diff options
Diffstat (limited to 'kernel')
38 files changed, 993 insertions, 383 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index 9f3391090b3e..9a4715a2f6bf 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -491,13 +491,17 @@ static void do_acct_process(struct bsd_acct_struct *acct, u64 run_time; struct timespec uptime; struct tty_struct *tty; + const struct cred *orig_cred; + + /* Perform file operations on behalf of whoever enabled accounting */ + orig_cred = override_creds(file->f_cred); /* * First check to see if there is enough free_space to continue * the process accounting system. */ if (!check_free_space(acct, file)) - return; + goto out; /* * Fill the accounting struct with the needed info as recorded @@ -578,6 +582,8 @@ static void do_acct_process(struct bsd_acct_struct *acct, sizeof(acct_t), &file->f_pos); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; set_fs(fs); +out: + revert_creds(orig_cred); } /** diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b6eadfe30e7b..c7ece8f027f2 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -600,6 +600,7 @@ static struct inode_operations cgroup_dir_inode_operations; static struct file_operations proc_cgroupstats_operations; static struct backing_dev_info cgroup_backing_dev_info = { + .name = "cgroup", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; diff --git a/kernel/cred.c b/kernel/cred.c index 1bb4d7e5d616..006fcab009d5 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -18,6 +18,18 @@ #include <linux/cn_proc.h> #include "cred-internals.h" +#if 0 +#define kdebug(FMT, ...) \ + printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__) +#else +static inline __attribute__((format(printf, 1, 2))) +void no_printk(const char *fmt, ...) +{ +} +#define kdebug(FMT, ...) \ + no_printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__) +#endif + static struct kmem_cache *cred_jar; /* @@ -36,6 +48,10 @@ static struct thread_group_cred init_tgcred = { */ struct cred init_cred = { .usage = ATOMIC_INIT(4), +#ifdef CONFIG_DEBUG_CREDENTIALS + .subscribers = ATOMIC_INIT(2), + .magic = CRED_MAGIC, +#endif .securebits = SECUREBITS_DEFAULT, .cap_inheritable = CAP_INIT_INH_SET, .cap_permitted = CAP_FULL_SET, @@ -48,6 +64,31 @@ struct cred init_cred = { #endif }; +static inline void set_cred_subscribers(struct cred *cred, int n) +{ +#ifdef CONFIG_DEBUG_CREDENTIALS + atomic_set(&cred->subscribers, n); +#endif +} + +static inline int read_cred_subscribers(const struct cred *cred) +{ +#ifdef CONFIG_DEBUG_CREDENTIALS + return atomic_read(&cred->subscribers); +#else + return 0; +#endif +} + +static inline void alter_cred_subscribers(const struct cred *_cred, int n) +{ +#ifdef CONFIG_DEBUG_CREDENTIALS + struct cred *cred = (struct cred *) _cred; + + atomic_add(n, &cred->subscribers); +#endif +} + /* * Dispose of the shared task group credentials */ @@ -85,9 +126,22 @@ static void put_cred_rcu(struct rcu_head *rcu) { struct cred *cred = container_of(rcu, struct cred, rcu); + kdebug("put_cred_rcu(%p)", cred); + +#ifdef CONFIG_DEBUG_CREDENTIALS + if (cred->magic != CRED_MAGIC_DEAD || + atomic_read(&cred->usage) != 0 || + read_cred_subscribers(cred) != 0) + panic("CRED: put_cred_rcu() sees %p with" + " mag %x, put %p, usage %d, subscr %d\n", + cred, cred->magic, cred->put_addr, + atomic_read(&cred->usage), + read_cred_subscribers(cred)); +#else if (atomic_read(&cred->usage) != 0) panic("CRED: put_cred_rcu() sees %p with usage %d\n", cred, atomic_read(&cred->usage)); +#endif security_cred_free(cred); key_put(cred->thread_keyring); @@ -106,12 +160,90 @@ static void put_cred_rcu(struct rcu_head *rcu) */ void __put_cred(struct cred *cred) { + kdebug("__put_cred(%p{%d,%d})", cred, + atomic_read(&cred->usage), + read_cred_subscribers(cred)); + BUG_ON(atomic_read(&cred->usage) != 0); +#ifdef CONFIG_DEBUG_CREDENTIALS + BUG_ON(read_cred_subscribers(cred) != 0); + cred->magic = CRED_MAGIC_DEAD; + cred->put_addr = __builtin_return_address(0); +#endif + BUG_ON(cred == current->cred); + BUG_ON(cred == current->real_cred); call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); +/* + * Clean up a task's credentials when it exits + */ +void exit_creds(struct task_struct *tsk) +{ + struct cred *cred; + + kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred, + atomic_read(&tsk->cred->usage), + read_cred_subscribers(tsk->cred)); + + cred = (struct cred *) tsk->real_cred; + tsk->real_cred = NULL; + validate_creds(cred); + alter_cred_subscribers(cred, -1); + put_cred(cred); + + cred = (struct cred *) tsk->cred; + tsk->cred = NULL; + validate_creds(cred); + alter_cred_subscribers(cred, -1); + put_cred(cred); + + cred = (struct cred *) tsk->replacement_session_keyring; + if (cred) { + tsk->replacement_session_keyring = NULL; + validate_creds(cred); + put_cred(cred); + } +} + +/* + * Allocate blank credentials, such that the credentials can be filled in at a + * later date without risk of ENOMEM. + */ +struct cred *cred_alloc_blank(void) +{ + struct cred *new; + + new = kmem_cache_zalloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + +#ifdef CONFIG_KEYS + new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL); + if (!new->tgcred) { + kfree(new); + return NULL; + } + atomic_set(&new->tgcred->usage, 1); +#endif + + atomic_set(&new->usage, 1); + + if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + goto error; + +#ifdef CONFIG_DEBUG_CREDENTIALS + new->magic = CRED_MAGIC; +#endif + return new; + +error: + abort_creds(new); + return NULL; +} + /** * prepare_creds - Prepare a new set of credentials for modification * @@ -132,16 +264,19 @@ struct cred *prepare_creds(void) const struct cred *old; struct cred *new; - BUG_ON(atomic_read(&task->real_cred->usage) < 1); + validate_process_creds(); new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; + kdebug("prepare_creds() alloc %p", new); + old = task->cred; memcpy(new, old, sizeof(struct cred)); atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); get_group_info(new->group_info); get_uid(new->user); @@ -157,6 +292,7 @@ struct cred *prepare_creds(void) if (security_prepare_creds(new, old, GFP_KERNEL) < 0) goto error; + validate_creds(new); return new; error: @@ -229,9 +365,12 @@ struct cred *prepare_usermodehelper_creds(void) if (!new) return NULL; + kdebug("prepare_usermodehelper_creds() alloc %p", new); + memcpy(new, &init_cred, sizeof(struct cred)); atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); get_group_info(new->group_info); get_uid(new->user); @@ -250,6 +389,7 @@ struct cred *prepare_usermodehelper_creds(void) #endif if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0) goto error; + validate_creds(new); BUG_ON(atomic_read(&new->usage) != 1); return new; @@ -286,6 +426,10 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) ) { p->real_cred = get_cred(p->cred); get_cred(p->cred); + alter_cred_subscribers(p->cred, 2); + kdebug("share_creds(%p{%d,%d})", + p->cred, atomic_read(&p->cred->usage), + read_cred_subscribers(p->cred)); atomic_inc(&p->cred->user->processes); return 0; } @@ -331,6 +475,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) atomic_inc(&new->user->processes); p->cred = p->real_cred = get_cred(new); + alter_cred_subscribers(new, 2); + validate_creds(new); return 0; error_put: @@ -355,13 +501,20 @@ error_put: int commit_creds(struct cred *new) { struct task_struct *task = current; - const struct cred *old; + const struct cred *old = task->real_cred; - BUG_ON(task->cred != task->real_cred); - BUG_ON(atomic_read(&task->real_cred->usage) < 2); + kdebug("commit_creds(%p{%d,%d})", new, + atomic_read(&new->usage), + read_cred_subscribers(new)); + + BUG_ON(task->cred != old); +#ifdef CONFIG_DEBUG_CREDENTIALS + BUG_ON(read_cred_subscribers(old) < 2); + validate_creds(old); + validate_creds(new); +#endif BUG_ON(atomic_read(&new->usage) < 1); - old = task->real_cred; security_commit_creds(new, old); get_cred(new); /* we will require a ref for the subj creds too */ @@ -390,12 +543,14 @@ int commit_creds(struct cred *new) * cheaply with the new uid cache, so if it matters * we should be checking for it. -DaveM */ + alter_cred_subscribers(new, 2); if (new->user != old->user) atomic_inc(&new->user->processes); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user) atomic_dec(&old->user->processes); + alter_cred_subscribers(old, -2); sched_switch_user(task); @@ -428,6 +583,13 @@ EXPORT_SYMBOL(commit_creds); */ void abort_creds(struct cred *new) { + kdebug("abort_creds(%p{%d,%d})", new, + atomic_read(&new->usage), + read_cred_subscribers(new)); + +#ifdef CONFIG_DEBUG_CREDENTIALS + BUG_ON(read_cred_subscribers(new) != 0); +#endif BUG_ON(atomic_read(&new->usage) < 1); put_cred(new); } @@ -444,7 +606,20 @@ const struct cred *override_creds(const struct cred *new) { const struct cred *old = current->cred; - rcu_assign_pointer(current->cred, get_cred(new)); + kdebug("override_creds(%p{%d,%d})", new, + atomic_read(&new->usage), + read_cred_subscribers(new)); + + validate_creds(old); + validate_creds(new); + get_cred(new); + alter_cred_subscribers(new, 