diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 4 | ||||
-rw-r--r-- | kernel/audit_tree.c | 91 | ||||
-rw-r--r-- | kernel/auditfilter.c | 14 | ||||
-rw-r--r-- | kernel/cgroup_freezer.c | 19 | ||||
-rw-r--r-- | kernel/cpuset.c | 12 | ||||
-rw-r--r-- | kernel/exit.c | 13 | ||||
-rw-r--r-- | kernel/fork.c | 13 | ||||
-rw-r--r-- | kernel/hrtimer.c | 9 | ||||
-rw-r--r-- | kernel/kprobes.c | 23 | ||||
-rw-r--r-- | kernel/kthread.c | 3 | ||||
-rw-r--r-- | kernel/marker.c | 114 | ||||
-rw-r--r-- | kernel/module.c | 9 | ||||
-rw-r--r-- | kernel/posix-cpu-timers.c | 7 | ||||
-rw-r--r-- | kernel/power/main.c | 2 | ||||
-rw-r--r-- | kernel/profile.c | 2 | ||||
-rw-r--r-- | kernel/relay.c | 9 | ||||
-rw-r--r-- | kernel/sched.c | 24 | ||||
-rw-r--r-- | kernel/sched_debug.c | 5 | ||||
-rw-r--r-- | kernel/sched_stats.h | 15 | ||||
-rw-r--r-- | kernel/signal.c | 2 | ||||
-rw-r--r-- | kernel/stop_machine.c | 5 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 1 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 84 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 1 | ||||
-rw-r--r-- | kernel/trace/trace.c | 3 | ||||
-rw-r--r-- | kernel/trace/trace.h | 2 | ||||
-rw-r--r-- | kernel/trace/trace_branch.c | 4 | ||||
-rw-r--r-- | kernel/trace/trace_functions_return.c | 15 | ||||
-rw-r--r-- | kernel/tracepoint.c | 34 |
29 files changed, 380 insertions, 159 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index af3be57acbbb..03a45e7e87b7 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,8 +11,6 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o -CFLAGS_REMOVE_sched.o = -mno-spe - ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files CFLAGS_REMOVE_lockdep.o = -pg @@ -21,7 +19,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_sched_clock.o = -pg -CFLAGS_REMOVE_sched.o = -mno-spe -pg +CFLAGS_REMOVE_sched.o = -pg endif ifdef CONFIG_FUNCTION_RET_TRACER CFLAGS_REMOVE_extable.o = -pg # For __kernel_text_address() diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 8ba0e0d934f2..8b509441f49a 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -24,6 +24,7 @@ struct audit_chunk { struct list_head trees; /* with root here */ int dead; int count; + atomic_long_t refs; struct rcu_head head; struct node { struct list_head list; @@ -56,7 +57,8 @@ static LIST_HEAD(prune_list); * tree is refcounted; one reference for "some rules on rules_list refer to * it", one for each chunk with pointer to it. * - * chunk is refcounted by embedded inotify_watch. + * chunk is refcounted by embedded inotify_watch + .refs (non-zero refcount + * of watch contributes 1 to .refs). * * node.index allows to get from node.list to containing chunk. * MSB of that sucker is stolen to mark taggings that we might have to @@ -121,6 +123,7 @@ static struct audit_chunk *alloc_chunk(int count) INIT_LIST_HEAD(&chunk->hash); INIT_LIST_HEAD(&chunk->trees); chunk->count = count; + atomic_long_set(&chunk->refs, 1); for (i = 0; i < count; i++) { INIT_LIST_HEAD(&chunk->owners[i].list); chunk->owners[i].index = i; @@ -129,9 +132,8 @@ static struct audit_chunk *alloc_chunk(int count) return chunk; } -static void __free_chunk(struct rcu_head *rcu) +static void free_chunk(struct audit_chunk *chunk) { - struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head); int i; for (i = 0; i < chunk->count; i++) { @@ -141,14 +143,16 @@ static void __free_chunk(struct rcu_head *rcu) kfree(chunk); } -static inline void free_chunk(struct audit_chunk *chunk) +void audit_put_chunk(struct audit_chunk *chunk) { - call_rcu(&chunk->head, __free_chunk); + if (atomic_long_dec_and_test(&chunk->refs)) + free_chunk(chunk); } -void audit_put_chunk(struct audit_chunk *chunk) +static void __put_chunk(struct rcu_head *rcu) { - put_inotify_watch(&chunk->watch); + struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head); + audit_put_chunk(chunk); } enum {HASH_SIZE = 128}; @@ -176,7 +180,7 @@ struct audit_chunk *audit_tree_lookup(const struct inode *inode) list_for_each_entry_rcu(p, list, hash) { if (p->watch.inode == inode) { - get_inotify_watch(&p->watch); + atomic_long_inc(&p->refs); return p; } } @@ -194,17 +198,49 @@ int audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree) /* tagging and untagging inodes with trees */ -static void untag_chunk(struct audit_chunk *chunk, struct node *p) +static struct audit_chunk *find_chunk(struct node *p) +{ + int index = p->index & ~(1U<<31); + p -= index; + return container_of(p, struct audit_chunk, owners[0]); +} + +static void untag_chunk(struct