Merge branch 'perf/urgent' into perf/core, to pick up fixes and to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 182 insertions, 57 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1d1fe9361d29..fc7f4748d34a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -548,9 +548,6 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
 
         rcu_read_lock();
         cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-                if (cp == root_cs)
-                        continue;
-
                 /* skip the whole subtree if @cp doesn't have any CPU */
                 if (cpumask_empty(cp->cpus_allowed)) {
                         pos_css = css_rightmost_descendant(pos_css);
@@ -873,7 +870,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
                  * If it becomes empty, inherit the effective mask of the
                  * parent, which is guaranteed to have some CPUs.
                  */
-                if (cpumask_empty(new_cpus))
+                if (cgroup_on_dfl(cp->css.cgroup) && cpumask_empty(new_cpus))
                         cpumask_copy(new_cpus, parent->effective_cpus);
 
                 /* Skip the whole subtree if the cpumask remains the same. */
@@ -1129,7 +1126,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
                  * If it becomes empty, inherit the effective mask of the
                  * parent, which is guaranteed to have some MEMs.
                  */
-                if (nodes_empty(*new_mems))
+                if (cgroup_on_dfl(cp->css.cgroup) && nodes_empty(*new_mems))
                         *new_mems = parent->effective_mems;
 
                 /* Skip the whole subtree if the nodemask remains the same. */
@@ -1979,7 +1976,9 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
         spin_lock_irq(&callback_lock);
         cs->mems_allowed = parent->mems_allowed;
+        cs->effective_mems = parent->mems_allowed;
         cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+        cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
         spin_unlock_irq(&callback_lock);
 out_unlock:
         mutex_unlock(&cpuset_mutex);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8bb20cc39a92..9a5f339a0e2d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3610,7 +3610,7 @@ static void put_event(struct perf_event *event)
         ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
         WARN_ON_ONCE(ctx->parent_ctx);
         perf_remove_from_context(event, true);
-        mutex_unlock(&ctx->mutex);
+        perf_event_ctx_unlock(event, ctx);
 
         _free_event(event);
 }
@@ -4593,6 +4593,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
         struct perf_event *event = container_of(entry,
                         struct perf_event, pending);
+        int rctx;
+
+        rctx = perf_swevent_get_recursion_context();
+        /*
+         * If we 'fail' here, that's OK, it means recursion is already disabled
+         * and we won't recurse 'further'.
+         */
 
         if (event->pending_disable) {
                 event->pending_disable = 0;
@@ -4603,6 +4610,9 @@ static void perf_pending_event(struct irq_work *entry)
                 event->pending_wakeup = 0;
                 perf_event_wakeup(event);
         }
+
+        if (rctx >= 0)
+                perf_swevent_put_recursion_context(rctx);
 }
 
 /*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 196a06fbc122..886d09e691d5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1474,8 +1474,13 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
          * otherwise we'll have trouble later trying to figure out
          * which interrupt is which (messes up the interrupt freeing
          * logic etc).
+         *
+         * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
+         * it cannot be set along with IRQF_NO_SUSPEND.
          */
-        if ((irqflags & IRQF_SHARED) && !dev_id)
+        if (((irqflags & IRQF_SHARED) && !dev_id) ||
+            (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
+            ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
                 return -EINVAL;
 
         desc = irq_to_desc(irq);
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 3ca532592704..5204a6d1b985 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -43,9 +43,12 @@ void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action)
 
         if (action->flags & IRQF_NO_SUSPEND)
                 desc->no_suspend_depth++;
+        else if (action->flags & IRQF_COND_SUSPEND)
+                desc->cond_suspend_depth++;
 
         WARN_ON_ONCE(desc->no_suspend_depth &&
-                     desc->no_suspend_depth != desc->nr_actions);
+                     (desc->no_suspend_depth +
+                        desc->cond_suspend_depth) != desc->nr_actions);
 }
 
 /*
@@ -61,6 +64,8 @@ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
 
         if (action->flags & IRQF_NO_SUSPEND)
                 desc->no_suspend_depth--;
+        else if (action->flags & IRQF_COND_SUSPEND)
+                desc->cond_suspend_depth--;
 }
 
 static bool suspend_device_irq(struct irq_desc *desc, int irq)
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index ff7f47d026ac..3f9f1d6b4c2e 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -89,16 +89,28 @@ static bool klp_is_object_loaded(struct klp_object *obj)
 /* sets obj->mod if object is not vmlinux and module is found */
 static void klp_find_object_module(struct klp_object *obj)
 {
+        struct module *mod;
+
         if (!klp_is_module(obj))
                 return;
 
