diff options
| author | Alex Gonzalez <alex.gonzalez@digi.com> | 2012-01-19 13:54:23 +0100 |
|---|---|---|
| committer | Alex Gonzalez <alex.gonzalez@digi.com> | 2012-01-19 13:54:23 +0100 |
| commit | 802699c91a967767fc94759f7a3e5e82d8269245 (patch) | |
| tree | c8b714dd25edd333efbbf8bb1eb6c3d379084cc4 /kernel | |
| parent | f135e68daa6745fd3dbb285e6161ae2758c4027f (diff) | |
| parent | 675f7660ffb0e1880011f6b3c4f9ac241491e3cd (diff) | |
Merge commit 'v2.6.35.14' into del-5.8/main
Conflicts:
arch/arm/plat-mxc/include/mach/gpio.h
arch/x86/kernel/cpu/mtrr/main.c
drivers/mmc/core/core.c
drivers/net/smsc911x.c
fs/proc/task_mmu.c
include/linux/pm_runtime.h
mm/memory.c
mm/mlock.c
Signed-off-by: Alex Gonzalez <alex.gonzalez@digi.com>
Diffstat (limited to 'kernel')
51 files changed, 1298 insertions, 339 deletions
diff --git a/kernel/compat.c b/kernel/compat.c index 5adab05a3172..91b33fbcb427 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -1137,3 +1137,24 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info) return 0; } + +/* + * Allocate user-space memory for the duration of a single system call, + * in order to marshall parameters inside a compat thunk. + */ +void __user *compat_alloc_user_space(unsigned long len) +{ + void __user *ptr; + + /* If len would occupy more than half of the entire compat space... */ + if (unlikely(len > (((compat_uptr_t)~0) >> 1))) + return NULL; + + ptr = arch_compat_alloc_user_space(len); + + if (unlikely(!access_ok(VERIFY_WRITE, ptr, len))) + return NULL; + + return ptr; +} +EXPORT_SYMBOL_GPL(compat_alloc_user_space); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 02b9611eadde..8c781d59f2e6 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1576,8 +1576,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, return -ENODEV; trialcs = alloc_trial_cpuset(cs); - if (!trialcs) - return -ENOMEM; + if (!trialcs) { + retval = -ENOMEM; + goto out; + } switch (cft->private) { case FILE_CPULIST: @@ -1592,6 +1594,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, } free_trial_cpuset(trialcs); +out: cgroup_unlock(); return retval; } diff --git a/kernel/cred.c b/kernel/cred.c index 60bc8b1e32e6..a8d12feda053 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -256,13 +256,13 @@ struct cred *cred_alloc_blank(void) #endif atomic_set(&new->usage, 1); +#ifdef CONFIG_DEBUG_CREDENTIALS + new->magic = CRED_MAGIC; +#endif if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) goto error; -#ifdef CONFIG_DEBUG_CREDENTIALS - new->magic = CRED_MAGIC; -#endif return new; error: @@ -663,6 +663,8 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) validate_creds(old); *new = *old; + atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); get_uid(new->user); get_group_info(new->group_info); @@ -680,8 +682,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (security_prepare_creds(new, old, GFP_KERNEL) < 0) goto error; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); put_cred(old); validate_creds(new); return new; @@ -754,7 +754,11 @@ bool creds_are_invalid(const struct cred *cred) if (cred->magic != CRED_MAGIC) return true; #ifdef CONFIG_SECURITY_SELINUX - if (selinux_is_enabled()) { + /* + * cred->security == NULL if security_cred_alloc_blank() or + * security_prepare_creds() returned an error. + */ + if (selinux_is_enabled() && cred->security) { if ((unsigned long) cred->security < PAGE_SIZE) return true; if ((*(u32 *)cred->security & 0xffffff00) == diff --git a/kernel/exit.c b/kernel/exit.c index ceffc67b564a..41d44c36816f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -95,6 +95,14 @@ static void __exit_signal(struct task_struct *tsk) sig->tty = NULL; } else { /* + * This can only happen if the caller is de_thread(). + * FIXME: this is the temporary hack, we should teach + * posix-cpu-timers to handle this case correctly. + */ + if (unlikely(has_group_leader_pid(tsk))) + posix_cpu_timers_exit_group(tsk); + + /* * If there is any task waiting for the group exit * then notify it: */ @@ -900,6 +908,15 @@ NORET_TYPE void do_exit(long code) if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); + /* + * If do_exit is called because this processes oopsed, it's possible + * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before + * continuing. Amongst other possible reasons, this is to prevent + * mm_release()->clear_child_tid() from writing to a user-controlled + * kernel address. + */ + set_fs(USER_DS); + tracehook_report_exit(&code); validate_creds_for_do_exit(tsk); @@ -1383,8 +1400,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - /* don't need the RCU readlock here as we're holding a spinlock */ - uid = __task_cred(p)->uid; + uid = task_uid(p); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1457,7 +1473,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = __task_cred(p)->uid; + uid = task_uid(p); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); diff --git a/kernel/fork.c b/kernel/fork.c index be07d4e18ed5..7ca45cab959c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -319,7 +319,7 @@ out: #ifdef CONFIG_MMU static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { - struct vm_area_struct *mpnt, *tmp, **pprev; + struct vm_area_struct *mpnt, *tmp, *prev, **pprev; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; @@ -347,6 +347,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; + prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { struct file *file; @@ -378,7 +379,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; tmp->vm_mm = mm; - tmp->vm_next = NULL; + tmp->vm_next = tmp->vm_prev = NULL; file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; @@ -411,6 +412,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) */ *pprev = tmp; pprev = &tmp->vm_next; + tmp->vm_prev = prev; + prev = tmp; __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; diff --git a/kernel/futex.c b/kernel/futex.c index 6a3a5fa1526d..185ee68a6d18 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -306,8 +306,8 @@ static int fault_in_user_writeable(u32 __user *uaddr) int ret; down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, (unsigned long)uaddr, - 1, 1, 0, NULL, NULL); + ret = fixup_user_fault(current, mm, (unsigned long)uaddr, + FAULT_FLAG_WRITE); up_read(&mm->mmap_sem); return ret < 0 ? ret : 0; @@ -1363,7 +1363,6 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) { struct futex_hash_bucket *hb; - get_futex_key_refs(&q->key); hb = hash_futex(&q->key); q->lock_ptr = &hb->lock; @@ -1375,7 +1374,6 @@ static inline void queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb) { spin_unlock(&hb->lock); - drop_futex_key_refs(&q->key); } /** @@ -1480,8 +1478,6 @@ static void unqueue_me_pi(struct futex_q *q) q->pi_state = NULL; spin_unlock(q->lock_ptr); - - drop_futex_key_refs(&q->key); } /* @@ -1812,7 +1808,10 @@ static int futex_wait(u32 __user *uaddr, int fshared, } retry: - /* Prepare to wait on uaddr. */ + /* + * Prepare to wait on uaddr. On success, holds hb lock and increments + * q.key refs. + */ ret = futex_wait_setup(uaddr, val, fshared, &q, &hb); if (ret) goto out; @@ -1822,24 +1821,23 @@ retry: /* If we were woken (and unqueued), we succeeded, whatever. */ ret = 0; + /* unqueue_me() drops q.key ref */ if (!unqueue_me(&q)) - goto out_put_key; + goto out; ret = -ETIMEDOUT; if (to && !to->task) - goto out_put_key; + goto out; /* * We expect signal_pending(current), but we might be the * victim of a spurious wakeup as well. */ - if (!signal_pending(current)) { - put_futex_key(fshared, &q.key); + if (!signal_pending(current)) goto retry; - } ret = -ERESTARTSYS; if (!abs_time) - goto out_put_key; + goto out; restart = ¤t_thread_info()->restart_block; restart->fn = futex_wait_restart; @@ -1856,8 +1854,6 @@ retry: ret = -ERESTART_RESTARTBLOCK; -out_put_key: - put_futex_key(fshared, &q.key); out: if (to) { hrtimer_cancel(&to->timer); @@ -2236,7 +2232,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared, q.rt_waiter = &rt_waiter; q.requeue_pi_key = &key2; - /* Prepare to wait on uaddr. */ + /* + * Prepare to wait on uaddr. On success, increments q.key (key1) ref + * count. + */ ret = futex_wait_setup(uaddr, val, fshared, &q, &hb); if (ret) goto out_key2; @@ -2254,7 +2253,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared, * In order for us to be here, we know our q.key == key2, and since * we took the hb->lock above, we also know that futex_requeue() has * completed and we no longer have to concern ourselves with a wakeup - * race with the atomic proxy lock acquition by the requeue code. + * race with the atomic proxy lock acquisition by the requeue code. The + * futex_requeue dropped our key1 reference and incremented our key2 + * reference count. */ /* Check if the requeue code acquired the second futex for us. */ diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index ef3c3f88a7a3..f83972b16564 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -33,10 +33,11 @@ * @children: child nodes * @all: list head for list of all nodes * @parent: parent node - * @info: associated profiling data structure if not a directory - * @ghost: when an object file containing profiling data is unloaded we keep a - * copy of the profiling data here to allow collecting coverage data - * for cleanup code. Such a node is called a "ghost". + * @loaded_info: array of pointers to profiling data sets for loaded object + * files. + * @num_loaded: number of profiling data sets for loaded object files. + * @unloaded_info: accumulated copy of profiling data sets for unloaded + * object files. Used only when gcov_persist=1. * @dentry: main debugfs entry, either a directory or data file * @links: associated symbolic links * @name: data file basename @@ -51,10 +52,11 @@ struct gcov_node { struct list_head children; struct list_head all; struct gcov_node *parent; - struct gcov_info *info; - struct gcov_info *ghost; + struct gcov_info **loaded_info; + struct gcov_info *unloaded_info; struct dentry *dentry; struct dentry **links; + int num_loaded; char name[0]; }; @@ -136,16 +138,37 @@ static const struct seq_operations gcov_seq_ops = { }; /* - * Return the profiling data set for a given node. This can either be the - * original profiling data structure or a duplicate (also called "ghost") - * in case the associated object file has been unloaded. + * Return a profiling data set associated with the given node. This is + * either a data set for a loaded object file or a data set copy in case + * all associated object files have been unloaded. */ static struct gcov_info *get_node_info(struct gcov_node *node) { - if (node->info) - return node->info; + if (node->num_loaded > 0) + return node->loaded_info[0]; - return node->ghost; + return node->unloaded_info; +} + +/* + * Return a newly allocated profiling data set which contains the sum of + * all profiling data associated with the given node. + */ +static struct gcov_info *get_accumulated_info(struct gcov_node *node) +{ + struct gcov_info *info; + int i = 0; + + if (node->unloaded_info) + info = gcov_info_dup(node->unloaded_info); + else + info = gcov_info_dup(node->loaded_info[i++]); + if (!info) + return NULL; + for (; i < node->num_loaded; i++) + gcov_info_add(info, node->loaded_info[i]); + + return info; } /* @@ -163,9 +186,10 @@ static int gcov_seq_open(struct inode *inode, struct file *file) mutex_lock(&node_lock); /* * Read from a profiling data copy to minimize reference tracking - * complexity and concurrent access. + * complexity and concurrent access and to keep accumulating multiple + * profiling data sets associated with one node simple. */ - info = gcov_info_dup(get_node_info(node)); + info = get_accumulated_info(node); if (!info) goto out_unlock; iter = gcov_iter_new(info); @@ -225,12 +249,25 @@ static struct gcov_node *get_node_by_name(const char *name) return NULL; } +/* + * Reset all profiling data associated with the specified