node *p) { + struct audit_chunk *chunk = find_chunk(p); struct audit_chunk *new; struct audit_tree *owner; int size = chunk->count - 1; int i, j; + if (!pin_inotify_watch(&chunk->watch)) { + /* + * Filesystem is shutting down; all watches are getting + * evicted, just take it off the node list for this + * tree and let the eviction logics take care of the + * rest. + */ + owner = p->owner; + if (owner->root == chunk) { + list_del_init(&owner->same_root); + owner->root = NULL; + } + list_del_init(&p->list); + p->owner = NULL; + put_tree(owner); + return; + } + + spin_unlock(&hash_lock); + + /* + * pin_inotify_watch() succeeded, so the watch won't go away + * from under us. + */ mutex_lock(&chunk->watch.inode->inotify_mutex); if (chunk->dead) { mutex_unlock(&chunk->watch.inode->inotify_mutex); - return; + goto out; } owner = p->owner; @@ -221,7 +257,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct node *p) inotify_evict_watch(&chunk->watch); mutex_unlock(&chunk->watch.inode->inotify_mutex); put_inotify_watch(&chunk->watch); - return; + goto out; } new = alloc_chunk(size); @@ -263,7 +299,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct node *p) inotify_evict_watch(&chunk->watch); mutex_unlock(&chunk->watch.inode->inotify_mutex); put_inotify_watch(&chunk->watch); - return; + goto out; Fallback: // do the best we can @@ -277,6 +313,9 @@ Fallback: put_tree(owner); spin_unlock(&hash_lock); mutex_unlock(&chunk->watch.inode->inotify_mutex); +out: + unpin_inotify_watch(&chunk->watch); + spin_lock(&hash_lock); } static int create_chunk(struct inode *inode, struct audit_tree *tree) @@ -387,13 +426,6 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) return 0; } -static struct audit_chunk *find_chunk(struct node *p) -{ - int index = p->index & ~(1U<<31); - p -= index; - return container_of(p, struct audit_chunk, owners[0]); -} - static void kill_rules(struct audit_tree *tree) { struct audit_krule *rule, *next; @@ -431,17 +463,10 @@ static void prune_one(struct audit_tree *victim) spin_lock(&hash_lock); while (!list_empty(&victim->chunks)) { struct node *p; - struct audit_chunk *chunk; p = list_entry(victim->chunks.next, struct node, list); - chunk = find_chunk(p); - get_inotify_watch(&chunk->watch); - spin_unlock(&hash_lock); - - untag_chunk(chunk, p); - put_inotify_watch(&chunk->watch); - spin_lock(&hash_lock); + untag_chunk(p); } spin_unlock(&hash_lock); put_tree(victim); @@ -469,7 +494,6 @@ static void trim_marked(struct audit_tree *tree) while (!list_empty(&tree->chunks)) { struct node *node; - struct audit_chunk *chunk; node = list_entry(tree->chunks.next, struct node, list); @@ -477,14 +501,7 @@ static void trim_marked(struct audit_tree *tree) if (!(node->index & (1U<<31))) break; - chunk = find_chunk(node); - get_inotify_watch(&chunk->watch); - spin_unlock(&hash_lock); - - untag_chunk(chunk, node); - - put_inotify_watch(&chunk->watch); - spin_lock(&hash_lock); + untag_chunk(node); } if (!tree->root && !tree->goner) { tree->goner = 1; @@ -878,7 +895,7 @@ static void handle_event(struct inotify_watch *watch, u32 wd, u32 mask, static void destroy_watch(struct inotify_watch *watch) { struct audit_chunk *chunk = container_of(watch, struct audit_chunk, watch); - free_chunk(chunk); + call_rcu(&chunk->head, __put_chunk); } static const struct inotify_operations rtree_inotify_ops = { diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b7d354e2b0ef..9fd85a4640a0 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1094,8 +1094,8 @@ static void audit_inotify_unregister(struct list_head *in_list) list_for_each_entry_safe(p, n, in_list, ilist) { list_del(&p->ilist); inotify_rm_watch(audit_ih, &p->wdata); - /* the put matching the get in audit_do_del_rule() */ - put_inotify_watch(&p->wdata); + /* the unpin matching the pin in audit_do_del_rule() */ + unpin_inotify_watch(&p->wdata); } } @@ -1389,9 +1389,13 @@ static inline int audit_del_rule(struct audit_entry *entry, /* Put parent on the inotify un-registration * list. Grab a reference before releasing * audit_filter_mutex, to be released in - * audit_inotify_unregister(). */ - list_add(&parent->ilist, &inotify_list); - get_inotify_watch(&parent->wdata); + * audit_inotify_unregister(). + * If filesystem is going away, just leave + * the sucker alone, eviction will take + * care of it. + */ + if (pin_inotify_watch(&parent->wdata)) + list_add(&parent->ilist, &inotify_list); } } } diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 7fa476f01d05..fb249e2bcada 