         mutex_lock(&module_mutex);
         /*
-         * We don't need to take a reference on the module here because we have
-         * the klp_mutex, which is also taken by the module notifier.  This
-         * prevents any module from unloading until we release the klp_mutex.
+         * We do not want to block removal of patched modules and therefore
+         * we do not take a reference here. The patches are removed by
+         * a going module handler instead.
+         */
+        mod = find_module(obj->name);
+        /*
+         * Do not mess work of the module coming and going notifiers.
+         * Note that the patch might still be needed before the going handler
+         * is called. Module functions can be called even in the GOING state
+         * until mod->exit() finishes. This is especially important for
+         * patches that modify semantic of the functions.
          */
-        obj->mod = find_module(obj->name);
+        if (mod && mod->klp_alive)
+                obj->mod = mod;
+
         mutex_unlock(&module_mutex);
 }
 
@@ -248,11 +260,12 @@ static int klp_find_external_symbol(struct module *pmod, const char *name,
         /* first, check if it's an exported symbol */
         preempt_disable();
         sym = find_symbol(name, NULL, NULL, true, true);
-        preempt_enable();
         if (sym) {
                 *addr = sym->value;
+                preempt_enable();
                 return 0;
         }
+        preempt_enable();
 
         /* otherwise check if it's in another .o within the patch module */
         return klp_find_object_symbol(pmod->name, name, addr);
@@ -314,12 +327,12 @@ static void notrace klp_ftrace_handler(unsigned long ip,
         rcu_read_lock();
         func = list_first_or_null_rcu(&ops->func_stack, struct klp_func,
                                       stack_node);
-        rcu_read_unlock();
-
         if (WARN_ON_ONCE(!func))
-                return;
+                goto unlock;
 
         klp_arch_set_pc(regs, (unsigned long)func->new_func);
+unlock:
+        rcu_read_unlock();
 }
 
 static int klp_disable_func(struct klp_func *func)
@@ -731,7 +744,7 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
         func->state = KLP_DISABLED;
 
         return kobject_init_and_add(&func->kobj, &klp_ktype_func,
-                                    obj->kobj, func->old_name);
+                                    obj->kobj, "%s", func->old_name);
 }
 
 /* parts of the initialization that is done only when the object is loaded */
@@ -766,6 +779,7 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
                 return -EINVAL;
 
         obj->state = KLP_DISABLED;
+        obj->mod = NULL;
 
         klp_find_object_module(obj);
 
@@ -807,7 +821,7 @@ static int klp_init_patch(struct klp_patch *patch)
         patch->state = KLP_DISABLED;
 
         ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch,
-                                   klp_root_kobj, patch->mod->name);
+                                   klp_root_kobj, "%s", patch->mod->name);
         if (ret)
                 goto unlock;
 
@@ -960,6 +974,15 @@ static int klp_module_notify(struct notifier_block *nb, unsigned long action,
 
         mutex_lock(&klp_mutex);
 
+        /*
+         * Each module has to know that the notifier has been called.
+         * We never know what module will get patched by a new patch.
+         */
+        if (action == MODULE_STATE_COMING)
+                mod->klp_alive = true;
+        else /* MODULE_STATE_GOING */
+                mod->klp_alive = false;
+
         list_for_each_entry(patch, &klp_patches, list) {
                 for (obj = patch->objs; obj->funcs; obj++) {
                         if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index e16e5542bf13..6357265a31ad 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1193,6 +1193,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
                 ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
 
         if (unlikely(ret)) {
+                __set_current_state(TASK_RUNNING);
                 if (rt_mutex_has_waiters(lock))
                         remove_waiter(lock, &waiter);
                 rt_mutex_handle_deadlock(ret, chwalk, &waiter);
diff --git a/kernel/module.c b/kernel/module.c
index b34813f725e9..b3d634ed06c9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -56,7 +56,6 @@
 #include <linux/async.h>
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
-#include <linux/kasan.h>
 #include <linux/jump_label.h>
 #include <linux/pfn.h>
 #include <linux/bsearch.h>
@@ -1814,7 +1813,6 @@ static void unset_module_init_ro_nx(struct module *mod) { }
 void __weak module_memfree(void *module_region)
 {
         vfree(module_region);
-        kasan_module_free(module_region);
 }
 
 void __weak module_arch_cleanup(struct module *mod)
@@ -2313,11 +2311,13 @@ static void layout_symtab(struct module *mod, struct load_info *info)
         info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
         info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym);
         mod->core_size += strtab_size;
+        mod->core_size = debug_align(mod->core_size);
 