node. + */ +static void reset_node(struct gcov_node *node) +{ + int i; + + if (node->unloaded_info) + gcov_info_reset(node->unloaded_info); + for (i = 0; i < node->num_loaded; i++) + gcov_info_reset(node->loaded_info[i]); +} + static void remove_node(struct gcov_node *node); /* * write() implementation for gcov data files. Reset profiling data for the - * associated file. If the object file has been unloaded (i.e. this is - * a "ghost" node), remove the debug fs node as well. + * corresponding file. If all associated object files have been unloaded, + * remove the debug fs node as well. */ static ssize_t gcov_seq_write(struct file *file, const char __user *addr, size_t len, loff_t *pos) @@ -245,10 +282,10 @@ static ssize_t gcov_seq_write(struct file *file, const char __user *addr, node = get_node_by_name(info->filename); if (node) { /* Reset counts or remove node for unloaded modules. */ - if (node->ghost) + if (node->num_loaded == 0) remove_node(node); else - gcov_info_reset(node->info); + reset_node(node); } /* Reset counts for open file. */ gcov_info_reset(info); @@ -378,7 +415,10 @@ static void init_node(struct gcov_node *node, struct gcov_info *info, INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->children); INIT_LIST_HEAD(&node->all); - node->info = info; + if (node->loaded_info) { + node->loaded_info[0] = info; + node->num_loaded = 1; + } node->parent = parent; if (name) strcpy(node->name, name); @@ -394,9 +434,13 @@ static struct gcov_node *new_node(struct gcov_node *parent, struct gcov_node *node; node = kzalloc(sizeof(struct gcov_node) + strlen(name) + 1, GFP_KERNEL); - if (!node) { - pr_warning("out of memory\n"); - return NULL; + if (!node) + goto err_nomem; + if (info) { + node->loaded_info = kcalloc(1, sizeof(struct gcov_info *), + GFP_KERNEL); + if (!node->loaded_info) + goto err_nomem; } init_node(node, info, name, parent); /* Differentiate between gcov data file nodes and directory nodes. */ @@ -416,6 +460,11 @@ static struct gcov_node *new_node(struct gcov_node *parent, list_add(&node->all, &all_head); return node; + +err_nomem: + kfree(node); + pr_warning("out of memory\n"); + return NULL; } /* Remove symbolic links associated with node. */ @@ -441,8 +490,9 @@ static void release_node(struct gcov_node *node) list_del(&node->all); debugfs_remove(node->dentry); remove_links(node); - if (node->ghost) - gcov_info_free(node->ghost); + kfree(node->loaded_info); + if (node->unloaded_info) + gcov_info_free(node->unloaded_info); kfree(node); } @@ -477,7 +527,7 @@ static struct gcov_node *get_child_by_name(struct gcov_node *parent, /* * write() implementation for reset file. Reset all profiling data to zero - * and remove ghost nodes. + * and remove nodes for which all associated object files are unloaded. */ static ssize_t reset_write(struct file *file, const char __user *addr, size_t len, loff_t *pos) @@ -487,8 +537,8 @@ static ssize_t reset_write(struct file *file, const char __user *addr, mutex_lock(&node_lock); restart: list_for_each_entry(node, &all_head, all) { - if (node->info) - gcov_info_reset(node->info); + if (node->num_loaded > 0) + reset_node(node); else if (list_empty(&node->children)) { remove_node(node); /* Several nodes may have gone - restart loop. */ @@ -564,37 +614,115 @@ err_remove: } /* - * The profiling data set associated with this node is being unloaded. Store a - * copy of the profiling data and turn this node into a "ghost". + * Associate a profiling data set with an existing node. Needs to be called + * with node_lock held. */ -static int ghost_node(struct gcov_node *node) +static void add_info(struct gcov_node *node, struct gcov_info *info) { - node->ghost = gcov_info_dup(node->info); - if (!node->ghost) { - pr_warning("could not save data for '%s' (out of memory)\n", - node->info->filename); - return -ENOMEM; + struct gcov_info **loaded_info; + int num = node->num_loaded; + + /* + * Prepare new array. This is done first to simplify cleanup in + * case the new data set is incompatible, the node only contains + * unloaded data sets and there's not enough memory for the array. + */ + loaded_info = kcalloc(num + 1, sizeof(struct gcov_info *), GFP_KERNEL); + if (!loaded_info) { + pr_warning("could not add '%s' (out of memory)\n", + info->filename); + return; + } + memcpy(loaded_info, node->loaded_info, + num * sizeof(struct gcov_info *)); + loaded_info[num] = info; + /* Check if the new data set is compatible. */ + if (num == 0) { + /* + * A module was unloaded, modified and reloaded. The new + * data set replaces the copy of the last one. + */ + if (!gcov_info_is_compatible(node->unloaded_info, info)) { + pr_warning("discarding saved data for %s " + "(incompatible version)\n", info->filename); + gcov_info_free(node->unloaded_info); + node->unloaded_info = NULL; + } + } else { + /* + * Two different versions of the same object file are loaded. + * The initial one takes precedence. + */ + if (!gcov_info_is_compatible(node->loaded_info[0], info)) { + pr_warning("could not add '%s' (incompatible " + "version)\n", info->filename); + kfree(loaded_info); + return; + } } - node->info = NULL; + /* Overwrite previous array. */ + kfree(node->loaded_info); + node->loaded_info = loaded_info; + node->num_loaded = num + 1; +} - return 0; +/* + * Return the index of a profiling data set associated with a node. + */ +static int get_info_index(struct gcov_node *node, struct gcov_info *info) +{ + int i; + + for (i = 0; i < node->num_loaded; i++) { + if (node->loaded_info[i] == info) + return i; + } + return -ENOENT; } /* - * Profiling data for this node has been loaded again. Add profiling data - * from previous instantiation and turn this node into a regular node. + * Save the data of a profiling data set which is being unloaded. */ -static void revive_node(struct gcov_node *node, struct gcov_info *info) +static void save_info(struct gcov_node *node, struct gcov_info *info) { - if (gcov_info_is_compatible(node->ghost, info)) - gcov_info_add(info, node->ghost); + if (node->unloaded_info) + gcov_info_add(node->unloaded_info, info); else { - pr_warning("discarding saved data for '%s' (version changed)\n", + node->unloaded_info = gcov_info_dup(info); + if (!node->unloaded_info) { + pr_warning("could not save data for '%s' " + "(out of memory)\n", info->filename); + } + } +} + +/* + * Disassociate a profiling data set from a node. Needs to be called with + * node_lock held. + */ +static void remove_info(struct gcov_node *node, struct gcov_info *info) +{ + int i; + + i = get_info_index(node, info); + if (i < 0) { + pr_warning("could not remove '%s' (not found)\n", info->filename); + return; } - gcov_info_free(node->ghost); - node->ghost = NULL; - node->info = info; + if (gcov_persist) + save_info(node, info); + /* Shrink array. */ + node->loaded_info[i] = node->loaded_info[node->num_loaded - 1]; + node->num_loaded--; + if (node->num_loaded > 0) + return; + /* Last loaded data set was removed. */ + kfree(node->loaded_info); + node->loaded_info = NULL; + node->num_loaded = 0; + if (!node->unloaded_info) + remove_node(node); } /* @@ -609,30 +737,18 @@ void gcov_event(enum gcov_action action, struct gcov_info *info) node = get_node_by_name(info->filename); switch (action) { case GCOV_ADD: - /* Add new node or revive ghost. */ - if (!node) { + if (node) + add_info(node, info); + else add_node(info); - break; - } - if (gcov_persist) - revive_node(node, info); - else { - pr_warning("could not add '%s' (already exists)\n", - info->filename); - } break; case GCOV_REMOVE: - /* Remove node or turn into ghost. */ - if (!node) { + if (node) + remove_info(node, info); + else { pr_warning("could not remove '%s' (not found)\n", info->filename); - break; } - if (gcov_persist) { - if (!ghost_node(node)) - break; - } - remove_node(node); break; } mutex_unlock(&node_lock); diff --git a/kernel/groups.c b/kernel/groups.c index 53b1916c9492..253dc0f35cf4 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -143,10 +143,9 @@ int groups_search(const struct group_info *group_info, gid_t grp) right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; - int cmp = grp - GROUP_AT(group_info, mid); - if (cmp > 0) + if (grp > GROUP_AT(group_info, mid)) left = mid + 1; - else if (cmp < 0) + else if (grp < GROUP_AT(group_info, mid)) right = mid; else return 1; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 5c69e996bd0f..21e0c5e468b6 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -936,6 +936,7 @@ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) { if (hrtimer_is_queued(timer)) { + unsigned long state; int reprogram; /* @@ -949,8 +950,13 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) debug_deactivate(timer); timer_stats_hrtimer_clear_start_info(timer); reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases); - __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, - reprogram); + /* + * We must preserve the CALLBACK state flag here, + * otherwise we could move the timer base in + * switch_hrtimer_base. + */ + state = timer->state & HRTIMER_STATE_CALLBACK; + __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; @@ -1237,6 +1243,9 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) BUG_ON(timer->state != HRTIMER_STATE_CALLBACK); enqueue_hrtimer(timer, base); } + + WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK)); + timer->state &= ~HRTIMER_STATE_CALLBACK; } diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index 7a56b22e0602..6eb642219713 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -417,7 +417,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, struct task_struct *tsk) { - return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); + return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk), + triggered); } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e1497481fe8a..a6a8b6af1fe7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -216,7 +216,7 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend) { if (suspend) { - if (!desc->action || (desc->action->flags & IRQF_TIMER)) + if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND)) return; desc->status |= IRQ_SUSPENDED; } @@ -281,8 +281,17 @@ EXPORT_SYMBOL(disable_irq); void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) { - if (resume) + if (resume) { + if (!(desc->status & IRQ_SUSPENDED)) { + if (!desc->action) + return; + if (!(desc->action->flags & IRQF_FORCE_RESUME)) + return; + /* Pretend that it got disabled ! */ + desc->depth++; + } desc->status &= ~IRQ_SUSPENDED; + } switch (desc->depth) { case 0: @@ -1093,7 +1102,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, if (retval) kfree(action); -#ifdef CONFIG_DEBUG_SHIRQ +#ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index 0d4005d85b03..d6bfb89cce91 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -53,9 +53,6 @@ void resume_device_irqs(void) for_each_irq_desc(irq, desc) { unsigned long flags; - if (!