diff options
| author | Tejun Heo <tj@kernel.org> | 2012-04-01 21:30:01 +0200 |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2012-04-01 21:55:00 +0200 |
| commit | 959d851caa48829eb85cb85aa949fd6b4c5d5bc6 (patch) | |
| tree | 3ba9c94ec346275fb44c4f0d1cd2537cdff8d811 /kernel | |
| parent | blkcg: change a spin_lock() to spin_lock_irq() (diff) | |
| parent | cgroup: make css->refcnt clearing on cgroup removal optional (diff) | |
| download | linux-959d851caa48829eb85cb85aa949fd6b4c5d5bc6.tar.xz linux-959d851caa48829eb85cb85aa949fd6b4c5d5bc6.zip | |
Merge branch 'for-3.5' of ../cgroup into block/for-3.5/core-merged
cgroup/for-3.5 contains the following changes which blk-cgroup needs
to proceed with the on-going cleanup.
* Dynamic addition and removal of cftypes to make config/stat file
handling modular for policies.
* cgroup removal update to not wait for css references to drain to fix
blkcg removal hang caused by cfq caching cfqgs.
Pull in cgroup/for-3.5 into block/for-3.5/core. This causes the
following conflicts in block/blk-cgroup.c.
* 761b3ef50e "cgroup: remove cgroup_subsys argument from callbacks"
conflicts with blkiocg_pre_destroy() addition and blkiocg_attach()
removal. Resolved by removing @subsys from all subsys methods.
* 676f7c8f84 "cgroup: relocate cftype and cgroup_subsys definitions in
controllers" conflicts with ->pre_destroy() and ->attach() updates
and removal of modular config. Resolved by dropping forward
declarations of the methods and applying updates to the relocated
blkio_subsys.
* 4baf6e3325 "cgroup: convert all non-memcg controllers to the new
cftype interface" builds upon the previous item. Resolved by adding
->base_cftypes to the relocated blkio_subsys.
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'kernel')
106 files changed, 5181 insertions, 3197 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 5068e2a4e75f..2251882daf53 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -124,8 +124,8 @@ config INLINE_SPIN_LOCK_IRQSAVE def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ ARCH_INLINE_SPIN_LOCK_IRQSAVE -config INLINE_SPIN_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK) +config UNINLINE_SPIN_UNLOCK + bool config INLINE_SPIN_UNLOCK_BH def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 24e7cb0ba26a..3f9c97419f02 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -36,6 +36,7 @@ config PREEMPT_VOLUNTARY config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" select PREEMPT_COUNT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) diff --git a/kernel/Makefile b/kernel/Makefile index 2d9de86b7e76..cb41b9547c9f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -27,7 +27,6 @@ obj-y += power/ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o -obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o diff --git a/kernel/audit.c b/kernel/audit.c index bb0eb5bb9a0a..1c7f2c61416b 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1418,7 +1418,7 @@ void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) /* This is a helper-function to print the escaped d_path */ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, - struct path *path) + const struct path *path) { char *p, *pathname; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a5d3b5325f77..2905977e0f33 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -63,6 +63,9 @@ #include <linux/atomic.h> +/* css deactivation bias, makes css->refcnt negative to deny new trygets */ +#define CSS_DEACT_BIAS INT_MIN + /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. @@ -127,6 +130,9 @@ struct cgroupfs_root { /* A list running through the active hierarchies */ struct list_head root_list; + /* All cgroups on this root, cgroup_mutex protected */ + struct list_head allcg_list; + /* Hierarchy-specific flags */ unsigned long flags; @@ -145,6 +151,15 @@ struct cgroupfs_root { static struct cgroupfs_root rootnode; /* + * cgroupfs file entry, pointed to from leaf dentry->d_fsdata. + */ +struct cfent { + struct list_head node; + struct dentry *dentry; + struct cftype *type; +}; + +/* * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when * cgroup_subsys->use_id != 0. */ @@ -239,6 +254,14 @@ int cgroup_lock_is_held(void) EXPORT_SYMBOL_GPL(cgroup_lock_is_held); +/* the current nr of refs, always >= 0 whether @css is deactivated or not */ +static int css_refcnt(struct cgroup_subsys_state *css) +{ + int v = atomic_read(&css->refcnt); + + return v >= 0 ? v : v - CSS_DEACT_BIAS; +} + /* convenient tests for these bits */ inline int cgroup_is_removed(const struct cgroup *cgrp) { @@ -279,6 +302,21 @@ list_for_each_entry(_ss, &_root->subsys_list, sibling) #define for_each_active_root(_root) \ list_for_each_entry(_root, &roots, root_list) +static inline struct cgroup *__d_cgrp(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +static inline struct cfent *__d_cfe(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +static inline struct cftype *__d_cft(struct dentry *dentry) +{ + return __d_cfe(dentry)->type; +} + /* the list of cgroups eligible for automatic release. Protected by * release_list_lock */ static LIST_HEAD(release_list); @@ -816,12 +854,17 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp) struct cgroup_subsys *ss; int ret = 0; - for_each_subsys(cgrp->root, ss) - if (ss->pre_destroy) { - ret = ss->pre_destroy(ss, cgrp); - if (ret) - break; + for_each_subsys(cgrp->root, ss) { + if (!ss->pre_destroy) + continue; + + ret = ss->pre_destroy(cgrp); + if (ret) { + /* ->pre_destroy() failure is being deprecated */ + WARN_ON_ONCE(!ss->__DEPRECATED_clear_css_refs); + break; } + } return ret; } @@ -846,7 +889,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) * Release the subsystem state objects. */ for_each_subsys(cgrp->root, ss) - ss->destroy(ss, cgrp); + ss->destroy(cgrp); cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); @@ -864,6 +907,14 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) BUG_ON(!list_empty(&cgrp->pidlists)); kfree_rcu(cgrp, rcu_head); + } else { + struct cfent *cfe = __d_cfe(dentry); + struct cgroup *cgrp = dentry->d_parent->d_fsdata; + + WARN_ONCE(!list_empty(&cfe->node) && + cgrp != &cgrp->root->top_cgroup, + "cfe still linked for %s\n", cfe->type->name); + kfree(cfe); } iput(inode); } @@ -882,34 +933,36 @@ static void remove_dir(struct dentry *d) dput(parent); } -static void cgroup_clear_directory(struct dentry *dentry) -{ - struct list_head *node; - - BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); - spin_lock(&dentry->d_lock); - node = dentry->d_subdirs.next; - while (node != &dentry->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_u.d_child); - - spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); - list_del_init(node); - if (d->d_inode) { - /* This should never be called on a cgroup - * directory with child cgroups */ - BUG_ON(d->d_inode->i_mode & S_IFDIR); - dget_dlock(d); - spin_unlock(&d->d_lock); - spin_unlock(&dentry->d_lock); - d_delete(d); - simple_unlink(dentry->d_inode, d); - dput(d); - spin_lock(&dentry->d_lock); - } else - spin_unlock(&d->d_lock); - node = dentry->d_subdirs.next; +static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) +{ + struct cfent *cfe; + + lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); + lockdep_assert_held(&cgroup_mutex); + + list_for_each_entry(cfe, &cgrp->files, node) { + struct dentry *d = cfe->dentry; + + if (cft && cfe->type != cft) + continue; + + dget(d); + d_delete(d); + simple_unlink(d->d_inode, d); + list_del_init(&cfe->node); + dput(d); + + return 0; } - spin_unlock(&dentry->d_lock); + return -ENOENT; +} + +static void cgroup_clear_directory(struct dentry *dir) +{ + struct cgroup *cgrp = __d_cgrp(dir); + + while (!list_empty(&cgrp->files)) + cgroup_rm_file(cgrp, NULL); } /* @@ -1015,7 +1068,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) - ss->bind(ss, cgrp); + ss->bind(cgrp); mutex_unlock(&ss->hierarchy_mutex); /* refcount was already taken, and we're keeping it */ } else if (bit & removed_bits) { @@ -1025,7 +1078,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]->cgroup != cgrp); mutex_lock(&ss->hierarchy_mutex); if (ss->bind) - ss->bind(ss, dummytop); + ss->bind(dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; subsys[i]->root = &rootnode; @@ -1294,6 +1347,11 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) if (ret) goto out_unlock; + /* See feature-removal-schedule.txt */ + if (opts.subsys_bits != root->actual_subsys_bits || opts.release_agent) + pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n", + task_tgid_nr(current), current->comm); + /* Don't allow flags or name to change at remount */ if (opts.flags != root->flags || (opts.name && strcmp(opts.name, root->name))) { @@ -1308,7 +1366,8 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) goto out_unlock; } - /* (re)populate subsystem files */ + /* clear out any existing files and repopulate subsystem files */ + cgroup_clear_directory(cgrp->dentry); cgroup_populate_dir(cgrp); if (opts.release_agent) @@ -1333,6 +1392,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) { INIT_LIST_HEAD(&cgrp->sibling); INIT_LIST_HEAD(&cgrp->children); + INIT_LIST_HEAD(&cgrp->files); INIT_LIST_HEAD(&cgrp->css_sets); INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); @@ -1344,11 +1404,14 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) static void init_cgroup_root(struct cgroupfs_root *root) { struct cgroup *cgrp = &root->top_cgroup; + INIT_LIST_HEAD(&root->subsys_list); INIT_LIST_HEAD(&root->root_list); + INIT_LIST_HEAD(&root->allcg_list); root->number_of_cgroups = 1; cgrp->root = root; cgrp->top_cgroup = cgrp; + list_add_tail(&cgrp->allcg_node, &root->allcg_list); init_cgroup_housekeeping(cgrp); } @@ -1472,7 +1535,6 @@ static int cgroup_get_rootdir(struct super_block *sb) struct inode *inode = cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb); - struct dentry *dentry; if (!inode) return -ENOMEM; @@ -1481,12 +1543,9 @@ static int cgroup_get_rootdir(struct super_block *sb) inode->i_op = &cgroup_dir_inode_operations; /* directories start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); - dentry = d_alloc_root(inode); - if (!dentry) { - iput(inode); + sb->s_root = d_make_root(inode); + if (!sb->s_root) return -ENOMEM; - } - sb->s_root = dentry; /* for everything else we want ->d_op set */ sb->s_d_op = &cgroup_dops; return 0; @@ -1696,16 +1755,6 @@ static struct file_system_type cgroup_fs_type = { static struct kobject *cgroup_kobj; -static inline struct cgroup *__d_cgrp(struct dentry *dentry) -{ - return dentry->d_fsdata; -} - -static inline struct cftype *__d_cft(struct dentry *dentry) -{ - return dentry->d_fsdata; -} - /** * cgroup_path - generate the path of a cgroup * @cgrp: the cgroup in question @@ -1763,6 +1812,7 @@ EXPORT_SYMBOL_GPL(cgroup_path); struct task_and_cgroup { struct task_struct *task; struct cgroup *cgrp; + struct css_set *cg; }; struct cgroup_taskset { @@ -1843,11 +1893,10 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_size); * will already exist. If not set, this function might sleep, and can fail with * -ENOMEM. Must be called with cgroup_mutex and threadgroup locked. */ -static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, - struct task_struct *tsk, bool guarantee) +static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, + struct task_struct *tsk, struct css_set *newcg) { struct css_set *oldcg; - struct css_set *newcg; /* * We are synchronized through threadgroup_lock() against PF_EXITING @@ -1857,23 +1906,6 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, WARN_ON_ONCE(tsk->flags & PF_EXITING); oldcg = tsk->cgroups; - /* locate or allocate a new css_set for this task. */ - if (guarantee) { - /* we know the css_set we want already exists. */ - struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT]; - read_lock(&css_set_lock); - newcg = find_existing_css_set(oldcg, cgrp, template); - BUG_ON(!newcg); - get_css_set(newcg); - read_unlock(&css_set_lock); - } else { - might_sleep(); - /* find_css_set will give us newcg already referenced. */ - newcg = find_css_set(oldcg, cgrp); - if (!newcg) - return -ENOMEM; - } - task_lock(tsk); rcu_assign_pointer(tsk->cgroups, newcg); task_unlock(tsk); @@ -1892,7 +1924,6 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, put_css_set(oldcg); set_bit(CGRP_RELEASABLE, &oldcgrp->flags); - return 0; } /** @@ -1905,11 +1936,12 @@ static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, */ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { - int retval; + int retval = 0; struct cgroup_subsys *ss, *failed_ss = NULL; struct cgroup *oldcgrp; struct cgroupfs_root *root = cgrp->root; struct cgroup_taskset tset = { }; + struct css_set *newcg; /* @tsk either already exited or can't exit until the end */ if (tsk->flags & PF_EXITING) @@ -1925,7 +1957,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, &tset); + retval = ss->can_attach(cgrp, &tset); if (retval) { /* * Remember on which subsystem the can_attach() @@ -1939,13 +1971,17 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) } } - retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false); - if (retval) + newcg = find_css_set(tsk->cgroups, cgrp); + if (!newcg) { + retval = -ENOMEM; goto out; + } + + cgroup_task_migrate(cgrp, oldcgrp, tsk, newcg); for_each_subsys(root, ss) { if (ss->attach) - ss->attach(ss, cgrp, &tset); + ss->attach(cgrp, &tset); } synchronize_rcu(); @@ -1967,7 +2003,7 @@ out: */ break; if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, &tset); + ss->cancel_attach(cgrp, &tset); } } return retval; @@ -1997,66 +2033,6 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); -/* - * cgroup_attach_proc works in two stages, the first of which prefetches all - * new css_sets needed (to make sure we have enough memory before committing - * to the move) and stores them in a list of entries of the following type. - * TODO: possible optimization: use css_set->rcu_head for chaining instead - */ -struct cg_list_entry { - struct css_set *cg; - struct list_head links; -}; - -static bool css_set_check_fetched(struct cgroup *cgrp, - struct task_struct *tsk, struct css_set *cg, - struct list_head *newcg_list) -{ - struct css_set *newcg; - struct cg_list_entry *cg_entry; - struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT]; - - read_lock(&css_set_lock); - newcg = find_existing_css_set(cg, cgrp, template); - read_unlock(&css_set_lock); - - /* doesn't exist at all? */ - if (!newcg) - return false; - /* see if it's already in the list */ - list_for_each_entry(cg_entry, newcg_list, links) - if (cg_entry->cg == newcg) - return true; - - /* not found */ - return false; -} - -/* - * Find the new css_set and store it in the list in preparation for moving the - * given task to the given cgroup. Returns 0 or -ENOMEM. - */ -static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg, - struct list_head *newcg_list) -{ - struct css_set *newcg; - struct cg_list_entry *cg_entry; - - /* ensure a new css_set will exist for this thread */ - newcg = find_css_set(cg, cgrp); - if (!newcg) - return -ENOMEM; - /* add it to the list */ - cg_entry = kmalloc(sizeof(struct cg_list_entry), GFP_KERNEL); - if (!cg_entry) { - put_css_set(newcg); - return -ENOMEM; - } - cg_entry->cg = newcg; - list_add(&cg_entry->links, newcg_list); - return 0; -} - /** * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup * @cgrp: the cgroup to attach to @@ -2070,20 +2046,12 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) int retval, i, group_size; struct cgroup_subsys *ss, *failed_ss = NULL; /* guaranteed to be initialized later, but the compiler needs this */ - struct css_set *oldcg; struct cgroupfs_root *root = cgrp->root; /* threadgroup list cursor and array */ struct task_struct *tsk; struct task_and_cgroup *tc; struct flex_array *group; struct cgroup_taskset tset = { }; - /* - * we need to make sure we have css_sets for all the tasks we're - * going to move -before- we actually start moving them, so that in - * case we get an ENOMEM we can bail out before making any changes. - */ - struct list_head newcg_list; - struct cg_list_entry *cg_entry, *temp_nobe; /* * step 0: in order to do expensive, possibly blocking operations for @@ -2102,23 +2070,14 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) if (retval) goto out_free_group_list; - /* prevent changes to the threadgroup list while we take a snapshot. */ - read_lock(&tasklist_lock); - if (!thread_group_leader(leader)) { - /* - * a race with de_thread from another thread's exec() may strip - * us of our leadership, making while_each_thread unsafe to use - * on this task. if this happens, there is no choice but to - * throw this task away and try again (from cgroup_procs_write); - * this is "double-double-toil-and-trouble-check locking". - */ - read_unlock(&tasklist_lock); - retval = -EAGAIN; - goto out_free_group_list; - } - tsk = leader; i = 0; + /* + * Prevent freeing of tasks while we take a snapshot. Tasks that are + * already PF_EXITING could be freed from underneath us unless we + * take an rcu_read_lock. + */ + rcu_read_lock(); do { struct task_and_cgroup ent; @@ -2128,24 +2087,24 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) /* as per above, nr_threads may decrease, but not increase. */ BUG_ON(i >= group_size); - /* - * saying GFP_ATOMIC has no effect here because we did prealloc - * earlier, but it's good form to communicate our expectations. - */ ent.task = tsk; ent.cgrp = task_cgroup_from_root(tsk, root); /* nothing to do if this task is already in the cgroup */ if (ent.cgrp == cgrp) continue; + /* + * saying GFP_ATOMIC has no effect here because we did prealloc + * earlier, but it's good form to communicate our expectations. + */ retval = flex_array_put(group, i, &ent, GFP_ATOMIC); BUG_ON(retval != 0); i++; } while_each_thread(leader, tsk); + rcu_read_unlock(); /* remember the number of threads in the array for later. */ group_size = i; tset.tc_array = group; tset.tc_array_len = group_size; - read_unlock(&tasklist_lock); /* methods shouldn't be called if no task is actually migrating */ retval = 0; @@ -2157,7 +2116,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, &tset); + retval = ss->can_attach(cgrp, &tset); if (retval) { failed_ss = ss; goto out_cancel_attach; @@ -2169,17 +2128,12 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) * step 2: make sure css_sets exist for all threads to be migrated. * we use find_css_set, which allocates a new one if necessary. */ - INIT_LIST_HEAD(&newcg_list); for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); - oldcg = tc->task->cgroups; - - /* if we don't already have it in the list get a new one */ - if (!css_set_check_fetched(cgrp, tc->task, oldcg, - &newcg_list)) { - retval = css_set_prefetch(cgrp, oldcg, &newcg_list); - if (retval) - goto out_list_teardown; + tc->cg = find_css_set(tc->task->cgroups, cgrp); + if (!tc->cg) { + retval = -ENOMEM; + goto out_put_css_set_refs; } } @@ -2190,8 +2144,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); - retval = cgroup_task_migrate(cgrp, tc->cgrp, tc->task, true); - BUG_ON(retval); + cgroup_task_migrate(cgrp, tc->cgrp, tc->task, tc->cg); } /* nothing is sensitive to fork() after this point. */ @@ -2200,7 +2153,7 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) */ for_each_subsys(root, ss) { if (ss->attach) - ss->attach(ss, cgrp, &tset); + ss->attach(cgrp, &tset); } /* @@ -2209,21 +2162,22 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) synchronize_rcu(); cgroup_wakeup_rmdir_waiter(cgrp); retval = 0; -out_list_teardown: - /* clean up the list of prefetched css_sets. */ - list_for_each_entry_safe(cg_entry, temp_nobe, &newcg_list, links) { - list_del(&cg_entry->links); - put_css_set(cg_entry->cg); - kfree(cg_entry); +out_put_css_set_refs: + if (retval) { + for (i = 0; i < group_size; i++) { + tc = flex_array_get(group, i); + if (!tc->cg) + break; + put_css_set(tc->cg); + } } out_cancel_attach: - /* same deal as in cgroup_attach_task */ if (retval) { for_each_subsys(root, ss) { if (ss == failed_ss) break; if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, &tset); + ss->cancel_attach(cgrp, &tset); } } out_free_group_list: @@ -2245,22 +2199,14 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) if (!cgroup_lock_live_group(cgrp)) return -ENODEV; +retry_find_task: + rcu_read_lock(); if (pid) { - rcu_read_lock(); tsk = find_task_by_vpid(pid); if (!tsk) { rcu_read_unlock(); - cgroup_unlock(); - return -ESRCH; - } - if (threadgroup) { - /* - * RCU protects this access, since tsk was found in the - * tid map. a race with de_thread may cause group_leader - * to stop being the leader, but cgroup_attach_proc will - * detect it later. - */ - tsk = tsk->group_leader; + ret= -ESRCH; + goto out_unlock_cgroup; } /* * even if we're attaching all tasks in the thread group, we @@ -2271,29 +2217,38 