1); + rcu_assign_pointer(current->cred, new); + alter_cred_subscribers(old, -1); + + kdebug("override_creds() = %p{%d,%d}", old, + atomic_read(&old->usage), + read_cred_subscribers(old)); return old; } EXPORT_SYMBOL(override_creds); @@ -460,7 +635,15 @@ void revert_creds(const struct cred *old) { const struct cred *override = current->cred; + kdebug("revert_creds(%p{%d,%d})", old, + atomic_read(&old->usage), + read_cred_subscribers(old)); + + validate_creds(old); + validate_creds(override); + alter_cred_subscribers(old, 1); rcu_assign_pointer(current->cred, old); + alter_cred_subscribers(override, -1); put_cred(override); } EXPORT_SYMBOL(revert_creds); @@ -502,11 +685,15 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (!new) return NULL; + kdebug("prepare_kernel_cred() alloc %p", new); + if (daemon) old = get_task_cred(daemon); else old = get_cred(&init_cred); + validate_creds(old); + *new = *old; get_uid(new->user); get_group_info(new->group_info); @@ -526,7 +713,9 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) goto error; atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); put_cred(old); + validate_creds(new); return new; error: @@ -589,3 +778,95 @@ int set_create_files_as(struct cred *new, struct inode *inode) return security_kernel_create_files_as(new, inode); } EXPORT_SYMBOL(set_create_files_as); + +#ifdef CONFIG_DEBUG_CREDENTIALS + +/* + * dump invalid credentials + */ +static void dump_invalid_creds(const struct cred *cred, const char *label, + const struct task_struct *tsk) +{ + printk(KERN_ERR "CRED: %s credentials: %p %s%s%s\n", + label, cred, + cred == &init_cred ? "[init]" : "", + cred == tsk->real_cred ? "[real]" : "", + cred == tsk->cred ? "[eff]" : ""); + printk(KERN_ERR "CRED: ->magic=%x, put_addr=%p\n", + cred->magic, cred->put_addr); + printk(KERN_ERR "CRED: ->usage=%d, subscr=%d\n", + atomic_read(&cred->usage), + read_cred_subscribers(cred)); + printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n", + cred->uid, cred->euid, cred->suid, cred->fsuid); + printk(KERN_ERR "CRED: ->*gid = { %d,%d,%d,%d }\n", + cred->gid, cred->egid, cred->sgid, cred->fsgid); +#ifdef CONFIG_SECURITY + printk(KERN_ERR "CRED: ->security is %p\n", cred->security); + if ((unsigned long) cred->security >= PAGE_SIZE && + (((unsigned long) cred->security & 0xffffff00) != + (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))) + printk(KERN_ERR "CRED: ->security {%x, %x}\n", + ((u32*)cred->security)[0], + ((u32*)cred->security)[1]); +#endif +} + +/* + * report use of invalid credentials + */ +void __invalid_creds(const struct cred *cred, const char *file, unsigned line) +{ + printk(KERN_ERR "CRED: Invalid credentials\n"); + printk(KERN_ERR "CRED: At %s:%u\n", file, line); + dump_invalid_creds(cred, "Specified", current); + BUG(); +} +EXPORT_SYMBOL(__invalid_creds); + +/* + * check the credentials on a process + */ +void __validate_process_creds(struct task_struct *tsk, + const char *file, unsigned line) +{ + if (tsk->cred == tsk->real_cred) { + if (unlikely(read_cred_subscribers(tsk->cred) < 2 || + creds_are_invalid(tsk->cred))) + goto invalid_creds; + } else { + if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 || + read_cred_subscribers(tsk->cred) < 1 || + creds_are_invalid(tsk->real_cred) || + creds_are_invalid(tsk->cred))) + goto invalid_creds; + } + return; + +invalid_creds: + printk(KERN_ERR "CRED: Invalid process credentials\n"); + printk(KERN_ERR "CRED: At %s:%u\n", file, line); + + dump_invalid_creds(tsk->real_cred, "Real", tsk); + if (tsk->cred != tsk->real_cred) + dump_invalid_creds(tsk->cred, "Effective", tsk); + else + printk(KERN_ERR "CRED: Effective creds == Real creds\n"); + BUG(); +} +EXPORT_SYMBOL(__validate_process_creds); + +/* + * check creds for do_exit() + */ +void validate_creds_for_do_exit(struct task_struct *tsk) +{ + kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})", + tsk->real_cred, tsk->cred, + atomic_read(&tsk->cred->usage), + read_cred_subscribers(tsk->cred)); + + __validate_process_creds(tsk, __FILE__, __LINE__); +} + +#endif /* CONFIG_DEBUG_CREDENTIALS */ diff --git a/kernel/exit.c b/kernel/exit.c index 869dc221733e..c98ff7a8025f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -901,6 +901,8 @@ NORET_TYPE void do_exit(long code) tracehook_report_exit(&code); + validate_creds_for_do_exit(tsk); + /* * We're taking recursive faults here in do_exit. Safest is to just * leave this task alone and wait for reboot. @@ -1009,6 +1011,8 @@ NORET_TYPE void do_exit(long code) if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); + validate_creds_for_do_exit(tsk); + preempt_disable(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; diff --git a/kernel/fork.c b/kernel/fork.c index 29b532e718f7..aab8579c6093 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -152,8 +152,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); - put_cred(tsk->real_cred); - put_cred(tsk->cred); + exit_creds(tsk); delayacct_tsk_free(tsk); if (!profile_handoff_task(tsk)) @@ -426,7 +425,6 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); mm->flags = (current->mm) ? current->mm->flags : default_dump_filter; - mm->oom_adj = (current->mm) ? current->mm->oom_adj : 0; mm->core_state = NULL; mm->nr_ptes = 0; set_mm_counter(mm, file_rss, 0); @@ -568,18 +566,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) * the value intact in a core dump, and to save the unnecessary * trouble otherwise. Userland only wants this done for a sys_exit. */ - if (tsk->clear_child_tid - && !(tsk->flags & PF_SIGNALED) - && atomic_read(&mm->mm_users) > 1) { - u32 __user * tidptr = tsk->clear_child_tid; + if (tsk->clear_child_tid) { + if (!(tsk->flags & PF_SIGNALED) && + atomic_read(&mm->mm_users) > 1) { + /* + * We don't check the error code - if userspace has + * not set up a proper pointer then tough luck. + */ + put_user(0, tsk->clear_child_tid); + sys_futex(tsk->clear_child_tid, FUTEX_WAKE, + 1, NULL, NULL, 0); + } tsk->clear_child_tid = NULL; - - /* - * We don't check the error code - if userspace has - * not set up a proper pointer then tough luck. - */ - put_user(0, tidptr); - sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0); } } @@ -816,11 +814,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; - if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); + if (clone_flags & CLONE_THREAD) return 0; - } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -878,16 +873,6 @@ void __cleanup_signal(struct signal_struct *sig) kmem_cache_free(signal_cachep, sig); } -static void cleanup_signal(struct task_struct *tsk) -{ - struct signal_struct *sig = tsk->signal; - - atomic_dec(&sig->live); - - if (atomic_dec_and_test(&sig->count)) - __cleanup_signal(sig); -} - static void copy_flags(unsigned long clone_flags, struct task_struct *p) { unsigned long new_flags = p->flags; @@ -1240,6 +1225,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (clone_flags & CLONE_THREAD) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); } @@ -1269,6 +1256,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); + perf_counter_fork(p); return p; bad_fork_free_pid: @@ -1282,7 +1270,8 @@ bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: - cleanup_signal(p); + if (!(clone_flags & CLONE_THREAD)) + __cleanup_signal(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: @@ -1307,8 +1296,7 @@ bad_fork_cleanup_put_domain: module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); - put_cred(p->real_cred); - put_cred(p->cred); + exit_creds(p); bad_fork_free: free_task(p); fork_out: @@ -1410,9 +1398,6 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - if (!(clone_flags & CLONE_THREAD)) - perf_counter_fork(p); - audit_finish_fork(p); tracehook_report_clone(regs, clone_flags, nr, p); diff --git a/kernel/futex.c b/kernel/futex.c index 0672ff88f159..e18cfbdc7190 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1010,15 +1010,19 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue * q: the futex_q * key: the key of the requeue target futex + * hb: the hash_bucket of the requeue target futex * * During futex_requeue, with requeue_pi=1, it is possible to acquire the * target futex if it is uncontended or via a lock steal. Set the futex_q key * to the requeue target futex so the waiter can detect the wakeup on the right * futex, but remove it from the hb and NULL the rt_waiter so it can detect - * atomic lock acquisition. Must be called with the q->lock_ptr held. + * atomic lock acquisition. Set the q->lock_ptr to the requeue target hb->lock + * to protect access to the pi_state to fixup the owner later. Must be called + * with both q->lock_ptr and hb->lock held. */ static inline -void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key) +void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, + struct futex_hash_bucket *hb) { drop_futex_key_refs(&q->key); get_futex_key_refs(key); @@ -1030,6 +1034,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key) WARN_ON(!q->rt_waiter); q->rt_waiter = NULL; + q->lock_ptr = &hb->lock; +#ifdef CONFIG_DEBUG_PI_LIST + q->list.plist.lock = &hb->lock; +#endif + wake_up_state(q->task, TASK_NORMAL); } @@ -1088,7 +1097,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex, ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, set_waiters); if (ret == 1) - requeue_pi_wake_futex(top_waiter, key2); + requeue_pi_wake_futex(top_waiter, key2, hb2); return ret; } @@ -1247,8 +1256,15 @@ retry_private: if (!match_futex(&this->key, &key1)) continue; - WARN_ON(!requeue_pi && this->rt_waiter); - WARN_ON(requeue_pi && !this->rt_waiter); + /* + * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always + * be paired with each other and no other futex ops. + */ + if ((requeue_pi && !this->rt_waiter) || + (!requeue_pi && this->rt_waiter)) { + ret = -EINVAL; + break; + } /* * Wake nr_wake waiters. For requeue_pi, if we acquired the @@ -1273,7 +1289,7 @@ retry_private: this->task, 1); if (ret == 1) { /* We got the lock. */ - requeue_pi_wake_futex(this, &key2); + requeue_pi_wake_futex(this, &key2, hb2); continue; } else if (ret) { /* -EDEADLK */ diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index d607a5b9ee29..235716556bf1 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -180,7 +180,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, int cmd = op & FUTEX_CMD_MASK; if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET)) { + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { if (get_compat_timespec(&ts, utime)) return -EFAULT; if (!timespec_valid(&ts)) @@ -191,7 +192,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, t = ktime_add_safe(ktime_get(), t); tp = &t; } - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE) + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) val2 = (int) (unsigned long) utime; return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 61c679db4687..0ec9ed831737 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -607,7 +607,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ get_task_struct(t); new->thread = t; - wake_up_process(t); } /* @@ -690,6 +689,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) (int)(new->flags & IRQF_TRIGGER_MASK)); } + new->irq = irq; *old_ptr = new; /* Reset broken irq detection when installing new handler */ @@ -707,7 +707,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) spin_unlock_irqrestore(&desc->lock, flags); - new->irq = irq; + /* + * Strictly no need to wake it up, but hung_task complains + * when no hard interrupt wakes the thread up. + */ + if (new->thread) + wake_up_process(new->thread); + register_irq_proc(irq, desc); new->dir = NULL; register_handler_proc(irq, new); @@ -761,7 +767,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action, **action_ptr; - struct task_struct *irqthread; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); @@ -809,9 +814,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) desc->chip->disable(irq); } - irqthread = action->thread; - action->thread = NULL; - spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); @@ -819,12 +821,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* Make sure it's not being used on another CPU: */ synchronize_irq(irq); - if (irqthread) { - if (!test_bit(IRQTF_DIED, &action->thread_flags)) - kthread_stop(irqthread); - put_task_struct(irqthread); - } - #ifdef CONFIG_DEBUG_SHIRQ /* * It's a shared IRQ -- the driver ought to be prepared for an IRQ @@ -840,6 +836,13 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) local_irq_restore(flags); } #endif + + if (action->thread) { + if (!test_bit(IRQTF_DIED, &action->thread_flags)) + kthread_stop(action->thread); + put_task_struct(action->thread); + } + return action; } diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index 2f69bee57bf2..3fd30197da2e 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -107,8 +107,8 @@ out_unlock: struct irq_desc *move_irq_desc(struct irq_desc *desc, int node) { - /* those all static, do move them */ - if (desc->irq < NR_IRQS_LEGACY) + /* those static or target node is -1, do not move them */ + if (desc->irq < NR_IRQS_LEGACY || node == -1) return desc; if (desc->node != node) diff --git a/kernel/kmod.c b/kernel/kmod.c index 385c31a1bdbf..4e8cae2e9148 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -78,6 +78,10 @@ int __request_module(bool wait, const char *fmt, ...) #define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */ static int kmod_loop_msg; + ret = security_kernel_module_request(); + if (ret) + return ret; + va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); @@ -462,6 +466,7 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int retval = 0; BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + validate_creds(sub_info->cred); helper_lock(); if (sub_info->path[0] == '\0') diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index d7135aa2d2c4..e94caa666dba 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -758,7 +758,8 @@ static int __init lockdep_proc_init(void) &proc_lockdep_stats_operations); #ifdef CONFIG_LOCK_STAT - proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations); + proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, + &proc_lock_stat_operations); #endif return 0; diff --git a/kernel/module.c b/kernel/module.c index fd1411403558..2d537186191f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -909,16 +909,18 @@ void __symbol_put(const char *symbol) } EXPORT_SYMBOL(__symbol_put); +/* Note this assumes addr is a function, which it currently always is. */ void symbol_put_addr(void *addr) { struct module *modaddr; + unsigned long a = (unsigned long)dereference_function_descriptor(addr); - if (core_kernel_text((unsigned long)addr)) + if (core_kernel_text(a)) return; /* module_text_address is safe here: we're supposed to have reference * to module from symbol_get, so it can't go away. */ - modaddr = __module_text_address((unsigned long)addr); + modaddr = __module_text_address(a); BUG_ON(!modaddr); module_put(modaddr); } @@ -1272,6 +1274,10 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, struct module_notes_attrs *notes_attrs; struct bin_attribute *nattr; + /* failed to create section attributes, so can't create notes */ + if (!mod->sect_attrs) + return; + /* Count notes sections and allocate structures. */ notes = 0; for (i = 0; i < nsect; i++) diff --git a/kernel/panic.c b/kernel/panic.c index 984b3ecbd72c..512ab73b0ca3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -301,6 +301,7 @@ int oops_may_print(void) */ void oops_enter(void) { + tracing_off(); /* can't trust the integrity of the kernel anymore: */ debug_locks_off(); do_oops_enter_exit(); diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 950931041954..d7cbc579fc80 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -42,6 +42,7 @@ static int perf_overcommit __read_mostly = 1; static atomic_t nr_counters __read_mostly; static atomic_t nr_mmap_counters __read_mostly; static atomic_t nr_comm_counters __read_mostly; +static atomic_t nr_task_counters __read_mostly; /* * perf counter paranoia level: @@ -49,7 +50,7 @@ static atomic_t nr_comm_counters __read_mostly; * 1 - disallow cpu counters to unpriv * 2 - disallow kernel profiling to unpriv */ -int sysctl_perf_counter_paranoid __read_mostly; +int sysctl_perf_counter_paranoid __read_mostly = 1; static inline bool perf_paranoid_cpu(void) { @@ -87,6 +88,7 @@ void __weak hw_perf_disable(void) { barrier(); } void __weak hw_perf_enable(void) { barrier(); } void __weak hw_perf_counter_setup(int cpu) { barrier(); } +void __weak hw_perf_counter_setup_online(int cpu) { barrier(); } int __weak hw_perf_group_sched_in(struct perf_counter *group_leader, @@ -305,6 +307,10 @@ counter_sched_out(struct perf_counter *counter, return; counter->state = PERF_COUNTER_STATE_INACTIVE; + if (counter->pending_disable) { + counter->pending_disable = 0; + counter->state = PERF_COUNTER_STATE_OFF; + } counter->tstamp_stopped = ctx->time; counter->pmu->disable(counter); counter->oncpu = -1; @@ -1103,7 +1109,7 @@ static void perf_counter_sync_stat(struct perf_counter_context *ctx, __perf_counter_sync_stat(counter, next_counter); counter = list_next_entry(counter, event_entry); - next_counter = list_next_entry(counter, event_entry); + next_counter = list_next_entry(next_counter, event_entry); } } @@ -1497,10 +1503,21 @@ static void perf_counter_enable_on_exec(struct task_struct *task) */ static void __perf_counter_read(void *info) { + struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); struct perf_counter *counter = info; struct perf_counter_context *ctx = counter->ctx; unsigned long flags; + /* + * If this is a task context, we need to check whether it is + * the current task context of this cpu. If not it has been + * scheduled out before the smp call arrived. In that case + * counter->count would have been updated to a recent sample + * when the counter was scheduled out. + */ + if (ctx->task && cpuctx->task_ctx != ctx) + return; + local_irq_save(flags); if (ctx->is_active) update_context_time(ctx); @@ -1654,6 +1671,8 @@ static void