(desc->status & IRQ_SUSPENDED)) - continue; - raw_spin_lock_irqsave(&desc->lock, flags); __enable_irq(desc, irq, true); raw_spin_unlock_irqrestore(&desc->lock, flags); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 09a2ee540bd2..345e0b75fe1e 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -214,7 +214,7 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v) static int irq_spurious_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_spurious_proc_show, NULL); + return single_open(file, irq_spurious_proc_show, PDE(inode)->data); } static const struct file_operations irq_spurious_proc_fops = { diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 877fb306d415..17110a4a4fc2 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -194,14 +194,7 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) account_global_scheduler_latency(tsk, &lat); - /* - * short term hack; if we're > 32 we stop; future we recycle: - */ - tsk->latency_record_count++; - if (tsk->latency_record_count >= LT_SAVECOUNT) - goto out_unlock; - - for (i = 0; i < LT_SAVECOUNT; i++) { + for (i = 0; i < tsk->latency_record_count; i++) { struct latency_record *mylat; int same = 1; @@ -227,8 +220,14 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) } } + /* + * short term hack; if we're > 32 we stop; future we recycle: + */ + if (tsk->latency_record_count >= LT_SAVECOUNT) + goto out_unlock; + /* Allocated a new one: */ - i = tsk->latency_record_count; + i = tsk->latency_record_count++; memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record)); out_unlock: diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 54286798c37b..e6c932b4ddc6 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3250,7 +3250,7 @@ int lock_is_held(struct lockdep_map *lock) int ret = 0; if (unlikely(current->lockdep_recursion)) - return ret; + return 1; /* avoid false negative lockdep_assert_held() */ raw_local_irq_save(flags); check_flags(flags); diff --git a/kernel/perf_event.c b/kernel/perf_event.c index ff86c558af4c..fa8123e48353 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -58,7 +58,8 @@ static atomic_t nr_task_events __read_mostly; */ int sysctl_perf_event_paranoid __read_mostly = 1; -int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */ +/* Minimum for 128 pages + 1 for the user control page */ +int sysctl_perf_event_mlock __read_mostly = 516; /* 'free' kb per user */ /* * max perf event sample rate @@ -1609,8 +1610,12 @@ static void rotate_ctx(struct perf_event_context *ctx) { raw_spin_lock(&ctx->lock); - /* Rotate the first entry last of non-pinned groups */ - list_rotate_left(&ctx->flexible_groups); + /* + * Rotate the first entry last of non-pinned groups. Rotation might be + * disabled by the inheritance code. + */ + if (!ctx->rotate_disable) + list_rotate_left(&ctx->flexible_groups); raw_spin_unlock(&ctx->lock); } @@ -1757,7 +1762,13 @@ static u64 perf_event_read(struct perf_event *event) unsigned long flags; raw_spin_lock_irqsave(&ctx->lock, flags); - update_context_time(ctx); + /* + * may read while context is not active + * (e.g., thread is blocked), in that case + * we cannot update context time + */ + if (ctx->is_active) + update_context_time(ctx); update_event_times(event); raw_spin_unlock_irqrestore(&ctx->lock, flags); } @@ -5390,17 +5401,20 @@ __perf_event_exit_task(struct perf_event *child_event, struct perf_event_context *child_ctx, struct task_struct *child) { - struct perf_event *parent_event; + if (child_event->parent) { + raw_spin_lock_irq(&child_ctx->lock); + perf_group_detach(child_event); + raw_spin_unlock_irq(&child_ctx->lock); + } perf_event_remove_from_context(child_event); - parent_event = child_event->parent; /* - * It can happen that parent exits first, and has events + * It can happen that the parent exits first, and has events * that are still around due to the child reference. These - * events need to be zapped - but otherwise linger. + * events need to be zapped. */ - if (parent_event) { + if (child_event->parent) { sync_child_event(child_event, child); free_event(child_event); } @@ -5590,6 +5604,7 @@ int perf_event_init_task(struct task_struct *child) struct perf_event *event; struct task_struct *parent = current; int inherited_all = 1; + unsigned long flags; int ret = 0; child->perf_event_ctxp = NULL; @@ -5630,6 +5645,15 @@ int perf_event_init_task(struct task_struct *child) break; } + /* + * We can't hold ctx->lock when iterating the ->flexible_group list due + * to allocations, but we need to prevent rotation because + * rotate_ctx() will change the list from interrupt context. + */ + raw_spin_lock_irqsave(&parent_ctx->lock, flags); + parent_ctx->rotate_disable = 1; + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); + list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) { ret = inherit_task_group(event, parent, parent_ctx, child, &inherited_all); @@ -5637,6 +5661,10 @@ int perf_event_init_task(struct task_struct *child) break; } + raw_spin_lock_irqsave(&parent_ctx->lock, flags); + parent_ctx->rotate_disable = 0; + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); + child_ctx = child->perf_event_ctxp; if (child_ctx && inherited_all) { diff --git a/kernel/pid.c b/kernel/pid.c index e9fd8c132d26..4d0a9fc6e8a0 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -183,11 +183,14 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) return -1; } -int next_pidmap(struct pid_namespace *pid_ns, int last) +int next_pidmap(struct pid_namespace *pid_ns, unsigned int last) { int offset; struct pidmap *map, *end; + if (last >= PID_MAX_LIMIT) + return -1; + offset = (last + 1) & BITS_PER_PAGE_MASK; map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE]; end = &pid_ns->pidmap[PIDMAP_ENTRIES]; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index aa9e916da4d5..684463e7e263 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -324,7 +324,6 @@ static int create_image(int platform_mode) int hibernation_snapshot(int platform_mode) { int error; - gfp_t saved_mask; error = platform_begin(platform_mode); if (error) @@ -336,7 +335,7 @@ int hibernation_snapshot(int platform_mode) goto Close; suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); + pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Recover_platform; @@ -345,7 +344,10 @@ int hibernation_snapshot(int platform_mode) goto Recover_platform; error = create_image(platform_mode); - /* Control returns here after successful restore */ + /* + * Control returns here (1) after the image has been created or the + * image creation has failed and (2) after a successful restore. + */ Resume_devices: /* We may need to release the preallocated image pages here. */ @@ -354,7 +356,10 @@ int hibernation_snapshot(int platform_mode) dpm_resume_end(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); - set_gfp_allowed_mask(saved_mask); + + if (error || !in_suspend) + pm_restore_gfp_mask(); + resume_console(); Close: platform_end(platform_mode); @@ -449,17 +454,16 @@ static int resume_target_kernel(bool platform_mode) int hibernation_restore(int platform_mode) { int error; - gfp_t saved_mask; pm_prepare_console(); suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); + pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); dpm_resume_end(PMSG_RECOVER); } - set_gfp_allowed_mask(saved_mask); + pm_restore_gfp_mask(); resume_console(); pm_restore_console(); return error; @@ -473,7 +477,6 @@ int hibernation_restore(int platform_mode) int hibernation_platform_enter(void) { int error; - gfp_t saved_mask; if (!hibernation_ops) return -ENOSYS; @@ -489,7 +492,6 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -527,7 +529,6 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); - set_gfp_allowed_mask(saved_mask); resume_console(); Close: @@ -635,6 +636,7 @@ int hibernate(void) swsusp_free(); if (!error) power_down(); + pm_restore_gfp_mask(); } else { pr_debug("PM: Image restored successfully.\n"); } diff --git a/kernel/power/main.c b/kernel/power/main.c index bfb684a4d412..a6797d310227 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -302,6 +302,7 @@ static int __init pm_init(void) int error = pm_start_workqueue(); if (error) return error; + hibernate_image_size_init(); power_kobj = kobject_create_and_add("power", NULL); if (!power_kobj) return -ENOMEM; diff --git a/kernel/power/power.h b/kernel/power/power.h index 006270fe382d..54580cb4eaa7 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -14,6 +14,9 @@ struct swsusp_info { } __attribute__((aligned(PAGE_SIZE))); #ifdef CONFIG_HIBERNATION +/* kernel/power/snapshot.c */ +extern void __init hibernate_image_size_init(void); + #ifdef CONFIG_ARCH_HIBERNATION_HEADER /* Maximum size of architecture specific data in a hibernation header */ #define MAX_ARCH_HEADER_SIZE (sizeof(struct new_utsname) + 4) @@ -49,7 +52,11 @@ static inline char *check_image_kernel(struct swsusp_info *info) extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); extern int hibernation_platform_enter(void); -#endif + +#else /* !CONFIG_HIBERNATION */ + +static inline void hibernate_image_size_init(void) {} +#endif /* !CONFIG_HIBERNATION */ extern int pfn_is_nosave(unsigned long); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 25ce010e9f8b..d0c3c4420eec 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -46,7 +46,12 @@ static void swsusp_unset_page_forbidden(struct page *); * size will not exceed N bytes, but if that is impossible, it will * try to create the smallest image possible. */ -unsigned long image_size = 500 * 1024 * 1024; +unsigned long image_size; + +void __init hibernate_image_size_init(void) +{ + image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE; +} /* List of PBEs needed for restoring the pages that were allocated before * the suspend and included in the suspend image, but have also been @@ -1121,9 +1126,19 @@ static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask) return nr_alloc; } -static unsigned long preallocate_image_memory(unsigned long nr_pages) +static unsigned long preallocate_image_memory(unsigned long nr_pages, + unsigned long avail_normal) { - return preallocate_image_pages(nr_pages, GFP_IMAGE); + unsigned long alloc; + + if (avail_normal <= alloc_normal) + return 0; + + alloc = avail_normal - alloc_normal; + if (nr_pages < alloc) + alloc = nr_pages; + + return preallocate_image_pages(alloc, GFP_IMAGE); } #ifdef CONFIG_HIGHMEM @@ -1169,15 +1184,26 @@ static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, */ static void free_unnecessary_pages(void) { - unsigned long save_highmem, to_free_normal, to_free_highmem; + unsigned long save, to_free_normal, to_free_highmem; - to_free_normal = alloc_normal - count_data_pages(); - save_highmem = count_highmem_pages(); - if (alloc_highmem > save_highmem) { - to_free_highmem = alloc_highmem - save_highmem; + save = count_data_pages(); + if (alloc_normal >= save) { + to_free_normal = alloc_normal - save; + save = 0; + } else { + to_free_normal = 0; + save -= alloc_normal; + } + save += count_highmem_pages(); + if (alloc_highmem >= save) { + to_free_highmem = alloc_highmem - save; } else { to_free_highmem = 0; - to_free_normal -= save_highmem - alloc_highmem; + save -= alloc_highmem; + if (to_free_normal > save) + to_free_normal -= save; + else + to_free_normal = 0; } memory_bm_position_reset(©_bm); @@ -1258,7 +1284,7 @@ int hibernate_preallocate_memory(void) { struct zone *zone; unsigned long saveable, size, max_size, count, highmem, pages = 0; - unsigned long alloc, save_highmem, pages_highmem; + unsigned long alloc, save_highmem, pages_highmem, avail_normal; struct timeval start, stop; int error; @@ -1295,26 +1321,38 @@ int hibernate_preallocate_memory(void) else count += zone_page_state(zone, NR_FREE_PAGES); } + avail_normal = count; count += highmem; count -= totalreserve_pages; /* Compute the maximum number of saveable pages to leave in memory. */ max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES; + /* Compute the desired number of image pages specified by image_size. */ size = DIV_ROUND_UP(image_size, PAGE_SIZE); if (size > max_size) size = max_size; /* - * If the maximum is not less than the current number of saveable pages - * in memory, allocate page frames for the image and we're done. + * If the desired number of image pages is at least as large as the + * current number of saveable pages in memory, allocate page frames for + * the image and we're done. */ if (size >= saveable) { pages = preallocate_image_highmem(save_highmem); - pages += preallocate_image_memory(saveable - pages); + pages += preallocate_image_memory(saveable - pages, avail_normal); goto out; } /* Estimate the minimum size of the image. */ pages = minimum_image_size(saveable); + /* + * To avoid excessive pressure on the normal zone, leave room in it to + * accommodate an image of the minimum size (unless it's already too + * small, in which case don't preallocate pages from it at all). + */ + if (avail_normal > pages) + avail_normal -= pages; + else + avail_normal = 0; if (size < pages) size = min_t(unsigned long, pages, max_size); @@ -1335,16 +1373,34 @@ int hibernate_preallocate_memory(void) */ pages_highmem = preallocate_image_highmem(highmem / 2); alloc = (count - max_size) - pages_highmem; - pages = preallocate_image_memory(alloc); - if (pages < alloc) - goto err_out; - size = max_size - size; - alloc = size; - size = preallocate_highmem_fraction(size, highmem, count); - pages_highmem += size; - alloc -= size; - pages += preallocate_image_memory(alloc); - pages += pages_highmem; + pages = preallocate_image_memory(alloc, avail_normal); + if (pages < alloc) { + /* We have exhausted non-highmem pages, try highmem. */ + alloc -= pages; + pages += pages_highmem; + pages_highmem = preallocate_image_highmem(alloc); + if (pages_highmem < alloc) + goto err_out; + pages += pages_highmem; + /* + * size is the desired number of saveable pages to leave in + * memory, so try to preallocate (all memory - size) pages. + */ + alloc = (count - pages) - size; + pages += preallocate_image_highmem(alloc); + } else { + /* + * There are approximately max_size saveable pages at this point + * and we want to reduce this number down to size. + */ + alloc = max_size - size; + size = preallocate_highmem_fraction(alloc, highmem, count); + pages_highmem += size; + alloc -= size; + size = preallocate_image_memory(alloc, avail_normal); + pages_highmem += preallocate_image_highmem(alloc - size); + pages += pages_highmem + size; + } /* * We only need as many page frames for the image as there are saveable @@ -1467,11 +1523,8 @@ static int swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, unsigned int nr_pages, unsigned int nr_highmem) { - int error = 0; - if (nr_highmem > 0) { - error = get_highmem_buffer(PG_ANY); - if (error) + if (get_highmem_buffer(PG_ANY)) goto err_out; if (nr_highmem > alloc_highmem) { nr_highmem -= alloc_highmem; @@ -1494,7 +1547,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, err_out: swsusp_free(); - return error; + return -ENOMEM; } asmlinkage int swsusp_save(void) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f37cb7dd4402..b0f28dddc04e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -196,7 +196,6 @@ static int suspend_enter(suspend_state_t state) int suspend_devices_and_enter(suspend_state_t state) { int error; - gfp_t saved_mask; if (!suspend_ops) return -ENOSYS; @@ -207,7 +206,7 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); - saved_mask = clear_gfp_allowed_mask(GFP_IOFS); + pm_restrict_gfp_mask(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -224,7 +223,7 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); - set_gfp_allowed_mask(saved_mask); + pm_restore_gfp_mask(); resume_console(); Close: if (suspend_ops->end) diff --git a/kernel/power/user.c b/kernel/power/user.c index e819e17877ca..fe4f1ab3f746 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -113,8 +113,10 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) pm_notifier_call_chain(PM_POST_RESTORE); } - if (error) + if (error) { + free_basic_memory_bitmaps(); atomic_inc(&snapshot_device_available); + } data->frozen = 0; data->ready = 0; data->platform_support = 0; @@ -137,7 +139,7 @@ static int snapshot_release(struct inode *inode, struct file *filp) free_all_swap_pages(data->swap); if (data->frozen) thaw_processes(); - pm_notifier_call_chain(data->mode == O_WRONLY ? + pm_notifier_call_chain(data->mode == O_RDONLY ? PM_POST_HIBERNATION : PM_POST_RESTORE); atomic_inc(&snapshot_device_available); @@ -263,6 +265,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, case SNAPSHOT_UNFREEZE: if (!data->frozen || data->ready) break; + pm_restore_gfp_mask(); thaw_processes(); usermodehelper_enable(); data->frozen = 0; @@ -275,6 +278,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, error = -EPERM; break; } + pm_restore_gfp_mask(); error = hibernation_snapshot(data->platform_support); if (!error) error = put_user(in_suspend, (int __user *)arg); diff --git a/kernel/printk.c b/kernel/printk.c index 444b770c9595..b7b7f90aad6e 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1034,13 +1034,15 @@ void printk_tick(void) int printk_needs_cpu(int cpu) { + if (unlikely(cpu_is_offline(cpu))) + printk_tick(); return per_cpu(printk_pending, cpu); } void wake_up_klogd(void) { if (waitqueue_active(&log_wait)) - __raw_get_cpu_var(printk_pending) = 1; + this_cpu_write(printk_pending, 1); } /** diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 74a3d693c196..752321eeca8b 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -313,7 +313,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data) child->exit_code = data; dead = __ptrace_detach(current, child); if (!child->exit_state) - wake_up_process(child); + wake_up_state(child, TASK_TRACED | TASK_STOPPED); } write_unlock_irq(&tasklist_lock); diff --git a/kernel/sched.c b/kernel/sched.c index 889aef148201..d40d662392cf 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -491,6 +491,7 @@ struct rq { struct mm_struct *prev_mm; u64 clock; + u64 clock_task; atomic_t nr_iowait; @@ -518,6 +519,10 @@ struct rq { u64 avg_idle; #endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif + /* calc_load related fields */ unsigned long calc_load_update; long calc_load_active; @@ -641,10 +646,21 @@ static inline struct task_group *task_group(struct task_struct *p) #endif /* CONFIG_CGROUP_SCHED */ +static u64 irq_time_cpu(int cpu); +static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time); + inline void update_rq_clock(struct rq *rq) { + int cpu = cpu_of(rq); + u64 irq_time; + if (!rq->skip_clock_update) rq->clock = sched_clock_cpu(cpu_of(rq)); + irq_time = irq_time_cpu(cpu); + if (rq->clock - irq_time > rq->clock_task) + rq->clock_task = rq->clock - irq_time; + + sched_irq_time_avg_update(rq, irq_time); } /* @@ -1231,16 +1247,6 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } -int nohz_ratelimit(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - u64 diff = rq->clock - rq->nohz_stamp; - - rq->nohz_stamp = rq->clock; - - return diff < (NSEC_PER_SEC / HZ) >> 1; -} - #endif /* CONFIG_NO_HZ */ static u64 sched_avg_period(void) @@ -1280,6 +1286,10 @@ static void resched_task(struct task_struct *p) static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } + +static void sched_avg_update(struct rq *rq) +{ +} #endif /* CONFIG_SMP */ #if BITS_PER_LONG == 32 @@ -1825,6 +1835,94 @@ static const struct sched_class rt_sched_class; #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in account_system_vtime, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/account_system_vtime on this CPU. We would either get old + * or new value (or semi updated value on 32 bit) with a side effect of + * accounting a slice of irq time to wrong task when irq is in progress + * while we read rq->clock. That is a worthy compromise in place of having + * locks on each irq in account_system_time. + */ +static DEFINE_PER_CPU(u64, cpu_hardirq_time); +static DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +static u64 irq_time_cpu(int cpu) +{ + if (!sched_clock_irqtime) + return 0; + + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} + +void account_system_vtime(struct task_struct *curr) +{ + unsigned long flags; + int cpu; + u64 now, delta; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + now = sched_clock_cpu(cpu); + delta = now - per_cpu(irq_start_time, cpu); + per_cpu(irq_start_time, cpu) = now; + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + per_cpu(cpu_hardirq_time, cpu) += delta; + else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) + per_cpu(cpu_softirq_time, cpu) += delta; + + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(account_system_vtime); + +static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) +{ + if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) { + u64 delta_irq = curr_irq_time - rq->prev_irq_time; + rq->prev_irq_time = curr_irq_time; + sched_rt_avg_update(rq, delta_irq); + } +} + +#else + +static u64 irq_time_cpu(int cpu) +{ + return 0; +} + +static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { } + +#endif + #include "sched_stats.h" static void inc_nr_running(struct rq *rq) @@ -1978,6 +2076,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) if (p->sched_class != &fair_sched_class) return 0; + if (unlikely(p->policy == SCHED_IDLE)) + return 0; + /* * Buddy candidates are cache hot: */ @@ -2900,6 +3001,15 @@ static long calc_load_fold_active(struct rq *this_rq) return delta; } +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + load += 1UL << (FSHIFT - 1); + return load >> FSHIFT; +} + #ifdef CONFIG_NO_HZ /* * For NO_HZ we delay the active fold to the next LOAD_FREQ update. @@ -2929,6 +3039,128 @@ static long calc_load_fold_idle(void) return delta; } + +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +static unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + +/* + * NO_HZ can leave us missing all per-cpu ticks calling + * calc_load_account_active(), but since an idle CPU folds its delta into + * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold + * in the pending idle delta if our idle period crossed a load cycle boundary. + * + * Once we've updated the global active value, we need to apply the exponential + * weights adjusted to the number of cycles missed. + */ +static void calc_global_nohz(unsigned long ticks) +{ + long delta, active, n; + + if (time_before(jiffies, calc_load_update)) + return; + + /* + * If we crossed a calc_load_update boundary, make sure to fold + * any pending idle changes, the respective CPUs might have + * missed the tick driven calc_load_account_active() update + * due to NO_HZ. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + + /* + * If we were idle for multiple load cycles, apply them. + */ + if (ticks >= LOAD_FREQ) { + n = ticks / LOAD_FREQ; + + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; + + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + + calc_load_update += n * LOAD_FREQ; + } + + /* + * Its possible the remainder of the above division also crosses + * a LOAD_FREQ period, the regular check in calc_global_load() + * which comes after this will take care of that. + * + * Consider us being 11 ticks before a cycle completion, and us + * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will + * age us 4 cycles, and the test in calc_global_load() will + * pick up the final one. + */ +} #else static void calc_load_account_idle(struct rq *this_rq) { @@ -2938,6 +3170,10 @@ static inline long calc_load_fold_idle(void) { return 0; } + +static void calc_global_nohz(unsigned long ticks) +{ +} #endif /** @@ -2955,24 +3191,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) loads[2] = (avenrun[2] + offset) << shift; } -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - load *= exp; - load += active * (FIXED_1 - exp); - return load >> FSHIFT; -} - /* * calc_load - update the avenrun load estimates 10 ticks after the * CPUs have updated calc_load_tasks. */ -void calc_global_load(void) +void calc_global_load(unsigned long ticks) { - unsigned long upd = calc_load_update + 10; long active; - if (time_before(jiffies, upd)) + calc_global_nohz(ticks); + + if (time_before(jiffies, calc_load_update + 10)) return; active = atomic_long_read(&calc_load_tasks); @@ -3034,6 +3263,8 @@ static void update_cpu_load(struct rq *this_rq) } calc_load_account_active(this_rq); + + sched_avg_update(this_rq); } #ifdef CONFIG_SMP @@ -3087,7 +3318,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) if (task_current(rq, p)) { update_rq_clock(rq); - ns = rq->clock - p->se.exec_start; + ns = rq->clock_task - p->se.exec_start; if ((s64)ns < 0) ns = 0; } @@ -3236,7 +3467,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, tmp = cputime_to_cputime64(cputime); if (hardirq_count() - hardirq_offset) cpustat->irq = cputime64_add(cpustat->irq, tmp); - else if (softirq_count()) + else if (in_serving_softirq()) cpustat->softirq = cputime64_add(cpustat->softirq, tmp); else cpustat->system = cputime64_add(cpustat->system, tmp); @@ -3697,8 +3928,16 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) /* * Owner changed, break to re-assess state. */ - if (lock->owner != owner) + if (lock->owner != owner) { + /* + * If the lock has switched to a different owner, + * we likely have heavy contention. Return 0 to quit + * optimistic spinning and not contend further: + */ + if (lock->owner) + return 0; break; + } /* * Is that owner really running on that cpu? @@ -5189,7 +5428,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; - ftrace_graph_init_task(idle); + ftrace_graph_init_idle_task(idle, cpu); } /* @@ -6600,6 +6839,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) if (cpu != group_first_cpu(sd->groups)) return; + sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); + child = sd->child; sd->groups->cpu_power = 0; @@ -8093,12 +8334,12 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); - set_task_rq(tsk, task_cpu(tsk)); - #ifdef CONFIG_FAIR_GROUP_SCHED - if (tsk->sched_class->moved_group) - tsk->sched_class->moved_group(tsk, on_rq); + if (tsk->sched_class->task_move_group) + tsk->sched_class->task_move_group(tsk, on_rq); + else #endif + set_task_rq(tsk, task_cpu(tsk)); if (unlikely(running)) tsk->sched_class->set_curr_task(rq); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a878b5332daa..09a98114ec32 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -519,7 +519,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; - u64 now = rq_of(cfs_rq)->clock; + u64 now = rq_of(cfs_rq)->clock_task; unsigned long delta_exec; if (unlikely(!curr)) @@ -602,7 +602,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) /* * We are starting a new run period: */ - se->exec_start = rq_of(cfs_rq)->clock; + se->exec_start = rq_of(cfs_rq)->clock_task; } /************************************************** @@ -1765,6 +1765,10 @@ static void pull_task(struct rq *src_rq, struct task_struct *p, set_task_cpu(p, this_cpu); activate_task(this_rq, p, 0); check_preempt_curr(this_rq, p, 0); + + /* re-arm NEWIDLE balancing when moving tasks */ + src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost; + this_rq->idle_stamp = 0; } /* @@ -1799,7 +1803,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq->clock, sd); + tsk_cache_hot = task_hot(p, rq->clock_task, sd); if (!tsk_cache_hot || sd->nr_balance_failed > sd->cache_nice_tries) { #ifdef CONFIG_SCHEDSTATS @@ -2031,12 +2035,17 @@ struct sd_lb_stats { unsigned long this_load; unsigned long this_load_per_task; unsigned long this_nr_running; + unsigned long this_has_capacity; + unsigned int this_idle_cpus; /* Statistics of the busiest group */ + unsigned int busiest_idle_cpus; unsigned long max_load; unsigned long busiest_load_per_task; unsigned long busiest_nr_running; unsigned long busiest_group_capacity; + unsigned long busiest_has_capacity; + unsigned int busiest_group_weight; int group_imb; /* Is there imbalance in this sd */ #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) @@ -2058,7 +2067,10 @@ struct sg_lb_stats { unsigned long sum_nr_running; /* Nr tasks running in the group */ unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long group_capacity; + unsigned long idle_cpus; + unsigned long group_weight; int group_imb; /* Is there an imbalance in the group ? */ + int group_has_capacity; /* Is there extra capacity in the group? */ }; /** @@ -2268,11 +2280,14 @@ unsigned long scale_rt_power(int cpu) struct rq *rq = cpu_rq(cpu); u64 total, available; - sched_avg_update(rq); - total = sched_avg_period() + (rq->clock - rq->age_stamp); - available = total - rq->rt_avg; + if (unlikely(total < rq->rt_avg)) { + /* Ensures that power won't end up being negative */ + available = 0; + } else { + available = total - rq->rt_avg; + } if (unlikely((s64)total < SCHED_LOAD_SCALE)) total = SCHED_LOAD_SCALE; @@ -2354,7 +2369,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, int local_group, const struct cpumask *cpus, int *balance, struct sg_lb_stats *sgs) { - unsigned long load, max_cpu_load, min_cpu_load; + unsigned long load, max_cpu_load, min_cpu_load, max_nr_running; int i; unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long avg_load_per_task = 0; @@ -2365,6 +2380,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, /* Tally up the load of all CPUs in the group */ max_cpu_load = 0; min_cpu_load = ~0UL; + max_nr_running = 0; for_each_cpu_and(i, sched_group_cpus(group), cpus) { struct rq *rq = cpu_rq(i); @@ -2382,8 +2398,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, load = target_load(i, load_idx); } else { load = source_load(i, load_idx); - if (load > max_cpu_load) + if (load > max_cpu_load) { max_cpu_load = load; + max_nr_running = rq->nr_running; + } if (min_cpu_load > load) min_cpu_load = load; } @@ -2391,7 +2409,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, sgs->group_load += load; sgs->sum_nr_running += rq->nr_running; sgs->sum_weighted_load += weighted_cpuload(i); - + if (idle_cpu(i)) + sgs->idle_cpus++; } /* @@ -2423,11 +2442,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, if (sgs->sum_nr_running) avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1) sgs->group_imb = 1; - sgs->group_capacity = - DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + sgs->group_weight = group->group_weight; + + if (sgs->group_capacity > sgs->sum_nr_running) + sgs->group_has_capacity = 1; } /** @@ -2474,9 +2496,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, /* * In case the child domain prefers tasks go to siblings * first, lower the group capacity to one so that we'll try - * and move all the excess tasks away. + * and move all the excess tasks away. We lower the capacity + * of a group only if the local group has the capacity to fit + * these excess tasks, i.e. nr_running < group_capacity. The + * extra check prevents the case where you always pull from the + * heaviest group when it is already under-utilized (possible + * with a large weight task outweighs the tasks on the system). */ - if (prefer_sibling) + if (prefer_sibling && !local_group && sds->this_has_capacity) sgs.group_capacity = min(sgs.group_capacity, 1UL); if (local_group) { @@ -2484,14 +2511,19 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, sds->this = group; sds->this_nr_running = sgs.sum_nr_running; sds->this_load_per_task = sgs.sum_weighted_load; + sds->this_has_capacity = sgs.group_has_capacity; + sds->this_idle_cpus = sgs.idle_cpus; } else if (sgs.avg_load > sds->max_load && (sgs.sum_nr_running > sgs.group_capacity || sgs.group_imb)) { sds->max_load = sgs.avg_load; sds->busiest = group; sds->busiest_nr_running = sgs.sum_nr_running; + sds->busiest_idle_cpus = sgs.idle_cpus; sds->busiest_group_capacity = sgs.group_capacity; + sds->busiest_group_weight = sgs.group_weight; sds->busiest_load_per_task = sgs.sum_weighted_load; + sds->busiest_has_capacity = sgs.group_has_capacity; sds->group_imb = sgs.group_imb; } @@ -2637,6 +2669,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, return fix_small_imbalance(sds, this_cpu, imbalance); } + /******* find_busiest_group() helpers end here *********************/ /** @@ -2688,6 +2721,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * 4) This group is more busy than the avg busieness at this * sched_domain. * 5) The imbalance is within the specified limit. + * + * Note: when doing newidle balance, if the local group has excess + * capacity (i.e. nr_running < group_capacity) and the busiest group + * does not have any capacity, we force a load balance to pull tasks + * to the local group. In this case, we skip past checks 3, 4 and 5. */ if (!(*balance)) goto ret; @@ -2695,6 +2733,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; + /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ + if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity && + !sds.busiest_has_capacity) + goto force_balance; + if (sds.this_load >= sds.max_load) goto out_balanced; @@ -2703,9 +2746,28 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (sds.this_load >= sds.avg_load) goto out_balanced; - if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) - goto out_balanced; + /* + * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative. + * And to check for busy balance use !idle_cpu instead of + * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE + * even when they are idle. + */ + if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) { + if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + goto out_balanced; + } else { + /* + * This cpu is idle. If the busiest group load doesn't + * have more tasks than the number of available cpu's and + * there is no imbalance between this and busiest group + * wrt to idle cpu's, it is balanced. + */ + if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) && + sds.busiest_nr_running <= sds.busiest_group_weight) + goto out_balanced; + } +force_balance: /* Looks like there is an imbalance. Compute it */ calculate_imbalance(&sds, this_cpu, imbalance); return sds.busiest; @@ -2896,7 +2958,14 @@ redo: if (!ld_moved) { schedstat_inc(sd, lb_failed[idle]); - sd->nr_balance_failed++; + /* + * Increment the failure counter only on periodic balance. + * We do not want newidle balance, which can be very + * frequent, pollute the failure counter causing + * excessive cache_hot migrations and active balances. + */ + if (idle != CPU_NEWLY_IDLE) + sd->nr_balance_failed++; if (need_active_balance(sd, sd_idle, idle)) { raw_spin_lock_irqsave(&busiest->lock, flags); @@ -3017,10 +3086,8 @@ static void idle_balance(int this_cpu, struct rq *this_rq) interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) next_balance = sd->last_balance + interval; - if (pulled_task) { - this_rq->idle_stamp = 0; + if (pulled_task) break; - } } raw_spin_lock(&this_rq->lock); @@ -3542,8 +3609,11 @@ static void task_fork_fair(struct task_struct *p) raw_spin_lock_irqsave(&rq->lock, flags); - if (unlikely(task_cpu(p) != this_cpu)) + if (unlikely(task_cpu(p) != this_cpu)) { + rcu_read_lock(); __set_task_cpu(p, this_cpu); + rcu_read_unlock(); + } update_curr(cfs_rq); @@ -3615,13 +3685,26 @@ static void set_curr_task_fair(struct rq *rq) } #ifdef CONFIG_FAIR_GROUP_SCHED -static void moved_group_fair(struct task_struct *p, int on_rq) +static void task_move_group_fair(struct task_struct *p, int on_rq) { - struct cfs_rq *cfs_rq = task_cfs_rq(p); - - update_curr(cfs_rq); + /* + * If the task was not on the rq at the time of this cgroup movement + * it must have been asleep, sleeping tasks keep their ->vruntime + * absolute on their old rq until wakeup (needed for the fair sleeper + * bonus in place_entity()). + * + * If it was on the rq, we've just 'preempted' it, which does convert + * ->vruntime to a relative base. + * + * Make sure both cases convert their relative position when migrating + * to another cgroup's rq. This does somewhat interfere with the + * fair sleeper stuff for the first placement, but who cares. + */ + if (!on_rq) + p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime; + set_task_rq(p, task_cpu(p)); if (!on_rq) - place_entity(cfs_rq, &p->se, 1); + p->se.vruntime += cfs_rq_of(&p->se)->min_vruntime; } #endif @@ -3673,7 +3756,7 @@ static const struct sched_class fair_sched_class = { .get_rr_interval = get_rr_interval_fair, #ifdef CONFIG_FAIR_GROUP_SCHED - .moved_group = moved_group_fair, + .task_move_group = task_move_group_fair, #endif }; diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 83c66e8ad3ee..185f920ec1a2 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -61,3 +61,8 @@ SCHED_FEAT(ASYM_EFF_LOAD, 1) * release the lock. Decreases scheduling