         /* Put string table section at end of init part of module. */
         strsect->sh_flags |= SHF_ALLOC;
         strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
                                          info->index.str) | INIT_OFFSET_MASK;
+        mod->init_size = debug_align(mod->init_size);
         pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
 }
 
diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h
index cbd69d842341..2ca4a8b5fe57 100644
--- a/kernel/printk/console_cmdline.h
+++ b/kernel/printk/console_cmdline.h
@@ -3,7 +3,7 @@
 
 struct console_cmdline
 {
-        char    name[8];                        /* Name of the driver       */
+        char    name[16];                       /* Name of the driver       */
         int     index;                          /* Minor dev. to use        */
         char    *options;                       /* Options for the driver   */
 #ifdef CONFIG_A11Y_BRAILLE_CONSOLE
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 01cfd69c54c6..bb0635bd74f2 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2464,6 +2464,7 @@ void register_console(struct console *newcon)
         for (i = 0, c = console_cmdline;
              i < MAX_CMDLINECONSOLES && c->name[0];
              i++, c++) {
+                BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
                 if (strcmp(c->name, newcon->name) != 0)
                         continue;
                 if (newcon->index >= 0 &&
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 94b2d7b88a27..80014a178342 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -82,6 +82,7 @@ static void cpuidle_idle_call(void)
         struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
         int next_state, entered_state;
         unsigned int broadcast;
+        bool reflect;
 
         /*
          * Check if the idle task must be rescheduled. If it is the
@@ -105,6 +106,9 @@ static void cpuidle_idle_call(void)
          */
         rcu_idle_enter();
 
+        if (cpuidle_not_available(drv, dev))
+                goto use_default;
+
         /*
          * Suspend-to-idle ("freeze") is a system state in which all user space
          * has been frozen, all I/O devices have been suspended and the only
@@ -115,30 +119,24 @@ static void cpuidle_idle_call(void)
          * until a proper wakeup interrupt happens.
          */
         if (idle_should_freeze()) {
-                cpuidle_enter_freeze();
-                local_irq_enable();
-                goto exit_idle;
-        }
+                entered_state = cpuidle_enter_freeze(drv, dev);
+                if (entered_state >= 0) {
+                        local_irq_enable();
+                        goto exit_idle;
+                }
 
-        /*
-         * Ask the cpuidle framework to choose a convenient idle state.
-         * Fall back to the default arch idle method on errors.
-         */
-        next_state = cpuidle_select(drv, dev);
-        if (next_state < 0) {
-use_default:
+                reflect = false;
+                next_state = cpuidle_find_deepest_state(drv, dev);
+        } else {
+                reflect = true;
                 /*
-                 * We can't use the cpuidle framework, let's use the default
-                 * idle routine.
+                 * Ask the cpuidle framework to choose a convenient idle state.
                  */
-                if (current_clr_polling_and_test())
-                        local_irq_enable();
-                else
-                        arch_cpu_idle();
-
-                goto exit_idle;
+                next_state = cpuidle_select(drv, dev);
         }
-
+        /* Fall back to the default arch idle method on errors. */
+        if (next_state < 0)
+                goto use_default;
 
         /*
          * The idle task must be scheduled, it is pointless to
@@ -183,7 +181,8 @@ use_default:
         /*
          * Give the governor an opportunity to reflect on the outcome
          */
-        cpuidle_reflect(dev, entered_state);
+        if (reflect)
+                cpuidle_reflect(dev, entered_state);
 
 exit_idle:
         __current_set_polling();
@@ -196,6 +195,19 @@ exit_idle:
 
         rcu_idle_exit();
         start_critical_timings();
+        return;
+
+use_default:
+        /*
+         * We can't use the cpuidle framework, let's use the default
+         * idle routine.
+         */
+        if (current_clr_polling_and_test())
+                local_irq_enable();
+        else
+                arch_cpu_idle();
+
+        goto exit_idle;
 }
 
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index 667b2e62fad2..a03d9cd23ed7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1108,6 +1108,7 @@ DECLARE_RWSEM(uts_sem);
 /*
  * Work around broken programs that cannot handle "Linux 3.0".
  * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ * And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60.
  */
 static int override_release(char __user *release, size_t len)
 {
@@ -1127,7 +1128,7 @@ static int override_release(char __user *release, size_t len)
                                 break;
                         rest++;
                 }
-                v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+                v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60;
                 copy = clamp_t(size_t, len, 1, sizeof(buf));
                 copy = scnprintf(buf, copy, "2.6.%u%s", v, rest);
                 ret = copy_to_user(release, buf, copy + 1);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 45e5cb143d17..4f228024055b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1059,6 +1059,12 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_graph_active;
+#else
+# define ftrace_graph_active 0
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static struct ftrace_ops *removed_ops;
@@ -2041,8 +2047,12 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
                 if (!ftrace_rec_count(rec))
                         rec->flags = 0;
                 else
-                        /* Just disable the record (keep REGS state) */
-                        rec->flags &= ~FTRACE_FL_ENABLED;
+                        /*
+                         * Just disable the record, but keep the ops TRAMP
+                         * and REGS states. The _EN flags must be disabled though.
+                         */
+                        rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN |
+                                        FTRACE_FL_REGS_EN);
         }
 
         return FTRACE_UPDATE_MAKE_NOP;
@@ -2688,24 +2698,36 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 
 static void ftrace_startup_sysctl(void)
 {
+        int command;
+
         if (unlikely(ftrace_disabled))
                 return;
 