free_counter(struct perf_counter *counter) atomic_dec(&nr_mmap_counters); if (counter->attr.comm) atomic_dec(&nr_comm_counters); + if (counter->attr.task) + atomic_dec(&nr_task_counters); } if (counter->destroy) @@ -1688,14 +1707,133 @@ static int perf_release(struct inode *inode, struct file *file) return 0; } +static int perf_counter_read_size(struct perf_counter *counter) +{ + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (counter->attr.read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (counter->attr.read_format & PERF_FORMAT_GROUP) { + nr += counter->group_leader->nr_siblings; + size += sizeof(u64); + } + + size += entry * nr; + + return size; +} + +static u64 perf_counter_read_value(struct perf_counter *counter) +{ + struct perf_counter *child; + u64 total = 0; + + total += perf_counter_read(counter); + list_for_each_entry(child, &counter->child_list, child_list) + total += perf_counter_read(child); + + return total; +} + +static int perf_counter_read_entry(struct perf_counter *counter, + u64 read_format, char __user *buf) +{ + int n = 0, count = 0; + u64 values[2]; + + values[n++] = perf_counter_read_value(counter); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(counter); + + count = n * sizeof(u64); + + if (copy_to_user(buf, values, count)) + return -EFAULT; + + return count; +} + +static int perf_counter_read_group(struct perf_counter *counter, + u64 read_format, char __user *buf) +{ + struct perf_counter *leader = counter->group_leader, *sub; + int n = 0, size = 0, err = -EFAULT; + u64 values[3]; + + values[n++] = 1 + leader->nr_siblings; + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = leader->total_time_enabled + + atomic64_read(&leader->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = leader->total_time_running + + atomic64_read(&leader->child_total_time_running); + } + + size = n * sizeof(u64); + + if (copy_to_user(buf, values, size)) + return -EFAULT; + + err = perf_counter_read_entry(leader, read_format, buf + size); + if (err < 0) + return err; + + size += err; + + list_for_each_entry(sub, &leader->sibling_list, list_entry) { + err = perf_counter_read_entry(sub, read_format, + buf + size); + if (err < 0) + return err; + + size += err; + } + + return size; +} + +static int perf_counter_read_one(struct perf_counter *counter, + u64 read_format, char __user *buf) +{ + u64 values[4]; + int n = 0; + + values[n++] = perf_counter_read_value(counter); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = counter->total_time_enabled + + atomic64_read(&counter->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = counter->total_time_running + + atomic64_read(&counter->child_total_time_running); + } + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(counter); + + if (copy_to_user(buf, values, n * sizeof(u64))) + return -EFAULT; + + return n * sizeof(u64); +} + /* * Read the performance counter - simple non blocking version for now */ static ssize_t perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count) { - u64 values[4]; - int n; + u64 read_format = counter->attr.read_format; + int ret; /* * Return end-of-file for a read on a counter that is in @@ -1705,28 +1843,18 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count) if (counter->state == PERF_COUNTER_STATE_ERROR) return 0; + if (count < perf_counter_read_size(counter)) + return -ENOSPC; + WARN_ON_ONCE(counter->ctx->parent_ctx); mutex_lock(&counter->child_mutex); - values[0] = perf_counter_read(counter); - n = 1; - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - values[n++] = counter->total_time_enabled + - atomic64_read(&counter->child_total_time_enabled); - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - values[n++] = counter->total_time_running + - atomic64_read(&counter->child_total_time_running); - if (counter->attr.read_format & PERF_FORMAT_ID) - values[n++] = primary_counter_id(counter); + if (read_format & PERF_FORMAT_GROUP) + ret = perf_counter_read_group(counter, read_format, buf); + else + ret = perf_counter_read_one(counter, read_format, buf); mutex_unlock(&counter->child_mutex); - if (count < n * sizeof(u64)) - return -EINVAL; - count = n * sizeof(u64); - - if (copy_to_user(buf, values, count)) - return -EFAULT; - - return count; + return ret; } static ssize_t @@ -1891,6 +2019,10 @@ int perf_counter_task_disable(void) return 0; } +#ifndef PERF_COUNTER_INDEX_OFFSET +# define PERF_COUNTER_INDEX_OFFSET 0 +#endif + static int perf_counter_index(struct perf_counter *counter) { if (counter->state != PERF_COUNTER_STATE_ACTIVE) @@ -2230,7 +2362,7 @@ static void perf_pending_counter(struct perf_pending_entry *entry) if (counter->pending_disable) { counter->pending_disable = 0; - perf_counter_disable(counter); + __perf_counter_disable(counter); } if (counter->pending_wakeup) { @@ -2615,7 +2747,80 @@ static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p) return task_pid_nr_ns(p, counter->ns); } -static void perf_counter_output(struct perf_counter *counter, int nmi, +static void perf_output_read_one(struct perf_output_handle *handle, + struct perf_counter *counter) +{ + u64 read_format = counter->attr.read_format; + u64 values[4]; + int n = 0; + + values[n++] = atomic64_read(&counter->count); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = counter->total_time_enabled + + atomic64_read(&counter->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = counter->total_time_running + + atomic64_read(&counter->child_total_time_running); + } + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(counter); + + perf_output_copy(handle, values, n * sizeof(u64)); +} + +/* + * XXX PERF_FORMAT_GROUP vs inherited counters seems difficult. + */ +static void perf_output_read_group(struct perf_output_handle *handle, + struct perf_counter *counter) +{ + struct perf_counter *leader = counter->group_leader, *sub; + u64 read_format = counter->attr.read_format; + u64 values[5]; + int n = 0; + + values[n++] = 1 + leader->nr_siblings; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = leader->total_time_enabled; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = leader->total_time_running; + + if (leader != counter) + leader->pmu->read(leader); + + values[n++] = atomic64_read(&leader->count); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(leader); + + perf_output_copy(handle, values, n * sizeof(u64)); + + list_for_each_entry(sub, &leader->sibling_list, list_entry) { + n = 0; + + if (sub != counter) + sub->pmu->read(sub); + + values[n++] = atomic64_read(&sub->count); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(sub); + + perf_output_copy(handle, values, n * sizeof(u64)); + } +} + +static void perf_output_read(struct perf_output_handle *handle, + struct perf_counter *counter) +{ + if (counter->attr.read_format & PERF_FORMAT_GROUP) + perf_output_read_group(handle, counter); + else + perf_output_read_one(handle, counter); +} + +void perf_counter_output(struct perf_counter *counter, int nmi, struct perf_sample_data *data) { int ret; @@ -2626,10 +2831,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, struct { u32 pid, tid; } tid_entry; - struct { - u64 id; - u64 counter; - } group_entry; struct perf_callchain_entry *callchain = NULL; int callchain_size = 0; u64 time; @@ -2684,10 +2885,8 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, if (sample_type & PERF_SAMPLE_PERIOD) header.size += sizeof(u64); - if (sample_type & PERF_SAMPLE_GROUP) { - header.size += sizeof(u64) + - counter->nr_siblings * sizeof(group_entry); - } + if (sample_type & PERF_SAMPLE_READ) + header.size += perf_counter_read_size(counter); if (sample_type & PERF_SAMPLE_CALLCHAIN) { callchain = perf_callchain(data->regs); @@ -2699,6 +2898,18 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, header.size += sizeof(u64); } + if (sample_type & PERF_SAMPLE_RAW) { + int size = sizeof(u32); + + if (data->raw) + size += data->raw->size; + else + size += sizeof(u32); + + WARN_ON_ONCE(size & (sizeof(u64)-1)); + header.size += size; + } + ret = perf_output_begin(&handle, counter, header.size, nmi, 1); if (ret) return; @@ -2732,26 +2943,8 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, if (sample_type & PERF_SAMPLE_PERIOD) perf_output_put(&handle, data->period); - /* - * XXX PERF_SAMPLE_GROUP vs inherited counters seems difficult. - */ - if (sample_type & PERF_SAMPLE_GROUP) { - struct perf_counter *leader, *sub; - u64 nr = counter->nr_siblings; - - perf_output_put(&handle, nr); - - leader = counter->group_leader; - list_for_each_entry(sub, &leader->sibling_list, list_entry) { - if (sub != counter) - sub->pmu->read(sub); - - group_entry.id = primary_counter_id(sub); - group_entry.counter = atomic64_read(&sub->count); - - perf_output_put(&handle, group_entry); - } - } + if (sample_type & PERF_SAMPLE_READ) + perf_output_read(&handle, counter); if (sample_type & PERF_SAMPLE_CALLCHAIN) { if (callchain) @@ -2762,6 +2955,22 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, } } + if (sample_type & PERF_SAMPLE_RAW) { + if (data->raw) { + perf_output_put(&handle, data->raw->size); + perf_output_copy(&handle, data->raw->data, data->raw->size); + } else { + struct { + u32 size; + u32 data; + } raw = { + .size = sizeof(u32), + .data = 0, + }; + perf_output_put(&handle, raw); + } + } + perf_output_end(&handle); } @@ -2774,8 +2983,6 @@ struct perf_read_event { u32 pid; u32 tid; - u64 value; - u64 format[3]; }; static void @@ -2787,80 +2994,74 @@ perf_counter_read_event(struct perf_counter *counter, .header = { .type = PERF_EVENT_READ, .misc = 0, - .size = sizeof(event) - sizeof(event.format), + .size = sizeof(event) + perf_counter_read_size(counter), }, .pid = perf_counter_pid(counter, task), .tid = perf_counter_tid(counter, task), - .value = atomic64_read(&counter->count), }; - int ret, i = 0; - - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { - event.header.size += sizeof(u64); - event.format[i++] = counter->total_time_enabled; - } - - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { - event.header.size += sizeof(u64); - event.format[i++] = counter->total_time_running; - } - - if (counter->attr.read_format & PERF_FORMAT_ID) { - event.header.size += sizeof(u64); - event.format[i++] = primary_counter_id(counter); - } + int ret; ret = perf_output_begin(&handle, counter, event.header.size, 0, 0); if (ret) return; - perf_output_copy(&handle, &event, event.header.size); + perf_output_put(&handle, event); + perf_output_read(&handle, counter); + perf_output_end(&handle); } /* - * fork tracking + * task tracking -- fork/exit + * + * enabled by: attr.comm | attr.mmap | attr.task */ -struct perf_fork_event { - struct task_struct *task; +struct perf_task_event { + struct task_struct *task; + struct perf_counter_context *task_ctx; struct { struct perf_event_header header; u32 pid; u32 ppid; + u32 tid; + u32 ptid; } event; }; -static void perf_counter_fork_output(struct perf_counter *counter, - struct perf_fork_event *fork_event) +static void perf_counter_task_output(struct perf_counter *counter, + struct perf_task_event *task_event) { struct perf_output_handle handle; - int size = fork_event->event.header.size; - struct task_struct *task = fork_event->task; + int size = task_event->event.header.size; + struct task_struct *task = task_event->task; int ret = perf_output_begin(&handle, counter, size, 0, 0); if (ret) return; - fork_event->event.pid = perf_counter_pid(counter, task); - fork_event->event.ppid = perf_counter_pid(counter, task->real_parent); + task_event->event.pid = perf_counter_pid(counter, task); + task_event->event.ppid = perf_counter_pid(counter, current); - perf_output_put(&handle, fork_event->event); + task_event->event.tid = perf_counter_tid(counter, task); + task_event->event.ptid = perf_counter_tid(counter, current); + + perf_output_put(&handle, task_event->event); perf_output_end(&handle); } -static int perf_counter_fork_match(struct perf_counter *counter) +static int perf_counter_task_match(struct perf_counter *counter) { - if (counter->attr.comm || counter->attr.mmap) + if (counter->attr.comm || counter->attr.mmap || counter->attr.task) return 1; return 0; } -static void perf_counter_fork_ctx(struct perf_counter_context *ctx, - struct perf_fork_event *fork_event) +static void perf_counter_task_ctx(struct perf_counter_context *ctx, + struct perf_task_event *task_event) { struct perf_counter *counter; @@ -2869,54 +3070,62 @@ static void perf_counter_fork_ctx(struct perf_counter_context *ctx, rcu_read_lock(); list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) { - if (perf_counter_fork_match(counter)) - perf_counter_fork_output(counter, fork_event); + if (perf_counter_task_match(counter)) + perf_counter_task_output(counter, task_event); } rcu_read_unlock(); } -static void perf_counter_fork_event(struct perf_fork_event *fork_event) +static void perf_counter_task_event(struct perf_task_event *task_event) { struct perf_cpu_context *cpuctx; - struct perf_counter_context *ctx; + struct perf_counter_context *ctx = task_event->task_ctx; cpuctx = &get_cpu_var(perf_cpu_context); - perf_counter_fork_ctx(&cpuctx->ctx, fork_event); + perf_counter_task_ctx(&cpuctx->ctx, task_event); put_cpu_var(perf_cpu_context); rcu_read_lock(); - /* - * doesn't really matter which of the child contexts the - * events ends up in. - */ - ctx = rcu_dereference(current->perf_counter_ctxp); + if (!ctx) + ctx = rcu_dereference(task_event->task->perf_counter_ctxp); if (ctx) - perf_counter_fork_ctx(ctx, fork_event); + perf_counter_task_ctx(ctx, task_event); rcu_read_unlock(); } -void perf_counter_fork(struct task_struct *task) +static void perf_counter_task(struct task_struct *task, + struct perf_counter_context *task_ctx, + int new) { - struct perf_fork_event fork_event; + struct perf_task_event task_event; if (!atomic_read(&nr_comm_counters) && - !atomic_read(&nr_mmap_counters)) + !atomic_read(&nr_mmap_counters) && + !atomic_read(&nr_task_counters)) return; - fork_event = (struct perf_fork_event){ - .task = task, - .event = { + task_event = (struct perf_task_event){ + .task = task, + .task_ctx = task_ctx, + .event = { .header = { - .type = PERF_EVENT_FORK, + .type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT, .misc = 0, - .size = sizeof(fork_event.event), + .size = sizeof(task_event.event), }, /* .pid */ /* .ppid */ + /* .tid */ + /* .ptid */ }, }; - perf_counter_fork_event(&fork_event); + perf_counter_task_event(&task_event); +} + +void perf_counter_fork(struct task_struct *task) +{ + perf_counter_task(task, NULL, 1); } /* @@ -3305,125 +3514,111 @@ int perf_counter_overflow(struct perf_counter *counter, int nmi, * Generic software counter infrastructure */ -static void perf_swcounter_update(struct perf_counter *counter) +/* + * We directly increment counter->count and keep a second value in + * counter->hw.period_left to count intervals. This period counter + * is kept in the range [-sample_period, 0] so that we can use the + * sign as trigger. + */ + +static u64 perf_swcounter_set_period(struct perf_counter *counter) { struct hw_perf_counter *hwc = &counter->hw; - u64 prev, now; - s64 delta; + u64 period = hwc->last_period; + u64 nr, offset; + s64 old, val; + + hwc->last_period = hwc->sample_period; again: - prev = atomic64_read(&hwc->prev_count); - now = atomic64_read(&hwc->count); - if (atomic64_cmpxchg(&hwc->prev_count, prev, now) != prev) - goto again; + old = val = atomic64_read(&hwc->period_left); + if (val < 0) + return 0; - delta = now - prev; + nr = div64_u64(period + val, period); + offset = nr * period; + val -= offset; + if (atomic64_cmpxchg(&hwc->period_left, old, val) != old) + goto again; - atomic64_add(delta, &counter->count); - atomic64_sub(delta, &hwc->period_left); + return nr; } -static void perf_swcounter_set_period(struct perf_counter *counter) +static void perf_swcounter_overflow(struct perf_counter *counter, + int nmi, struct perf_sample_data *data) { struct hw_perf_counter *hwc = &counter->hw; - s64 left = atomic64_read(&hwc->period_left); - s64 period = hwc->sample_period; + u64 overflow; - if (unlikely(left <= -period)) { - left = period; - atomic64_set(&hwc->period_left, left); - hwc->last_period = period; - } + data->period = counter->hw.last_period; + overflow = perf_swcounter_set_period(counter); - if (unlikely(left <= 0)) { - left += period; - atomic64_add(period, &hwc->period_left); - hwc->last_period = period; - } + if (hwc->interrupts == MAX_INTERRUPTS) + return; - atomic64_set(&hwc->prev_count, -left); - atomic64_set(&hwc->count, -left); + for (; overflow; overflow--) { + if (perf_counter_overflow(counter, nmi, data)) { + /* + * We inhibit the overflow from happening when + * hwc->interrupts == MAX_INTERRUPTS. + */ + break; + } + } } -static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer) +static void perf_swcounter_unthrottle(struct perf_counter *counter) { - enum hrtimer_restart ret = HRTIMER_RESTART; - struct perf_sample_data data; - struct perf_counter *counter; - u64 period; - - counter = container_of(hrtimer, struct perf_counter, hw.hrtimer); - counter->pmu->read(counter); - - data.addr = 0; - data.regs = get_irq_regs(); /* - * In case we exclude kernel IPs or are somehow not in interrupt - * context, provide the next best thing, the user IP. + * Nothing to do, we already reset hwc->interrupts. */ - if ((counter->attr.exclude_kernel || !data.regs) && - !counter->attr.exclude_user) - data.regs = task_pt_regs(current); +} - if (data.regs) { - if (perf_counter_overflow(counter, 0, &data)) - ret = HRTIMER_NORESTART; - } +static void perf_swcounter_add(struct perf_counter *counter, u64 nr, + int nmi, struct perf_sample_data *data) +{ + struct hw_perf_counter *hwc = &counter->hw; - period = max_t(u64, 10000, counter->hw.sample_period); - hrtimer_forward_now(hrtimer, ns_to_ktime(period)); + atomic64_add(nr, &counter->count); - return ret; -} + if (!hwc->sample_period) + return; -static void perf_swcounter_overflow(struct perf_counter *counter, - int nmi, struct perf_sample_data *data) -{ - data->period = counter->hw.last_period; + if (!data->regs) + return; - perf_swcounter_update(counter); - perf_swcounter_set_period(counter); - if (perf_counter_overflow(counter, nmi, data)) - /* soft-disable the counter */ - ; + if (!atomic64_add_negative(nr, &hwc->period_left)) + perf_swcounter_overflow(counter, nmi, data); } static int perf_swcounter_is_counting(struct perf_counter *counter) { - struct perf_counter_context *ctx; - unsigned long flags; - int count; - + /* + * The counter is active, we're good! + */ if (counter->state == PERF_COUNTER_STATE_ACTIVE) return 1; + /* + * The counter is off/error, not counting. + */ if (counter->state != PERF_COUNTER_STATE_INACTIVE) return 0; /* - * If the counter is inactive, it could be just because - * its task is scheduled out, or because it's in a group - * which could not go on the PMU. We want to count in - * the first case but not the second. If the context is - * currently active then an inactive software counter must - * be the second case. If it's not currently active then - * we need to know whether the counter was active when the - * context was last active, which we can determine by - * comparing counter->tstamp_stopped with ctx->time. - * - * We are within an RCU read-side critical section, - * which protects the existence of *ctx. + * The counter is inactive, if the context is active + * we're part of a group that didn't make it on the 'pmu', + * not counting. */ - ctx = counter->ctx; - spin_lock_irqsave(&ctx->lock, flags); - count = 1; - /* Re-check state now we have the lock */ - if (counter->state < PERF_COUNTER_STATE_INACTIVE || - counter->ctx->is_active || - counter->tstamp_stopped < ctx->time) - count = 0; - spin_unlock_irqrestore(&ctx->lock, flags); - return count; + if (counter->ctx->is_active) + return 0; + + /* + * We're inactive and the context is too, this means the + * task is scheduled out, we're counting events that happen + * to us, like migration events. + */ + return 1; } static int perf_swcounter_match(struct perf_counter *counter, @@ -3449,15 +3644,6 @@ static int perf_swcounter_match(struct perf_counter *counter, return 1; } -static void perf_swcounter_add(struct perf_counter *counter, u64 nr, - int nmi, struct perf_sample_data *data) -{ - int neg = atomic64_add_negative(nr, &counter->hw.count); - - if (counter->hw.sample_period && !neg && data->regs) - perf_swcounter_overflow(counter, nmi, data); -} - static void perf_swcounter_ctx_event(struct perf_counter_context *ctx, enum perf_type_id type, u32 event, u64 nr, int nmi, @@ -3536,27 +3722,66 @@ void __perf_swcounter_event(u32 event, u64 nr, int nmi, static void perf_swcounter_read(struct perf_counter *counter) { - perf_swcounter_update(counter); } static int perf_swcounter_enable(struct perf_counter *counter) { - perf_swcounter_set_period(counter); + struct hw_perf_counter *hwc = &counter->hw; + + if (hwc->sample_period) { + hwc->last_period = hwc->sample_period; + perf_swcounter_set_period(counter); + } return 0; } static void perf_swcounter_disable(struct perf_counter *counter) { - perf_swcounter_update(counter); } static const struct pmu perf_ops_generic = { .enable = perf_swcounter_enable, .disable = perf_swcounter_disable, .read = perf_swcounter_read, + .unthrottle = perf_swcounter_unthrottle, }; /* + * hrtimer based swcounter callback + */ + +static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer) +{ + enum hrtimer_restart ret = HRTIMER_RESTART; + struct perf_sample_data data; + struct perf_counter *counter; + u64 period; + + counter = container_of(hrtimer, struct perf_counter, hw.hrtimer); + counter->pmu->read(counter); + + data.addr = 0; + data.regs = get_irq_regs(); + /* + * In case we exclude kernel IPs or are somehow not in interrupt + * context, provide the next best thing, the user IP. + */ + if ((counter->attr.exclude_kernel || !data.regs) && + !counter->attr.exclude_user) + data.regs = task_pt_regs(current); + + if (data.regs) { + if (perf_counter_overflow(counter, 0, &data)) + ret = HRTIMER_NORESTART; + } + + period = max_t(u64, 10000, counter->hw.sample_period); + hrtimer_forward_now(hrtimer, ns_to_ktime(period)); + + return ret; +} + +/* * Software counter: cpu wall time clock */ @@ -3673,17 +3898,24 @@ static const struct pmu perf_ops_task_clock = { }; #ifdef CONFIG_EVENT_PROFILE -void perf_tpcounter_event(int event_id) +void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record, + int entry_size) { + struct perf_raw_record raw = { + .size = entry_size, + .data = record, + }; + struct perf_sample_data data = { .regs = get_irq_regs(), - .addr = 0, + .addr = addr, + .raw = &raw, }; if (!data.regs) data.regs = task_pt_regs(current); - do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, &data); + do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data); } EXPORT_SYMBOL_GPL(perf_tpcounter_event); @@ -3697,6 +3929,14 @@ static void tp_perf_counter_destroy(struct perf_counter *counter) static const struct pmu *tp_perf_counter_init(struct perf_counter *counter) { + /* + * Raw tracepoint data is a severe data leak, only allow root to + * have these. + */ + if ((counter->attr.sample_type & PERF_SAMPLE_RAW) && + !capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + if (ftrace_profile_enable(counter->attr.config)) return NULL; @@ -3826,13 +4066,14 @@ perf_counter_alloc(struct perf_counter_attr *attr, hwc->sample_period = attr->sample_period; if (attr->freq && attr->sample_freq) hwc->sample_period = 1; + hwc->last_period = hwc->sample_period; atomic64_set(&hwc->period_left, hwc->sample_period); /* - * we currently do not support PERF_SAMPLE_GROUP on inherited counters + * we currently do not support PERF_FORMAT_GROUP on inherited counters */ - if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP)) + if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) goto done; switch (attr->type) { @@ -3875,6 +4116,8 @@ done: atomic_inc(&nr_mmap_counters); if (counter->attr.comm) atomic_inc(&nr_comm_counters); + if (counter->attr.task) + atomic_inc(&nr_task_counters); } return counter; @@ -4236,8 +4479,10 @@ void perf_counter_exit_task(struct task_struct *child) struct perf_counter_context *child_ctx; unsigned long flags; - if (likely(!child->perf_counter_ctxp)) + if (likely(!child->perf_counter_ctxp)) { + perf_counter_task(child, NULL, 0); return; + } local_irq_save(flags); /* @@ -4262,8 +4507,14 @@ void perf_counter_exit_task(struct task_struct *child) * the counters from it. */ unclone_ctx(child_ctx); - spin_unlock(&child_ctx->lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&child_ctx->lock, flags); + + /* + * Report the task dead after unscheduling the counters so that we + * won't get any samples after PERF_EVENT_EXIT. We can however still + * get a few PERF_EVENT_READ events. + */ + perf_counter_task(child, child_ctx, 0); /* * We can recurse on the same lock type through: @@ -4484,6 +4735,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) perf_counter_init_cpu(cpu); break; + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + hw_perf_counter_setup_online(cpu); + break; + case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: perf_counter_exit_cpu(cpu); @@ -4508,6 +4764,8 @@ void __init perf_counter_init(void) { perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); + perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE, + (void *)(long)smp_processor_id()); register_cpu_notifier(&perf_cpu_nb); } diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index bece7c0b67b2..e33a21cb9407 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -521,11 +521,12 @@ void posix_cpu_timers_exit(struct task_struct *tsk) } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - struct task_cputime cputime; + struct signal_struct *const sig = tsk->signal; - thread_group_cputimer(tsk, &cputime); cleanup_timers(tsk->signal->cpu_timers, - cputime.utime, cputime.stime, cputime.sum_exec_runtime); + cputime_add(tsk->utime, sig->utime), + cputime_add(tsk->stime, sig->stime), + tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 052ec4d195c7..d089d052c4a9 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -202,6 +202,12 @@ static int no_timer_create(struct k_itimer *new_timer) return -EOPNOTSUPP; } +static int no_nsleep(const clockid_t which_clock, int flags, + struct timespec *tsave, struct timespec __user *rmtp) +{ + return -EOPNOTSUPP; +} + /* * Return nonzero if we know a priori this clockid_t value is bogus. */ @@ -254,6 +260,7 @@ static __init int init_posix_timers(void) .clock_get = posix_get_monotonic_raw, .clock_set = do_posix_clock_nosettime, .timer_create = no_timer_create, + .nsleep = no_nsleep, }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 082c320e4dbf..307c285af59e 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -152,7 +152,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) if (!dumpable && !capable(CAP_SYS_PTRACE)) return -EPERM; - return security_ptrace_may_access(task, mode); + return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index fcd107a78c5a..29bd4baf9e75 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -1039,16 +1039,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) { /* We got the lock for task. */ debug_rt_mutex_lock(lock); - rt_mutex_set_owner(lock, task, 0); - + spin_unlock(&lock->wait_lock); rt_mutex_deadlock_account_lock(lock, task); return 1; } ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); - if (ret && !waiter->task) { /* * Reset the return value. We might have diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index e6c251790dde..d014efbf947a 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -81,8 +81,21 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) continue; - if (lowest_mask) + if (lowest_mask) { cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + + /* + * We have to ensure that we have at least one bit + * still set in the array, since the map could have + * been concurrently emptied between the first and + * second reads of vec->mask. If we hit this + * condition, simply act as though we never hit this + * priority level and continue on. + */ + if (cpumask_any(lowest_mask) >= nr_cpu_ids) + continue; + } + return 1; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 9ffb2b2ceba4..652e8bdef9aa 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -611,9 +611,13 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { #ifdef CONFIG_SCHEDSTATS + struct task_struct *tsk = NULL; + + if (entity_is_task(se)) + tsk = task_of(se); + if (se->sleep_start) { u64 delta = rq_of(cfs_rq)->clock - se->sleep_start; - struct task_struct *tsk = task_of(se); if ((s64)delta < 0) delta = 0; @@ -624,11 +628,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->sleep_start = 0; se->sum_sleep_runtime += delta; - account_scheduler_latency(tsk, delta >> 10, 1); + if (tsk) + account_scheduler_latency(tsk, delta >> 10, 1); } if (se->block_start) { u64 delta = rq_of(cfs_rq)->clock - se->block_start; - struct task_struct *tsk = task_of(se); if ((s64)delta < 0) delta = 0; @@ -639,17 +643,19 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->block_start = 0; se->sum_sleep_runtime += delta; - /* - * Blocking time is in units of nanosecs, so shift by 20 to - * get a milliseconds-range estimation of the amount of - * time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - - profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk), - delta >> 20); + if (tsk) { + /* + * Blocking time is in units of nanosecs, so shift by + * 20 to get a milliseconds-range estimation of the + * amount of time that the task spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + profile_hits(SLEEP_PROFILING, + (void *)get_wchan(tsk), + delta >> 20); + } + account_scheduler_latency(tsk, delta >> 10, 0); } - account_scheduler_latency(tsk, delta >> 10, 0); } #endif } diff --git a/kernel/signal.c b/kernel/signal.c index ccf1ceedaebe..64c5deeaca5d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2454,11 +2454,9 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s stack_t oss; int error; - if (uoss) { - oss.ss_sp = (void __user *) current->sas_ss_sp; - oss.ss_size = current->sas_ss_size; - oss.ss_flags = sas_ss_flags(sp); - } + oss.ss_sp = (void __user *) current->sas_ss_sp; + oss.ss_size = current->sas_ss_size; + oss.ss_flags = sas_ss_flags(sp); if (uss) { void __user *ss_sp; @@ -2466,10 +2464,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s int ss_flags; error = -EFAULT; - if (!access_ok(VERIFY_READ, uss, sizeof(*uss)) - || __get_user(ss_sp, &uss->ss_sp) - || __get_user(ss_flags, &uss->ss_flags) - || __get_user(ss_size, &uss->ss_size)) + if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) + goto out; + error = __get_user(ss_sp, &uss->ss_sp) | + __get_user(ss_flags, &uss->ss_flags) | + __get_user(ss_size, &uss->ss_size); + if (error) goto out; error = -EPERM; @@ -2501,13 +2501,16 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s current->sas_ss_size = ss_size; } + error = 0; if (uoss) { error = -EFAULT; - if (copy_to_user(uoss, &oss, sizeof(oss))) + if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss))) goto out; + error = __put_user(oss.ss_sp, &uoss->ss_sp) | + __put_user(oss.ss_size, &uoss->ss_size) | + __put_user(oss.ss_flags, &uoss->ss_flags); } - error = 0; out: return error; } diff --git a/kernel/smp.c b/kernel/smp.c index ad63d8501207..94188b8ecc33 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -57,7 +57,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) return NOTIFY_BAD; break; -#ifdef CONFIG_CPU_HOTPLUG +#ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 98e02328c67d..71d8dc7f9920 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1306,10 +1306,10 @@ static struct ctl_table vm_table[] = { { .ctl_name = CTL_UNNUMBERED, .procname = "mmap_min_addr", - .data = &mmap_min_addr, - .maxlen = sizeof(unsigned long), + .data = &dac_mmap_min_addr, + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = &mmap_min_addr_handler, }, #ifdef CONFIG_NUMA { diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index a6dcd67b041d..620b58abdc32 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -137,11 +137,12 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, */ int clockevents_register_notifier(struct notifier_block *nb) { + unsigned long flags; int ret; - spin_lock(&clockevents_lock); + spin_lock_irqsave(&clockevents_lock, flags); ret = raw_notifier_chain_register(&clockevents_chain, nb); - spin_unlock(&clockevents_lock); + spin_unlock_irqrestore(&clockevents_lock, flags); return ret; } @@ -178,16 +179,18 @@ static void clockevents_notify_released(void) */ void clockevents_register_device(struct clock_event_device *dev) { + unsigned long flags; + BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); BUG_ON(!dev->cpumask); - spin_lock(&clockevents_lock); + spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); clockevents_notify_released(); - spin_unlock(&clockevents_lock); + spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_register_device); @@ -235,8 +238,9 @@ void clockevents_exchange_device(struct clock_event_device *old, void clockevents_notify(unsigned long reason, void *arg) { struct list_head *node, *tmp; + unsigned long flags; - spin_lock(&clockevents_lock); + spin_lock_irqsave(&clockevents_lock, flags); clockevents_do_notify(reason, arg); switch (reason) { @@ -251,7 +255,7 @@ void clockevents_notify(unsigned long reason, void *arg) default: break; } - spin_unlock(&clockevents_lock); + spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_notify); #endif diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 877dbedc3118..c2ec25087a35 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -205,11 +205,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) * Powerstate information: The system enters/leaves a state, where * affected devices might stop */ -static void tick_do_broadcast_on_off(void *why) +static void tick_do_broadcast_on_off(unsigned long *reason) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags, *reason = why; + unsigned long flags; int cpu, bc_stopped; spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -276,8 +276,7 @@ void tick_broadcast_on_off(unsigned long reason, int *oncpu) printk(KERN_ERR "tick-broadcast: ignoring broadcast for " "offline CPU #%d\n", *oncpu); else - smp_call_function_single(*oncpu, tick_do_broadcast_on_off, - &reason, 1); + tick_do_broadcast_on_off(&reason); } /* diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index a999b92a1277..fddd69d16e03 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -286,7 +286,7 @@ static int __init init_timer_list_procfs(void) { struct proc_dir_entry *pe; - pe = proc_create("timer_list", 0644, NULL, &timer_list_fops); + pe = proc_create("timer_list", 0444, NULL, &timer_list_fops); if (!pe) return -ENOMEM; return 0; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 1090b0aed9ba..7a34cb563fec 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -267,8 +267,8 @@ static void blk_trace_free(struct blk_trace *bt) { debugfs_remove(bt->msg_file); debugfs_remove(bt->dropped_file); - debugfs_remove(bt->dir); relay_close(bt->rchan); + debugfs_remove(bt->dir); free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); @@ -378,18 +378,8 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, static int blk_remove_buf_file_callback(struct dentry *dentry) { - struct dentry *parent = dentry->d_parent; debugfs_remove(dentry); - /* - * this will fail for all but the last file, but that is ok. what we - * care about is the top level buts->name directory going away, when - * the last trace file is gone. Then we don't have to rmdir() that - * manually on trace stop, so it nicely solves the issue with - * force killing of running traces. - */ - - debugfs_remove(parent); return 0; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1f3ec2afa511..25edd5cc5935 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1662,7 +1662,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) mutex_lock(&ftrace_regex_lock); if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) + (file->f_flags & O_TRUNC)) ftrace_filter_reset(enable); if (file->f_mode & FMODE_READ) { @@ -2278,7 +2278,11 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, read++; cnt--; - if (!