6 +631,11 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
#ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+ return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
static int tracepoint_module_coming(struct module *mod)
{
struct tp_module *tp_mod, *iter;
@@ -641,7 +646,7 @@ static int tracepoint_module_coming(struct module *mod)
* module headers (for forced load), to make sure we don't cause a crash.
* Staging and out-of-tree GPL modules are fine.
*/
- if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+ if (trace_module_has_bad_taint(mod))
return 0;
mutex_lock(&tracepoints_mutex);
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 240fb62cf394..dd06439b9c84 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -225,7 +225,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id)
*
* When there is no mapping defined for the user-namespace uid
* pair INVALID_UID is returned. Callers are expected to test
- * for and handle handle INVALID_UID being returned. INVALID_UID
+ * for and handle INVALID_UID being returned. INVALID_UID
* may be tested for using uid_valid().
*/
kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 82ef9f3b7473..193e977a10ea 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1851,6 +1851,12 @@ static void destroy_worker(struct worker *worker)
if (worker->flags & WORKER_IDLE)
pool->nr_idle--;
+ /*
+ * Once WORKER_DIE is set, the kworker may destroy itself at any
+ * point. Pin to ensure the task stays until we're done with it.
+ */
+ get_task_struct(worker->task);
+
list_del_init(&worker->entry);
worker->flags |= WORKER_DIE;
@@ -1859,6 +1865,7 @@ static void destroy_worker(struct worker *worker)
spin_unlock_irq(&pool->lock);
kthread_stop(worker->task);
+ put_task_struct(worker->task);
kfree(worker);
spin_lock_irq(&pool->lock);