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -184,9 +184,20 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) { struct freezer *freezer; - task_lock(task); + /* + * No lock is needed, since the task isn't on tasklist yet, + * so it can't be moved to another cgroup, which means the + * freezer won't be removed and will be valid during this + * function call. + */ freezer = task_freezer(task); - task_unlock(task); + + /* + * The root cgroup is non-freezable, so we can skip the + * following check. + */ + if (!freezer->css.cgroup->parent) + return; spin_lock_irq(&freezer->lock); BUG_ON(freezer->state == CGROUP_FROZEN); @@ -331,7 +342,7 @@ static int freezer_write(struct cgroup *cgroup, else if (strcmp(buffer, freezer_state_strs[CGROUP_FROZEN]) == 0) goal_state = CGROUP_FROZEN; else - return -EIO; + return -EINVAL; if (!cgroup_lock_live_group(cgroup)) return -ENODEV; @@ -350,6 +361,8 @@ static struct cftype files[] = { static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup) { + if (!cgroup->parent) + return 0; return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files)); } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3e00526f52ec..81fc6791a296 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -587,7 +587,6 @@ static int generate_sched_domains(cpumask_t **domains, int ndoms; /* number of sched domains in result */ int nslot; /* next empty doms[] cpumask_t slot */ - ndoms = 0; doms = NULL; dattr = NULL; csa = NULL; @@ -674,10 +673,8 @@ restart: * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL); - if (!doms) { - ndoms = 0; + if (!doms) goto done; - } /* * The rest of the code, including the scheduler, can deal with @@ -732,6 +729,13 @@ restart: done: kfree(csa); + /* + * Fallback to the default domain if kmalloc() failed. + * See comments in partition_sched_domains(). + */ + if (doms == NULL) + ndoms = 1; + *domains = doms; *attributes = dattr; return ndoms; diff --git a/kernel/exit.c b/kernel/exit.c index ae2b92be5fae..35c8ec2ba03a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -40,7 +40,6 @@ #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> -#include <linux/compat.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> @@ -54,6 +53,10 @@ #include <asm/pgtable.h> #include <asm/mmu_context.h> +DEFINE_TRACE(sched_process_free); +DEFINE_TRACE(sched_process_exit); +DEFINE_TRACE(sched_process_wait); + static void exit_mm(struct task_struct * tsk); static inline int task_detached(struct task_struct *p) @@ -1059,14 +1062,6 @@ NORET_TYPE void do_exit(long code) exit_itimers(tsk->signal); } acct_collect(code, group_dead); -#ifdef CONFIG_FUTEX - if (unlikely(tsk->robust_list)) - exit_robust_list(tsk); -#ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) - compat_exit_robust_list(tsk); -#endif -#endif if (group_dead) tty_audit_exit(); if (unlikely(tsk->audit_context)) diff --git a/kernel/fork.c b/kernel/fork.c index f6083561dfe0..ac62f43ee430 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -40,6 +40,7 @@ #include <linux/jiffies.h> #include <linux/tracehook.h> #include <linux/futex.h> +#include <linux/compat.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> @@ -79,6 +80,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ +DEFINE_TRACE(sched_process_fork); + int nr_processes(void) { int cpu; @@ -519,6 +522,16 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) { struct completion *vfork_done = tsk->vfork_done; + /* Get rid of any futexes when releasing the mm */ +#ifdef CONFIG_FUTEX + if (unlikely(tsk->robust_list)) + exit_robust_list(tsk); +#ifdef CONFIG_COMPAT + if (unlikely(tsk->compat_robust_list)) + compat_exit_robust_list(tsk); +#endif +#endif + /* Get rid of any cached register state */ deactivate_mm(tsk, mm); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 95d3949f2ae5..47e63349d1b2 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -664,14 +664,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, /* Timer is expired, act upon the callback mode */ switch(timer->cb_mode) { - case HRTIMER_CB_IRQSAFE_NO_RESTART: - debug_hrtimer_deactivate(timer); - /* - * We can call the callback from here. No restart - * happens, so no danger of recursion - */ - BUG_ON(timer->function(timer) != HRTIMER_NORESTART); - return 1; case HRTIMER_CB_IRQSAFE_PERCPU: case HRTIMER_CB_IRQSAFE_UNLOCKED: /* @@ -683,7 +675,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, */ debug_hrtimer_deactivate(timer); return 1; - case HRTIMER_CB_IRQSAFE: case HRTIMER_CB_SOFTIRQ: /* * Move everything else into the softirq pending list ! diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 8b57a2597f21..9f8a3f25259a 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -72,7 +72,7 @@ static bool kprobe_enabled; DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { - spinlock_t lock ____cacheline_aligned; + spinlock_t lock ____cacheline_aligned_in_smp; } kretprobe_table_locks[KPROBE_TABLE_SIZE]; static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) @@ -613,30 +613,37 @@ static int __kprobes __register_kprobe(struct kprobe *p, return -EINVAL; p->addr = addr; - if (!kernel_text_address((unsigned long) p->addr) || - in_kprobes_functions((unsigned long) p->addr)) + preempt_disable(); + if (!__kernel_text_address((unsigned long) p->addr) || + in_kprobes_functions((unsigned long) p->addr)) { + preempt_enable(); return -EINVAL; + } p->mod_refcounted = 0; /* * Check if are we probing a module. */ - probed_mod = module_text_address((unsigned long) p->addr); + probed_mod = __module_text_address((unsigned long) p->addr); if (probed_mod) { - struct module *calling_mod = module_text_address(called_from); + struct module *calling_mod; + calling_mod = __module_text_address(called_from); /* * We must allow modules to probe themself and in this case * avoid incrementing the module refcount, so as to allow * unloading of self probing modules. */ if (calling_mod && calling_mod != probed_mod) { - if (unlikely(!try_module_get(probed_mod))) + if (unlikely(!try_module_get(probed_mod))) { + preempt_enable(); return -EINVAL; + } p->mod_refcounted = 1; } else probed_mod = NULL; } + preempt_enable(); p->nmissed = 0; INIT_LIST_HEAD(&p->list); @@ -718,6 +725,10 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) struct kprobe *old_p; if (p->mod_refcounted) { + /* + * Since we've already incremented refcount, + * we don't need to disable preemption. + */ mod = module_text_address((unsigned long)p->addr); if (mod) module_put(mod); diff --git a/kernel/kthread.c b/kernel/kthread.c index 8e7a7ce3ed0a..4fbc456f393d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; +DEFINE_TRACE(sched_kthread_stop); +DEFINE_TRACE(sched_kthread_stop_ret); + struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ diff --git a/kernel/marker.c b/kernel/marker.c index 2898b647d415..ea54f2647868 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -81,7 +81,7 @@ struct marker_entry { * though the function pointer change and the marker enabling are two distinct * operations that modifies the execution flow of preemptible code. */ -void __mark_empty_function(void *probe_private, void *call_private, +notrace void __mark_empty_function(void *probe_private, void *call_private, const char *fmt, va_list *args) { } @@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function); * need to put a full smp_rmb() in this branch. This is why we do not use * rcu_dereference() for the pointer read. */ -void marker_probe_cb(const struct marker *mdata, void *call_private, ...) +notrace void marker_probe_cb(const struct marker *mdata, + void *call_private, ...) { va_list args; char ptype; @@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) * sure the teardown of the callbacks can be done correctly when they * are in modules and they insure RCU read coherency. */ - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) va_end(args); } } - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); } EXPORT_SYMBOL_GPL(marker_probe_cb); @@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb); * * Should be connected to markers "MARK_NOARGS". */ -static void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) +static notrace void marker_probe_cb_noarg(const struct marker *mdata, + void *call_private, ...) { va_list args; /* not initialized */ char ptype; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -195,7 +197,7 @@ static void marker_probe_cb_noarg(const struct marker *mdata, void *call_private multi[i].func(multi[i].probe_private, call_private, mdata->format, &args); } - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); } static void free_old_closure(struct rcu_head *head) @@ -477,7 +479,7 @@ static int marker_set_format(struct marker_entry *entry, const char *format) static int set_marker(struct marker_entry *entry, struct marker *elem, int active) { - int ret; + int ret = 0; WARN_ON(strcmp(entry->name, elem->name) != 0); if (entry->format) { @@ -529,9 +531,40 @@ static int set_marker(struct marker_entry *entry, struct marker *elem, */ smp_wmb(); elem->ptype = entry->ptype; + + if (elem->tp_name && (active ^ elem->state)) { + WARN_ON(!elem->tp_cb); + /* + * It is ok to directly call the probe registration because type + * checking has been done in the __trace_mark_tp() macro. + */ + + if (active) { + /* + * try_module_get should always succeed because we hold + * lock_module() to get the tp_cb address. + */ + ret = try_module_get(__module_text_address( + (unsigned long)elem->tp_cb)); + BUG_ON(!ret); + ret = tracepoint_probe_register_noupdate( + elem->tp_name, + elem->tp_cb); + } else { + ret = tracepoint_probe_unregister_noupdate( + elem->tp_name, + elem->tp_cb); + /* + * tracepoint_probe_update_all() must be called + * before the module containing tp_cb is unloaded. + */ + module_put(__module_text_address( + (unsigned long)elem->tp_cb)); + } + } elem->state = active; - return 0; + return ret; } /* @@ -542,7 +575,24 @@ static int set_marker(struct marker_entry *entry, struct marker *elem, */ static void disable_marker(struct marker *elem) { + int ret; + /* leave "call" as is. It is known statically. */ + if (elem->tp_name && elem->state) { + WARN_ON(!elem->tp_cb); + /* + * It is ok to directly call the probe registration because type + * checking has been done in the __trace_mark_tp() macro. + */ + ret = tracepoint_probe_unregister_noupdate(elem->tp_name, + elem->tp_cb); + WARN_ON(ret); + /* + * tracepoint_probe_update_all() must be called + * before the module containing tp_cb is unloaded. + */ + module_put(__module_text_address((unsigned long)elem->tp_cb)); + } elem->state = 0; elem->single.func = __mark_empty_function; /* Update the function before setting the ptype */ @@ -606,6 +656,7 @@ static void marker_update_probes(void) marker_update_probe_range(__start___markers, __stop___markers); /* Markers in modules. */ module_update_markers(); + tracepoint_probe_update_all(); } /** @@ -653,10 +704,11 @@ int marker_probe_register(const char *name, const char *format, goto end; } mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker(name); - WARN_ON(!entry); + if (!entry) + goto end; if (entry->rcu_pending) rcu_barrier_sched(); entry->oldptr = old; @@ -697,7 +749,7 @@ int marker_probe_unregister(const char *name, rcu_barrier_sched(); old = marker_entry_remove_probe(entry, probe, probe_private); mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker(name); if (!entry) @@ -778,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe, rcu_barrier_sched(); old = marker_entry_remove_probe(entry, NULL, probe_private); mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker_from_private_data(probe, probe_private); - WARN_ON(!entry); + if (!entry) + goto end; if (entry->rcu_pending) rcu_barrier_sched(); entry->oldptr = old; @@ -842,3 +895,36 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe, return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(marker_get_private_data); + +#ifdef CONFIG_MODULES + +int marker_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + marker_update_probe_range(mod->markers, + mod->markers + mod->num_markers); + break; + case MODULE_STATE_GOING: + marker_update_probe_range(mod->markers, + mod->markers + mod->num_markers); + break; + } + return 0; +} + +struct notifier_block marker_module_nb = { + .notifier_call = marker_module_notify, + .priority = 0, +}; + +static int init_markers(void) +{ + return register_module_notifier(&marker_module_nb); +} +__initcall(init_markers); + +#endif /* CONFIG_MODULES */ diff --git a/kernel/module.c b/kernel/module.c index 69791274e899..89bcf7c1327d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2184,18 +2184,9 @@ static noinline struct module *load_module(void __user *umod, struct mod_debug *debug; unsigned int num_debug; -#ifdef CONFIG_MARKERS - marker_update_probe_range(mod->markers, - mod->markers + mod->num_markers); -#endif debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); dynamic_printk_setup(debug, num_debug); - -#ifdef CONFIG_TRACEPOINTS - tracepoint_update_probe_range(mod->tracepoints, - mod->tracepoints + mod->num_tracepoints); -#endif } /* sechdrs[0].sh_size is always zero */ diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 153dcb2639c3..895337b16a24 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1308,9 +1308,10 @@ static inline int task_cputime_expired(const struct task_cputime *sample, */ static inline int fastpath_timer_check(struct task_struct *tsk) { - struct signal_struct *sig = tsk->signal; + struct signal_struct *sig; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) return 0; if (!task_cputime_zero(&tsk->cputime_expires)) { @@ -1323,6 +1324,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) return 1; } + + sig = tsk->signal; if (!task_cputime_zero(&sig->cputime_expires)) { struct task_cputime group_sample; diff --git a/kernel/power/main.c b/kernel/power/main.c index 19122cf6d827..b8f7ce9473e8 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -174,7 +174,7 @@ static void suspend_test_finish(const char *label) * has some performance issues. The stack dump of a WARN_ON * is more likely to get the right attention than a printk... */ - WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000)); + WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label); } #else diff --git a/kernel/profile.c b/kernel/profile.c index 9830a037d8db..5b7d1ac7124c 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = { }; #ifdef CONFIG_SMP -static void __init profile_nop(void *unused) +static inline void profile_nop(void *unused) { } diff --git a/kernel/relay.c b/kernel/relay.c index 8d13a7855c08..32b0befdcb6a 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -400,7 +400,7 @@ void relay_reset(struct rchan *chan) } mutex_lock(&relay_channels_mutex); - for_each_online_cpu(i) + for_each_possible_cpu(i) if (chan->buf[i]) __relay_reset(chan->buf[i], 0); mutex_unlock(&relay_channels_mutex); @@ -611,10 +611,9 @@ struct rchan *relay_open(const char *base_filename, return chan; free_bufs: - for_each_online_cpu(i) { - if (!chan->buf[i]) - break; - relay_close_buf(chan->buf[i]); + for_each_possible_cpu(i) { + if (chan->buf[i]) + relay_close_buf(chan->buf[i]); } kref_put(&chan->kref, relay_destroy_channel); diff --git a/kernel/sched.c b/kernel/sched.c index 50a21f964679..4de56108c86f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -118,6 +118,12 @@ */ #define RUNTIME_INF ((u64)~0ULL) +DEFINE_TRACE(sched_wait_task); +DEFINE_TRACE(sched_wakeup); +DEFINE_TRACE(sched_wakeup_new); +DEFINE_TRACE(sched_switch); +DEFINE_TRACE(sched_migrate_task); + #ifdef CONFIG_SMP /* * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) @@ -1456,6 +1462,8 @@ static unsigned long cpu_avg_load_per_task(int cpu) if (rq->nr_running) rq->avg_load_per_task = rq->load.weight / rq->nr_running; + else + rq->avg_load_per_task = 0; return rq->avg_load_per_task; } @@ -5868,6 +5876,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; + spin_lock_irqsave(&rq->lock, flags); + __sched_fork(idle); idle->se.exec_start = sched_clock(); @@ -5875,7 +5885,6 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) idle->cpus_allowed = cpumask_of_cpu(cpu); __set_task_cpu(idle, cpu); - spin_lock_irqsave(&rq->lock, flags); rq->curr = rq->idle = idle; #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) idle->oncpu = 1; @@ -7786,13 +7795,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * * The passed in 'doms_new' should be kmalloc'd. This routine takes * ownership of it and will kfree it when done with it. If the caller - * failed the kmalloc call, then it can pass in doms_new == NULL, - * and partition_sched_domains() will fallback to the single partition - * 'fallback_doms', it also forces the domains to be rebuilt. + * failed the kmalloc call, then it can pass in doms_new == NULL && + * ndoms_new == 1, and partition_sched_domains() will fallback to + * the single partition 'fallback_doms', it also forces the domains + * to be rebuilt. * - * If doms_new==NULL it will be replaced with cpu_online_map. - * ndoms_new==0 is a special case for destroying existing domains. - * It will not create the default domain. + * If doms_new == NULL it will be replaced with cpu_online_map. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. * * Call with hotplug lock held */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 48ecc51e7701..26ed8e3d1c15 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -423,10 +423,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #undef __P { + unsigned int this_cpu = raw_smp_processor_id(); u64 t0, t1; - t0 = sched_clock(); - t1 = sched_clock(); + t0 = cpu_clock(this_cpu); + t1 = cpu_clock(this_cpu); SEQ_printf(m, "%-35s:%21Ld\n", "clock-delta", (long long)(t1-t0)); } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index ee71bec1da66..7dbf72a2b02c 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -298,9 +298,11 @@ static inline void account_group_user_time(struct task_struct *tsk, { struct signal_struct *sig; - sig = tsk->signal; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal */ + if (unlikely(tsk->exit_state)) return; + + sig = tsk->signal; if (sig->cputime.totals) { struct