Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
	net/ipv6/ip6_tunnel.c
	net/ipv6/ip6_vti.c

ipv6 tunnel statistic bug fixes conflicting with consolidation into
generic sw per-cpu net stats.

qlogic conflict between queue counting bug fix and the addition
of multiple MAC address support.

Signed-off-by: David S. Miller <davem@davemloft.net>

14 files changed, 93 insertions, 32 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index bbaf7d59c1bb..bc010ee272b6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -137,9 +137,10 @@ $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
 ###############################################################################
 ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
 X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
-X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
-X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509
+X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
                                 $(or $(realpath $(CERT)),$(CERT))))
+X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw))
 
 ifeq ($(X509_CERTIFICATES),)
 $(warning *** No X.509 certificates found ***)
@@ -164,9 +165,9 @@ $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
 targets += $(obj)/.x509.list
 $(obj)/.x509.list:
         @echo $(X509_CERTIFICATES) >$@
+endif
 
 clean-files := x509_certificate_list .x509.list
-endif
 
 ifeq ($(CONFIG_MODULE_SIG),y)
 ###############################################################################
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 5253204afdca..9fd4246b04b8 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -22,6 +22,6 @@ void foo(void)
 #ifdef CONFIG_SMP
         DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
 #endif
-        DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int));
+        DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
         /* End of constants */
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b729c278b64..bc1dcabe9217 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -890,6 +890,16 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
                 struct cgroup *cgrp = dentry->d_fsdata;
 
                 BUG_ON(!(cgroup_is_dead(cgrp)));
+
+                /*
+                 * XXX: cgrp->id is only used to look up css's.  As cgroup
+                 * and css's lifetimes will be decoupled, it should be made
+                 * per-subsystem and moved to css->id so that lookups are
+                 * successful until the target css is released.
+                 */
+                idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+                cgrp->id = -1;
+
                 call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
         } else {
                 struct cfent *cfe = __d_cfe(dentry);
@@ -4268,6 +4278,7 @@ static void css_release(struct percpu_ref *ref)
         struct cgroup_subsys_state *css =
                 container_of(ref, struct cgroup_subsys_state, refcnt);
 
+        rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
         call_rcu(&css->rcu_head, css_free_rcu_fn);
 }
 
@@ -4426,14 +4437,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
         list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
         root->number_of_cgroups++;
 
-        /* each css holds a ref to the cgroup's dentry and the parent css */
-        for_each_root_subsys(root, ss) {
-                struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
-                dget(dentry);
-                css_get(css->parent);
-        }
-
         /* hold a ref to the parent's dentry */
         dget(parent->dentry);
 
@@ -4445,6 +4448,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
                 if (err)
                         goto err_destroy;
 
+                /* each css holds a ref to the cgroup's dentry and parent css */
+                dget(dentry);
+                css_get(css->parent);
+
+                /* mark it consumed for error path */
+                css_ar[ss->subsys_id] = NULL;
+
                 if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
                     parent->parent) {
                         pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
@@ -4491,6 +4501,14 @@ err_free_cgrp:
         return err;
 
 err_destroy:
+        for_each_root_subsys(root, ss) {
+                struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
+
+                if (css) {
+                        percpu_ref_cancel_init(&css->refcnt);
+                        ss->css_free(css);
+                }
+        }
         cgroup_destroy_locked(cgrp);
         mutex_unlock(&cgroup_mutex);
         mutex_unlock(&dentry->d_inode->i_mutex);
@@ -4652,8 +4670,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
          * will be invoked to perform the rest of destruction once the
          * percpu refs of all css's are confirmed to be killed.
          */
-        for_each_root_subsys(cgrp->root, ss)
-                kill_css(cgroup_css(cgrp, ss));
+        for_each_root_subsys(cgrp->root, ss) {
+                struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
+
+                if (css)
+                        kill_css(css);
+        }
 
         /*
          * Mark @cgrp dead.  This prevents further task migration and child
@@ -4722,14 +4744,6 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp)
         /* delete this cgroup from parent->children */
         list_del_rcu(&cgrp->sibling);
 
-        /*
-         * We should remove the cgroup object from idr before its grace
-         * period starts, so we won't be looking up a cgroup while the
-         * cgroup is being freed.
-         */
-        idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-        cgrp->id = -1;
-
         dput(d);
 
         set_bit(CGRP_RELEASABLE, &parent->flags);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72348dc192c1..f5744010a8d2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1396,6 +1396,8 @@ event_sched_out(struct perf_event *event,
         if (event->state != PERF_EVENT_STATE_ACTIVE)
                 return;
 
+        perf_pmu_disable(event->pmu);
+
         event->state = PERF_EVENT_STATE_INACTIVE;
         if (event->pending_disable) {
                 event->pending_disable = 0;
@@ -1412,6 +1414,8 @@ event_sched_out(struct perf_event *event,
                 ctx->nr_freq--;
         if (event->attr.exclusive || !cpuctx->active_oncpu)
                 cpuctx->exclusive = 0;
+
+        perf_pmu_enable(event->pmu);
 }
 
 static void
@@ -1652,6 +1656,7 @@ event_sched_in(struct perf_event *event,
                  struct perf_event_context *ctx)
 {
         u64 tstamp = perf_event_time(event);
+        int ret = 0;
 
         if (event->state <= PERF_EVENT_STATE_OFF)
                 return 0;
@@ -1674,10 +1679,13 @@ event_sched_in(struct perf_event *event,
          */
         smp_wmb();
 