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) cred->euid != tcred->uid && cred->euid != tcred->suid) { rcu_read_unlock(); - cgroup_unlock(); - return -EACCES; + ret = -EACCES; + goto out_unlock_cgroup; } - get_task_struct(tsk); - rcu_read_unlock(); - } else { - if (threadgroup) - tsk = current->group_leader; - else - tsk = current; - get_task_struct(tsk); - } - - threadgroup_lock(tsk); + } else + tsk = current; if (threadgroup) + tsk = tsk->group_leader; + get_task_struct(tsk); + rcu_read_unlock(); + + threadgroup_lock(tsk); + if (threadgroup) { + if (!thread_group_leader(tsk)) { + /* + * a race with de_thread from another thread's exec() + * may strip us of our leadership, if this happens, + * there is no choice but to throw this task away and + * try again; this is + * "double-double-toil-and-trouble-check locking". + */ + threadgroup_unlock(tsk); + put_task_struct(tsk); + goto retry_find_task; + } ret = cgroup_attach_proc(cgrp, tsk); - else + } else ret = cgroup_attach_task(cgrp, tsk); - threadgroup_unlock(tsk); put_task_struct(tsk); +out_unlock_cgroup: cgroup_unlock(); return ret; } @@ -2305,16 +2260,7 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid) static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid) { - int ret; - do { - /* - * attach_proc fails with -EAGAIN if threadgroup leadership - * changes in the middle of the operation, in which case we need - * to find the task_struct for the new leader and start over. - */ - ret = attach_task_by_pid(cgrp, tgid, true); - } while (ret == -EAGAIN); - return ret; + return attach_task_by_pid(cgrp, tgid, true); } /** @@ -2710,50 +2656,191 @@ static umode_t cgroup_file_mode(const struct cftype *cft) return mode; } -int cgroup_add_file(struct cgroup *cgrp, - struct cgroup_subsys *subsys, - const struct cftype *cft) +static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, + const struct cftype *cft) { struct dentry *dir = cgrp->dentry; + struct cgroup *parent = __d_cgrp(dir); struct dentry *dentry; + struct cfent *cfe; int error; umode_t mode; - char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; + + /* does @cft->flags tell us to skip creation on @cgrp? */ + if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent) + return 0; + if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent) + return 0; + if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) { strcpy(name, subsys->name); strcat(name, "."); } strcat(name, cft->name); + BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex)); + + cfe = kzalloc(sizeof(*cfe), GFP_KERNEL); + if (!cfe) + return -ENOMEM; + dentry = lookup_one_len(name, dir, strlen(name)); - if (!IS_ERR(dentry)) { - mode = cgroup_file_mode(cft); - error = cgroup_create_file(dentry, mode | S_IFREG, - cgrp->root->sb); - if (!error) - dentry->d_fsdata = (void *)cft; - dput(dentry); - } else + if (IS_ERR(dentry)) { error = PTR_ERR(dentry); + goto out; + } + + mode = cgroup_file_mode(cft); + error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); + if (!error) { + cfe->type = (void *)cft; + cfe->dentry = dentry; + dentry->d_fsdata = cfe; + list_add_tail(&cfe->node, &parent->files); + cfe = NULL; + } + dput(dentry); +out: + kfree(cfe); return error; } -EXPORT_SYMBOL_GPL(cgroup_add_file); -int cgroup_add_files(struct cgroup *cgrp, - struct cgroup_subsys *subsys, - const struct cftype cft[], - int count) +static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, + const struct cftype cfts[], bool is_add) { - int i, err; - for (i = 0; i < count; i++) { - err = cgroup_add_file(cgrp, subsys, &cft[i]); - if (err) - return err; + const struct cftype *cft; + int err, ret = 0; + + for (cft = cfts; cft->name[0] != '\0'; cft++) { + if (is_add) + err = cgroup_add_file(cgrp, subsys, cft); + else + err = cgroup_rm_file(cgrp, cft); + if (err) { + pr_warning("cgroup_addrm_files: failed to %s %s, err=%d\n", + is_add ? "add" : "remove", cft->name, err); + ret = err; + } + } + return ret; +} + +static DEFINE_MUTEX(cgroup_cft_mutex); + +static void cgroup_cfts_prepare(void) + __acquires(&cgroup_cft_mutex) __acquires(&cgroup_mutex) +{ + /* + * Thanks to the entanglement with vfs inode locking, we can't walk + * the existing cgroups under cgroup_mutex and create files. + * Instead, we increment reference on all cgroups and build list of + * them using @cgrp->cft_q_node. Grab cgroup_cft_mutex to ensure + * exclusive access to the field. + */ + mutex_lock(&cgroup_cft_mutex); + mutex_lock(&cgroup_mutex); +} + +static void cgroup_cfts_commit(struct cgroup_subsys *ss, + const struct cftype *cfts, bool is_add) + __releases(&cgroup_mutex) __releases(&cgroup_cft_mutex) +{ + LIST_HEAD(pending); + struct cgroup *cgrp, *n; + + /* %NULL @cfts indicates abort and don't bother if @ss isn't attached */ + if (cfts && ss->root != &rootnode) { + list_for_each_entry(cgrp, &ss->root->allcg_list, allcg_node) { + dget(cgrp->dentry); + list_add_tail(&cgrp->cft_q_node, &pending); + } + } + + mutex_unlock(&cgroup_mutex); + + /* + * All new cgroups will see @cfts update on @ss->cftsets. Add/rm + * files for all cgroups which were created before. + */ + list_for_each_entry_safe(cgrp, n, &pending, cft_q_node) { + struct inode *inode = cgrp->dentry->d_inode; + + mutex_lock(&inode->i_mutex); + mutex_lock(&cgroup_mutex); + if (!cgroup_is_removed(cgrp)) + cgroup_addrm_files(cgrp, ss, cfts, is_add); + mutex_unlock(&cgroup_mutex); + mutex_unlock(&inode->i_mutex); + + list_del_init(&cgrp->cft_q_node); + dput(cgrp->dentry); } + + mutex_unlock(&cgroup_cft_mutex); +} + +/** + * cgroup_add_cftypes - add an array of cftypes to a subsystem + * @ss: target cgroup subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Register @cfts to @ss. Files described by @cfts are created for all + * existing cgroups to which @ss is attached and all future cgroups will + * have them too. This function can be called anytime whether @ss is + * attached or not. + * + * Returns 0 on successful registration, -errno on failure. Note that this + * function currently returns 0 as long as @cfts registration is successful + * even if some file creation attempts on existing cgroups fail. + */ +int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts) +{ + struct cftype_set *set; + + set = kzalloc(sizeof(*set), GFP_KERNEL); + if (!set) + return -ENOMEM; + + cgroup_cfts_prepare(); + set->cfts = cfts; + list_add_tail(&set->node, &ss->cftsets); + cgroup_cfts_commit(ss, cfts, true); + return 0; } -EXPORT_SYMBOL_GPL(cgroup_add_files); +EXPORT_SYMBOL_GPL(cgroup_add_cftypes); + +/** + * cgroup_rm_cftypes - remove an array of cftypes from a subsystem + * @ss: target cgroup subsystem + * @cfts: zero-length name terminated array of cftypes + * + * Unregister @cfts from @ss. Files described by @cfts are removed from + * all existing cgroups to which @ss is attached and all future cgroups + * won't have them either. This function can be called anytime whether @ss + * is attached or not. + * + * Returns 0 on successful unregistration, -ENOENT if @cfts is not + * registered with @ss. + */ +int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts) +{ + struct cftype_set *set; + + cgroup_cfts_prepare(); + + list_for_each_entry(set, &ss->cftsets, node) { + if (set->cfts == cfts) { + list_del_init(&set->node); + cgroup_cfts_commit(ss, cfts, false); + return 0; + } + } + + cgroup_cfts_commit(ss, NULL, false); + return -ENOENT; +} /** * cgroup_task_count - count the number of tasks in a cgroup. @@ -2804,15 +2891,20 @@ static void cgroup_advance_iter(struct cgroup *cgrp, * using their cgroups capability, we don't maintain the lists running * through each css_set to its tasks until we see the list actually * used - in other words after the first call to cgroup_iter_start(). - * - * The tasklist_lock is not held here, as do_each_thread() and - * while_each_thread() are protected by RCU. */ static void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; write_lock(&css_set_lock); use_task_css_set_links = 1; + /* + * We need tasklist_lock because RCU is not safe against + * while_each_thread(). Besides, a forking task that has passed + * cgroup_post_fork() without seeing use_task_css_set_links = 1 + * is not guaranteed to have its child immediately visible in the + * tasklist if we walk through it with RCU. + */ + read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); /* @@ -2824,6 +2916,7 @@ static void cgroup_enable_task_cg_lists(void) list_add(&p->cg_list, &p->cgroups->tasks); task_unlock(p); } while_each_thread(g, p); + read_unlock(&tasklist_lock); write_unlock(&css_set_lock); } @@ -3043,6 +3136,38 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * */ +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* how many files are using the current array */ + int use_count; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* protects the other fields */ + struct rw_semaphore mutex; +}; + /* * The following two functions "fix" the issue where there are more pids * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. @@ -3694,13 +3819,14 @@ static struct cftype files[] = { .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, -}; - -static struct cftype cft_release_agent = { - .name = "release_agent", - .read_seq_string = cgroup_release_agent_show, - .write_string = cgroup_release_agent_write, - .max_write_len = PATH_MAX, + { + .name = "release_agent", + .flags = CFTYPE_ONLY_ON_ROOT, + .read_seq_string = cgroup_release_agent_show, + .write_string = cgroup_release_agent_write, + .max_write_len = PATH_MAX, + }, + { } /* terminate */ }; static int cgroup_populate_dir(struct cgroup *cgrp) @@ -3708,22 +3834,21 @@ static int cgroup_populate_dir(struct cgroup *cgrp) int err; struct cgroup_subsys *ss; - /* First clear out any existing files */ - cgroup_clear_directory(cgrp->dentry); - - err = cgroup_add_files(cgrp, NULL, files, ARRAY_SIZE(files)); + err = cgroup_addrm_files(cgrp, NULL, files, true); if (err < 0) return err; - if (cgrp == cgrp->top_cgroup) { - if ((err = cgroup_add_file(cgrp, NULL, &cft_release_agent)) < 0) - return err; - } - + /* process cftsets of each subsystem */ for_each_subsys(cgrp->root, ss) { + struct cftype_set *set; + if (ss->populate && (err = ss->populate(ss, cgrp)) < 0) return err; + + list_for_each_entry(set, &ss->cftsets, node) + cgroup_addrm_files(cgrp, ss, set->cfts, true); } + /* This cgroup is ready now */ for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; @@ -3739,6 +3864,14 @@ static int cgroup_populate_dir(struct cgroup *cgrp) return 0; } +static void css_dput_fn(struct work_struct *work) +{ + struct cgroup_subsys_state *css = + container_of(work, struct cgroup_subsys_state, dput_work); + + dput(css->cgroup->dentry); +} + static void init_cgroup_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) @@ -3751,6 +3884,16 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, set_bit(CSS_ROOT, &css->flags); BUG_ON(cgrp->subsys[ss->subsys_id]); cgrp->subsys[ss->subsys_id] = css; + + /* + * If !clear_css_refs, css holds an extra ref to @cgrp->dentry + * which is put on the last css_put(). dput() requires process + * context, which css_put() may be called without. @css->dput_work + * will be used to invoke dput() asynchronously from css_put(). + */ + INIT_WORK(&css->dput_work, css_dput_fn); + if (ss->__DEPRECATED_clear_css_refs) + set_bit(CSS_CLEAR_CSS_REFS, &css->flags); } static void cgroup_lock_hierarchy(struct cgroupfs_root *root) @@ -3827,7 +3970,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); for_each_subsys(root, ss) { - struct cgroup_subsys_state *css = ss->create(ss, cgrp); + struct cgroup_subsys_state *css = ss->create(cgrp); if (IS_ERR(css)) { err = PTR_ERR(css); @@ -3841,7 +3984,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, } /* At error, ->destroy() callback has to free assigned ID. */ if (clone_children(parent) && ss->post_clone) - ss->post_clone(ss, cgrp); + ss->post_clone(cgrp); } cgroup_lock_hierarchy(root); @@ -3853,9 +3996,16 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (err < 0) goto err_remove; + /* If !clear_css_refs, each css holds a ref to the cgroup's dentry */ + for_each_subsys(root, ss) + if (!ss->__DEPRECATED_clear_css_refs) + dget(dentry); + /* The cgroup directory was pre-locked for us */ BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex)); + list_add_tail(&cgrp->allcg_node, &root->allcg_list); + err = cgroup_populate_dir(cgrp); /* If err < 0, we have a half-filled directory - oh well ;) */ @@ -3875,7 +4025,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, for_each_subsys(root, ss) { if (cgrp->subsys[ss->subsys_id]) - ss->destroy(ss, cgrp); + ss->destroy(cgrp); } mutex_unlock(&cgroup_mutex); @@ -3895,18 +4045,19 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return cgroup_create(c_parent, dentry, mode | S_IFDIR); } +/* + * Check the reference count on each subsystem. Since we already + * established that there are no tasks in the cgroup, if the css refcount + * is also 1, then there should be no outstanding references, so the + * subsystem is safe to destroy. We scan across all subsystems rather than + * using the per-hierarchy linked list of mounted subsystems since we can + * be called via check_for_release() with no synchronization other than + * RCU, and the subsystem linked list isn't RCU-safe. + */ static int cgroup_has_css_refs(struct cgroup *cgrp) { - /* Check the reference count on each subsystem. Since we - * already established that there are no tasks in the - * cgroup, if the css refcount is also 1, then there should - * be no outstanding references, so the subsystem is safe to - * destroy. We scan across all subsystems rather than using - * the per-hierarchy linked list of mounted subsystems since - * we can be called via check_for_release() with no - * synchronization other than RCU, and the subsystem linked - * list isn't RCU-safe */ int i; + /* * We won't need to lock the subsys array, because the subsystems * we're concerned about aren't going anywhere since our cgroup root @@ -3915,17 +4066,21 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; struct cgroup_subsys_state *css; + /* Skip subsystems not present or not in this hierarchy */ if (ss == NULL || ss->root != cgrp->root) continue; + css = cgrp->subsys[ss->subsys_id]; - /* When called from check_for_release() it's possible + /* + * When called from check_for_release() it's possible * that by this point the cgroup has been removed * and the css deleted. But a false-positive doesn't * matter, since it can only happen if the cgroup * has been deleted and hence no longer needs the - * release agent to be called anyway. */ - if (css && (atomic_read(&css->refcnt) > 1)) + * release agent to be called anyway. + */ + if (css && css_refcnt(css) > 1) return 1; } return 0; @@ -3935,51 +4090,63 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) * Atomically mark all (or else none) of the cgroup's CSS objects as * CSS_REMOVED. Return true on success, or false if the cgroup has * busy subsystems. Call with cgroup_mutex held + * + * Depending on whether a subsys has __DEPRECATED_clear_css_refs set or + * not, cgroup removal behaves differently. + * + * If clear is set, css refcnt for the subsystem should be zero before + * cgroup removal can be committed. This is implemented by + * CGRP_WAIT_ON_RMDIR and retry logic around ->pre_destroy(), which may be + * called multiple times until all css refcnts reach zero and is allowed to + * veto removal on any invocation. This behavior is deprecated and will be + * removed as soon as the existing user (memcg) is updated. + * + * If clear is not set, each css holds an extra reference to the cgroup's + * dentry and cgroup removal proceeds regardless of css refs. + * ->pre_destroy() will be called at least once and is not allowed to fail. + * On the last put of each css, whenever that may be, the extra dentry ref + * is put so that dentry destruction happens only after all css's are + * released. */ - static int cgroup_clear_css_refs(struct cgroup *cgrp) { struct cgroup_subsys *ss; unsigned long flags; bool failed = false; + local_irq_save(flags); + + /* + * Block new css_tryget() by deactivating refcnt. If all refcnts + * for subsystems w/ clear_css_refs set were 1 at the moment of + * deactivation, we succeeded. + */ for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; - int refcnt; - while (1) { - /* We can only remove a CSS with a refcnt==1 */ - refcnt = atomic_read(&css->refcnt); - if (refcnt > 1) { - failed = true; - goto done; - } - BUG_ON(!refcnt); - /* - * Drop the refcnt to 0 while we check other - * subsystems. This will cause any racing - * css_tryget() to spin until we set the - * CSS_REMOVED bits or abort - */ - if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt) - break; - cpu_relax(); - } + + WARN_ON(atomic_read(&css->refcnt) < 0); + atomic_add(CSS_DEACT_BIAS, &css->refcnt); + + if (ss->__DEPRECATED_clear_css_refs) + failed |= css_refcnt(css) != 1; } - done: + + /* + * If succeeded, set REMOVED and put all the base refs; otherwise, + * restore refcnts to positive values. Either way, all in-progress + * css_tryget() will be released. + */ for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; - if (failed) { - /* - * Restore old refcnt if we previously managed - * to clear it from 1 to 0 - */ - if (!atomic_read(&css->refcnt)) - atomic_set(&css->refcnt, 1); - } else { - /* Commit the fact that the CSS is removed */ + + if (!failed) { set_bit(CSS_REMOVED, &css->flags); + css_put(css); + } else { + atomic_sub(CSS_DEACT_BIAS, &css->refcnt); } } + local_irq_restore(flags); return !failed; } @@ -4064,6 +4231,8 @@ again: list_del_init(&cgrp->sibling); cgroup_unlock_hierarchy(cgrp->root); + list_del_init(&cgrp->allcg_node); + d = dget(cgrp->dentry); cgroup_d_remove_dir(d); @@ -4090,16 +4259,33 @@ again: return 0; } +static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss) +{ + INIT_LIST_HEAD(&ss->cftsets); + + /* + * base_cftset is embedded in subsys itself, no need to worry about + * deregistration. + */ + if (ss->base_cftypes) { + ss->base_cftset.cfts = ss->base_cftypes; + list_add_tail(&ss->base_cftset.node, &ss->cftsets); + } +} + static void __init cgroup_init_subsys(struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name); + /* init base cftset */ + cgroup_init_cftsets(ss); + /* Create the top cgroup state for this subsystem */ list_add(&ss->sibling, &rootnode.subsys_list); ss->root = &rootnode; - css = ss->create(ss, dummytop); + css = ss->create(dummytop); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_cgroup_css(css, ss, dummytop); @@ -4165,6 +4351,9 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) return 0; } + /* init base cftset */ + cgroup_init_cftsets(ss); + /* * need to register a subsys id before anything else - for example, * init_cgroup_css needs it. @@ -4188,7 +4377,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) * no ss->create seems to need anything important in the ss struct, so * this can happen first (i.e. before the rootnode attachment). */ - css = ss->create(ss, dummytop); + css = ss->create(dummytop); if (IS_ERR(css)) { /* failure case - need to deassign the subsys[] slot. */ subsys[i] = NULL; @@ -4206,7 +4395,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) int ret = cgroup_init_idr(ss, css); if (ret) { dummytop->subsys[ss->subsys_id] = NULL; - ss->destroy(ss, dummytop); + ss->destroy(dummytop); subsys[i] = NULL; mutex_unlock(&cgroup_mutex); return ret; @@ -4304,7 +4493,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) * pointer to find their state. note that this also takes care of * freeing the css_id. */ - ss->destroy(ss, dummytop); + ss->destroy(dummytop); dummytop->subsys[ss->subsys_id] = NULL; mutex_unlock(&cgroup_mutex); @@ -4580,7 +4769,7 @@ void cgroup_fork_callbacks(struct task_struct *child) for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->fork) - ss->fork(ss, child); + ss->fork(child); } } } @@ -4596,6 +4785,17 @@ void cgroup_fork_callbacks(struct task_struct *child) */ void cgroup_post_fork(struct task_struct *child) { + /* + * use_task_css_set_links is set to 1 before we walk the tasklist + * under the tasklist_lock and we read it here after we added the child + * to the tasklist under the tasklist_lock as well. If the child wasn't + * yet in the tasklist when we walked through it from + * cgroup_enable_task_cg_lists(), then use_task_css_set_links value + * should be visible now due to the paired locking and barriers implied + * by LOCK/UNLOCK: it is written before the tasklist_lock unlock + * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock + * lock on fork. + */ if (use_task_css_set_links) { write_lock(&css_set_lock); if (list_empty(&child->cg_list)) { @@ -4682,7 +4882,7 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) struct cgroup *old_cgrp = rcu_dereference_raw(cg->subsys[i])->cgroup; struct cgroup *cgrp = task_cgroup(tsk, i); - ss->exit(ss, cgrp, old_cgrp, tsk); + ss->exit(cgrp, old_cgrp, tsk); } } } @@ -4743,21 +4943,41 @@ static void check_for_release(struct cgroup *cgrp) } /* Caller must verify that the css is not for root cgroup */ -void __css_put(struct cgroup_subsys_state *css, int count) +bool __css_tryget(struct cgroup_subsys_state *css) +{ + do { + int v = css_refcnt(css); + + if (atomic_cmpxchg(&css->refcnt, v, v + 1) == v) + return true; + cpu_relax(); + } while (!test_bit(CSS_REMOVED, &css->flags)); + + return false; +} +EXPORT_SYMBOL_GPL(__css_tryget); + +/* Caller must verify that the css is not for root cgroup */ +void __css_put(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; - int val; + rcu_read_lock(); - val = atomic_sub_return(count, &css->refcnt); - if (val == 1) { + atomic_dec(&css->refcnt); + switch (css_refcnt(css)) { + case 1: if (notify_on_release(cgrp)) { set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } cgroup_wakeup_rmdir_waiter(cgrp); + break; + case 0: + if (!test_bit(CSS_CLEAR_CSS_REFS, &css->flags)) + schedule_work(&css->dput_work); + break; } rcu_read_unlock(); - WARN_ON_ONCE(val < 1); } EXPORT_SYMBOL_GPL(__css_put); @@ -4876,7 +5096,7 @@ unsigned short css_id(struct cgroup_subsys_state *css) * on this or this is under rcu_read_lock(). Once css->id is allocated, * it's unchanged until freed. */ - cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt)); + cssid = rcu_dereference_check(css->id, css_refcnt(css)); if (cssid) return cssid->id; @@ -4888,7 +5108,7 @@ unsigned short css_depth(struct cgroup_subsys_state *css) { struct css_id *cssid; - cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt)); + cssid = rcu_dereference_check(css->id, css_refcnt(css)); if (cssid) return cssid->depth; @@ -4939,9 +5159,9 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) rcu_assign_pointer(id->css, NULL); rcu_assign_pointer(css->id, NULL); - write_lock(&ss->id_lock); + spin_lock(&ss->id_lock); idr_remove(&ss->idr, id->id); - write_unlock(&ss->id_lock); + spin_unlock(&ss->id_lock); kfree_rcu(id, rcu_head); } EXPORT_SYMBOL_GPL(free_css_id); @@ -4967,10 +5187,10 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) error = -ENOMEM; goto err_out; } - write_lock(&ss->id_lock); + spin_lock(&ss->id_lock); /* Don't use 0. allocates an ID of 1-65535 */ error = idr_get_new_above(&ss->idr, newid, 1, &myid); - write_unlock(&ss->id_lock); + spin_unlock(&ss->id_lock); /* Returns error when there are no free spaces for new ID.