(iter->flags & ~FTRACE_ITER_CONT)) { + /* + * If the parser haven't finished with the last write, + * continue reading the user input without skipping spaces. + */ + if (!(iter->flags & FTRACE_ITER_CONT)) { /* skip white space */ while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); @@ -2288,8 +2292,9 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, cnt--; } + /* only spaces were written */ if (isspace(ch)) { - file->f_pos += read; + *ppos += read; ret = read; goto out; } @@ -2319,12 +2324,12 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, if (ret) goto out; iter->buffer_idx = 0; - } else + } else { iter->flags |= FTRACE_ITER_CONT; + iter->buffer[iter->buffer_idx++] = ch; + } - - file->f_pos += read; - + *ppos += read; ret = read; out: mutex_unlock(&ftrace_regex_lock); @@ -2577,7 +2582,7 @@ ftrace_graph_open(struct inode *inode, struct file *file) mutex_lock(&graph_lock); if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) { + (file->f_flags & O_TRUNC)) { ftrace_graph_count = 0; memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs)); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bf27bb7a63e2..a330513d96ce 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -735,6 +735,7 @@ ring_buffer_free(struct ring_buffer *buffer) put_online_cpus(); + kfree(buffer->buffers); free_cpumask_var(buffer->cpumask); kfree(buffer); @@ -1785,7 +1786,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer, */ RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing)); - if (!rb_try_to_discard(cpu_buffer, event)) + if (rb_try_to_discard(cpu_buffer, event)) goto out; /* @@ -2383,7 +2384,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) * the box. Return the padding, and we will release * the current locks, and try again. */ - rb_advance_reader(cpu_buffer); return event; case RINGBUF_TYPE_TIME_EXTEND: @@ -2486,7 +2486,7 @@ static inline int rb_ok_to_lock(void) * buffer too. A one time deal is all you get from reading * the ring buffer from an NMI. */ - if (likely(!in_nmi() && !oops_in_progress)) + if (likely(!in_nmi())) return 1; tracing_off_permanent(); @@ -2519,6 +2519,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) if (dolock) spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(buffer, cpu, ts); + if (event && event->type_len == RINGBUF_TYPE_PADDING) + rb_advance_reader(cpu_buffer); if (dolock) spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); @@ -2590,12 +2592,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(buffer, cpu, ts); - if (!event) - goto out_unlock; - - rb_advance_reader(cpu_buffer); + if (event) + rb_advance_reader(cpu_buffer); - out_unlock: if (dolock) spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8bc8d8afea6a..8c358395d338 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -848,6 +848,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); } +EXPORT_SYMBOL_GPL(tracing_generic_entry_update); struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, int type, @@ -2031,7 +2032,7 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) { + (file->f_flags & O_TRUNC)) { long cpu = (long) inode->i_private; if (cpu == TRACE_PIPE_ALL_CPU) @@ -3085,7 +3086,8 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) break; } - trace_consume(iter); + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(iter); rem -= count; if (!find_next_entry_inc(iter)) { rem = 0; @@ -3894,17 +3896,9 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (ret < 0) return ret; - switch (val) { - case 0: - trace_flags &= ~(1 << index); - break; - case 1: - trace_flags |= 1 << index; - break; - - default: + if (val != 0 && val != 1) return -EINVAL; - } + set_tracer_flags(1 << index, val); *ppos += cnt; @@ -4233,8 +4227,11 @@ static void __ftrace_dump(bool disable_tracing) iter.pos = -1; if (find_next_entry_inc(&iter) != NULL) { - print_trace_line(&iter); - trace_consume(&iter); + int ret; + + ret = print_trace_line(&iter); + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(&iter); } trace_printk_seq(&iter.seq); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3548ae5cc780..8b9f4f6e9559 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -438,10 +438,6 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); -void tracing_generic_entry_update(struct trace_entry *entry, - unsigned long flags, - int pc); - void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index 5b5895afecfe..11ba5bb4ed0a 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -14,7 +14,7 @@ int ftrace_profile_enable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id) { + if (event->id == event_id && event->profile_enable) { ret = event->profile_enable(event); break; } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 53c8fd376a88..e75276a49cf5 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -376,7 +376,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file) const struct seq_operations *seq_ops; if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) + (file->f_flags & O_TRUNC)) ftrace_clear_events(); seq_ops = inode->i_private; @@ -940,7 +940,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, entry = trace_create_file("enable", 0644, call->dir, call, enable); - if (call->id) + if (call->id && call->profile_enable) entry = trace_create_file("id", 0444, call->dir, call, id); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 936c621bbf46..f32dc9d1ea7b 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -624,9 +624,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, return -ENOSPC; } - filter->preds[filter->n_preds] = pred; - filter->n_preds++; - list_for_each_entry(call, &ftrace_events, list) { if (!call->define_fields) @@ -643,6 +640,9 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, } replace_filter_string(call->filter, filter_string); } + + filter->preds[filter->n_preds] = pred; + filter->n_preds++; out: return err; } @@ -1029,12 +1029,17 @@ static int replace_preds(struct event_subsystem *system, if (elt->op == OP_AND || elt->op == OP_OR) { pred = create_logical_pred(elt->op); + if (!pred) + return -ENOMEM; if (call) { err = filter_add_pred(ps, call, pred); filter_free_pred(pred); - } else + } else { err = filter_add_subsystem_pred(ps, system, pred, filter_string); + if (err) + filter_free_pred(pred); + } if (err) return err; @@ -1048,12 +1053,17 @@ static int replace_preds(struct event_subsystem *system, } pred = create_pred(elt->op, operand1, operand2); + if (!pred) + return -ENOMEM; if (call) { err = filter_add_pred(ps, call, pred); filter_free_pred(pred); - } else + } else { err = filter_add_subsystem_pred(ps, system, pred, filter_string); + if (err) + filter_free_pred(pred); + } if (err) return err; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index d2249abafb53..420ec3487579 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -843,9 +843,16 @@ print_graph_function(struct trace_iterator *iter) switch (entry->type) { case TRACE_GRAPH_ENT: { - struct ftrace_graph_ent_entry *field; + /* + * print_graph_entry() may consume the current event, + * thus @field may become invalid, so we need to save it. + * sizeof(struct ftrace_graph_ent_entry) is very small, + * it can be safely saved at the stack. + */ + struct ftrace_graph_ent_entry *field, saved; trace_assign_type(field, entry); - return print_graph_entry(field, s, iter); + saved = *field; + return print_graph_entry(&saved, s, iter); } case TRACE_GRAPH_RET: { struct ftrace_graph_ret_entry *field; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 7b6278110827..687699d365ae 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -176,7 +176,7 @@ static int t_show(struct seq_file *m, void *v) const char *str = *fmt; int i; - seq_printf(m, "0x%lx : \"", (unsigned long)fmt); + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); /* * Tabs and new lines need to be converted. diff --git a/kernel/wait.c b/kernel/wait.c index ea7c3b4275cf..c4bd3d825f35 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -10,13 +10,14 @@ #include <linux/wait.h> #include <linux/hash.h> -void init_waitqueue_head(wait_queue_head_t *q) +void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *key) { spin_lock_init(&q->lock); + lockdep_set_class(&q->lock, key); INIT_LIST_HEAD(&q->task_list); } -EXPORT_SYMBOL(init_waitqueue_head); +EXPORT_SYMBOL(__init_waitqueue_head); void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0668795d8818..3c44b56b0da7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -600,7 +600,12 @@ static struct workqueue_struct *keventd_wq __read_mostly; * schedule_work - put work task in global workqueue * @work: job to be done * - * This puts a job in the kernel-global workqueue. + * Returns zero if @work was already on the kernel-global workqueue and + * non-zero otherwise. + * + * This puts a job in the kernel-global workqueue if it was not already + * queued and leaves it in the same position on the kernel-global + * workqueue otherwise. */ int schedule_work(struct work_struct *work) { |