         /* Force update next time */
         saved_ftrace_func = NULL;
         /* ftrace_start_up is true if we want ftrace running */
-        if (ftrace_start_up)
-                ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+        if (ftrace_start_up) {
+                command = FTRACE_UPDATE_CALLS;
+                if (ftrace_graph_active)
+                        command |= FTRACE_START_FUNC_RET;
+                ftrace_startup_enable(command);
+        }
 }
 
 static void ftrace_shutdown_sysctl(void)
 {
+        int command;
+
         if (unlikely(ftrace_disabled))
                 return;
 
         /* ftrace_start_up is true if ftrace is running */
-        if (ftrace_start_up)
-                ftrace_run_update_code(FTRACE_DISABLE_CALLS);
+        if (ftrace_start_up) {
+                command = FTRACE_DISABLE_CALLS;
+                if (ftrace_graph_active)
+                        command |= FTRACE_STOP_FUNC_RET;
+                ftrace_run_update_code(command);
+        }
 }
 
 static cycle_t          ftrace_update_time;
@@ -5558,12 +5580,12 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
         if (ftrace_enabled) {
 
-                ftrace_startup_sysctl();
-
                 /* we are starting ftrace again */
                 if (ftrace_ops_list != &ftrace_list_end)
                         update_ftrace_function();
 
+                ftrace_startup_sysctl();
+
         } else {
                 /* stopping ftrace calls (just send to ftrace_stub) */
                 ftrace_trace_function = ftrace_stub;
@@ -5590,8 +5612,6 @@ static struct ftrace_ops graph_ops = {
         ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
 };
 
-static int ftrace_graph_active;
-
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
         return 0;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f28849394791..41ff75b478c6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2728,19 +2728,57 @@ bool flush_work(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
+struct cwt_wait {
+        wait_queue_t            wait;
+        struct work_struct      *work;
+};
+
+static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+        struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
+
+        if (cwait->work != key)
+                return 0;
+        return autoremove_wake_function(wait, mode, sync, key);
+}
+
 static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
 {
+        static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
         unsigned long flags;
         int ret;
 
         do {
                 ret = try_to_grab_pending(work, is_dwork, &flags);
                 /*
-                 * If someone else is canceling, wait for the same event it
-                 * would be waiting for before retrying.
+                 * If someone else is already canceling, wait for it to
+                 * finish.  flush_work() doesn't work for PREEMPT_NONE
+                 * because we may get scheduled between @work's completion
+                 * and the other canceling task resuming and clearing
+                 * CANCELING - flush_work() will return false immediately
+                 * as @work is no longer busy, try_to_grab_pending() will
+                 * return -ENOENT as @work is still being canceled and the
+                 * other canceling task won't be able to clear CANCELING as
+                 * we're hogging the CPU.
+                 *
+                 * Let's wait for completion using a waitqueue.  As this
+                 * may lead to the thundering herd problem, use a custom
+                 * wake function which matches @work along with exclusive
+                 * wait and wakeup.
                  */
-                if (unlikely(ret == -ENOENT))
-                        flush_work(work);
+                if (unlikely(ret == -ENOENT)) {
+                        struct cwt_wait cwait;
+
+                        init_wait(&cwait.wait);
+                        cwait.wait.func = cwt_wakefn;
+                        cwait.work = work;
+
+                        prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
+                                                  TASK_UNINTERRUPTIBLE);
+                        if (work_is_canceling(work))
+                                schedule();
+                        finish_wait(&cancel_waitq, &cwait.wait);
+                }
         } while (unlikely(ret < 0));
 
         /* tell other tasks trying to grab @work to back off */
@@ -2749,6 +2787,16 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
 
         flush_work(work);
         clear_work_data(work);
+
+        /*
+         * Paired with prepare_to_wait() above so that either
+         * waitqueue_active() is visible here or !work_is_canceling() is
+         * visible there.
+         */
+        smp_mb();
+        if (waitqueue_active(&cancel_waitq))
+                __wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
+
         return ret;
 }