*/ if (error) { @@ -4985,9 +5205,9 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) return newid; remove_idr: error = -ENOSPC; - write_lock(&ss->id_lock); + spin_lock(&ss->id_lock); idr_remove(&ss->idr, myid); - write_unlock(&ss->id_lock); + spin_unlock(&ss->id_lock); err_out: kfree(newid); return ERR_PTR(error); @@ -4999,7 +5219,7 @@ static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss, { struct css_id *newid; - rwlock_init(&ss->id_lock); + spin_lock_init(&ss->id_lock); idr_init(&ss->idr); newid = get_new_cssid(ss, 0); @@ -5087,6 +5307,8 @@ css_get_next(struct cgroup_subsys *ss, int id, return NULL; BUG_ON(!ss->use_id); + WARN_ON_ONCE(!rcu_read_lock_held()); + /* fill start point for scan */ tmpid = id; while (1) { @@ -5094,10 +5316,7 @@ css_get_next(struct cgroup_subsys *ss, int id, * scan next entry from bitmap(tree), tmpid is updated after * idr_get_next(). */ - read_lock(&ss->id_lock); tmp = idr_get_next(&ss->idr, &tmpid); - read_unlock(&ss->id_lock); - if (!tmp) break; if (tmp->depth >= depth && tmp->stack[depth] == rootid) { @@ -5137,8 +5356,7 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id) } #ifdef CONFIG_CGROUP_DEBUG -static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss, - struct cgroup *cont) +static struct cgroup_subsys_state *debug_create(struct cgroup *cont) { struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); @@ -5148,7 +5366,7 @@ static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss, return css; } -static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont) +static void debug_destroy(struct cgroup *cont) { kfree(cont->subsys[debug_subsys_id]); } @@ -5271,19 +5489,15 @@ static struct cftype debug_files[] = { .name = "releasable", .read_u64 = releasable_read, }, -}; -static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont) -{ - return cgroup_add_files(cont, ss, debug_files, - ARRAY_SIZE(debug_files)); -} + { } /* terminate */ +}; struct cgroup_subsys debug_subsys = { .name = "debug", .create = debug_create, .destroy = debug_destroy, - .populate = debug_populate, .subsys_id = debug_subsys_id, + .base_cftypes = debug_files, }; #endif /* CONFIG_CGROUP_DEBUG */ diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index fc0646b78a64..3649fc6b3eaa 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -128,8 +128,7 @@ struct cgroup_subsys freezer_subsys; * task->alloc_lock (inside __thaw_task(), prevents race with refrigerator()) * sighand->siglock */ -static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, - struct cgroup *cgroup) +static struct cgroup_subsys_state *freezer_create(struct cgroup *cgroup) { struct freezer *freezer; @@ -142,8 +141,7 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, return &freezer->css; } -static void freezer_destroy(struct cgroup_subsys *ss, - struct cgroup *cgroup) +static void freezer_destroy(struct cgroup *cgroup) { struct freezer *freezer = cgroup_freezer(cgroup); @@ -164,8 +162,7 @@ static bool is_task_frozen_enough(struct task_struct *task) * a write to that file racing against an attach, and hence the * can_attach() result will remain valid until the attach completes. */ -static int freezer_can_attach(struct cgroup_subsys *ss, - struct cgroup *new_cgroup, +static int freezer_can_attach(struct cgroup *new_cgroup, struct cgroup_taskset *tset) { struct freezer *freezer; @@ -185,7 +182,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss, return 0; } -static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) +static void freezer_fork(struct task_struct *task) { struct freezer *freezer; @@ -361,24 +358,19 @@ static int freezer_write(struct cgroup *cgroup, static struct cftype files[] = { { .name = "state", + .flags = CFTYPE_NOT_ON_ROOT, .read_seq_string = freezer_read, .write_string = freezer_write, }, + { } /* terminate */ }; -static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup) -{ - if (!cgroup->parent) - return 0; - return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files)); -} - struct cgroup_subsys freezer_subsys = { .name = "freezer", .create = freezer_create, .destroy = freezer_destroy, - .populate = freezer_populate, .subsys_id = freezer_subsys_id, .can_attach = freezer_can_attach, .fork = freezer_fork, + .base_cftypes = files, }; diff --git a/kernel/compat.c b/kernel/compat.c index f346cedfe24d..74ff8498809a 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -31,11 +31,10 @@ #include <asm/uaccess.h> /* - * Note that the native side is already converted to a timespec, because - * that's what we want anyway. + * Get/set struct timeval with struct timespec on the native side */ -static int compat_get_timeval(struct timespec *o, - struct compat_timeval __user *i) +static int compat_get_timeval_convert(struct timespec *o, + struct compat_timeval __user *i) { long usec; @@ -46,8 +45,8 @@ static int compat_get_timeval(struct timespec *o, return 0; } -static int compat_put_timeval(struct compat_timeval __user *o, - struct timeval *i) +static int compat_put_timeval_convert(struct compat_timeval __user *o, + struct timeval *i) { return (put_user(i->tv_sec, &o->tv_sec) || put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0; @@ -117,7 +116,7 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, if (tv) { struct timeval ktv; do_gettimeofday(&ktv); - if (compat_put_timeval(tv, &ktv)) + if (compat_put_timeval_convert(tv, &ktv)) return -EFAULT; } if (tz) { @@ -135,7 +134,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, struct timezone ktz; if (tv) { - if (compat_get_timeval(&kts, tv)) + if (compat_get_timeval_convert(&kts, tv)) return -EFAULT; } if (tz) { @@ -146,12 +145,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); } +int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv) +{ + return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) || + __get_user(tv->tv_sec, &ctv->tv_sec) || + __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; +} +EXPORT_SYMBOL_GPL(get_compat_timeval); + +int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv) +{ + return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) || + __put_user(tv->tv_sec, &ctv->tv_sec) || + __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; +} +EXPORT_SYMBOL_GPL(put_compat_timeval); + int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || __get_user(ts->tv_sec, &cts->tv_sec) || __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } +EXPORT_SYMBOL_GPL(get_compat_timespec); int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts) { @@ -161,6 +177,42 @@ int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user } EXPORT_SYMBOL_GPL(put_compat_timespec); +int compat_get_timeval(struct timeval *tv, const void __user *utv) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0; + else + return get_compat_timeval(tv, utv); +} +EXPORT_SYMBOL_GPL(compat_get_timeval); + +int compat_put_timeval(const struct timeval *tv, void __user *utv) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0; + else + return put_compat_timeval(tv, utv); +} +EXPORT_SYMBOL_GPL(compat_put_timeval); + +int compat_get_timespec(struct timespec *ts, const void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0; + else + return get_compat_timespec(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_get_timespec); + +int compat_put_timespec(const struct timespec *ts, void __user *uts) +{ + if (COMPAT_USE_64BIT_TIME) + return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0; + else + return put_compat_timespec(ts, uts); +} +EXPORT_SYMBOL_GPL(compat_put_timespec); + static long compat_nanosleep_restart(struct restart_block *restart) { struct compat_timespec __user *rmtp; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index a09ac2b9a661..2382683617a3 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -964,7 +964,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, { bool need_loop; -repeat: /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. @@ -983,45 +982,19 @@ repeat: */ need_loop = task_has_mempolicy(tsk) || !nodes_intersects(*newmems, tsk->mems_allowed); - nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); - mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); - /* - * ensure checking ->mems_allowed_change_disable after setting all new - * allowed nodes. - * - * the read-side task can see an nodemask with new allowed nodes and - * old allowed nodes. and if it allocates page when cpuset clears newly - * disallowed ones continuous, it can see the new allowed bits. - * - * And if setting all new allowed nodes is after the checking, setting - * all new allowed nodes and clearing newly disallowed ones will be done - * continuous, and the read-side task may find no node to alloc page. - */ - smp_mb(); - - /* - * Allocation of memory is very fast, we needn't sleep when waiting - * for the read-side. - */ - while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) { - task_unlock(tsk); - if (!task_curr(tsk)) - yield(); - goto repeat; - } + if (need_loop) + write_seqcount_begin(&tsk->mems_allowed_seq); - /* - * ensure checking ->mems_allowed_change_disable before clearing all new - * disallowed nodes. - * - * if clearing newly disallowed bits before the checking, the read-side - * task may find no node to alloc page. - */ - smp_mb(); + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); tsk->mems_allowed = *newmems; + + if (need_loop) + write_seqcount_end(&tsk->mems_allowed_seq); + task_unlock(tsk); } @@ -1399,8 +1372,7 @@ static nodemask_t cpuset_attach_nodemask_from; static nodemask_t cpuset_attach_nodemask_to; /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct cpuset *cs = cgroup_cs(cgrp); struct task_struct *task; @@ -1436,8 +1408,7 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, return 0; } -static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct mm_struct *mm; struct task_struct *task; @@ -1794,28 +1765,17 @@ static struct cftype files[] = { .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, -}; -static struct cftype cft_memory_pressure_enabled = { - .name = "memory_pressure_enabled", - .read_u64 = cpuset_read_u64, - .write_u64 = cpuset_write_u64, - .private = FILE_MEMORY_PRESSURE_ENABLED, -}; - -static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont) -{ - int err; + { + .name = "memory_pressure_enabled", + .flags = CFTYPE_ONLY_ON_ROOT, + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_PRESSURE_ENABLED, + }, - err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files)); - if (err) - return err; - /* memory_pressure_enabled is in root cpuset only */ - if (!cont->parent) - err = cgroup_add_file(cont, ss, - &cft_memory_pressure_enabled); - return err; -} + { } /* terminate */ +}; /* * post_clone() is called during cgroup_create() when the @@ -1833,8 +1793,7 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont) * (and likewise for mems) to the new cgroup. Called with cgroup_mutex * held. */ -static void cpuset_post_clone(struct cgroup_subsys *ss, - struct cgroup *cgroup) +static void cpuset_post_clone(struct cgroup *cgroup) { struct cgroup *parent, *child; struct cpuset *cs, *parent_cs; @@ -1857,13 +1816,10 @@ static void cpuset_post_clone(struct cgroup_subsys *ss, /* * cpuset_create - create a cpuset - * ss: cpuset cgroup subsystem * cont: control group that the new cpuset will be part of */ -static struct cgroup_subsys_state *cpuset_create( - struct cgroup_subsys *ss, - struct cgroup *cont) +static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont) { struct cpuset *cs; struct cpuset *parent; @@ -1902,7 +1858,7 @@ static struct cgroup_subsys_state *cpuset_create( * will call async_rebuild_sched_domains(). */ -static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont) +static void cpuset_destroy(struct cgroup *cont) { struct cpuset *cs = cgroup_cs(cont); @@ -1920,9 +1876,9 @@ struct cgroup_subsys cpuset_subsys = { .destroy = cpuset_destroy, .can_attach = cpuset_can_attach, .attach = cpuset_attach, - .populate = cpuset_populate, .post_clone = cpuset_post_clone, .subsys_id = cpuset_subsys_id, + .base_cftypes = files, .early_init = 1, }; @@ -2195,10 +2151,9 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) mutex_unlock(&callback_mutex); } -int cpuset_cpus_allowed_fallback(struct task_struct *tsk) +void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpuset *cs; - int cpu; rcu_read_lock(); cs = task_cs(tsk); @@ -2219,22 +2174,10 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. + * + * select_fallback_rq() will fix things ups and set cpu_possible_mask + * if required. */ - - cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask); - if (cpu >= nr_cpu_ids) { - /* - * Either tsk->cpus_allowed is wrong (see above) or it - * is actually empty. The latter case is only possible - * if we are racing with remove_tasks_in_empty_cpuset(). - * Like above we can temporary set any mask and rely on - * set_cpus_allowed_ptr() as synchronization point. - */ - do_set_cpus_allowed(tsk, cpu_possible_mask); - cpu = cpumask_any(cpu_active_mask); - } - - return cpu; } void cpuset_init_current_mems_allowed(void) diff --git a/kernel/cred.c b/kernel/cred.c index 5791612a4045..97b36eeca4c9 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -16,6 +16,7 @@ #include <linux/keyctl.h> #include <linux/init_task.h> #include <linux/security.h> +#include <linux/binfmts.h> #include <linux/cn_proc.h> #if 0 diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 0d7c08784efb..1dc53bae56e1 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -41,6 +41,7 @@ #include <linux/delay.h> #include <linux/sched.h> #include <linux/sysrq.h> +#include <linux/reboot.h> #include <linux/init.h> #include <linux/kgdb.h> #include <linux/kdb.h> @@ -52,7 +53,6 @@ #include <asm/cacheflush.h> #include <asm/byteorder.h> #include <linux/atomic.h> -#include <asm/system.h> #include "debug_core.h" @@ -75,6 +75,8 @@ static int exception_level; struct kgdb_io *dbg_io_ops; static DEFINE_SPINLOCK(kgdb_registration_lock); +/* Action for the reboot notifiter, a global allow kdb to change it */ +static int kgdbreboot; /* kgdb console driver is loaded */ static int kgdb_con_registered; /* determine if kgdb console output should be used */ @@ -96,6 +98,7 @@ static int __init opt_kgdb_con(char *str) early_param("kgdbcon", opt_kgdb_con); module_param(kgdb_use_con, int, 0644); +module_param(kgdbreboot, int, 0644); /* * Holds information about breakpoints in a kernel. These breakpoints are @@ -784,6 +787,33 @@ void __init dbg_late_init(void) kdb_init(KDB_INIT_FULL); } +static int +dbg_notify_reboot(struct notifier_block *this, unsigned long code, void *x) +{ + /* + * Take the following action on reboot notify depending on value: + * 1 == Enter debugger + * 0 == [the default] detatch debug client + * -1 == Do nothing... and use this until the board resets + */ + switch (kgdbreboot) { + case 1: + kgdb_breakpoint(); + case -1: + goto done; + } + if (!dbg_kdb_mode) + gdbstub_exit(code); +done: + return NOTIFY_DONE; +} + +static struct notifier_block dbg_reboot_notifier = { + .notifier_call = dbg_notify_reboot, + .next = NULL, + .priority = INT_MAX, +}; + static void kgdb_register_callbacks(void) { if (!kgdb_io_module_registered) { @@ -791,6 +821,7 @@ static void kgdb_register_callbacks(void) kgdb_arch_init(); if (!dbg_is_early) kgdb_arch_late(); + register_reboot_notifier(&dbg_reboot_notifier); atomic_notifier_chain_register(&panic_notifier_list, &kgdb_panic_event_nb); #ifdef CONFIG_MAGIC_SYSRQ @@ -812,6 +843,7 @@ static void kgdb_unregister_callbacks(void) */ if (kgdb_io_module_registered) { kgdb_io_module_registered = 0; + unregister_reboot_notifier(&dbg_reboot_notifier); atomic_notifier_chain_unregister(&panic_notifier_list, &kgdb_panic_event_nb); kgdb_arch_exit(); diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index c22d8c28ad84..ce615e064482 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1111,6 +1111,13 @@ void gdbstub_exit(int status) unsigned char checksum, ch, buffer[3]; int loop; + if (!kgdb_connected) + return; + kgdb_connected = 0; + + if (!dbg_io_ops || dbg_kdb_mode) + return; + buffer[0] = 'W'; buffer[1] = hex_asc_hi(status); buffer[2] = hex_asc_lo(status); @@ -1129,5 +1136,6 @@ void gdbstub_exit(int status) dbg_io_ops->write_char(hex_asc_lo(checksum)); /* make sure the output is flushed, lest the bootloader clobber it */ - dbg_io_ops->flush(); + if (dbg_io_ops->flush) + dbg_io_ops->flush(); } diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 20059ef4459a..8418c2f8ec5d 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -153,6 +153,13 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) } else { kdb_printf("%s: failed to set breakpoint at 0x%lx\n", __func__, bp->bp_addr); +#ifdef CONFIG_DEBUG_RODATA + if (!bp->bp_type) { + kdb_printf("Software breakpoints are unavailable.