task_cputime *times; @@ -325,9 +327,11 @@ static inline void account_group_system_time(struct task_struct *tsk, { struct signal_struct *sig; - sig = tsk->signal; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal */ + if (unlikely(tsk->exit_state)) return; + + sig = tsk->signal; if (sig->cputime.totals) { struct task_cputime *times; @@ -353,8 +357,11 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, struct signal_struct *sig; sig = tsk->signal; + /* see __exit_signal()->task_rq_unlock_wait() */ + barrier(); if (unlikely(!sig)) return; + if (sig->cputime.totals) { struct task_cputime *times; diff --git a/kernel/signal.c b/kernel/signal.c index 4530fc654455..e9afe63da24b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -41,6 +41,8 @@ static struct kmem_cache *sigqueue_cachep; +DEFINE_TRACE(sched_signal_send); + static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 9bc4c00872c9..24e8ceacc388 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -112,7 +112,7 @@ static int chill(void *unused) int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) { struct work_struct *sm_work; - int i; + int i, ret; /* Set up initial state. */ mutex_lock(&lock); @@ -137,8 +137,9 @@ int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) /* This will release the thread on our CPU. */ put_cpu(); flush_workqueue(stop_machine_wq); + ret = active.fnret; mutex_unlock(&lock); - return active.fnret; + return ret; } int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9c89526b6b7c..b8378fad29a3 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -59,7 +59,6 @@ config FUNCTION_TRACER config FUNCTION_RET_TRACER bool "Kernel Function return Tracer" - depends on !DYNAMIC_FTRACE depends on HAVE_FUNCTION_RET_TRACER depends on FUNCTION_TRACER help diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b42ec1de546b..f212da486689 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -50,6 +50,9 @@ static int last_ftrace_enabled; /* Quick disabling of function tracer. */ int function_trace_stop; +/* By default, current tracing type is normal tracing. */ +enum ftrace_tracing_type_t ftrace_tracing_type = FTRACE_TYPE_ENTER; + /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. @@ -385,12 +388,21 @@ static void ftrace_bug(int failed, unsigned long ip) } } -#define FTRACE_ADDR ((long)(ftrace_caller)) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { unsigned long ip, fl; + unsigned long ftrace_addr; + +#ifdef CONFIG_FUNCTION_RET_TRACER + if (ftrace_tracing_type == FTRACE_TYPE_ENTER) + ftrace_addr = (unsigned long)ftrace_caller; + else + ftrace_addr = (unsigned long)ftrace_return_caller; +#else + ftrace_addr = (unsigned long)ftrace_caller; +#endif ip = rec->ip; @@ -450,9 +462,9 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) } if (rec->flags & FTRACE_FL_ENABLED) - return ftrace_make_call(rec, FTRACE_ADDR); + return ftrace_make_call(rec, ftrace_addr); else - return ftrace_make_nop(NULL, rec, FTRACE_ADDR); + return ftrace_make_nop(NULL, rec, ftrace_addr); } static void ftrace_replace_code(int enable) @@ -682,7 +694,7 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) cnt = num_to_init / ENTRIES_PER_PAGE; pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt); + num_to_init, cnt + 1); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -765,13 +777,11 @@ static void *t_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l = -1; - if (*pos != iter->pos) { - for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) - ; - } else { - l = *pos; - p = t_next(m, p, &l); - } + if (*pos > iter->pos) + *pos = iter->pos; + + l = *pos; + p = t_next(m, p, &l); return p; } @@ -782,15 +792,21 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; if (!rec) return 0; kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - seq_printf(m, "%s\n", str); + ret = seq_printf(m, "%s\n", str); + if (ret < 0) { + iter->pos--; + iter->idx--; + } return 0; } @@ -816,7 +832,7 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -903,7 +919,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; iter->flags = enable ? FTRACE_ITER_FILTER : FTRACE_ITER_NOTRACE; @@ -1405,10 +1421,17 @@ int register_ftrace_function(struct ftrace_ops *ops) return -1; mutex_lock(&ftrace_sysctl_lock); + + if (ftrace_tracing_type == FTRACE_TYPE_RETURN) { + ret = -EBUSY; + goto out; + } + ret = __register_ftrace_function(ops); ftrace_startup(); - mutex_unlock(&ftrace_sysctl_lock); +out: + mutex_unlock(&ftrace_sysctl_lock); return ret; } @@ -1474,16 +1497,45 