11 files changed, 90 insertions, 49 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/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 105f273b6f86..0c753ddd223b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4112,17 +4112,17 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
         err = percpu_ref_init(&css->refcnt, css_release);
         if (err)
-                goto err_free;
+                goto err_free_css;
 
         init_css(css, ss, cgrp);
 
         err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
         if (err)
-                goto err_free;
+                goto err_free_percpu_ref;
 
         err = online_css(css);
         if (err)
-                goto err_free;
+                goto err_clear_dir;
 
         dget(cgrp->dentry);
         css_get(css->parent);
@@ -4138,8 +4138,11 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
         return 0;
 
-err_free:
+err_clear_dir:
+        cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+err_free_percpu_ref:
         percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
         ss->css_free(css);
         return err;
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 44a1261cb9ff..08ec814ad9d2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -234,6 +234,7 @@ static const struct futex_q futex_q_init = {
  * waiting on a futex.
  */
 struct futex_hash_bucket {
+        atomic_t waiters;
         spinlock_t lock;
         struct plist_head chain;
 } ____cacheline_aligned_in_smp;
@@ -253,22 +254,37 @@ static inline void futex_get_mm(union futex_key *key)
         smp_mb__after_atomic_inc();
 }
 
-static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
 {
 #ifdef CONFIG_SMP
+        atomic_inc(&hb->waiters);
         /*
-         * Tasks trying to enter the critical region are most likely
-         * potential waiters that will be added to the plist. Ensure
-         * that wakers won't miss to-be-slept tasks in the window between
-         * the wait call and the actual plist_add.
+         * Full barrier (A), see the ordering comment above.
          */
-        if (spin_is_locked(&hb->lock))
-                return true;
-        smp_rmb(); /* Make sure we check the lock state first */
+        smp_mb__after_atomic_inc();
+#endif
+}
+
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+        atomic_dec(&hb->waiters);
+#endif
+}
 
-        return !plist_head_empty(&hb->chain);
+static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+        return atomic_read(&hb->waiters);
 #else
-        return true;
+        return 1;
 #endif
 }
 
@@ -954,6 +970,7 @@ static void __unqueue_futex(struct futex_q *q)
 
         hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
         plist_del(&q->list, &hb->chain);
+        hb_waiters_dec(hb);
 }
 
 /*
@@ -1257,7 +1274,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
          */
         if (likely(&hb1->chain != &hb2->chain)) {
                 plist_del(&q->list, &hb1->chain);
+                hb_waiters_dec(hb1);
                 plist_add(&q->list, &hb2->chain);
+                hb_waiters_inc(hb2);
                 q->lock_ptr = &hb2->lock;
         }
         get_futex_key_refs(key2);
@@ -1600,6 +1619,17 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
         struct futex_hash_bucket *hb;
 
         hb = hash_futex(&q->key);
+
+        /*
+         * Increment the counter before taking the lock so that
+         * a potential waker won't miss a to-be-slept task that is
+         * waiting for the spinlock. This is safe as all queue_lock()
+         * users end up calling queue_me(). Similarly, for housekeeping,
+         * decrement the counter at queue_unlock() when some error has
+         * occurred and we don't end up adding the task to the list.
+         */
+        hb_waiters_inc(hb);
+
         q->lock_ptr = &hb->lock;
 
         spin_lock(&hb->lock); /* implies MB (A) */
@@ -1611,6 +1641,7 @@ queue_unlock(struct futex_hash_bucket *hb)
         __releases(&hb->lock)
 {
         spin_unlock(&hb->lock);
+        hb_waiters_dec(hb);
 }
 
 /**
@@ -2342,6 +2373,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
                  * Unqueue the futex_q and determine which it was.
                  */
                 plist_del(&q->list, &hb->chain);
+                hb_waiters_dec(hb);
 
                 /* Handle spurious wakeups gracefully */
                 ret = -EWOULDBLOCK;
@@ -2875,6 +2907,7 @@ static int __init futex_init(void)
                 futex_cmpxchg_enabled = 1;
 
         for (i = 0; i < futex_hashsize; i++) {
+                atomic_set(&futex_queues[i].waiters, 0);
                 plist_head_init(&futex_queues[i].chain);
                 spin_lock_init(&futex_queues[i].lock);
         }
diff --git a/kernel/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 6edbef296ece..f5c6635b806c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -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.
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/trace/trace_events.c b/kernel/trace/trace_events.c
index f3989ceb5cd5..7b16d40bd64d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e72e2b6..ee0a5098ac43 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __array
 #define __array(type, item, len)                                        \
         do {                                                            \
+                char *type_str = #type"["__stringify(len)"]";           \
                 BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                 \
-                mutex_lock(&event_storage_mutex);                       \
-                snprintf(event_storage, sizeof(event_storage),          \
-                         "%s[%d]", #type, len);                         \
-                ret = trace_define_field(event_call, event_storage, #item, \
+                ret = trace_define_field(event_call, type_str, #item,   \
                                  offsetof(typeof(field), item),         \
                                  sizeof(field.item),                    \
                                  is_signed_type(type), filter_type);    \
-                mutex_unlock(&event_storage_mutex);                     \
                 if (ret)                                                \
                         return ret;                                     \
         } while (0);