+        perf_pmu_disable(event->pmu);
+
         if (event->pmu->add(event, PERF_EF_START)) {
                 event->state = PERF_EVENT_STATE_INACTIVE;
                 event->oncpu = -1;
-                return -EAGAIN;
+                ret = -EAGAIN;
+                goto out;
         }
 
         event->tstamp_running += tstamp - event->tstamp_stopped;
@@ -1693,7 +1701,10 @@ event_sched_in(struct perf_event *event,
         if (event->attr.exclusive)
                 cpuctx->exclusive = 1;
 
-        return 0;
+out:
+        perf_pmu_enable(event->pmu);
+
+        return ret;
 }
 
 static int
@@ -2743,6 +2754,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
                 if (!event_filter_match(event))
                         continue;
 
+                perf_pmu_disable(event->pmu);
+
                 hwc = &event->hw;
 
                 if (hwc->interrupts == MAX_INTERRUPTS) {
@@ -2752,7 +2765,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
                 }
 
                 if (!event->attr.freq || !event->attr.sample_freq)
-                        continue;
+                        goto next;
 
                 /*
                  * stop the event and update event->count
@@ -2774,6 +2787,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
                         perf_adjust_period(event, period, delta, false);
 
                 event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
+        next:
+                perf_pmu_enable(event->pmu);
         }
 
         perf_pmu_enable(ctx->pmu);
diff --git a/kernel/fork.c b/kernel/fork.c
index 728d5be9548c..5721f0e3f2da 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
         spin_lock_init(&mm->page_table_lock);
         mm_init_aio(mm);
         mm_init_owner(mm, p);
+        clear_tlb_flush_pending(mm);
 
         if (likely(!mm_alloc_pgd(mm))) {
                 mm->def_flags = 0;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index b462fa197517..aa6a8aadb911 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@ EXPORT_SYMBOL(system_freezing_cnt);
 bool pm_freezing;
 bool pm_nosig_freezing;
 
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
 /* protects freezing and frozen transitions */
 static DEFINE_SPINLOCK(freezer_lock);
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index d0d8fca54065..9c970167e402 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1680,6 +1680,7 @@ int kernel_kexec(void)
         {
                 kexec_in_progress = true;
                 kernel_restart_prepare(NULL);
+                migrate_to_reboot_cpu();
                 printk(KERN_EMERG "Starting new kernel\n");
                 machine_shutdown();
         }
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 463aa6736751..eacb8bd8cab4 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -81,6 +81,7 @@ void pm_vt_switch_unregister(struct device *dev)
         list_for_each_entry(tmp, &pm_vt_switch_list, head) {
                 if (tmp->dev == dev) {
                         list_del(&tmp->head);
+                        kfree(tmp);
                         break;
                 }
         }
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f813b3474646..662c83fc16b7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
 {
         /* The boot cpu is always logical cpu 0 */
         int cpu = reboot_cpu;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 19af58f3a261..a88f4a485c5e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4902,6 +4902,7 @@ DEFINE_PER_CPU(struct sched_domain *, sd_asym);
 static void update_top_cache_domain(int cpu)
 {
         struct sched_domain *sd;
+        struct sched_domain *busy_sd = NULL;
         int id = cpu;
         int size = 1;
 
@@ -4909,9 +4910,9 @@ static void update_top_cache_domain(int cpu)
         if (sd) {
                 id = cpumask_first(sched_domain_span(sd));
                 size = cpumask_weight(sched_domain_span(sd));
-                sd = sd->parent; /* sd_busy */
+                busy_sd = sd->parent; /* sd_busy */
         }
-        rcu_assign_pointer(per_cpu(sd_busy, cpu), sd);
+        rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
 
         rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
         per_cpu(sd_llc_size, cpu) = size;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9030da7bcb15..c7395d97e4cb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1738,6 +1738,13 @@ void task_numa_work(struct callback_head *work)
                     (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
                         continue;
 
+                /*
+                 * Skip inaccessible VMAs to avoid any confusion between
+                 * PROT_NONE and NUMA hinting ptes
+                 */
+                if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+                        continue;
+
                 do {
                         start = max(start, vma->vm_start);
                         end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7d57275fc396..1c4065575fa2 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -901,6 +901,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
         struct rq *rq = rq_of_rt_rq(rt_rq);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+        /*
+         * Change rq's cpupri only if rt_rq is the top queue.
+         */
+        if (&rq->rt != rt_rq)
+                return;
+#endif
         if (rq->online && prio < prev_prio)
                 cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 }
@@ -910,6 +917,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
         struct rq *rq = rq_of_rt_rq(rt_rq);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+        /*
+         * Change rq's cpupri only if rt_rq is the top queue.
+         */
+        if (&rq->rt != rt_rq)
+                return;
+#endif
         if (rq->online && rt_rq->highest_prio.curr != prev_prio)
                 cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0e9f9eaade2f..72a0f81dc5a8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -775,7 +775,7 @@ static int ftrace_profile_init(void)
         int cpu;
         int ret = 0;
 
-        for_each_online_cpu(cpu) {
+        for_each_possible_cpu(cpu) {
                 ret = ftrace_profile_init_cpu(cpu);
                 if (ret)
                         break;
diff --git a/kernel/user.c b/kernel/user.c
index a3a0dbfda329..c006131beb77 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,9 +51,9 @@ struct user_namespace init_user_ns = {
         .owner = GLOBAL_ROOT_UID,
         .group = GLOBAL_ROOT_GID,
         .proc_inum = PROC_USER_INIT_INO,
-#ifdef CONFIG_KEYS_KERBEROS_CACHE
-        .krb_cache_register_sem =
-        __RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+        .persistent_keyring_register_sem =
+        __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
 #endif
 };
 EXPORT_SYMBOL_GPL(init_user_ns);