\n" + " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " OR use hw breaks: help bph\n"); + } +#endif return 1; } return 0; diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 7179eac7b41c..07c9bbb94a0b 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -15,7 +15,6 @@ #include <linux/sched.h> #include <linux/kdb.h> #include <linux/nmi.h> -#include <asm/system.h> #include "kdb_private.h" diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 4802eb5840e1..9b5f17da1c56 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -689,7 +689,7 @@ kdb_printit: if (!dbg_kdb_mode && kgdb_connected) { gdbstub_msg_write(kdb_buffer, retlen); } else { - if (!dbg_io_ops->is_console) { + if (dbg_io_ops && !dbg_io_ops->is_console) { len = strlen(kdb_buffer); cp = kdb_buffer; while (len--) { diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index 4bca634975c0..118527aa60ea 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -25,6 +25,7 @@ #define KBD_STAT_MOUSE_OBF 0x20 /* Mouse output buffer full */ static int kbd_exists; +static int kbd_last_ret; /* * Check if the keyboard controller has a keypress for us. @@ -90,8 +91,11 @@ int kdb_get_kbd_char(void) return -1; } - if ((scancode & 0x80) != 0) + if ((scancode & 0x80) != 0) { + if (scancode == 0x9c) + kbd_last_ret = 0; return -1; + } scancode &= 0x7f; @@ -178,35 +182,82 @@ int kdb_get_kbd_char(void) return -1; /* ignore unprintables */ } - if ((scancode & 0x7f) == 0x1c) { - /* - * enter key. All done. Absorb the release scancode. - */ + if (scancode == 0x1c) { + kbd_last_ret = 1; + return 13; + } + + return keychar & 0xff; +} +EXPORT_SYMBOL_GPL(kdb_get_kbd_char); + +/* + * Best effort cleanup of ENTER break codes on leaving KDB. Called on + * exiting KDB, when we know we processed an ENTER or KP ENTER scan + * code. + */ +void kdb_kbd_cleanup_state(void) +{ + int scancode, scanstatus; + + /* + * Nothing to clean up, since either + * ENTER was never pressed, or has already + * gotten cleaned up. + */ + if (!kbd_last_ret) + return; + + kbd_last_ret = 0; + /* + * Enter key. Need to absorb the break code here, lest it gets + * leaked out if we exit KDB as the result of processing 'g'. + * + * This has several interesting implications: + * + Need to handle KP ENTER, which has break code 0xe0 0x9c. + * + Need to handle repeat ENTER and repeat KP ENTER. Repeats + * only get a break code at the end of the repeated + * sequence. This means we can't propagate the repeated key + * press, and must swallow it away. + * + Need to handle possible PS/2 mouse input. + * + Need to handle mashed keys. + */ + + while (1) { while ((inb(KBD_STATUS_REG) & KBD_STAT_OBF) == 0) - ; + cpu_relax(); /* - * Fetch the scancode + * Fetch the scancode. */ scancode = inb(KBD_DATA_REG); scanstatus = inb(KBD_STATUS_REG); - while (scanstatus & KBD_STAT_MOUSE_OBF) { - scancode = inb(KBD_DATA_REG); - scanstatus = inb(KBD_STATUS_REG); - } + /* + * Skip mouse input. + */ + if (scanstatus & KBD_STAT_MOUSE_OBF) + continue; - if (scancode != 0x9c) { - /* - * Wasn't an enter-release, why not? - */ - kdb_printf("kdb: expected enter got 0x%x status 0x%x\n", - scancode, scanstatus); - } + /* + * If we see 0xe0, this is either a break code for KP + * ENTER, or a repeat make for KP ENTER. Either way, + * since the second byte is equivalent to an ENTER, + * skip the 0xe0 and try again. + * + * If we see 0x1c, this must be a repeat ENTER or KP + * ENTER (and we swallowed 0xe0 before). Try again. + * + * We can also see make and break codes for other keys + * mashed before or after pressing ENTER. Thus, if we + * see anything other than 0x9c, we have to try again. + * + * Note, if you held some key as ENTER was depressed, + * that break code would get leaked out. + */ + if (scancode != 0x9c) + continue; - return 13; + return; } - - return keychar & 0xff; } -EXPORT_SYMBOL_GPL(kdb_get_kbd_char); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index e2ae7349437f..67b847dfa2bb 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1400,6 +1400,9 @@ int kdb_main_loop(kdb_reason_t reason, kdb_reason_t reason2, int error, if (KDB_STATE(DOING_SS)) KDB_STATE_CLEAR(SSBPT); + /* Clean up any keyboard devices before leaving */ + kdb_kbd_cleanup_state(); + return result; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index e381d105b40b..47c4e56e513b 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -246,6 +246,13 @@ extern void debug_kusage(void); extern void kdb_set_current_task(struct task_struct *); extern struct task_struct *kdb_current_task; + +#ifdef CONFIG_KDB_KEYBOARD +extern void kdb_kbd_cleanup_state(void); +#else /* ! CONFIG_KDB_KEYBOARD */ +#define kdb_kbd_cleanup_state() +#endif /* ! CONFIG_KDB_KEYBOARD */ + #ifdef CONFIG_MODULES extern struct list_head *kdb_modules; #endif /* CONFIG_MODULES */ diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 7d6fb40d2188..d35cc2d3a4cc 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -384,9 +384,9 @@ static int kdb_getphys(void *res, unsigned long addr, size_t size) if (!pfn_valid(pfn)) return 1; page = pfn_to_page(pfn); - vaddr = kmap_atomic(page, KM_KDB); + vaddr = kmap_atomic(page); memcpy(res, vaddr + (addr & (PAGE_SIZE - 1)), size); - kunmap_atomic(vaddr, KM_KDB); + kunmap_atomic(vaddr); return 0; } diff --git a/kernel/dma.c b/kernel/dma.c index 68a2306522c8..6c6262f86c17 100644 --- a/kernel/dma.c +++ b/kernel/dma.c @@ -18,7 +18,6 @@ #include <linux/proc_fs.h> #include <linux/init.h> #include <asm/dma.h> -#include <asm/system.h> diff --git a/kernel/events/core.c b/kernel/events/core.c index 1b5c081d8b9f..a6a9ec4cd8f5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info) PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP) +/* + * branch priv levels that need permission checks + */ +#define PERF_SAMPLE_BRANCH_PERM_PLM \ + (PERF_SAMPLE_BRANCH_KERNEL |\ + PERF_SAMPLE_BRANCH_HV) + enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, @@ -128,8 +135,9 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -struct jump_label_key_deferred perf_sched_events __read_mostly; +struct static_key_deferred perf_sched_events __read_mostly; static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); +static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events); static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; @@ -881,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) if (is_cgroup_event(event)) ctx->nr_cgroups++; + if (has_branch_stack(event)) + ctx->nr_branch_stack++; + list_add_rcu(&event->event_entry, &ctx->event_list); if (!ctx->nr_events) perf_pmu_rotate_start(ctx->pmu); @@ -1020,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) cpuctx->cgrp = NULL; } + if (has_branch_stack(event)) + ctx->nr_branch_stack--; + ctx->nr_events--; if (event->attr.inherit_stat) ctx->nr_stat--; @@ -2195,6 +2209,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, } /* + * When sampling the branck stack in system-wide, it may be necessary + * to flush the stack on context switch. This happens when the branch + * stack does not tag its entries with the pid of the current task. + * Otherwise it becomes impossible to associate a branch entry with a + * task. This ambiguity is more likely to appear when the branch stack + * supports priv level filtering and the user sets it to monitor only + * at the user level (which could be a useful measurement in system-wide + * mode). In that case, the risk is high of having a branch stack with + * branch from multiple tasks. Flushing may mean dropping the existing + * entries or stashing them somewhere in the PMU specific code layer. + * + * This function provides the context switch callback to the lower code + * layer. It is invoked ONLY when there is at least one system-wide context + * with at least one active event using taken branch sampling. + */ +static void perf_branch_stack_sched_in(struct task_struct *prev, + struct task_struct *task) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + /* no need to flush branch stack if not changing task */ + if (prev == task) + return; + + local_irq_save(flags); + + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + + /* + * check if the context has at least one + * event using PERF_SAMPLE_BRANCH_STACK + */ + if (cpuctx->ctx.nr_branch_stack > 0 + && pmu->flush_branch_stack) { + + pmu = cpuctx->ctx.pmu; + + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + + perf_pmu_disable(pmu); + + pmu->flush_branch_stack(); + + perf_pmu_enable(pmu); + + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); + } + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + +/* * Called from scheduler to add the events of the current task * with interrupts disabled. * @@ -2225,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev, */ if (atomic_read(&__get_cpu_var(perf_cgroup_events))) perf_cgroup_sched_in(prev, task); + + /* check for system-wide branch_stack events */ + if (atomic_read(&__get_cpu_var(perf_branch_stack_events))) + perf_branch_stack_sched_in(prev, task); } static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) @@ -2778,7 +2856,7 @@ static void free_event(struct perf_event *event) if (!event->parent) { if (event->attach_state & PERF_ATTACH_TASK) - jump_label_dec_deferred(&perf_sched_events); + static_key_slow_dec_deferred(&perf_sched_events); if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.comm) @@ -2789,7 +2867,15 @@ static void free_event(struct perf_event *event) put_callchain_buffers(); if (is_cgroup_event(event)) { atomic_dec(&per_cpu(perf_cgroup_events, event->cpu)); - jump_label_dec_deferred(&perf_sched_events); + static_key_slow_dec_deferred(&perf_sched_events); + } + + if (has_branch_stack(event)) { + static_key_slow_dec_deferred(&perf_sched_events); + /* is system-wide event */ + if (!(event->attach_state & PERF_ATTACH_TASK)) + atomic_dec(&per_cpu(perf_branch_stack_events, + event->cpu)); } } @@ -3238,10 +3324,6 @@ int perf_event_task_disable(void) return 0; } -#ifndef PERF_EVENT_INDEX_OFFSET -# define PERF_EVENT_INDEX_OFFSET 0 -#endif - static int perf_event_index(struct perf_event *event) { if (event->hw.state & PERF_HES_STOPPED) @@ -3250,21 +3332,26 @@ static int perf_event_index(struct perf_event *event) if (event->state != PERF_EVENT_STATE_ACTIVE) return 0; - return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET; + return event->pmu->event_idx(event); } static void calc_timer_values(struct perf_event *event, + u64 *now, u64 *enabled, u64 *running) { - u64 now, ctx_time; + u64 ctx_time; - now = perf_clock(); - ctx_time = event->shadow_ctx_time + now; + *now = perf_clock(); + ctx_time = event->shadow_ctx_time + *now; *enabled = ctx_time - event->tstamp_enabled; *running = ctx_time - event->tstamp_running; } +void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) +{ +} + /* * Callers need to ensure there can be no nesting of this function, otherwise * the seqlock logic goes bad. We can not serialize this because the arch @@ -3274,7 +3361,7 @@ void perf_event_update_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; struct ring_buffer *rb; - u64 enabled, running; + u64 enabled, running, now; rcu_read_lock(); /* @@ -3286,7 +3373,7 @@ void perf_event_update_userpage(struct perf_event *event) * because of locking issue as we can be called in * NMI context */ - calc_timer_values(event, &enabled, &running); + calc_timer_values(event, &now, &enabled, &running); rb = rcu_dereference(event->rb); if (!rb) goto unlock; @@ -3302,7 +3389,7 @@ void perf_event_update_userpage(struct perf_event *event) barrier(); userpg->index = perf_event_index(event); userpg->offset = perf_event_count(event); - if (event->state == PERF_EVENT_STATE_ACTIVE) + if (userpg->index) userpg->offset -= local64_read(&event->hw.prev_count); userpg->time_enabled = enabled + @@ -3311,6 +3398,8 @@ void perf_event_update_userpage(struct perf_event *event) userpg->time_running = running + atomic64_read(&event->child_total_time_running); + arch_perf_update_userpage(userpg, now); + barrier(); ++userpg->lock; preempt_enable(); @@ -3568,6 +3657,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) event->mmap_user = get_current_user(); vma->vm_mm->pinned_vm += event->mmap_locked; + perf_event_update_userpage(event); + unlock: if (!ret) atomic_inc(&event->mmap_count); @@ -3799,7 +3890,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, static void perf_output_read(struct perf_output_handle *handle, struct perf_event *event) { - u64 enabled = 0, running = 0; + u64 enabled = 0, running = 0, now; u64 read_format = event->attr.read_format; /* @@ -3812,7 +3903,7 @@ static void perf_output_read(struct perf_output_handle *handle, * NMI context */ if (read_format & PERF_FORMAT_TOTAL_TIMES) - calc_timer_values(event, &enabled, &running); + calc_timer_values(event, &now, &enabled, &running); if (event->attr.read_format & PERF_FORMAT_GROUP) perf_output_read_group(handle, event, enabled, running); @@ -3902,6 +3993,24 @@ void perf_output_sample(struct perf_output_handle *handle, } } } + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + if (data->br_stack) { + size_t size; + + size = data->br_stack->nr + * sizeof(struct perf_branch_entry); + + perf_output_put(handle, data->br_stack->nr); + perf_output_copy(handle, data->br_stack->entries, size); + } else { + /* + * we always store at least the value of nr + */ + u64 nr = 0; + perf_output_put(handle, nr); + } + } } void perf_prepare_sample(struct perf_event_header *header, @@ -3944,6 +4053,15 @@ void perf_prepare_sample(struct perf_event_header *header, WARN_ON_ONCE(size & (sizeof(u64)-1)); header->size += size; } + + if (sample_type & PERF_SAMPLE_BRANCH_STACK) { + int size = sizeof(u64); /* nr */ + if (data->br_stack) { + size += data->br_stack->nr + * sizeof(struct perf_branch_entry); + } + header->size += size; + } } static void perf_event_output(struct perf_event *event, @@ -4986,7 +5104,7 @@ fail: return err; } -struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; +struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; static void sw_perf_event_destroy(struct perf_event *event) { @@ -4994,7 +5112,7 @@ static void sw_perf_event_destroy(struct perf_event *event) WARN_ON(event->parent); - jump_label_dec(&perf_swevent_enabled[event_id]); + static_key_slow_dec(&perf_swevent_enabled[event_id]); swevent_hlist_put(event); } @@ -5005,6 +5123,12 @@ static int perf_swevent_init(struct perf_event *event) if (event->attr.type != PERF_TYPE_SOFTWARE) return -ENOENT; + /* + * no branch sampling for software events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + switch (event_id) { case PERF_COUNT_SW_CPU_CLOCK: case PERF_COUNT_SW_TASK_CLOCK: @@ -5024,13 +5148,18 @@ static int perf_swevent_init(struct perf_event *event) if (err) return err; - jump_label_inc(&perf_swevent_enabled[event_id]); + static_key_slow_inc(&perf_swevent_enabled[event_id]); event->destroy = sw_perf_event_destroy; } return 0; } +static int perf_swevent_event_idx(struct perf_event *event) +{ + return 0; +} + static struct pmu perf_swevent = { .task_ctx_nr = perf_sw_context, @@ -5040,6 +5169,8 @@ static struct pmu perf_swevent = { .start = perf_swevent_start, .stop = perf_swevent_stop, .read = perf_swevent_read, + + .event_idx = perf_swevent_event_idx, }; #ifdef CONFIG_EVENT_TRACING @@ -5108,6 +5239,12 @@ static int perf_tp_event_init(struct perf_event *event) if (event->attr.type != PERF_TYPE_TRACEPOINT) return -ENOENT; + /* + * no branch sampling for tracepoint events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + err = perf_trace_init(event); if (err) return err; @@ -5126,6 +5263,8 @@ static struct pmu perf_tracepoint = { .start = perf_swevent_start, .stop = perf_swevent_stop, .read = perf_swevent_read, + + .event_idx = perf_swevent_event_idx, }; static inline void perf_tp_register(void) @@ -5331,6 +5470,12 @@ static int cpu_clock_event_init(struct perf_event *event) if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK) return -ENOENT; + /* + * no branch sampling for software events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + perf_swevent_init_hrtimer(event); return 0; @@ -5345,6 +5490,8 @@ static struct pmu perf_cpu_clock = { .start = cpu_clock_event_start, .stop = cpu_clock_event_stop, .read = cpu_clock_event_read, + + .event_idx = perf_swevent_event_idx, }; /* @@ -5403,6 +5550,12 @@ static int task_clock_event_init(struct perf_event *event) if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK) return -ENOENT; + /* + * no branch sampling for software events + */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + perf_swevent_init_hrtimer(event); return 0; @@ -5417,6 +5570,8 @@ static struct pmu perf_task_clock = { .start = task_clock_event_start, .stop = task_clock_event_stop, .read = task_clock_event_read, + + .event_idx = perf_swevent_event_idx, }; static void perf_pmu_nop_void(struct pmu *pmu) @@ -5444,6 +5599,11 @@ static void perf_pmu_cancel_txn(struct pmu *pmu) perf_pmu_enable(pmu); } +static int perf_event_idx_default(struct perf_event *event) +{ + return event->hw.idx + 1; +} + /* * Ensures all contexts with the same task_ctx_nr have the same * pmu_cpu_context too. @@ -5530,6 +5690,7 @@ static int pmu_dev_alloc(struct pmu *pmu) if (!pmu->dev) goto out; + pmu->dev->groups = pmu->attr_groups; device_initialize(pmu->dev); ret = dev_set_name(pmu->dev, "%s", pmu->name); if (ret) @@ -5633,6 +5794,9 @@ got_cpu_context: pmu->pmu_disable = perf_pmu_nop_void; } + if (!pmu->event_idx) + pmu->event_idx = perf_event_idx_default; + list_add_rcu(&pmu->entry, &pmus); ret = 0; unlock: @@ -5825,7 +5989,7 @@ done: if (!event->parent) { if (event->attach_state & PERF_ATTACH_TASK) - jump_label_inc(&perf_sched_events.key); + static_key_slow_inc(&perf_sched_events.key); if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); if (event->attr.comm) @@ -5839,6 +6003,12 @@ done: return ERR_PTR(err); } } + if (has_branch_stack(event)) { + static_key_slow_inc(&perf_sched_events.key); + if (!(event->attach_state & PERF_ATTACH_TASK)) + atomic_inc(&per_cpu(perf_branch_stack_events, + event->cpu)); + } } return event; @@ -5908,6 +6078,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (attr->read_format & ~(PERF_FORMAT_MAX-1)) return -EINVAL; + if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) { + u64 mask = attr->branch_sample_type; + + /* only using defined bits */ + if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1)) + return -EINVAL; + + /* at least one branch bit must be set */ + if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL)) + return -EINVAL; + + /* kernel level capture: check permissions */ + if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM) + && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + /* propagate priv level, when not set for branch */ + if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) { + + /* exclude_kernel checked on syscall entry */ + if (!attr->exclude_kernel) + mask |= PERF_SAMPLE_BRANCH_KERNEL; + + if (!attr->exclude_user) + mask |= PERF_SAMPLE_BRANCH_USER; + + if (!attr->exclude_hv) + mask |= PERF_SAMPLE_BRANCH_HV; + /* + * adjust user setting (for HW filter setup) + */ + attr->branch_sample_type = mask; + } + } out: return ret; @@ -6063,7 +6267,7 @@ SYSCALL_DEFINE5(perf_event_open, * - that may need work on context switch */ atomic_inc(&per_cpu(perf_cgroup_events, event->cpu)); - jump_label_inc(&perf_sched_events.key); + static_key_slow_inc(&perf_sched_events.key); } /* @@ -6912,6 +7116,13 @@ void __init perf_event_init(void) /* do not patch jump label more than once per second */ jump_label_rate_limit(&perf_sched_events, HZ); + + /* + * Build time assertion that we keep the data_head at the intended + * location. IOW, validation we got the __reserved[] size right. + */ + BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head)) + != 1024); } static int __init perf_event_sysfs_init(void) @@ -6943,8 +7154,7 @@ unlock: device_initcall(perf_event_sysfs_init); #ifdef CONFIG_CGROUP_PERF -static struct cgroup_subsys_state *perf_cgroup_create( - struct cgroup_subsys *ss, struct cgroup *cont) +static struct cgroup_subsys_state *perf_cgroup_create(struct cgroup *cont) { struct perf_cgroup *jc; @@ -6961,8 +7171,7 @@ static struct cgroup_subsys_state *perf_cgroup_create( return &jc->css; } -static void perf_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void perf_cgroup_destroy(struct cgroup *cont) { struct perf_cgroup *jc; jc = container_of(cgroup_subsys_state(cont, perf_subsys_id), @@ -6978,8 +7187,7 @@ static int __perf_cgroup_move(void *info) return 0; } -static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup_taskset *tset) +static void perf_cgroup_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *task; @@ -6987,8 +7195,8 @@ static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, task_function_call(task, __perf_cgroup_move, task); } -static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task) +static void perf_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp, + struct task_struct *task) { /* * cgroup_exit() is called in the copy_process() failure path. diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index b7971d6f38bf..bb38c4d3ee12 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp) if (bp->attr.type != PERF_TYPE_BREAKPOINT) return -ENOENT; + /* + * no branch sampling for breakpoint events + */ + if (has_branch_stack(bp)) + return -EOPNOTSUPP; + err = register_perf_hw_breakpoint(bp); if (err) return err; @@ -613,6 +619,11 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags) bp->hw.state = PERF_HES_STOPPED; } +static int hw_breakpoint_event_idx(struct perf_event *bp) +{ + return 0; +} + static struct pmu perf_breakpoint = { .task_ctx_nr = perf_sw_context, /* could eventually get its own */ @@ -622,6 +633,8 @@ static struct pmu perf_breakpoint = { .start = hw_breakpoint_start, .stop = hw_breakpoint_stop, .read = hw_breakpoint_pmu_read, + + .event_idx = hw_breakpoint_event_idx, }; int __init init_hw_breakpoint(void) @@ -651,10 +664,10 @@ int __init init_hw_breakpoint(void) err_alloc: for_each_possible_cpu(err_cpu) { - if (err_cpu == cpu) - break; for (i = 0; i < TYPE_MAX; i++) kfree(per_cpu(nr_task_bp_pinned[i], cpu)); + if (err_cpu == cpu) + break; } return -ENOMEM; diff --git a/kernel/exit.c b/kernel/exit.c index 4b4042f9bc6a..d8bd3b425fa7 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -52,6 +52,7 @@ #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> +#include <linux/shm.