overhead. */ SCHED_FEAT(OWNER_SPIN, 1) + +/* + * Decrement CPU power based on irq activity + */ +SCHED_FEAT(NONIRQ_POWER, 1) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 8afb953e31c6..a851cc0796b3 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -609,7 +609,7 @@ static void update_curr_rt(struct rq *rq) if (!task_has_rt_policy(curr)) return; - delta_exec = rq->clock - curr->se.exec_start; + delta_exec = rq->clock_task - curr->se.exec_start; if (unlikely((s64)delta_exec < 0)) delta_exec = 0; @@ -618,7 +618,7 @@ static void update_curr_rt(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq->clock; + curr->se.exec_start = rq->clock_task; cpuacct_charge(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); @@ -960,18 +960,19 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) * runqueue. Otherwise simply start this RT task * on its current runqueue. * - * We want to avoid overloading runqueues. Even if - * the RT task is of higher priority than the current RT task. - * RT tasks behave differently than other tasks. If - * one gets preempted, we try to push it off to another queue. - * So trying to keep a preempting RT task on the same - * cache hot CPU will force the running RT task to - * a cold CPU. So we waste all the cache for the lower - * RT task in hopes of saving some of a RT task - * that is just being woken and probably will have - * cold cache anyway. + * We want to avoid overloading runqueues. If the woken + * task is a higher priority, then it will stay on this CPU + * and the lower prio task should be moved to another CPU. + * Even though this will probably make the lower prio task + * lose its cache, we do not want to bounce a higher task + * around just because it gave up its CPU, perhaps for a + * lock? + * + * For equal prio tasks, we just let the scheduler sort it out. */ if (unlikely(rt_task(rq->curr)) && + (rq->curr->rt.nr_cpus_allowed < 2 || + rq->curr->prio < p->prio) && (p->rt.nr_cpus_allowed > 1)) { int cpu = find_lowest_rq(p); @@ -1074,7 +1075,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) } while (rt_rq); p = rt_task_of(rt_se); - p->se.exec_start = rq->clock; + p->se.exec_start = rq->clock_task; return p; } @@ -1491,7 +1492,10 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && has_pushable_tasks(rq) && - p->rt.nr_cpus_allowed > 1) + p->rt.nr_cpus_allowed > 1 && + rt_task(rq->curr) && + (rq->curr->rt.nr_cpus_allowed < 2 || + rq->curr->prio < p->prio)) push_rt_tasks(rq); } @@ -1712,7 +1716,7 @@ static void set_curr_task_rt(struct rq *rq) { struct task_struct *p = rq->curr; - p->se.exec_start = rq->clock; + p->se.exec_start = rq->clock_task; /* The running task is never eligible for pushing */ dequeue_pushable_task(rq, p); diff --git a/kernel/signal.c b/kernel/signal.c index 906ae5a1779c..fdecae014340 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -637,7 +637,7 @@ static inline bool si_fromuser(const struct siginfo *info) /* * Bad permissions for sending the signal - * - the caller must hold at least the RCU read lock + * - the caller must hold the RCU read lock */ static int check_kill_permission(int sig, struct siginfo *info, struct task_struct *t) @@ -1127,11 +1127,14 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long /* * send signal info to all the members of a group - * - the caller must hold the RCU read lock at least */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - int ret = check_kill_permission(sig, info, p); + int ret; + + rcu_read_lock(); + ret = check_kill_permission(sig, info, p); + rcu_read_unlock(); if (!ret && sig) ret = do_send_sig_info(sig, info, p, true); @@ -2407,9 +2410,13 @@ SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, return -EFAULT; /* Not even root can pretend to send signals from the kernel. - Nor can they impersonate a kill(), which adds source info. */ - if (info.si_code >= 0) + * Nor can they impersonate a kill()/tgkill(), which adds source info. + */ + if (info.si_code >= 0 || info.si_code == SI_TKILL) { + /* We used to allow any < 0 si_code */ + WARN_ON_ONCE(info.si_code < 0); return -EPERM; + } info.si_signo = sig; /* POSIX.1b doesn't mention process groups. */ @@ -2423,9 +2430,13 @@ long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) return -EINVAL; /* Not even root can pretend to send signals from the kernel. - Nor can they impersonate a kill(), which adds source info. */ - if (info->si_code >= 0) + * Nor can they impersonate a kill()/tgkill(), which adds source info. + */ + if (info->si_code >= 0 || info->si_code == SI_TKILL) { + /* We used to allow any < 0 si_code */ + WARN_ON_ONCE(info->si_code < 0); return -EPERM; + } info->si_signo = sig; return do_send_specific(tgid, pid, sig, info); diff --git a/kernel/smp.c b/kernel/smp.c index 75c970c715d3..b89ef31396c4 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -194,6 +194,24 @@ void generic_smp_call_function_interrupt(void) list_for_each_entry_rcu(data, &call_function.queue, csd.list) { int refs; + /* + * Since we walk the list without any locks, we might + * see an entry that was completed, removed from the + * list and is in the process of being reused. + * + * We must check that the cpu is in the cpumask before + * checking the refs, and both must be set before + * executing the callback on this cpu. + */ + + if (!cpumask_test_cpu(cpu, data->cpumask)) + continue; + + smp_rmb(); + + if (atomic_read(&data->refs) == 0) + continue; + if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) continue; @@ -409,7 +427,7 @@ void smp_call_function_many(const struct cpumask *mask, { struct call_function_data *data; unsigned long flags; - int cpu, next_cpu, this_cpu = smp_processor_id(); + int refs, cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. @@ -420,7 +438,7 @@ void smp_call_function_many(const struct cpumask *mask, WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); - /* So, what's a CPU they want? Ignoring this one. */ + /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); @@ -443,11 +461,48 @@ void smp_call_function_many(const struct cpumask *mask, data = &__get_cpu_var(cfd_data); csd_lock(&data->csd); + /* This BUG_ON verifies our reuse assertions and can be removed */ + BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask)); + + /* + * The global call function queue list add and delete are protected + * by a lock, but the list is traversed without any lock, relying + * on the rcu list add and delete to allow safe concurrent traversal. + * We reuse the call function data without waiting for any grace + * period after some other cpu removes it from the global queue. + * This means a cpu might find our data block as it is being + * filled out. + * + * We hold off the interrupt handler on the other cpu by + * ordering our writes to the cpu mask vs our setting of the + * refs counter. We assert only the cpu owning the data block + * will set a bit in cpumask, and each bit will only be cleared + * by the subject cpu. Each cpu must first find its bit is + * set and then check that refs is set indicating the element is + * ready to be processed, otherwise it must skip the entry. + * + * On the previous iteration refs was set to 0 by another cpu. + * To avoid the use of transitivity, set the counter to 0 here + * so the wmb will pair with the rmb in the interrupt handler. + */ + atomic_set(&data->refs, 0); /* convert 3rd to 1st party write */ + data->csd.func = func; data->csd.info = info; + + /* Ensure 0 refs is visible before mask. Also orders func and info */ + smp_wmb(); + + /* We rely on the "and" being processed before the store */ cpumask_and(data->cpumask, mask, cpu_online_mask); cpumask_clear_cpu(this_cpu, data->cpumask); - atomic_set(&data->refs, cpumask_weight(data->cpumask)); + refs = cpumask_weight(data->cpumask); + + /* Some callers race with other cpus changing the passed mask */ + if (unlikely(!refs)) { + csd_unlock(&data->csd); + return; + } raw_spin_lock_irqsave(&call_function.lock, flags); /* @@ -456,6 +511,12 @@ void smp_call_function_many(const struct cpumask *mask, * will not miss any other list entries: */ list_add_rcu(&data->csd.list, &call_function.queue); + /* + * We rely on the wmb() in list_add_rcu to complete our writes + * to the cpumask before this write to refs, which indicates + * data is on the list and is ready to be processed. + */ + atomic_set(&data->refs, refs); raw_spin_unlock_irqrestore(&call_function.lock, flags); /* diff --git a/kernel/softirq.c b/kernel/softirq.c index 07b4f1b1a73a..79ee8f1fc0e7 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -77,11 +77,21 @@ void wakeup_softirqd(void) } /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving + * softirq processing. + * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET) + * on local_bh_disable or local_bh_enable. + * This lets us distinguish between whether we are currently processing + * softirq and whether we just have bh disabled. + */ + +/* * This one is for softirq.c-internal use, * where hardirqs are disabled legitimately: */ #ifdef CONFIG_TRACE_IRQFLAGS -static void __local_bh_disable(unsigned long ip) +static void __local_bh_disable(unsigned long ip, unsigned int cnt) { unsigned long flags; @@ -95,32 +105,43 @@ static void __local_bh_disable(unsigned long ip) * We must manually increment preempt_count here and manually * call the trace_preempt_off later. */ - preempt_count() += SOFTIRQ_OFFSET; + preempt_count() += cnt; /* * Were softirqs turned off above: */ - if (softirq_count() == SOFTIRQ_OFFSET) + if (softirq_count() == cnt) trace_softirqs_off(ip); raw_local_irq_restore(flags); - if (preempt_count() == SOFTIRQ_OFFSET) + if (preempt_count() == cnt) trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); } #else /* !CONFIG_TRACE_IRQFLAGS */ -static inline void __local_bh_disable(unsigned long ip) +static inline void __local_bh_disable(unsigned long ip, unsigned int cnt) { - add_preempt_count(SOFTIRQ_OFFSET); + add_preempt_count(cnt); barrier(); } #endif /* CONFIG_TRACE_IRQFLAGS */ void local_bh_disable(void) { - __local_bh_disable((unsigned long)__builtin_return_address(0)); + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_DISABLE_OFFSET); } EXPORT_SYMBOL(local_bh_disable); +static void __local_bh_enable(unsigned int cnt) +{ + WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(!irqs_disabled()); + + if (softirq_count() == cnt) + trace_softirqs_on((unsigned long)__builtin_return_address(0)); + sub_preempt_count(cnt); +} + /* * Special-case - softirqs can safely be enabled in * cond_resched_softirq(), or by __do_softirq(), @@ -128,12 +149,7 @@ EXPORT_SYMBOL(local_bh_disable); */ void _local_bh_enable(void) { - WARN_ON_ONCE(in_irq()); - WARN_ON_ONCE(!irqs_disabled()); - - if (softirq_count() == SOFTIRQ_OFFSET) - trace_softirqs_on((unsigned long)__builtin_return_address(0)); - sub_preempt_count(SOFTIRQ_OFFSET); + __local_bh_enable(SOFTIRQ_DISABLE_OFFSET); } EXPORT_SYMBOL(_local_bh_enable); @@ -147,13 +163,13 @@ static inline void _local_bh_enable_ip(unsigned long ip) /* * Are softirqs going to be turned on now: */ - if (softirq_count() == SOFTIRQ_OFFSET) + if (softirq_count() == SOFTIRQ_DISABLE_OFFSET) trace_softirqs_on(ip); /* * Keep preemption disabled until we are done with * softirq processing: */ - sub_preempt_count(SOFTIRQ_OFFSET - 1); + sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1); if (unlikely(!in_interrupt() && local_softirq_pending())) do_softirq(); @@ -198,7 +214,8 @@ asmlinkage void __do_softirq(void) pending = local_softirq_pending(); account_system_vtime(current); - __local_bh_disable((unsigned long)__builtin_return_address(0)); + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_OFFSET); lockdep_softirq_enter(); cpu = smp_processor_id(); @@ -245,7 +262,7 @@ restart: lockdep_softirq_exit(); account_system_vtime(current); - _local_bh_enable(); + __local_bh_enable(SOFTIRQ_OFFSET); } #ifndef __ARCH_HAS_DO_SOFTIRQ @@ -279,10 +296,16 @@ void irq_enter(void) rcu_irq_enter(); if (idle_cpu(cpu) && !in_interrupt()) { - __irq_enter(); + /* + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ + local_bh_disable(); tick_check_idle(cpu); - } else - __irq_enter(); + _local_bh_enable(); + } + + __irq_enter(); } #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED @@ -696,6 +719,7 @@ static int run_ksoftirqd(void * __bind_cpu) { set_current_state(TASK_INTERRUPTIBLE); + current->flags |= PF_KSOFTIRQD; while (!kthread_should_stop()) { preempt_disable(); if (!local_softirq_pending()) { diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 70f8d90331e9..44b3163defe3 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -132,8 +132,8 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf); } +DEFINE_MUTEX(stop_cpus_mutex); /* static data for stop_cpus */ -static DEFINE_MUTEX(stop_cpus_mutex); static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) diff --git a/kernel/sys.c b/kernel/sys.c index e83ddbbaf89d..f4fcc6e870ff 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -931,6 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) pgid = pid; if (pgid < 0) return -EINVAL; + rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM @@ -984,6 +985,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); + rcu_read_unlock(); return err; } diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 11281d5792bd..5e21645efde1 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -292,16 +292,18 @@ ret: static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; - struct listener *s, *tmp; + struct listener *s, *tmp, *s2; unsigned int cpu; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; + s = NULL; if (isadd == REGISTER) { for_each_cpu(cpu, mask) { - s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, - cpu_to_node(cpu)); + if (!s) + s = kmalloc_node(sizeof(struct listener), + GFP_KERNEL, cpu_to_node(cpu)); if (!s) goto cleanup; s->pid = pid; @@ -310,9 +312,16 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); + list_for_each_entry_safe(s2, tmp, &listeners->list, list) { + if (s2->pid == pid) + goto next_cpu; + } list_add(&s->list, &listeners->list); + s = NULL; +next_cpu: up_write(&listeners->sem); } + kfree(s); return 0; } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f08e99c1d561..4db1e0adc7d7 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -184,7 +184,6 @@ static struct clocksource *watchdog; static struct timer_list watchdog_timer; static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); -static cycle_t watchdog_last; static int watchdog_running; static int clocksource_watchdog_kthread(void *data); @@ -253,11 +252,6 @@ static void clocksource_watchdog(unsigned long data) if (!watchdog_running) goto out; - wdnow = watchdog->read(watchdog); - wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask, - watchdog->mult, watchdog->shift); - watchdog_last = wdnow; - list_for_each_entry(cs, &watchdog_list, wd_list) { /* Clocksource already marked unstable? */ @@ -267,19 +261,28 @@ static void clocksource_watchdog(unsigned long data) continue; } + local_irq_disable(); csnow = cs->read(cs); + wdnow = watchdog->read(watchdog); + local_irq_enable(); /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { cs->flags |= CLOCK_SOURCE_WATCHDOG; - cs->wd_last = csnow; + cs->wd_last = wdnow; + cs->cs_last = csnow; continue; } - /* Check the deviation from the watchdog clocksource. */ - cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) & + wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, + watchdog->mult, watchdog->shift); + + cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & cs->mask, cs->mult, cs->shift); - cs->wd_last = csnow; + cs->cs_last = csnow; + cs->wd_last = wdnow; + + /* Check the deviation from the watchdog clocksource. */ if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { clocksource_unstable(cs, cs_nsec - wd_nsec); continue; @@ -317,7 +320,6 @@ static inline void clocksource_start_watchdog(void) return; init_timer(&watchdog_timer); watchdog_timer.function = clocksource_watchdog; - watchdog_last = watchdog->read(watchdog); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); watchdog_running = 1; @@ -665,8 +667,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); - clocksource_select(); clocksource_enqueue_watchdog(cs); + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index b3bafd5fc66d..0f888cb837cc 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -523,10 +523,11 @@ static void tick_broadcast_init_next_event(struct cpumask *mask, */ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { + int cpu = smp_processor_id(); + /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; - int cpu = smp_processor_id(); bc->event_handler = tick_handle_oneshot_broadcast; clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); @@ -552,6 +553,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_set_event(tick_next_period, 1); } else bc->next_event.tv64 = KTIME_MAX; + } else { + /* + * The first cpu which switches to oneshot mode sets + * the bit for all other cpus which are in the general + * (periodic) broadcast mask. So the bit is set and + * would prevent the first broadcast enter after this + * to program the bc device. + */ + tick_broadcast_clear_oneshot(cpu); } } @@ -600,4 +610,14 @@ int tick_broadcast_oneshot_active(void) return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; } +/* + * Check whether the broadcast device supports oneshot. + */ +bool tick_broadcast_oneshot_available(void) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; +} + #endif diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index b6b898d2eeef..61e296ba4392 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -51,7 +51,11 @@ int tick_is_oneshot_available(void) { struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; - return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT); + if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return 0; + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return 1; + return tick_broadcast_oneshot_available(); } /* diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 290eefbc1f60..f65d3a723a64 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -36,6 +36,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast(int cpu); +bool tick_broadcast_oneshot_available(void); # else /* BROADCAST */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { @@ -46,6 +47,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { } static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast(int cpu) { } +static inline bool tick_broadcast_oneshot_available(void) { return true; } # endif /* !BROADCAST */ #else /* !ONESHOT */ @@ -76,6 +78,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc) return 0; } static inline int tick_broadcast_oneshot_active(void) { return 0; } +static inline bool tick_broadcast_oneshot_available(void) { return false; } #endif /* !TICK_ONESHOT */ /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 813993b5fb61..f898af608171 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -325,7 +325,7 @@ void tick_nohz_stop_sched_tick(int inidle) } while (read_seqretry(&xtime_lock, seq)); if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || - arch_needs_cpu(cpu) || nohz_ratelimit(cpu)) { + arch_needs_cpu(cpu)) { next_jiffies = last_jiffies + 1; delta_jiffies = 1; } else { diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5fa8372e9379..4783717c2f42 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -32,6 +32,8 @@ struct timekeeper { cycle_t cycle_interval; /* Number of clock shifted nano seconds in one NTP interval. */ u64 xtime_interval; + /* shifted nano seconds left over when rounding cycle_interval */ + s64 xtime_remainder; /* Raw nano seconds accumulated per NTP interval. */ u32 raw_interval; @@ -62,7 +64,7 @@ struct timekeeper timekeeper; static void timekeeper_setup_internals(struct clocksource *clock) { cycle_t interval; - u64 tmp; + u64 tmp, ntpinterval; timekeeper.clock = clock; clock->cycle_last = clock->read(clock); @@ -70,6 +72,7 @@ static void timekeeper_setup_internals(struct clocksource *clock) /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; + ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) @@ -80,6 +83,7 @@ static void timekeeper_setup_internals(struct clocksource *clock) /* Go back from cycles -> shifted ns */ timekeeper.xtime_interval = (u64) interval * clock->mult; + timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval; timekeeper.raw_interval = ((u64) interval * clock->mult) >> clock->shift; @@ -740,6 +744,7 @@ static void timekeeping_adjust(s64 offset) static cycle_t logarithmic_accumulation(cycle_t offset, int shift) { u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; + u64 raw_nsecs; /* If the offset is smaller then a shifted interval, do nothing */ if (offset < timekeeper.cycle_interval<<shift) @@ -756,16 +761,20 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) second_overflow(); } - /* Accumulate into raw time */ - raw_time.tv_nsec += timekeeper.raw_interval << shift;; - while (raw_time.tv_nsec >= NSEC_PER_SEC) { - raw_time.tv_nsec -= NSEC_PER_SEC; - raw_time.tv_sec++; + /* Accumulate raw time */ + raw_nsecs = timekeeper.raw_interval << shift; + raw_nsecs += raw_time.tv_nsec; + if (raw_nsecs >= NSEC_PER_SEC) { + u64 raw_secs = raw_nsecs; + raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); + raw_time.tv_sec += raw_secs; } + raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ timekeeper.ntp_error += tick_length << shift; - timekeeper.ntp_error -= timekeeper.xtime_interval << + timekeeper.ntp_error -= + (timekeeper.xtime_interval + timekeeper.xtime_remainder) << (timekeeper.ntp_error_shift + shift); return offset; diff --git a/kernel/timer.c b/kernel/timer.c index ee305c8d4e18..f7dec455d826 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1237,6 +1237,12 @@ unsigned long get_next_timer_interrupt(unsigned long now) struct tvec_base *base = __get_cpu_var(tvec_bases); unsigned long expires; + /* + * Pretend that there is no timer pending if the cpu is offline. + * Possible pending timers will be migrated later to an active cpu. + */ + if (cpu_is_offline(smp_processor_id())) + return now + NEXT_TIMER_MAX_DELTA; spin_lock(&base->lock); if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); @@ -1302,7 +1308,7 @@ void do_timer(unsigned long ticks) { jiffies_64 += ticks; update_wall_time(); - calc_global_load(); + calc_global_load(ticks); } #ifdef __ARCH_WANT_SYS_ALARM diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6d2cb14f9449..f23b055e0d49 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -381,12 +381,19 @@ static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - static DEFINE_MUTEX(mutex); static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif + mutex_lock(&ftrace_profile_lock); + + /* we raced with function_profile_reset() */ + if (unlikely(rec->counter == 0)) { + ret = -EBUSY; + goto out; + } kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); seq_printf(m, " %-30.30s %10lu", str, rec->counter); @@ -408,7 +415,6 @@ static int function_stat_show(struct seq_file *m, void *v) do_div(stddev, (rec->counter - 1) * 1000); } - mutex_lock(&mutex); trace_seq_init(&s); trace_print_graph_duration(rec->time, &s); trace_seq_puts(&s, " "); @@ -416,11 +422,12 @@ static int function_stat_show(struct seq_file *m, void *v) trace_seq_puts(&s, " "); trace_print_graph_duration(stddev, &s); trace_print_seq(m, &s); - mutex_unlock(&mutex); #endif seq_putc(m, '\n'); +out: + mutex_unlock(&ftrace_profile_lock); - return 0; + return ret; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) @@ -1503,6 +1510,8 @@ static void *t_start(struct seq_file *m, loff_t *pos) if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; + /* reset in case of seek/pread */ + iter->flags &= ~FTRACE_ITER_HASH; return