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, } #ifdef CONFIG_FUNCTION_RET_TRACER + +/* The callback that hooks the return of a function */ trace_function_return_t ftrace_function_return = (trace_function_return_t)ftrace_stub; -void register_ftrace_return(trace_function_return_t func) + +int register_ftrace_return(trace_function_return_t func) { + int ret = 0; + + mutex_lock(&ftrace_sysctl_lock); + + /* + * Don't launch return tracing if normal function + * tracing is already running. + */ + if (ftrace_trace_function != ftrace_stub) { + ret = -EBUSY; + goto out; + } + + ftrace_tracing_type = FTRACE_TYPE_RETURN; ftrace_function_return = func; + ftrace_startup(); + +out: + mutex_unlock(&ftrace_sysctl_lock); + return ret; } void unregister_ftrace_return(void) { + mutex_lock(&ftrace_sysctl_lock); + ftrace_function_return = (trace_function_return_t)ftrace_stub; + ftrace_shutdown(); + /* Restore normal tracing type */ + ftrace_tracing_type = FTRACE_TYPE_ENTER; + + mutex_unlock(&ftrace_sysctl_lock); } #endif diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index caa4fda50f8a..85ced143c2c4 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -622,6 +622,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) list_del_init(&page->list); free_buffer_page(page); } + mutex_unlock(&buffer->mutex); return -ENOMEM; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 24b6238884f0..5653c6b07ba1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -259,9 +259,7 @@ static const char *trace_options[] = { "sched-tree", "ftrace_printk", "ftrace_preempt", -#ifdef CONFIG_BRANCH_TRACER "branch", -#endif "annotate", NULL }; @@ -2189,6 +2187,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) ring_buffer_read_finish(iter->buffer_iter[cpu]); } mutex_unlock(&trace_types_lock); + kfree(iter); return ERR_PTR(-ENOMEM); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index cdbd5cc22be8..37947f6b92bf 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -471,9 +471,7 @@ enum trace_iterator_flags { TRACE_ITER_SCHED_TREE = 0x200, TRACE_ITER_PRINTK = 0x400, TRACE_ITER_PREEMPTONLY = 0x800, -#ifdef CONFIG_BRANCH_TRACER TRACE_ITER_BRANCH = 0x1000, -#endif TRACE_ITER_ANNOTATE = 0x2000, }; diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 44bd39539d61..23f9b02ce967 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -41,7 +41,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) if (unlikely(!tr)) return; - local_irq_save(flags); + raw_local_irq_save(flags); cpu = raw_smp_processor_id(); if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) goto out; @@ -73,7 +73,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) out: atomic_dec(&tr->data[cpu]->disabled); - local_irq_restore(flags); + raw_local_irq_restore(flags); } static inline diff --git a/kernel/trace/trace_functions_return.c b/kernel/trace/trace_functions_return.c index 61185f756a13..a68564af022b 100644 --- a/kernel/trace/trace_functions_return.c +++ b/kernel/trace/trace_functions_return.c @@ -14,29 +14,18 @@ #include "trace.h" -static void start_return_trace(struct trace_array *tr) -{ - register_ftrace_return(&trace_function_return); -} - -static void stop_return_trace(struct trace_array *tr) -{ - unregister_ftrace_return(); -} - static int return_trace_init(struct trace_array *tr) { int cpu; for_each_online_cpu(cpu) tracing_reset(tr, cpu); - start_return_trace(tr); - return 0; + return register_ftrace_return(&trace_function_return); } static void return_trace_reset(struct trace_array *tr) { - stop_return_trace(tr); + unregister_ftrace_return(); } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index e96590f17de1..79602740bbb5 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -262,6 +262,7 @@ static void set_tracepoint(struct tracepoint_entry **entry, static void disable_tracepoint(struct tracepoint *elem) { elem->state = 0; + rcu_assign_pointer(elem->funcs, NULL); } /** @@ -540,3 +541,36 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter) iter->tracepoint = NULL; } EXPORT_SYMBOL_GPL(tracepoint_iter_reset); + +#ifdef CONFIG_MODULES + +int tracepoint_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + break; + case MODULE_STATE_GOING: + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + break; + } + return 0; +} + +struct notifier_block tracepoint_module_nb = { + .notifier_call = tracepoint_module_notify, + .priority = 0, +}; + +static int init_tracepoints(void) +{ + return register_module_notifier(&tracepoint_module_nb); +} +__initcall(init_tracepoints); + +#endif /* CONFIG_MODULES */ |