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -424,7 +425,7 @@ void daemonize(const char *name, ...) */ exit_mm(current); /* - * We don't want to have TIF_FREEZE set if the system-wide hibernation + * We don't want to get frozen, in case system-wide hibernation * or suspend transition begins right now. */ current->flags |= (PF_NOFREEZE | PF_KTHREAD); @@ -473,7 +474,7 @@ static void close_files(struct files_struct * files) i = j * __NFDBITS; if (i >= fdt->max_fds) break; - set = fdt->open_fds->fds_bits[j++]; + set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); @@ -686,11 +687,11 @@ static void exit_mm(struct task_struct * tsk) } /* - * When we die, we re-parent all our children. - * Try to give them to another thread in our thread - * group, and if no such member exists, give it to - * the child reaper process (ie "init") in our pid - * space. + * When we die, we re-parent all our children, and try to: + * 1. give them to another thread in our thread group, if such a member exists + * 2. give it to the first ancestor process which prctl'd itself as a + * child_subreaper for its children (like a service manager) + * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father) __releases(&tasklist_lock) @@ -710,8 +711,11 @@ static struct task_struct *find_new_reaper(struct task_struct *father) if (unlikely(pid_ns->child_reaper == father)) { write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) - panic("Attempted to kill init!"); + if (unlikely(pid_ns == &init_pid_ns)) { + panic("Attempted to kill init! exitcode=0x%08x\n", + father->signal->group_exit_code ?: + father->exit_code); + } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); @@ -721,6 +725,29 @@ static struct task_struct *find_new_reaper(struct task_struct *father) * forget_original_parent() must move them somewhere. */ pid_ns->child_reaper = init_pid_ns.child_reaper; + } else if (father->signal->has_child_subreaper) { + struct task_struct *reaper; + + /* + * Find the first ancestor marked as child_subreaper. + * Note that the code below checks same_thread_group(reaper, + * pid_ns->child_reaper). This is what we need to DTRT in a + * PID namespace. However we still need the check above, see + * http://marc.info/?l=linux-kernel&m=131385460420380 + */ + for (reaper = father->real_parent; + reaper != &init_task; + reaper = reaper->real_parent) { + if (same_thread_group(reaper, pid_ns->child_reaper)) + break; + if (!reaper->signal->is_child_subreaper) + continue; + thread = reaper; + do { + if (!(thread->flags & PF_EXITING)) + return reaper; + } while_each_thread(reaper, thread); + } } return pid_ns->child_reaper; @@ -818,25 +845,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead) if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); - /* Let father know we died - * - * Thread signals are configurable, but you aren't going to use - * that to send signals to arbitrary processes. - * That stops right now. - * - * If the parent exec id doesn't match the exec id we saved - * when we started then we know the parent has changed security - * domain. - * - * If our self_exec id doesn't match our parent_exec_id then - * we have changed execution domain as these two values started - * the same after a fork. - */ - if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD && - (tsk->parent_exec_id != tsk->real_parent->self_exec_id || - tsk->self_exec_id != tsk->parent_exec_id)) - tsk->exit_signal = SIGCHLD; - if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && @@ -935,8 +943,6 @@ void do_exit(long code) schedule(); } - exit_irq_thread(); - exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against @@ -945,6 +951,8 @@ void do_exit(long code) smp_mb(); raw_spin_unlock_wait(&tsk->pi_lock); + exit_irq_thread(); + if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), @@ -953,7 +961,7 @@ void do_exit(long code) acct_update_integrals(tsk); /* sync mm's RSS info before statistics gathering */ if (tsk->mm) - sync_mm_rss(tsk, tsk->mm); + sync_mm_rss(tsk->mm); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { hrtimer_cancel(&tsk->signal->real_timer); diff --git a/kernel/fork.c b/kernel/fork.c index a1b632713e43..08eb8584e2a8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -66,6 +66,7 @@ #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> +#include <linux/signalfd.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -192,6 +193,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); + security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); @@ -354,7 +356,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) charge = 0; if (mpnt->vm_flags & VM_ACCOUNT) { unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT; - if (security_vm_enough_memory(len)) + if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } @@ -510,6 +512,23 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) return NULL; } +static void check_mm(struct mm_struct *mm) +{ + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) { + long x = atomic_long_read(&mm->rss_stat.count[i]); + + if (unlikely(x)) + printk(KERN_ALERT "BUG: Bad rss-counter state " + "mm:%p idx:%d val:%ld\n", mm, i, x); + } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + VM_BUG_ON(mm->pmd_huge_pte); +#endif +} + /* * Allocate and initialize an mm_struct. */ @@ -537,9 +556,7 @@ void __mmdrop(struct mm_struct *mm) mm_free_pgd(mm); destroy_context(mm); mmu_notifier_mm_destroy(mm); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON(mm->pmd_huge_pte); -#endif + check_mm(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); @@ -667,6 +684,38 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) return mm; } +static void complete_vfork_done(struct task_struct *tsk) +{ + struct completion *vfork; + + task_lock(tsk); + vfork = tsk->vfork_done; + if (likely(vfork)) { + tsk->vfork_done = NULL; + complete(vfork); + } + task_unlock(tsk); +} + +static int wait_for_vfork_done(struct task_struct *child, + struct completion *vfork) +{ + int killed; + + freezer_do_not_count(); + killed = wait_for_completion_killable(vfork); + freezer_count(); + + if (killed) { + task_lock(child); + child->vfork_done = NULL; + task_unlock(child); + } + + put_task_struct(child); + return killed; +} + /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. @@ -682,8 +731,6 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) */ void mm_release(struct task_struct *tsk, struct mm_struct *mm) { - struct completion *vfork_done = tsk->vfork_done; - /* Get rid of any futexes when releasing the mm */ #ifdef CONFIG_FUTEX if (unlikely(tsk->robust_list)) { @@ -703,17 +750,15 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) /* Get rid of any cached register state */ deactivate_mm(tsk, mm); - /* notify parent sleeping on vfork() */ - if (vfork_done) { - tsk->vfork_done = NULL; - complete(vfork_done); - } + if (tsk->vfork_done) + complete_vfork_done(tsk); /* * If we're exiting normally, clear a user-space tid field if * requested. We leave this alone when dying by signal, to leave * the value intact in a core dump, and to save the unnecessary - * trouble otherwise. Userland only wants this done for a sys_exit. + * trouble, say, a killed vfork parent shouldn't touch this mm. + * Userland only wants this done for a sys_exit. */ if (tsk->clear_child_tid) { if (!(tsk->flags & PF_SIGNALED) && @@ -934,8 +979,10 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_sighand(struct sighand_struct *sighand) { - if (atomic_dec_and_test(&sighand->count)) + if (atomic_dec_and_test(&sighand->count)) { + signalfd_cleanup(sighand); kmem_cache_free(sighand_cachep, sighand); + } } @@ -1003,6 +1050,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; + sig->has_child_subreaper = current->signal->has_child_subreaper || + current->signal->is_child_subreaper; + mutex_init(&sig->cred_guard_mutex); return 0; @@ -1014,7 +1064,6 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); new_flags |= PF_FORKNOEXEC; - new_flags |= PF_STARTING; p->flags = new_flags; } @@ -1191,6 +1240,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; + seqcount_init(&p->mems_allowed_seq); #endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; @@ -1309,7 +1359,13 @@ static struct task_struct *copy_process(unsigned long clone_flags, clear_all_latency_tracing(p); /* ok, now we should be set up.. */ - p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); + if (clone_flags & CLONE_THREAD) + p->exit_signal = -1; + else if (clone_flags & CLONE_PARENT) + p->exit_signal = current->group_leader->exit_signal; + else + p->exit_signal = (clone_flags & CSIGNAL); + p->pdeath_signal = 0; p->exit_state = 0; @@ -1544,16 +1600,9 @@ long do_fork(unsigned long clone_flags, if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); + get_task_struct(p); } - /* - * We set PF_STARTING at creation in case tracing wants to - * use this to distinguish a fully live task from one that - * hasn't finished SIGSTOP raising yet. Now we clear it - * and set the child going. - */ - p->flags &= ~PF_STARTING; - wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ @@ -1561,10 +1610,8 @@ long do_fork(unsigned long clone_flags, ptrace_event(trace, nr); if (clone_flags & CLONE_VFORK) { - freezer_do_not_count(); - wait_for_completion(&vfork); - freezer_count(); - ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); + if (!wait_for_vfork_done(p, &vfork)) + ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); } } else { nr = PTR_ERR(p); diff --git a/kernel/freezer.c b/kernel/freezer.c index 9815b8d1eed5..11f82a4d4eae 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -99,9 +99,9 @@ static void fake_signal_wake_up(struct task_struct *p) * freeze_task - send a freeze request to given task * @p: task to send the request to * - * If @p is freezing, the freeze request is sent by setting %TIF_FREEZE - * flag and either sending a fake signal to it or waking it up, depending - * on whether it has %PF_FREEZER_NOSIG set. + * If @p is freezing, the freeze request is sent either by sending a fake + * signal (if it's not a kernel thread) or waking it up (if it's a kernel + * thread). * * RETURNS: * %false, if @p is not freezing or already frozen; %true, otherwise diff --git a/kernel/futex.c b/kernel/futex.c index 1614be20173d..e2b0fb9a0b3b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -59,6 +59,7 @@ #include <linux/magic.h> #include <linux/pid.h> #include <linux/nsproxy.h> +#include <linux/ptrace.h> #include <asm/futex.h> @@ -2443,40 +2444,31 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, { struct robust_list_head __user *head; unsigned long ret; - const struct cred *cred = current_cred(), *pcred; + struct task_struct *p; if (!futex_cmpxchg_enabled) return -ENOSYS; + WARN_ONCE(1, "deprecated: get_robust_list will be deleted in 2013.\n"); + + rcu_read_lock(); + + ret = -ESRCH; if (!pid) - head = current->robust_list; + p = current; else { - struct task_struct *p; - - ret = -ESRCH; - rcu_read_lock(); p = find_task_by_vpid(pid); if (!p) goto err_unlock; - ret = -EPERM; - pcred = __task_cred(p); - /* If victim is in different user_ns, then uids are not - comparable, so we must have CAP_SYS_PTRACE */ - if (cred->user->user_ns != pcred->user->user_ns) { - if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE)) - goto err_unlock; - goto ok; - } - /* If victim is in same user_ns, then uids are comparable */ - if (cred->euid != pcred->euid && - cred->euid != pcred->uid && - !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE)) - goto err_unlock; -ok: - head = p->robust_list; - rcu_read_unlock(); } + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ)) + goto err_unlock; + + head = p->robust_list; + rcu_read_unlock(); + if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); @@ -2628,7 +2620,7 @@ void exit_robust_list(struct task_struct *curr) long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { - int ret = -ENOSYS, cmd = op & FUTEX_CMD_MASK; + int cmd = op & FUTEX_CMD_MASK; unsigned int flags = 0; if (!(op & FUTEX_PRIVATE_FLAG)) @@ -2641,49 +2633,44 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, } switch (cmd) { + case FUTEX_LOCK_PI: + case FUTEX_UNLOCK_PI: + case FUTEX_TRYLOCK_PI: + case FUTEX_WAIT_REQUEUE_PI: + case FUTEX_CMP_REQUEUE_PI: + if (!futex_cmpxchg_enabled) + return -ENOSYS; + } + + switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAIT_BITSET: - ret = futex_wait(uaddr, flags, val, timeout, val3); - break; + return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAKE_BITSET: - ret = futex_wake(uaddr, flags, val, val3); - break; + return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: - ret = futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); - break; + return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: - ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); - break; + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); case FUTEX_WAKE_OP: - ret = futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); - break; + return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_lock_pi(uaddr, flags, val, timeout, 0); - break; + return futex_lock_pi(uaddr, flags, val, timeout, 0); case FUTEX_UNLOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_unlock_pi(uaddr, flags); - break; + return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_lock_pi(uaddr, flags, 0, timeout, 1); - break; + return futex_lock_pi(uaddr, flags, 0, timeout, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; - ret = futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, - uaddr2); - break; + return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, + uaddr2); case FUTEX_CMP_REQUEUE_PI: - ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); - break; - default: - ret = -ENOSYS; + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); } - return ret; + return -ENOSYS; } diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 5f9e689dc8f0..83e368b005fc 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -10,6 +10,7 @@ #include <linux/compat.h> #include <linux/nsproxy.h> #include <linux/futex.h> +#include <linux/ptrace.h> #include <asm/uaccess.h> @@ -136,40 +137,31 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, { struct compat_robust_list_head __user *head; unsigned long ret; - const struct cred *cred = current_cred(), *pcred; + struct task_struct *p; if (!futex_cmpxchg_enabled) return -ENOSYS; + WARN_ONCE(1, "deprecated: get_robust_list will be deleted in 2013.\n"); + + rcu_read_lock(); + + ret = -ESRCH; if (!pid) - head = current->compat_robust_list; + p = current; else { - struct task_struct *p; - - ret = -ESRCH; - rcu_read_lock(); p = find_task_by_vpid(pid); if (!p) goto err_unlock; - ret = -EPERM; - pcred = __task_cred(p); - /* If victim is in different user_ns, then uids are not - comparable, so we must have CAP_SYS_PTRACE */ - if (cred->user->user_ns != pcred->user->user_ns) { - if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE)) - goto err_unlock; - goto ok; - } - /* If victim is in same user_ns, then uids are comparable */ - if (cred->euid != pcred->euid && - cred->euid != pcred->uid && - !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE)) - goto err_unlock; -ok: - head = p->compat_robust_list; - rcu_read_unlock(); } + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ)) + goto err_unlock; + + head = p->compat_robust_list; + rcu_read_unlock(); + if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 2e48ec0c2e91..c21449f85a2a 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -119,15 +119,20 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * For preemptible RCU it is sufficient to call rcu_read_unlock in order * to exit the grace period. For classic RCU, a reschedule is required. */ -static void rcu_lock_break(struct task_struct *g, struct task_struct *t) +static bool rcu_lock_break(struct task_struct *g, struct task_struct *t) { + bool can_cont; + get_task_struct(g); get_task_struct(t); rcu_read_unlock(); cond_resched(); rcu_read_lock(); + can_cont = pid_alive(g) && pid_alive(t); put_task_struct(t); put_task_struct(g); + + return can_cont; } /* @@ -154,9 +159,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) goto unlock; if (!--batch_count) { batch_count = HUNG_TASK_BATCHING; - rcu_lock_break(g, t); - /* Exit if t or g was unhashed during refresh. */ - if (t->state == TASK_DEAD || g->state == TASK_DEAD) + if (!rcu_lock_break(g, t)) goto unlock; } /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 5a38bf4de641..cf1a4a68ce44 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -13,7 +13,7 @@ config GENERIC_HARDIRQS # Options selectable by the architecture code # Make sparse irq Kconfig switch below available -config HAVE_SPARSE_IRQ +config MAY_HAVE_SPARSE_IRQ bool # Enable the generic irq autoprobe mechanism @@ -56,13 +56,22 @@ config GENERIC_IRQ_CHIP config IRQ_DOMAIN bool +config IRQ_DOMAIN_DEBUG + bool "Expose hardware/virtual IRQ mapping via debugfs" + depends on IRQ_DOMAIN && DEBUG_FS + help + This option will show the mapping relationship between hardware irq + numbers and Linux irq numbers. The mapping is exposed via debugfs + in the file "virq_mapping". + + If you don't know what this means you don't need it. + # Support forced irq threading config IRQ_FORCED_THREADING bool config SPARSE_IRQ - bool "Support sparse irq numbering" - depends on HAVE_SPARSE_IRQ + bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ ---help--- Sparse irq numbering is useful for distro kernels that want diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 342d8f44e401..0119b9d467ae 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -53,7 +53,7 @@ unsigned long probe_irq_on(void) if (desc->irq_data.chip->irq_set_type) desc->irq_data.chip->irq_set_type(&desc->irq_data, IRQ_TYPE_PROBE); - irq_startup(desc); + irq_startup(desc, false); } raw_spin_unlock_irq(&desc->lock); } @@ -70,7 +70,7 @@ unsigned long probe_irq_on(void) raw_spin_lock_irq(&desc->lock); if (!desc->action && irq_settings_can_probe(desc)) { desc->istate |= IRQS_AUTODETECT | IRQS_WAITING; - if (irq_startup(desc)) + if (irq_startup(desc, false)) desc->istate |= IRQS_PENDING; } raw_spin_unlock_irq(&desc->lock); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f7c543a801d9..6080f6bc8c33 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -16,6 +16,8 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <trace/events/irq.h> + #include "internals.h" /** @@ -61,8 +63,7 @@ int irq_set_irq_type(unsigned int irq, unsigned int type) return -EINVAL; type &= IRQ_TYPE_SENSE_MASK; - if (type != IRQ_TYPE_NONE) - ret = __irq_set_trigger(desc, irq, type); + ret = __irq_set_trigger(desc, irq, type); irq_put_desc_busunlock(desc, flags); return ret; } @@ -157,19 +158,22 @@ static void irq_state_set_masked(struct irq_desc *desc) irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); } -int irq_startup(struct irq_desc *desc) +int irq_startup(struct irq_desc *desc, bool resend) { + int ret = 0; + irq_state_clr_disabled(desc); desc->depth = 0; if (desc->irq_data.chip->irq_startup) { - int ret = desc->irq_data.chip->irq_startup(&desc->irq_data); + ret = desc->irq_data.chip->irq_startup(&desc->irq_data); irq_state_clr_masked(desc); - return ret; + } else { + irq_enable(desc); } - - irq_enable(desc); - return 0; + if (resend) + check_irq_resend(desc, desc->irq_data.irq); + return ret; } void irq_shutdown(struct irq_desc *desc) @@ -330,6 +334,24 @@ out_unlock: } EXPORT_SYMBOL_GPL(handle_simple_irq); +/* + * Called unconditionally from handle_level_irq() and only for oneshot + * interrupts from handle_fasteoi_irq() + */ +static void cond_unmask_irq(struct irq_desc *desc) +{ + /* + * We need to unmask in the following cases: + * - Standard level irq (IRQF_ONESHOT is not set) + * - Oneshot irq which did not wake the thread (caused by a + * spurious interrupt or a primary handler handling it + * completely). + */ + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) + unmask_irq(desc); +} + /** * handle_level_irq - Level type irq handler * @irq: the interrupt number @@ -362,8 +384,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc) handle_irq_event(desc); - if (!irqd_irq_disabled(&desc->irq_data) && !