iter; } @@ -2368,14 +2377,16 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) ftrace_match_records(parser->buffer, parser->idx, enable); } - mutex_lock(&ftrace_lock); - if (ftrace_start_up && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); - mutex_unlock(&ftrace_lock); - trace_parser_put(parser); kfree(iter); + if (file->f_mode & FMODE_WRITE) { + mutex_lock(&ftrace_lock); + if (ftrace_start_up && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + mutex_unlock(&ftrace_lock); + } + mutex_unlock(&ftrace_regex_lock); return 0; } @@ -2410,7 +2421,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = no_llseek, .release = ftrace_filter_release, }; @@ -3281,7 +3292,7 @@ static int start_graph_tracing(void) /* The cpu_boot init_task->ret_stack will never be freed */ for_each_online_cpu(cpu) { if (!idle_task(cpu)->ret_stack) - ftrace_graph_init_task(idle_task(cpu)); + ftrace_graph_init_idle_task(idle_task(cpu), cpu); } do { @@ -3371,6 +3382,49 @@ void unregister_ftrace_graph(void) mutex_unlock(&ftrace_lock); } +static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); + +static void +graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) +{ + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->ftrace_timestamp = 0; + /* make curr_ret_stack visable before we add the ret_stack */ + smp_wmb(); + t->ret_stack = ret_stack; +} + +/* + * Allocate a return stack for the idle task. May be the first + * time through, or it may be done by CPU hotplug online. + */ +void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) +{ + t->curr_ret_stack = -1; + /* + * The idle task has no parent, it either has its own + * stack or no stack at all. + */ + if (t->ret_stack) + WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu)); + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = per_cpu(idle_ret_stack, cpu); + if (!ret_stack) { + ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + per_cpu(idle_ret_stack, cpu) = ret_stack; + } + graph_init_task(t, ret_stack); + } +} + /* Allocate a return stack for newly created task */ void ftrace_graph_init_task(struct task_struct *t) { @@ -3386,12 +3440,7 @@ void ftrace_graph_init_task(struct task_struct *t) GFP_KERNEL); if (!ret_stack) return; - atomic_set(&t->tracing_graph_pause, 0); - atomic_set(&t->trace_overrun, 0); - t->ftrace_timestamp = 0; - /* make curr_ret_stack visable before we add the ret_stack */ - smp_wmb(); - t->ret_stack = ret_stack; + graph_init_task(t, ret_stack); } } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1da7b6ea8b85..6cd7334ee01e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -405,7 +405,7 @@ static inline int test_time_stamp(u64 delta) #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2)) /* Max number of timestamps that can fit on a page */ -#define RB_TIMESTAMPS_PER_PAGE (BUF_PAGE_SIZE / RB_LEN_TIME_STAMP) +#define RB_TIMESTAMPS_PER_PAGE (BUF_PAGE_SIZE / RB_LEN_TIME_EXTEND) int ring_buffer_print_page_header(struct trace_seq *s) { @@ -3868,6 +3868,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer, rpos = reader->read; pos += size; + if (rpos >= commit) + break; + event = rb_reader_event(cpu_buffer); size = rb_event_length(event); } while (len > size); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 086d36316805..755d3ee9d453 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2382,11 +2382,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf, return count; } +static loff_t tracing_seek(struct file *file, loff_t offset, int origin) +{ + if (file->f_mode & FMODE_READ) + return seq_lseek(file, offset, origin); + else + return 0; +} + static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, .write = tracing_write_stub, - .llseek = seq_lseek, + .llseek = tracing_seek, .release = tracing_release, }; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2cd96399463f..75ada72f55f8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -731,6 +731,7 @@ struct event_subsystem { struct dentry *entry; struct event_filter *filter; int nr_events; + int ref_count; }; struct filter_pred; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 53cffc0b0801..83ff94a475ba 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -182,6 +182,35 @@ static void ftrace_clear_events(void) mutex_unlock(&event_mutex); } +static void __put_system(struct event_subsystem *system) +{ + struct event_filter *filter = system->filter; + + WARN_ON_ONCE(system->ref_count == 0); + if (--system->ref_count) + return; + + if (filter) { + kfree(filter->filter_string); + kfree(filter); + } + kfree(system->name); + kfree(system); +} + +static void __get_system(struct event_subsystem *system) +{ + WARN_ON_ONCE(system->ref_count == 0); + system->ref_count++; +} + +static void put_system(struct event_subsystem *system) +{ + mutex_lock(&event_mutex); + __put_system(system); + mutex_unlock(&event_mutex); +} + /* * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events. */ @@ -466,7 +495,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { const char set_to_char[4] = { '?', '0', '1', 'X' }; - const char *system = filp->private_data; + struct event_subsystem *system = filp->private_data; struct ftrace_event_call *call; char buf[2]; int set = 0; @@ -478,7 +507,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, (!call->class->probe && !call->class->reg)) continue; - if (system && strcmp(call->class->system, system) != 0) + if (system && strcmp(call->class->system, system->name) != 0) continue; /* @@ -508,7 +537,8 @@ static ssize_t system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - const char *system = filp->private_data; + struct event_subsystem *system = filp->private_data; + const char *name = NULL; unsigned long val; char buf[64]; ssize_t ret; @@ -532,7 +562,14 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; - ret = __ftrace_set_clr_event(NULL, system, NULL, val); + /* + * Opening of "enable" adds a ref count to system, + * so the name is safe to use. + */ + if (system) + name = system->name; + + ret = __ftrace_set_clr_event(NULL, name, NULL, val); if (ret) goto out; @@ -704,6 +741,52 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +static LIST_HEAD(event_subsystems); + +static int subsystem_open(struct inode *inode, struct file *filp) +{ + struct event_subsystem *system = NULL; + int ret; + + if (!inode->i_private) + goto skip_search; + + /* Make sure the system still exists */ + mutex_lock(&event_mutex); + list_for_each_entry(system, &event_subsystems, list) { + if (system == inode->i_private) { + /* Don't open systems with no events */ + if (!system->nr_events) { + system = NULL; + break; + } + __get_system(system); + break; + } + } + mutex_unlock(&event_mutex); + + if (system != inode->i_private) + return -ENODEV; + + skip_search: + ret = tracing_open_generic(inode, filp); + if (ret < 0 && system) + put_system(system); + + return ret; +} + +static int subsystem_release(struct inode *inode, struct file *file) +{ + struct event_subsystem *system = inode->i_private; + + if (system) + put_system(system); + + return 0; +} + static ssize_t subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -836,15 +919,17 @@ static const struct file_operations ftrace_event_filter_fops = { }; static const struct file_operations ftrace_subsystem_filter_fops = { - .open = tracing_open_generic, + .open = subsystem_open, .read = subsystem_filter_read, .write = subsystem_filter_write, + .release = subsystem_release, }; static const struct file_operations ftrace_system_enable_fops = { - .open = tracing_open_generic, + .open = subsystem_open, .read = system_enable_read, .write = system_enable_write, + .release = subsystem_release, }; static const struct file_operations ftrace_show_header_fops = { @@ -872,8 +957,6 @@ static struct dentry *event_trace_events_dir(void) return d_events; } -static LIST_HEAD(event_subsystems); - static struct dentry * event_subsystem_dir(const char *name, struct dentry *d_events) { @@ -883,6 +966,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) /* First see if we did not already create this dir */ list_for_each_entry(system, &event_subsystems, list) { if (strcmp(system->name, name) == 0) { + __get_system(system); system->nr_events++; return system->entry; } @@ -905,6 +989,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) } system->nr_events = 1; + system->ref_count = 1; system->name = kstrdup(name, GFP_KERNEL); if (!system->name) { debugfs_remove(system->entry); @@ -932,8 +1017,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) "'%s/filter' entry\n", name); } - trace_create_file("enable", 0644, system->entry, - (void *)system->name, + trace_create_file("enable", 0644, system->entry, system, &ftrace_system_enable_fops); return system->entry; @@ -1050,16 +1134,9 @@ static void remove_subsystem_dir(const char *name) list_for_each_entry(system, &event_subsystems, list) { if (strcmp(system->name, name) == 0) { if (!--system->nr_events) { - struct event_filter *filter = system->filter; - debugfs_remove_recursive(system->entry); list_del(&system->list); - if (filter) { - kfree(filter->filter_string); - kfree(filter); - } - kfree(system->name); - kfree(system); + __put_system(system); } break; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 57bb1bb32999..ecf4a3e1273a 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1340,6 +1340,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system, if (err) goto out_unlock; + /* Make sure the system still has events */ + if (!system->nr_events) { + err = -ENODEV; + goto out_unlock; + } + if (!strcmp(strstrip(filter_string), "0")) { filter_free_subsystem_preds(system); remove_filter_string(system->filter); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 79f4bac99a94..b4c179ae4e45 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter, * if the output fails. */ data->ent = *curr; - data->ret = *next; + /* + * If the next event is not a return type, then + * we only care about what type it is. Otherwise we can + * safely copy the entire event. + */ + if (next->ent.type == TRACE_GRAPH_RET) + data->ret = *next; + else + data->ret.ent.type = next->ent.type; } } diff --git a/kernel/user.c b/kernel/user.c index 7e72614b736d..5c598ca781df 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -91,6 +91,7 @@ static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) + __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); @@ -157,6 +158,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { + put_user_ns(ns); key_put(new->uid_keyring); key_put(new->session_keyring); kmem_cache_free(uid_cachep, new); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index b2d70d38dff4..25915832291a 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -9,6 +9,7 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/user_namespace.h> +#include <linux/highuid.h> #include <linux/cred.h> /* @@ -82,3 +83,46 @@ void free_user_ns(struct kref *kref) schedule_work(&ns->destroyer); } EXPORT_SYMBOL(free_user_ns); + +uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid) +{ + struct user_namespace *tmp; + + if (likely(to == cred->user->user_ns)) + return uid; + + + /* Is cred->user the creator of the target user_ns + * or the creator of one of it's parents? + */ + for ( tmp = to; tmp != &init_user_ns; + tmp = tmp->creator->user_ns ) { + if (cred->user == tmp->creator) { + return (uid_t)0; + } + } + + /* No useful relationship so no mapping */ + return overflowuid; +} + +gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid) +{ + struct user_namespace *tmp; + + if (likely(to == cred->user->user_ns)) + return gid; + + /* Is cred->user the creator of the target user_ns + * or the creator of one of it's parents? + */ + for ( tmp = to; tmp != &init_user_ns; + tmp = tmp->creator->user_ns ) { + if (cred->user == tmp->creator) { + return (gid_t)0; + } + } + + /* No useful relationship so no mapping */ + return overflowgid; +} |