(desc->istate & IRQS_ONESHOT)) - unmask_irq(desc); + cond_unmask_irq(desc); + out_unlock: raw_spin_unlock(&desc->lock); } @@ -417,6 +439,9 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) preflow_handler(desc); handle_irq_event(desc); + if (desc->istate & IRQS_ONESHOT) + cond_unmask_irq(desc); + out_eoi: desc->irq_data.chip->irq_eoi(&desc->irq_data); out_unlock: @@ -625,7 +650,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); - irq_startup(desc); + irq_startup(desc, true); } out: irq_put_desc_busunlock(desc, flags); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 470d08c82bbe..bdb180325551 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -54,14 +54,18 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action) static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) { /* - * Wake up the handler thread for this action. In case the - * thread crashed and was killed we just pretend that we - * handled the interrupt. The hardirq handler has disabled the - * device interrupt, so no irq storm is lurking. If the + * In case the thread crashed and was killed we just pretend that + * we handled the interrupt. The hardirq handler has disabled the + * device interrupt, so no irq storm is lurking. + */ + if (action->thread->flags & PF_EXITING) + return; + + /* + * Wake up the handler thread for this action. If the * RUNTHREAD bit is already set, nothing to do. */ - if (test_bit(IRQTF_DIED, &action->thread_flags) || - test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + if (test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags)) return; /* @@ -110,6 +114,18 @@ static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) * threads_oneshot untouched and runs the thread another time. */ desc->threads_oneshot |= action->thread_mask; + + /* + * We increment the threads_active counter in case we wake up + * the irq thread. The irq thread decrements the counter when + * it returns from the handler or in the exit path and wakes + * up waiters which are stuck in synchronize_irq() when the + * active count becomes zero. synchronize_irq() is serialized + * against this code (hard irq handler) via IRQS_INPROGRESS + * like the finalize_oneshot() code. See comment above. + */ + atomic_inc(&desc->threads_active); + wake_up_process(action->thread); } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index b7952316016a..8e5c56b3b7d9 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -20,14 +20,12 @@ extern bool noirqdebug; /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run - * IRQTF_DIED - handler thread died * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded */ enum { IRQTF_RUNTHREAD, - IRQTF_DIED, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, @@ -67,7 +65,7 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp); extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume); -extern int irq_startup(struct irq_desc *desc); +extern int irq_startup(struct irq_desc *desc, bool resend); extern void irq_shutdown(struct irq_desc *desc); extern void irq_enable(struct irq_desc *desc); extern void irq_disable(struct irq_desc *desc); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 1f9e26526b69..3601f3fbf67c 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1,189 +1,793 @@ +#include <linux/debugfs.h> +#include <linux/hardirq.h> +#include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqdesc.h> #include <linux/irqdomain.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/smp.h> +#include <linux/fs.h> + +#define IRQ_DOMAIN_MAP_LEGACY 0 /* driver allocated fixed range of irqs. + * ie. legacy 8259, gets irqs 1..15 */ +#define IRQ_DOMAIN_MAP_NOMAP 1 /* no fast reverse mapping */ +#define IRQ_DOMAIN_MAP_LINEAR 2 /* linear map of interrupts */ +#define IRQ_DOMAIN_MAP_TREE 3 /* radix tree */ static LIST_HEAD(irq_domain_list); static DEFINE_MUTEX(irq_domain_mutex); +static DEFINE_MUTEX(revmap_trees_mutex); +static unsigned int irq_virq_count = NR_IRQS; +static struct irq_domain *irq_default_domain; + /** - * irq_domain_add() - Register an irq_domain - * @domain: ptr to initialized irq_domain structure + * irq_domain_alloc() - Allocate a new irq_domain data structure + * @of_node: optional device-tree node of the interrupt controller + * @revmap_type: type of reverse mapping to use + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer * - * Registers an irq_domain structure. The irq_domain must at a minimum be - * initialized with an ops structure pointer, and either a ->to_irq hook or - * a valid irq_base value. Everything else is optional. + * Allocates and initialize and irq_domain structure. Caller is expected to + * register allocated irq_domain with irq_domain_register(). Returns pointer + * to IRQ domain, or NULL on failure. */ -void irq_domain_add(struct irq_domain *domain) +static struct irq_domain *irq_domain_alloc(struct device_node *of_node, + unsigned int revmap_type, + const struct irq_domain_ops *ops, + void *host_data) { - struct irq_data *d; - int hwirq, irq; + struct irq_domain *domain; - /* - * This assumes that the irq_domain owner has already allocated - * the irq_descs. This block will be removed when support for dynamic - * allocation of irq_descs is added to irq_domain. - */ - irq_domain_for_each_irq(domain, hwirq, irq) { - d = irq_get_irq_data(irq); - if (!d) { - WARN(1, "error: assigning domain to non existant irq_desc"); - return; - } - if (d->domain) { - /* things are broken; just report, don't clean up */ - WARN(1, "error: irq_desc already assigned to a domain"); - return; + domain = kzalloc(sizeof(*domain), GFP_KERNEL); + if (WARN_ON(!domain)) + return NULL; + + /* Fill structure */ + domain->revmap_type = revmap_type; + domain->ops = ops; + domain->host_data = host_data; + domain->of_node = of_node_get(of_node); + + return domain; +} + +static void irq_domain_add(struct irq_domain *domain) +{ + mutex_lock(&irq_domain_mutex); + list_add(&domain->link, &irq_domain_list); + mutex_unlock(&irq_domain_mutex); + pr_debug("irq: Allocated domain of type %d @0x%p\n", + domain->revmap_type, domain); +} + +static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + irq_hw_number_t first_hwirq = domain->revmap_data.legacy.first_hwirq; + int size = domain->revmap_data.legacy.size; + + if (WARN_ON(hwirq < first_hwirq || hwirq >= first_hwirq + size)) + return 0; + return hwirq - first_hwirq + domain->revmap_data.legacy.first_irq; +} + +/** + * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. + * @of_node: pointer to interrupt controller's device tree node. + * @size: total number of irqs in legacy mapping + * @first_irq: first number of irq block assigned to the domain + * @first_hwirq: first hwirq number to use for the translation. Should normally + * be '0', but a positive integer can be used if the effective + * hwirqs numbering does not begin at zero. + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + * + * Note: the map() callback will be called before this function returns + * for all legacy interrupts except 0 (which is always the invalid irq for + * a legacy controller). + */ +struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + irq_hw_number_t first_hwirq, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + unsigned int i; + + domain = irq_domain_alloc(of_node, IRQ_DOMAIN_MAP_LEGACY, ops, host_data); + if (!domain) + return NULL; + + domain->revmap_data.legacy.first_irq = first_irq; + domain->revmap_data.legacy.first_hwirq = first_hwirq; + domain->revmap_data.legacy.size = size; + + mutex_lock(&irq_domain_mutex); + /* Verify that all the irqs are available */ + for (i = 0; i < size; i++) { + int irq = first_irq + i; + struct irq_data *irq_data = irq_get_irq_data(irq); + + if (WARN_ON(!irq_data || irq_data->domain)) { + mutex_unlock(&irq_domain_mutex); + of_node_put(domain->of_node); + kfree(domain); + return NULL; } - d->domain = domain; - d->hwirq = hwirq; } - mutex_lock(&irq_domain_mutex); - list_add(&domain->list, &irq_domain_list); + /* Claim all of the irqs before registering a legacy domain */ + for (i = 0; i < size; i++) { + struct irq_data *irq_data = irq_get_irq_data(first_irq + i); + irq_data->hwirq = first_hwirq + i; + irq_data->domain = domain; + } mutex_unlock(&irq_domain_mutex); + + for (i = 0; i < size; i++) { + int irq = first_irq + i; + int hwirq = first_hwirq + i; + + /* IRQ0 gets ignored */ + if (!irq) + continue; + + /* Legacy flags are left to default at this point, + * one can then use irq_create_mapping() to + * explicitly change them + */ + ops->map(domain, irq, hwirq); + + /* Clear norequest flags */ + irq_clear_status_flags(irq, IRQ_NOREQUEST); + } + + irq_domain_add(domain); + return domain; +} + +/** + * irq_domain_add_linear() - Allocate and register a legacy revmap irq_domain. + * @of_node: pointer to interrupt controller's device tree node. + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + */ +struct irq_domain *irq_domain_add_linear(struct device_node *of_node, + unsigned int size, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + unsigned int *revmap; + + revmap = kzalloc(sizeof(*revmap) * size, GFP_KERNEL); + if (WARN_ON(!revmap)) + return NULL; + + domain = irq_domain_alloc(of_node, IRQ_DOMAIN_MAP_LINEAR, ops, host_data); + if (!domain) { + kfree(revmap); + return NULL; + } + domain->revmap_data.linear.size = size; + domain->revmap_data.linear.revmap = revmap; + irq_domain_add(domain); + return domain; +} + +struct irq_domain *irq_domain_add_nomap(struct device_node *of_node, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain = irq_domain_alloc(of_node, + IRQ_DOMAIN_MAP_NOMAP, ops, host_data); + if (domain) + irq_domain_add(domain); + return domain; +} + +/** + * irq_domain_add_tree() + * @of_node: pointer to interrupt controller's device tree node. + * @ops: map/unmap domain callbacks + * + * Note: The radix tree will be allocated later during boot automatically + * (the reverse mapping will use the slow path until that happens). + */ +struct irq_domain *irq_domain_add_tree(struct device_node *of_node, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain = irq_domain_alloc(of_node, + IRQ_DOMAIN_MAP_TREE, ops, host_data); + if (domain) { + INIT_RADIX_TREE(&domain->revmap_data.tree, GFP_KERNEL); + irq_domain_add(domain); + } + return domain; } /** - * irq_domain_del() - Unregister an irq_domain - * @domain: ptr to registered irq_domain. + * irq_find_host() - Locates a domain for a given device node + * @node: device-tree node of the interrupt controller */ -void irq_domain_del(struct irq_domain *domain) +struct irq_domain *irq_find_host(struct device_node *node) { - struct irq_data *d; - int hwirq, irq; + struct irq_domain *h, *found = NULL; + int rc; + /* We might want to match the legacy controller last since + * it might potentially be set to match all interrupts in + * the absence of a device node. This isn't a problem so far + * yet though... + */ mutex_lock(&irq_domain_mutex); - list_del(&domain->list); + list_for_each_entry(h, &irq_domain_list, link) { + if (h->ops->match) + rc = h->ops->match(h, node); + else + rc = (h->of_node != NULL) && (h->of_node == node); + + if (rc) { + found = h; + break; + } + } mutex_unlock(&irq_domain_mutex); + return found; +} +EXPORT_SYMBOL_GPL(irq_find_host); + +/** + * irq_set_default_host() - Set a "default" irq domain + * @domain: default domain pointer + * + * For convenience, it's possible to set a "default" domain that will be used + * whenever NULL is passed to irq_create_mapping(). It makes life easier for + * platforms that want to manipulate a few hard coded interrupt numbers that + * aren't properly represented in the device-tree. + */ +void irq_set_default_host(struct irq_domain *domain) +{ + pr_debug("irq: Default domain set to @0x%p\n", domain); + + irq_default_domain = domain; +} + +/** + * irq_set_virq_count() - Set the maximum number of linux irqs + * @count: number of linux irqs, capped with NR_IRQS + * + * This is mainly for use by platforms like iSeries who want to program + * the virtual irq number in the controller to avoid the reverse mapping + */ +void irq_set_virq_count(unsigned int count) +{ + pr_debug("irq: Trying to set virq count to %d\n", count); - /* Clear the irq_domain assignments */ - irq_domain_for_each_irq(domain, hwirq, irq) { - d = irq_get_irq_data(irq); - d->domain = NULL; + BUG_ON(count < NUM_ISA_INTERRUPTS); + if (count < NR_IRQS) + irq_virq_count = count; +} + +static int irq_setup_virq(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + + irq_data->hwirq = hwirq; + irq_data->domain = domain; + if (domain->ops->map(domain, virq, hwirq)) { + pr_debug("irq: -> mapping failed, freeing\n"); + irq_data->domain = NULL; + irq_data->hwirq = 0; + return -1; } + + irq_clear_status_flags(virq, IRQ_NOREQUEST); + + return 0; } -#if defined(CONFIG_OF_IRQ) /** - * irq_create_of_mapping() - Map a linux irq number from a DT interrupt spec + * irq_create_direct_mapping() - Allocate an irq for direct mapping + * @domain: domain to allocate the irq for or NULL for default domain * - * Used by the device tree interrupt mapping code to translate a device tree - * interrupt specifier to a valid linux irq number. Returns either a valid - * linux IRQ number or 0. + * This routine is used for irq controllers which can choose the hardware + * interrupt numbers they generate. In such a case it's simplest to use + * the linux irq as the hardware interrupt number. + */ +unsigned int irq_create_direct_mapping(struct irq_domain *domain) +{ + unsigned int virq; + + if (domain == NULL) + domain = irq_default_domain; + + BUG_ON(domain == NULL); + WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP); + + virq = irq_alloc_desc_from(1, 0); + if (!virq) { + pr_debug("irq: create_direct virq allocation failed\n"); + return 0; + } + if (virq >= irq_virq_count) { + pr_err("ERROR: no free irqs available below %i maximum\n", + irq_virq_count); + irq_free_desc(virq); + return 0; + } + + pr_debug("irq: create_direct obtained virq %d\n", virq); + + if (irq_setup_virq(domain, virq, virq)) { + irq_free_desc(virq); + return 0; + } + + return virq; +} + +/** + * irq_create_mapping() - Map a hardware interrupt into linux irq space + * @domain: domain owning this hardware interrupt or NULL for default domain + * @hwirq: hardware irq number in that domain space * - * When the caller no longer need the irq number returned by this function it - * should arrange to call irq_dispose_mapping(). + * Only one mapping per hardware interrupt is permitted. Returns a linux + * irq number. + * If the sense/trigger is to be specified, set_irq_type() should be called + * on the number returned from that call. */ +unsigned int irq_create_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + unsigned int virq, hint; + + pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); + + /* Look for default domain if nececssary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) { + printk(KERN_WARNING "irq_create_mapping called for" + " NULL domain, hwirq=%lx\n", hwirq); + WARN_ON(1); + return 0; + } + pr_debug("irq: -> using domain @%p\n", domain); + + /* Check if mapping already exists */ + virq = irq_find_mapping(domain, hwirq); + if (virq) { + pr_debug("irq: -> existing mapping on virq %d\n", virq); + return virq; + } + + /* Get a virtual interrupt number */ + if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) + return irq_domain_legacy_revmap(domain, hwirq); + + /* Allocate a virtual interrupt number */ + hint = hwirq % irq_virq_count; + if (hint == 0) + hint++; + virq = irq_alloc_desc_from(hint, 0); + if (!virq) + virq = irq_alloc_desc_from(1, 0); + if (!virq) { + pr_debug("irq: -> virq allocation failed\n"); + return 0; + } + + if (irq_setup_virq(domain, virq, hwirq)) { + if (domain->revmap_type != IRQ_DOMAIN_MAP_LEGACY) + irq_free_desc(virq); + return 0; + } + + pr_debug("irq: irq %lu on domain %s mapped to virtual irq %u\n", + hwirq, domain->of_node ? domain->of_node->full_name : "null", virq); + + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_mapping); + unsigned int irq_create_of_mapping(struct device_node *controller, const u32 *intspec, unsigned int intsize) { struct irq_domain *domain; - unsigned long hwirq; - unsigned int irq, type; - int rc = -EINVAL; + irq_hw_number_t hwirq; + unsigned int type = IRQ_TYPE_NONE; + unsigned int virq; - /* Find a domain which can translate the irq spec */ - mutex_lock(&irq_domain_mutex); - list_for_each_entry(domain, &irq_domain_list, list) { - if (!domain->ops->dt_translate) - continue; - rc = domain->ops->dt_translate(domain, controller, - intspec, intsize, &hwirq, &type); - if (rc == 0) - break; + domain = controller ? irq_find_host(controller) : irq_default_domain; + if (!domain) { +#ifdef CONFIG_MIPS + /* + * Workaround to avoid breaking interrupt controller drivers + * that don't yet register an irq_domain. This is temporary + * code. ~~~gcl, Feb 24, 2012 + * + * Scheduled for removal in Linux v3.6. That should be enough + * time. + */ + if (intsize > 0) + return intspec[0]; +#endif + printk(KERN_WARNING "irq: no irq domain found for %s !\n", + controller->full_name); + return 0; } - mutex_unlock(&irq_domain_mutex); - if (rc != 0) - return 0; + /* If domain has no translation, then we assume interrupt line */ + if (domain->ops->xlate == NULL) + hwirq = intspec[0]; + else { + if (domain->ops->xlate(domain, controller, intspec, intsize, + &hwirq, &type)) + return 0; + } + + /* Create mapping */ + virq = irq_create_mapping(domain, hwirq); + if (!virq) + return virq; - irq = irq_domain_to_irq(domain, hwirq); - if (type != IRQ_TYPE_NONE) - irq_set_irq_type(irq, type); - pr_debug("%s: mapped hwirq=%i to irq=%i, flags=%x\n", - controller->full_name, (int)hwirq, irq, type); - return irq; + /* Set type if specified and different than the current one */ + if (type != IRQ_TYPE_NONE && + type != (irqd_get_trigger_type(irq_get_irq_data(virq)))) + irq_set_irq_type(virq, type); + return virq; } EXPORT_SYMBOL_GPL(irq_create_of_mapping); /** - * irq_dispose_mapping() - Discard a mapping created by irq_create_of_mapping() - * @irq: linux irq number to be discarded + * irq_dispose_mapping() - Unmap an interrupt + * @virq: linux irq number of the interrupt to unmap + */ +void irq_dispose_mapping(unsigned int virq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + struct irq_domain *domain; + irq_hw_number_t hwirq; + + if (!virq || !irq_data) + return; + + domain = irq_data->domain; + if (WARN_ON(domain == NULL)) + return; + + /* Never unmap legacy interrupts */ + if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) + return; + + irq_set_status_flags(virq, IRQ_NOREQUEST); + + /* remove chip and handler */ + irq_set_chip_and_handler(virq, NULL, NULL); + + /* Make sure it's completed */ + synchronize_irq(virq); + + /* Tell the PIC about it */ + if (domain->ops->unmap) + domain->ops->unmap(domain, virq); + smp_mb(); + + /* Clear reverse map */ + hwirq = irq_data->hwirq; + switch(domain->revmap_type) { + case IRQ_DOMAIN_MAP_LINEAR: + if (hwirq < domain->revmap_data.linear.size) + domain->revmap_data.linear.revmap[hwirq] = 0; + break; + case IRQ_DOMAIN_MAP_TREE: + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_data.tree, hwirq); + mutex_unlock(&revmap_trees_mutex); + break; + } + + irq_free_desc(virq); +} +EXPORT_SYMBOL_GPL(irq_dispose_mapping); + +/** + * irq_find_mapping() - Find a linux irq from an hw irq number. + * @domain: domain owning this hardware interrupt + * @hwirq: hardware irq number in that domain space + * + * This is a slow path, for use by generic code. It's expected that an + * irq controller implementation directly calls the appropriate low level + * mapping function. + */ +unsigned int irq_find_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + unsigned int i; + unsigned int hint = hwirq % irq_virq_count; + + /* Look for default domain if nececssary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) + return 0; + + /* legacy -> bail early */ + if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) + return irq_domain_legacy_revmap(domain, hwirq); + + /* Slow path does a linear search of the map */ + if (hint == 0) + hint = 1; + i = hint; + do { + struct irq_data *data = irq_get_irq_data(i); + if (data && (data->domain == domain) && (data->hwirq == hwirq)) + return i; + i++; + if (i >= irq_virq_count) + i = 1; + } while(i != hint); + return 0; +} +EXPORT_SYMBOL_GPL(irq_find_mapping); + +/** + * irq_radix_revmap_lookup() - Find a linux irq from a hw irq number. + * @domain: domain owning this hardware interrupt + * @hwirq: hardware irq number in that domain space * - * Calling this function indicates the caller no longer needs a reference to - * the linux irq number returned by a prior call to irq_create_of_mapping(). + * This is a fast path, for use by irq controller code that uses radix tree + * revmaps */ -void irq_dispose_mapping(unsigned int irq) +unsigned int irq_radix_revmap_lookup(struct irq_domain *domain, + irq_hw_number_t hwirq) { + struct irq_data *irq_data; + + if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_TREE)) + return irq_find_mapping(domain, hwirq); + + /* + * Freeing an irq can delete nodes along the path to + * do the lookup via call_rcu. + */ + rcu_read_lock(); + irq_data = radix_tree_lookup(&domain->revmap_data.tree, hwirq); + rcu_read_unlock(); + /* - * nothing yet; will be filled when support for dynamic allocation of - * irq_descs is added to irq_domain + * If found in radix tree, then fine. + * Else fallback to linear lookup - this should not happen in practice + * as it means that we failed to insert the node in the radix tree. */ + return irq_data ? irq_data->irq : irq_find_mapping(domain, hwirq); } -EXPORT_SYMBOL_GPL(irq_dispose_mapping); -int irq_domain_simple_dt_translate(struct irq_domain *d, - struct device_node *controller, - const u32 *intspec, unsigned int intsize, - unsigned long *out_hwirq, unsigned int *out_type) +/** + * irq_radix_revmap_insert() - Insert a hw irq to linux irq number mapping. + * @domain: domain owning this hardware interrupt + * @virq: linux irq number + * @hwirq: hardware irq number in that domain space + * + * This is for use by irq controllers that use a radix tree reverse + * mapping for fast lookup. + */ +void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) { - if (d->of_node != controller) - return -EINVAL; - if (intsize < 1) - return -EINVAL; - if (d->nr_irq && ((intspec[0] < d->hwirq_base) || - (intspec[0] >= d->hwirq_base + d->nr_irq))) - return -EINVAL; + struct irq_data *irq_data = irq_get_irq_data(virq); + + if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_TREE)) + return; + + if (virq) { + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data); + mutex_unlock(&revmap_trees_mutex); + } +} + +/** + * irq_linear_revmap() - Find a linux irq from a hw irq number. + * @domain: domain owning this hardware interrupt + * @hwirq: hardware irq number in that domain space + * + * This is a fast path, for use by irq controller code that uses linear + * revmaps. It does fallback to the slow path if the revmap doesn't exist + * yet and will create the revmap entry with appropriate locking + */ +unsigned int irq_linear_revmap(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + unsigned int *revmap; + + if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR)) + return irq_find_mapping(domain, hwirq); + + /* Check revmap bounds */ + if (unlikely(hwirq >= domain->revmap_data.linear.size)) + return irq_find_mapping(domain, hwirq); + + /* Check if revmap was allocated */ + revmap = domain->revmap_data.linear.revmap; + if (unlikely(revmap == NULL)) + return irq_find_mapping(domain, hwirq); + + /* Fill up revmap with slow path if no mapping found */ + if (unlikely(!revmap[hwirq])) + revmap[hwirq] = irq_find_mapping(domain, hwirq); + + return revmap[hwirq]; +} + +#ifdef CONFIG_IRQ_DOMAIN_DEBUG +static int virq_debug_show(struct seq_file *m, void *private) +{ + unsigned long flags; + struct irq_desc *desc; + const char *p; + static const char none[] = "none"; + void *data; + int i; + + seq_printf(m, "%-5s %-7s %-15s %-18s %s\n", "virq", "hwirq", + "chip name", "chip data", "domain name"); + + for (i = 1; i < nr_irqs; i++) { + desc = irq_to_desc(i); + if (!desc) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + + if (desc->action && desc->action->handler) { + struct irq_chip *chip; + + seq_printf(m, "%5d ", i); + seq_printf(m, "0x%05lx ", desc->irq_data.hwirq); + + chip = irq_desc_get_chip(desc); + if (chip && chip->name) + p = chip->name; + else + p = none; + seq_printf(m, "%-15s ", p); + + data = irq_desc_get_chip_data(desc); + seq_printf(m, "0x%16p ", data); + + if (desc->irq_data.domain && desc->irq_data.domain->of_node) + p = desc->irq_data.domain->of_node->full_name; + else + p = none; + seq_printf(m, "%s\n", p); + } + + raw_spin_unlock_irqrestore(&desc->lock, flags); + } + + return 0; +} +static int virq_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, virq_debug_show, inode->i_private); +} + +static const struct file_operations virq_debug_fops = { + .open = virq_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init irq_debugfs_init(void) +{ + if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL, + NULL, &virq_debug_fops) == NULL) + return -ENOMEM; + + return 0; +} +__initcall(irq_debugfs_init); +#endif /* CONFIG_IRQ_DOMAIN_DEBUG */ + +int irq_domain_simple_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) +{ + return 0; +} + +/** + * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings + * + * Device Tree IRQ specifier translation function which works with one cell + * bindings where the cell value maps directly to the hwirq number. + */ +int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; *out_hwirq = intspec[0]; *out_type = IRQ_TYPE_NONE; - if (intsize > 1) - *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; return 0; } +EXPORT_SYMBOL_GPL(irq_domain_xlate_onecell); /** - * irq_domain_create_simple() - Set up a 'simple' translation range + * irq_domain_xlate_twocell() - Generic xlate for direct two cell bindings + * + * Device Tree IRQ specifier translation function which works with two cell + * bindings where the cell values map directly to the hwirq number + * and linux irq flags. */ -void irq_domain_add_simple(struct device_node *controller, int irq_base) +int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_type) { - struct irq_domain *domain; - - domain = kzalloc(sizeof(*domain), GFP_KERNEL); - if (!domain) { - WARN_ON(1); - return; - } + if (WARN_ON(intsize < 2)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell); - domain->irq_base = irq_base; - domain->of_node = of_node_get(controller); - domain->ops = &irq_domain_simple_ops; - irq_domain_add(domain); +/** + * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings + * + * Device Tree IRQ specifier translation function which works with either one + * or two cell bindings where the cell values map directly to the hwirq number + * and linux irq flags. + * + * Note: don't use this function unless your interrupt controller explicitly + * supports both one and two cell bindings. For the majority of controllers + * the _onecell() or _twocell() variants above should be used. + */ +int irq_domain_xlate_onetwocell(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = (intsize > 1) ? intspec[1] : IRQ_TYPE_NONE; + return 0; } -EXPORT_SYMBOL_GPL(irq_domain_add_simple); +EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell); +const struct irq_domain_ops irq_domain_simple_ops = { + .map = irq_domain_simple_map, + .xlate = irq_domain_xlate_onetwocell, +}; +EXPORT_SYMBOL_GPL(irq_domain_simple_ops); + +#ifdef CONFIG_OF_IRQ void irq_domain_generate_simple(const struct of_device_id *match, u64 phys_base, unsigned int irq_start) { struct device_node *node; - pr_info("looking for phys_base=%llx, irq_start=%i\n", + pr_debug("looking for phys_base=%llx, irq_start=%i\n", (unsigned long long) phys_base, (int) irq_start); node = of_find_matching_node_by_address(NULL, match, phys_base); if (node) - irq_domain_add_simple(node, irq_start); - else - pr_info("no node found\n"); + irq_domain_add_legacy(node, 32, irq_start, 0, + &irq_domain_simple_ops, NULL); } EXPORT_SYMBOL_GPL(irq_domain_generate_simple); -#endif /* CONFIG_OF_IRQ */ - -struct irq_domain_ops irq_domain_simple_ops = { -#ifdef CONFIG_OF_IRQ - .dt_translate = irq_domain_simple_dt_translate, -#endif /* CONFIG_OF_IRQ */ -}; -EXPORT_SYMBOL_GPL(irq_domain_simple_ops); +#endif diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a9a9dbe49fea..89a3ea82569b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -282,7 +282,7 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) { struct irq_chip *chip = irq_desc_get_chip(desc); struct cpumask *set = irq_default_affinity; - int ret; + int ret, node = desc->irq_data.node; /* Excludes PER_CPU and NO_BALANCE interrupts */ if (!irq_can_set_affinity(irq)) @@ -301,6 +301,13 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) } cpumask_and(mask, cpu_online_mask, set); + if (node != NUMA_NO_NODE) { + const struct cpumask *nodemask = cpumask_of_node(node); + + /* make sure at least one of the cpus in nodemask is online */ + if (cpumask_intersects(mask, nodemask)) + cpumask_and(mask, mask, nodemask); + } ret = chip->irq_set_affinity(&desc->irq_data, mask, false); switch (ret) { case IRQ_SET_MASK_OK: @@ -645,7 +652,7 @@ static int irq_wait_for_interrupt(struct irqaction *action) * is marked MASKED. */ static void irq_finalize_oneshot(struct irq_desc *desc, - struct irqaction *action, bool force) + struct irqaction *action) { if (!(desc->istate & IRQS_ONESHOT)) return; @@ -679,7 +686,7 @@ again: * we would clear the threads_oneshot bit of this thread which * was just set. */ - if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) goto out_unlock; desc->threads_oneshot &= ~action->thread_mask; @@ -739,7 +746,7 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) local_bh_disable(); ret = action->thread_fn(action->irq, action->dev_id); - irq_finalize_oneshot(desc, action, false); + irq_finalize_oneshot(desc, action); local_bh_enable(); return ret; } @@ -755,10 +762,17 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc, irqreturn_t ret; ret = action->thread_fn(action->irq, action->dev_id); - irq_finalize_oneshot(desc, action, false); + irq_finalize_oneshot(desc, action); return ret; } +static void wake_threads_waitq(struct irq_desc *desc) +{ + if (atomic_dec_and_test(&desc->threads_active) && + waitqueue_active(&desc->wait_for_threads)) + wake_up(&desc->wait_for_threads); +} + /* * Interrupt handler thread */ @@ -771,57 +785,41 @@ static int irq_thread(void *data) struct irq_desc *desc = irq_to_desc(action->irq); irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); - int wake; - if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD, + if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, &action->thread_flags)) handler_fn = irq_forced_thread_fn; else handler_fn = irq_thread_fn; sched_setscheduler(current, SCHED_FIFO, ¶m); - current->irqaction = action; + current->irq_thread = 1; while (!irq_wait_for_interrupt(action)) { + irqreturn_t action_ret; irq_thread_check_affinity(desc, action); - atomic_inc(&desc->threads_active); + action_ret = handler_fn(desc, action); + if (!noirqdebug) + note_interrupt(action->irq, desc, action_ret); - raw_spin_lock_irq(&desc->lock); - if (unlikely(irqd_irq_disabled(&desc->irq_data))) { - /* - * CHECKME: We might need a dedicated - * IRQ_THREAD_PENDING flag here, which - * retriggers the thread in check_irq_resend() - * but AFAICT IRQS_PENDING should be fine as it - * retriggers the interrupt itself --- tglx - */ - desc->istate |= IRQS_PENDING; - raw_spin_unlock_irq(&desc->lock); - } else { - irqreturn_t action_ret; - - raw_spin_unlock_irq(&desc->lock); - action_ret = handler_fn(desc, action); - if (!noirqdebug) - note_interrupt(action->irq, desc, action_ret); - } - - wake = atomic_dec_and_test(&desc->threads_active); - - if (wake && waitqueue_active(&desc->wait_for_threads)) - wake_up(&desc->wait_for_threads); + wake_threads_waitq(desc); } - /* Prevent a stale desc->threads_oneshot */ - irq_finalize_oneshot(desc, action, true); - /* - * Clear irqaction. Otherwise exit_irq_thread() would make + * This is the regular exit path. __free_irq() is stopping the + * thread via kthread_stop() after calling + * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. We cannot verify that as we + * cannot touch the oneshot mask at this point anymore as + * __setup_irq() might have given out currents thread_mask + * again. + * + * Clear irq_thread. Otherwise exit_irq_thread() would make * fuzz about an active irq thread going into nirvana. */ - current->irqaction = NULL; + current->irq_thread = 0; return 0; } @@ -832,27 +830,28 @@ void exit_irq_thread(void) { struct task_struct *tsk = current; struct irq_desc *desc; + struct irqaction *action; - if (!tsk->irqaction) + if (!tsk->irq_thread) return; + action = kthread_data(tsk); + printk(KERN_ERR "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", - tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq); + tsk->comm ? tsk->comm : "", tsk->pid, action->irq); - desc = irq_to_desc(tsk->irqaction->irq); + desc = irq_to_desc(action->irq); /* - * Prevent a stale desc->threads_oneshot. Must be called - * before setting the IRQTF_DIED flag. + * If IRQTF_RUNTHREAD is set, we need to decrement + * desc->threads_active and wake possible waiters. */ - irq_finalize_oneshot(desc, tsk->irqaction, true); + if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + wake_threads_waitq(desc); - /* - * Set the THREAD DIED flag to prevent further wakeups of the - * soon to be gone threaded handler. - */ - set_bit(IRQTF_DIED, &tsk->irqaction->flags); + /* Prevent a stale desc->threads_oneshot */ + irq_finalize_oneshot(desc, action); } static void irq_setup_forced_threading(struct irqaction *new) @@ -985,6 +984,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) /* add new interrupt at end of irq queue */ do { + /* + * Or all existing action->thread_mask bits, + * so we can find the next zero bit for this + * new action. + */ thread_mask |= old->thread_mask; old_ptr = &old->next; old = *old_ptr; @@ -993,14 +997,41 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } /* - * Setup the thread mask for this irqaction. Unlikely to have - * 32 resp 64 irqs sharing one line, but who knows. + * Setup the thread mask for this irqaction for ONESHOT. For + * !ONESHOT irqs the thread mask is 0 so we can avoid a + * conditional in irq_wake_thread(). */ - if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) { - ret = -EBUSY; - goto out_mask; + if (new->flags & IRQF_ONESHOT) { + /* + * Unlikely to have 32 resp 64 irqs sharing one line, + * but who knows. + */ + if (thread_mask == ~0UL) { + ret = -EBUSY; + goto out_mask; + } + /* + * The thread_mask for the action is or'ed to + * desc->thread_active to indicate that the + * IRQF_ONESHOT thread handler has been woken, but not + * yet finished. The bit is cleared when a thread + * completes. When all threads of a shared interrupt + * line have completed desc->threads_active becomes + * zero and the interrupt line is unmasked. See + * handle.c:irq_wake_thread() for further information. + * + * If no thread is woken by primary (hard irq context) + * interrupt handlers, then desc->threads_active is + * also checked for zero to unmask the irq line in the + * affected hard irq flow handlers + * (handle_[fasteoi|level]_irq). + * + * The new action gets the first zero bit of + * thread_mask assigned. See the loop above which or's + * all existing action->thread_mask bits. + */ + new->thread_mask = 1 << ffz(thread_mask); } - new->thread_mask = 1 << ffz(thread_mask); if (!shared) { init_waitqueue_head(&desc->wait_for_threads); @@ -1027,7 +1058,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) desc->istate |= IRQS_ONESHOT; if (irq_settings_can_autoenable(desc)) - irq_startup(desc); + irq_startup(desc, true); else /* Undo nested disables: */ desc->depth = 1; @@ -1103,8 +1134,7 @@ out_thread: struct task_struct *t = new->thread; new->thread = NULL; - if (likely(!test_bit(IRQTF_DIED, &new->thread_flags))) - kthread_stop(t); + kthread_stop(t); put_task_struct(t); } out_mput: @@ -1214,8 +1244,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif if (action->thread) { - if (!test_bit(IRQTF_DIED, &action->thread_flags)) - kthread_stop(action->thread); + kthread_stop(action->thread); put_task_struct(action->thread); } diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 47420908fba0..c3c89751b327 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -43,12 +43,16 @@ void irq_move_masked_irq(struct irq_data *idata) * masking the irqs. */ if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask) - < nr_cpu_ids)) - if (!chip->irq_set_affinity(&desc->irq_data, - desc->pending_mask, false)) { + < nr_cpu_ids)) { + int ret = chip->irq_set_affinity(&desc->irq_data, + desc->pending_mask, false); + switch (ret) { + case IRQ_SET_MASK_OK: cpumask_copy(desc->irq_data.affinity, desc->pending_mask); + case IRQ_SET_MASK_OK_NOCOPY: irq_set_thread_affinity(desc); } + } cpumask_clear(desc->pending_mask); } diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 01d3b70fc98a..43049192b5ec 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -12,7 +12,7 @@ #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> -#include <linux/jump_label.h> +#include <linux/static_key.h> #ifdef HAVE_JUMP_LABEL @@ -29,11 +29,6 @@ void jump_label_unlock(void) mutex_unlock(&jump_label_mutex); } -bool jump_label_enabled(struct jump_label_key *key) -{ - return !!atomic_read(&key->enabled); -} - static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; @@ -58,56 +53,66 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL); } -static void jump_label_update(struct jump_label_key *key, int enable); +static void jump_label_update(struct static_key *key, int enable); -void jump_label_inc(struct jump_label_key *key) +void static_key_slow_inc(struct static_key *key) { if (atomic_inc_not_zero(&key->enabled)) return; jump_label_lock(); - if (atomic_read(&key->enabled) == 0) - jump_label_update(key, JUMP_LABEL_ENABLE); + if (atomic_read(&key->enabled) == 0) { + if (!jump_label_get_branch_default(key)) + jump_label_update(key, JUMP_LABEL_ENABLE); + else + jump_label_update(key, JUMP_LABEL_DISABLE); + } atomic_inc(&key->enabled); jump_label_unlock(); } -EXPORT_SYMBOL_GPL(jump_label_inc); +EXPORT_SYMBOL_GPL(static_key_slow_inc); -static void __jump_label_dec(struct jump_label_key *key, +static void __static_key_slow_dec(struct static_key *key, unsigned long rate_limit, struct delayed_work *work) { - if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) + if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) { + WARN(atomic_read(&key->enabled) < 0, + "jump label: negative count!\n"); return; + } if (rate_limit) { atomic_inc(&key->enabled); schedule_delayed_work(work, rate_limit); - } else - jump_label_update(key, JUMP_LABEL_DISABLE); - + } else { + if (!jump_label_get_branch_default(key)) + jump_label_update(key, JUMP_LABEL_DISABLE); + else + jump_label_update(key, JUMP_LABEL_ENABLE); + } jump_label_unlock(); } -EXPORT_SYMBOL_GPL(jump_label_dec); static void jump_label_update_timeout(struct work_struct *work) { - struct jump_label_key_deferred *key = - container_of(work, struct jump_label_key_deferred, work.work); - __jump_label_dec(&key->key, 0, NULL); + struct static_key_deferred *key = + container_of(work, struct static_key_deferred, work.work); + __static_key_slow_dec(&key->key, 0, NULL); } -void jump_label_dec(struct jump_label_key *key) +void static_key_slow_dec(struct static_key *key) { - __jump_label_dec(key, 0, NULL); + __static_key_slow_dec(key, 0, NULL); } +EXPORT_SYMBOL_GPL(static_key_slow_dec); -void jump_label_dec_deferred(struct jump_label_key_deferred *key) +void static_key_slow_dec_deferred(struct static_key_deferred *key) { - __jump_label_dec(&key->key, key->timeout, &key->work); + __static_key_slow_dec(&key->key, key->timeout, &key->work); } +EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); - -void jump_label_rate_limit(struct jump_label_key_deferred *key, +void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { key->timeout = rl; @@ -150,7 +155,7 @@ void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry arch_jump_label_transform(entry, type); } -static void __jump_label_update(struct jump_label_key *key, +static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, int enable) { @@ -167,27 +172,40 @@ static void __jump_label_update(struct jump_label_key *key, } } +static enum jump_label_type jump_label_type(struct static_key *key) +{ + bool true_branch = jump_label_get_branch_default(key); + bool state = static_key_enabled(key); + + if ((!true_branch && state) || (true_branch && !state)) + return JUMP_LABEL_ENABLE; + + return JUMP_LABEL_DISABLE; +} + void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; - struct jump_label_key *key = NULL; + struct static_key *key = NULL; struct jump_entry *iter; jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { - struct jump_label_key *iterk; + struct static_key *iterk; - iterk = (struct jump_label_key *)(unsigned long)iter->key; - arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ? - JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE); + iterk = (struct static_key *)(unsigned long)iter->key; + arch_jump_label_transform_static(iter, jump_label_type(iterk)); if (iterk == key) continue; key = iterk; - key->entries = iter; + /* + * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH. + */ + *((unsigned long *)&key->entries) += (unsigned long)iter; #ifdef CONFIG_MODULES key->next = NULL; #endif @@ -197,8 +215,8 @@ void __init jump_label_init(void) #ifdef CONFIG_MODULES -struct jump_label_mod { - struct jump_label_mod *next; +struct static_key_mod { + struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; @@ -218,9 +236,9 @@ static int __jump_label_mod_text_reserved(void *start, void *end) start, end); } -static void __jump_label_mod_update(struct jump_label_key *key, int enable) +static void __jump_label_mod_update(struct static_key *key, int enable) { - struct jump_label_mod *mod = key->next; + struct static_key_mod *mod = key->next; while (mod) { struct module *m = mod->mod; @@ -251,11 +269,7 @@ void jump_label_apply_nops(struct module *mod) return; for (iter = iter_start; iter < iter_stop; iter++) { - struct jump_label_key *iterk; - - iterk = (struct jump_label_key *)(unsigned long)iter->key; - arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ? - JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE); + arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE); } } @@ -264,8 +278,8 @@ static int jump_label_add_module(struct module *mod) struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; - struct jump_label_key *key = NULL; - struct jump_label_mod *jlm; + struct static_key *key = NULL; + struct static_key_mod *jlm; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) @@ -274,28 +288,30 @@ static int jump_label_add_module(struct module *mod) jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { - if (iter->key == (jump_label_t)(unsigned long)key) - continue; + struct static_key *iterk; - key = (struct jump_label_key *)(unsigned long)iter->key; + iterk = (struct static_key *)(unsigned long)iter->key; + if (iterk == key) + continue; + key = iterk; if (__module_address(iter->key) == mod) { - atomic_set(&key->enabled, 0); - key->entries = iter; + /* + * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH. + */ + *((unsigned long *)&key->entries) += (unsigned long)iter; key->next = NULL; continue; } - - jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL); + jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; - jlm->mod = mod; jlm->entries = iter; jlm->next = key->next; key->next = jlm; - if (jump_label_enabled(key)) + if (jump_label_type(key) == JUMP_LABEL_ENABLE) __jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE); } @@ -307,14 +323,14 @@ static void jump_label_del_module(struct module *mod) struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; - struct jump_label_key *key = NULL; - struct jump_label_mod *jlm, **prev; + struct static_key *key = NULL; + struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (iter->key == (jump_label_t)(unsigned long)key) continue; - key = (struct jump_label_key *)(unsigned long)iter->key; + key = (struct static_key *)(unsigned long)iter->key; if (__module_address(iter->key) == mod) continue; @@ -416,12 +432,13 @@ int jump_label_text_reserved(void *start, void *end) return ret; } -static void jump_label_update(struct jump_label_key *key, int enable) +static void jump_label_update(struct static_key *key, int enable) { - struct jump_entry *entry = key->entries, *stop = __stop___jump_table; + struct jump_entry *stop = __stop___jump_table; + struct jump_entry *entry = jump_label_get_entries(key); #ifdef CONFIG_MODULES - struct module *mod = __module_address((jump_label_t)key); + struct module *mod = __module_address((unsigned long)key); __jump_label_mod_update(key, enable); diff --git a/kernel/kexec.c b/kernel/kexec.c index 7b0886786701..4e2e472f6aeb 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -37,7 +37,6 @@ #include <asm/page.h> #include <asm/uaccess.h> #include <asm/io.h> -#include <asm/system.h> #include <asm/sections.h> /* Per cpu memory for storing cpu states in case of system crash. */ @@ -1359,6 +1358,10 @@ static int __init parse_crashkernel_simple(char *cmdline, if (*cur == '@') *crash_base = memparse(cur+1, &cur); + else if (*cur != ' ' && *cur != '\0') { + pr_warning("crashkernel: unrecognized char\n"); + return -EINVAL; + } return 0; } @@ -1462,7 +1465,9 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(init_uts_ns); VMCOREINFO_SYMBOL(node_online_map); +#ifdef CONFIG_MMU VMCOREINFO_SYMBOL(swapper_pg_dir); +#endif VMCOREINFO_SYMBOL(_stext); VMCOREINFO_SYMBOL(vmlist); @@ -1546,13 +1551,13 @@ int kernel_kexec(void) if (error) goto Resume_console; /* At this point, dpm_suspend_start() has been called, - * but *not* dpm_suspend_noirq(). We *must* call - * dpm_suspend_noirq() now. Otherwise, drivers for + * but *not* dpm_suspend_end(). We *must* call + * dpm_suspend_end() now. Otherwise, drivers for * some devices (e.g. interrupt controllers) become * desynchronized with the actual state of the * hardware at resume time, and evil weirdness ensues. */ - error = dpm_suspend_noirq(PMSG_FREEZE); + error = dpm_suspend_end(PMSG_FREEZE); if (error) goto Resume_devices; error = disable_nonboot_cpus(); @@ -1579,7 +1584,7 @@ int kernel_kexec(void) local_irq_enable(); Enable_cpus: enable_nonboot_cpus(); - dpm_resume_noirq(PMSG_RESTORE); + dpm_resume_start(PMSG_RESTORE); Resume_devices: dpm_resume_end(PMSG_RESTORE); Resume_console: diff --git a/kernel/kmod.c b/kernel/kmod.c index a0a88543934e..957a7aab8ebc 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -60,6 +60,43 @@ static DECLARE_RWSEM(umhelper_sem); */ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; +static void free_modprobe_argv(struct subprocess_info *info) +{ + kfree(info->argv[3]); /* check call_modprobe() */ + kfree(info->argv); +} + +static int call_modprobe(char *module_name, int wait) +{ + static char *envp[] = { + "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + + char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); + if (!argv) + goto out; + + module_name = kstrdup(module_name, GFP_KERNEL); + if (!module_name) + goto free_argv; + + argv[0] = modprobe_path; + argv[1] = "-q"; + argv[2] = "--"; + argv[3] = module_name; /* check free_modprobe_argv() */ + argv[4] = NULL; + + return call_usermodehelper_fns(modprobe_path, argv, envp, + wait | UMH_KILLABLE, NULL, free_modprobe_argv, NULL); +free_argv: + kfree(argv); +out: + return -ENOMEM; +} + /** * __request_module - try to load a kernel module * @wait: wait (or not) for the operation to complete @@ -81,11 +118,6 @@ int __request_module(bool wait, const char *fmt, ...) char module_name[MODULE_NAME_LEN]; unsigned int max_modprobes; int ret; - char *argv[] = { modprobe_path, "-q", "--", module_name, NULL }; - static char *envp[] = { "HOME=/", - "TERM=linux", - "PATH=/sbin:/usr/sbin:/bin:/usr/bin", - NULL }; static atomic_t kmod_concurrent = ATOMIC_INIT(0); #define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */ static int kmod_loop_msg; @@ -128,9 +160,7 @@ int __request_module(bool wait, const char *fmt, ...) trace_module_request(module_name, wait, _RET_IP_); - ret = call_usermodehelper_fns(modprobe_path, argv, envp, - wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC, - NULL, NULL, NULL); + ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); atomic_dec(&kmod_concurrent); return ret; @@ -188,7 +218,7 @@ static int ____call_usermodehelper(void *data) /* Exec failed? */ fail: sub_info->retval = retval; - do_exit(0); + return 0; } void call_usermodehelper_freeinfo(struct subprocess_info *info) @@ -199,6 +229,19 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info) } EXPORT_SYMBOL(call_usermodehelper_freeinfo); +static void umh_complete(struct subprocess_info *sub_info) +{ + struct completion *comp = xchg(&sub_info->complete, NULL); + /* + * See call_usermodehelper_exec(). If xchg() returns NULL + * we own sub_info, the UMH_KILLABLE caller has gone away. + */ + if (comp) + complete(comp); + else + call_usermodehelper_freeinfo(sub_info); +} + /* Keventd can't block, but this (a child) can. */ static int wait_for_helper(void *data) { @@ -235,7 +278,7 @@ static int wait_for_helper(void *data) sub_info->retval = ret; } - complete(sub_info->complete); + umh_complete(sub_info); return 0; } @@ -244,7 +287,7 @@ static void __call_usermodehelper(struct work_struct *work) { struct subprocess_info *sub_info = container_of(work, struct subprocess_info, work); - enum umh_wait wait = sub_info->wait; + int wait = sub_info->wait & ~UMH_KILLABLE; pid_t pid; /* CLONE_VFORK: wait until the usermode helper has execve'd @@ -269,7 +312,7 @@ static void __call_usermodehelper(struct work_struct *work) case UMH_WAIT_EXEC: if (pid < 0) sub_info->retval = pid; - complete(sub_info->complete); + umh_complete(sub_info); } } @@ -435,8 +478,7 @@ EXPORT_SYMBOL(call_usermodehelper_setfns); * asynchronously if wait is not set, and runs as a child of keventd. * (ie. it runs with full root capabilities). */ -int call_usermodehelper_exec(struct subprocess_info *sub_info, - enum umh_wait wait) +int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { DECLARE_COMPLETION_ONSTACK(done); int retval = 0; @@ -456,9 +498,21 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, queue_work(khelper_wq, &sub_info->work); if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; + + if (wait & UMH_KILLABLE) { + retval = wait_for_completion_killable(&done); + if (!retval) + goto wait_done; + + /* umh_complete() will see NULL and free sub_info */ + if (xchg(&sub_info->complete, NULL)) + goto unlock; + /* fallthrough, umh_complete() was already called */ + } + wait_for_completion(&done); +wait_done: retval = sub_info->retval; - out: call_usermodehelper_freeinfo(sub_info); unlock: diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9788c0ec6f43..c62b8546cc90 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1334,8 +1334,10 @@ int __kprobes register_kprobe(struct kprobe *p) if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || ftrace_text_reserved(p->addr, p->addr) || - jump_label_text_reserved(p->addr, p->addr)) - goto fail_with_jump_label; + jump_label_text_reserved(p->addr, p->addr)) { + ret = -EINVAL; + goto cannot_probe; + } /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; @@ -1352,7 +1354,7 @@ int __kprobes register_kprobe(struct kprobe *p) * its code to prohibit unexpected unloading. */ if (unlikely(!try_module_get(probed_mod))) - goto fail_with_jump_label; + goto cannot_probe; /* * If the module freed .init.text, we couldn't insert @@ -1361,7 +1363,7 @@ int __kprobes register_kprobe(struct kprobe *p) if (within_module_init((unsigned long)p->addr, probed_mod) && probed_mod->state != MODULE_STATE_COMING) { module_put(probed_mod); - goto fail_with_jump_label; + goto cannot_probe; } /* ret will be updated by following code */ } @@ -1409,7 +1411,7 @@ out: return ret; -fail_with_jump_label: +cannot_probe: preempt_enable(); jump_label_unlock(); return ret; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 8889f7dd7c46..ea9ee4518c35 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -4176,7 +4176,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) printk("-------------------------------\n"); printk("%s:%d %s!\n", file, line, s); printk("\nother info that might help us debug this:\n\n"); - printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks); + printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n", + !rcu_lockdep_current_cpu_online() + ? "RCU used illegally from offline CPU!\n" + : rcu_is_cpu_idle() + ? "RCU used illegally from idle CPU!\n" + : "", + rcu_scheduler_active, debug_locks); /* * If a CPU is in the RCU-free window in idle (ie: in the section diff --git a/kernel/module.c b/kernel/module.c index 2c932760fd33..78ac6ec1e425 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -105,6 +105,7 @@ struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ /* Block module loading/unloading? */ int modules_disabled = 0; +core_param(nomodule, modules_disabled, bint, 0); /* Waiting for a module to finish initializing? */ static DECLARE_WAIT_QUEUE_HEAD(module_wq); @@ -903,6 +904,36 @@ static ssize_t show_refcnt(struct module_attribute *mattr, static struct module_attribute modinfo_refcnt = __ATTR(refcnt, 0444, show_refcnt, NULL); +void __module_get(struct module *module) +{ + if (module) { + preempt_disable(); + __this_cpu_inc(module->refptr->incs); + trace_module_get(module, _RET_IP_); + preempt_enable(); + } +} +EXPORT_SYMBOL(__module_get); + +bool try_module_get(struct module *module) +{ + bool ret = true; + + if (module) { + preempt_disable(); + + if (likely(module_is_live(module))) { + __this_cpu_inc(module->refptr->incs); + trace_module_get(module, _RET_IP_); + } else + ret = false; + + preempt_enable(); + } + return ret; +} +EXPORT_SYMBOL(try_module_get); + void module_put(struct module *module) { if (module) { @@ -2380,8 +2411,7 @@ static int copy_and_check(struct load_info *info, return -ENOEXEC; /* Suck in entire file: we'll want most of it. */ - /* vmalloc barfs on "unusual" numbers. Check here */ - if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) + if ((hdr = vmalloc(len)) == NULL) return -ENOMEM; if (copy_from_user(hdr, umod, len) != 0) { @@ -2922,7 +2952,8 @@ static struct module *load_module(void __user *umod, mutex_unlock(&module_mutex); /* Module is ready to execute: parsing args may do that. */ - err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL); + err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, + -32768, 32767, NULL); if (err < 0) goto unlink; diff --git a/kernel/mutex.c b/kernel/mutex.c index 89096dd8786f..a307cc9c9526 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); spin_lock_mutex(&lock->wait_lock, flags); } diff --git a/kernel/padata.c b/kernel/padata.c index b45259931512..6f10eb285ece 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -29,7 +29,6 @@ #include <linux/sysfs.h> #include <linux/rcupdate.h> -#define MAX_SEQ_NR (INT_MAX - NR_CPUS) #define MAX_OBJ_NUM 1000 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) @@ -43,18 +42,19 @@ static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) return target_cpu; } -static int padata_cpu_hash(struct padata_priv *padata) +static int padata_cpu_hash(struct parallel_data *pd) { int cpu_index; - struct parallel_data *pd; - - pd = padata->pd; /* * Hash the sequence numbers to the cpus by taking * seq_nr mod. number of cpus in use. */ - cpu_index = padata->seq_nr % cpumask_weight(pd->cpumask.pcpu); + + spin_lock(&pd->seq_lock); + cpu_index = pd->seq_nr % cpumask_weight(pd->cpumask.pcpu); + pd->seq_nr++; + spin_unlock(&pd->seq_lock); return padata_index_to_cpu(pd, cpu_index); } @@ -132,12 +132,7 @@ int padata_do_parallel(struct padata_instance *pinst, padata->pd = pd; padata->cb_cpu = cb_cpu; - if (unlikely(atomic_read(&pd->seq_nr) == pd->max_seq_nr)) - atomic_set(&pd->seq_nr, -1); - - padata->seq_nr = atomic_inc_return(&pd->seq_nr); - - target_cpu = padata_cpu_hash(padata); + target_cpu = padata_cpu_hash(pd); queue = per_cpu_ptr(pd->pqueue, target_cpu); spin_lock(&queue->parallel.lock); @@ -173,7 +168,7 @@ EXPORT_SYMBOL(padata_do_parallel); static struct padata_priv *padata_get_next(struct parallel_data *pd) { int cpu, num_cpus; - int next_nr, next_index; + unsigned int next_nr, next_index; struct padata_parallel_queue *queue, *next_queue; struct padata_priv *padata; struct padata_list *reorder; @@ -189,14 +184,6 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd) cpu = padata_index_to_cpu(pd, next_index); next_queue = per_cpu_ptr(pd->pqueue, cpu); - if (unlikely(next_nr > pd->max_seq_nr)) { - next_nr = next_nr - pd->max_seq_nr - 1; - next_index = next_nr % num_cpus; - cpu = padata_index_to_cpu(pd, next_index); - next_queue = per_cpu_ptr(pd->pqueue, cpu); - pd->processed = 0; - } - padata = NULL; reorder = &next_queue->reorder; @@ -205,8 +192,6 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd) padata = list_entry(reorder->list.next, struct padata_priv, list); - BUG_ON(next_nr != padata->seq_nr); - spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); @@ -230,6 +215,7 @@ out: static void padata_reorder(struct parallel_data *pd) { + int cb_cpu; struct padata_priv *padata; struct padata_serial_queue *squeue; struct padata_instance *pinst = pd->pinst; @@ -270,13 +256,14 @@ static void padata_reorder(struct parallel_data *pd) return; } - squeue = per_cpu_ptr(pd->squeue, padata->cb_cpu); + cb_cpu = padata->cb_cpu; + squeue = per_cpu_ptr(pd->squeue, cb_cpu); spin_lock(&squeue->serial.lock); list_add_tail(&padata->list, &squeue->serial.list); spin_unlock(&squeue->serial.lock); - queue_work_on(padata->cb_cpu, pinst->wq, &squeue->work); + queue_work_on(cb_cpu, pinst->wq, &squeue->work); } spin_unlock_bh(&pd->lock); @@ -400,7 +387,7 @@ static void padata_init_squeues(struct parallel_data *pd) /* Initialize all percpu queues used by parallel workers */ static void padata_init_pqueues(struct parallel_data *pd) { - int cpu_index, num_cpus, cpu; + int cpu_index, cpu; struct padata_parallel_queue *pqueue; cpu_index = 0; @@ -415,9 +402,6 @@ static void padata_init_pqueues(struct parallel_data *pd) INIT_WORK(&pqueue->work, padata_parallel_worker); atomic_set(&pqueue->num_obj, 0); } - - num_cpus = cpumask_weight(pd->cpumask.pcpu); - pd->max_seq_nr = num_cpus ? (MAX_SEQ_NR / num_cpus) * num_cpus - 1 : 0; } /* Allocate and initialize the internal cpumask dependend resources. */ @@ -444,7 +428,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, padata_init_pqueues(pd); padata_init_squeues(pd); setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); - atomic_set(&pd->seq_nr, -1); + pd->seq_nr = 0; atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 0); pd->pinst = pinst; diff --git a/kernel/params.c b/kernel/params.c index 4bc965d8a1fe..f37d82631347 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -15,7 +15,6 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> @@ -88,6 +87,8 @@ static int parse_one(char *param, char *val, const struct kernel_param *params, unsigned num_params, + s16 min_level, + s16 max_level, int (*handle_unknown)(char *param, char *val)) { unsigned int i; @@ -96,6 +97,9 @@ static int parse_one(char *param, /* Find parameter */ for (i = 0; i < num_params; i++) { if (parameq(param, params[i].name)) { + if (params[i].level < min_level + || params[i].level > max_level) + return 0; /* No one handled NULL, so do it here. */ if (!val && params[i].ops->set != param_set_bool && params[i].ops->set != param_set_bint) @@ -175,6 +179,8 @@ int parse_args(const char *name, char *args, const struct kernel_param *params, unsigned num, + s16 min_level, + s16 max_level, int (*unknown)(char *param, char *val)) { char *param, *val; @@ -190,7 +196,8 @@ int parse_args(const char *name, args = next_arg(args, ¶m, &val); irq_was_disabled = irqs_disabled(); - ret = parse_one(param, val, params, num, unknown); + ret = parse_one(param, val, params, num, + min_level, max_level, unknown); if (irq_was_disabled && !irqs_disabled()) { printk(KERN_WARNING "parse_args(): option '%s' enabled " "irq's!\n", param); @@ -298,35 +305,18 @@ EXPORT_SYMBOL(param_ops_charp); /* Actually could be a bool or an int, for historical reasons. */ int param_set_bool(const char *val, const struct kernel_param *kp) { - bool v; - int ret; - /* No equals means "set"... */ if (!val) val = "1"; /* One of =[yYnN01] */ - ret = strtobool(val, &v); - if (ret) - return ret; - - if (kp->flags & KPARAM_ISBOOL) - *(bool *)kp->arg = v; - else - *(int *)kp->arg = v; - return 0; + return strtobool(val, kp->arg); } EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { - bool val; - if (kp->flags & KPARAM_ISBOOL) - val = *(bool *)kp->arg; - else - val = *(int *)kp->arg; - /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", val ? 'Y' : 'N'); + return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -344,7 +334,6 @@ int param_set_invbool(const char *val, const struct kernel_param *kp) struct kernel_param dummy; dummy.arg = &boolval; - dummy.flags = KPARAM_ISBOOL; ret = param_set_bool(val, &dummy); if (ret == 0) *(bool *)kp->arg = !boolval; @@ -373,7 +362,6 @@ int param_set_bint(const char *val, const struct kernel_param *kp) /* Match bool exactly, by re-using it. */ boolkp = *kp; boolkp.arg = &v; - boolkp.flags |= KPARAM_ISBOOL; ret = param_set_bool(val, &boolkp); if (ret == 0) @@ -394,7 +382,7 @@ static int param_array(const char *name, unsigned int min, unsigned int max, void *elem, int elemsize, int (*set)(const char *, const struct kernel_param *kp), - u16 flags, + s16 level, unsigned int *num) { int ret; @@ -404,7 +392,7 @@ static int param_array(const char *name, /* Get the name right for errors. */ kp.name = name; kp.arg = elem; - kp.flags = flags; + kp.level = level; *num = 0; /* We expect a comma-separated list of values. */ @@ -445,7 +433,7 @@ static int param_array_set(const char *val, const struct kernel_param *kp) unsigned int temp_num; return param_array(kp->name, val, 1, arr->max, arr->elem, - arr->elemsize, arr->ops->set, kp->flags, + arr->elemsize, arr->ops->set, kp->level, arr->num ?: &temp_num); } diff --git a/kernel/pid.c b/kernel/pid.c index ce8e00deaccb..9f08dfabaf13 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -543,12 +543,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) */ void __init pidhash_init(void) { - int i, pidhash_size; + unsigned int i, pidhash_size; pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18, HASH_EARLY | HASH_SMALL, &pidhash_shift, NULL, 4096); - pidhash_size = 1 << pidhash_shift; + pidhash_size = 1U << pidhash_shift; for (i = 0; i < pidhash_size; i++) INIT_HLIST_HEAD(&pid_hash[i]); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index a8968396046d..57bc1fd35b3c 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -15,6 +15,7 @@ #include <linux/acct.h> #include <linux/slab.h> #include <linux/proc_fs.h> +#include <linux/reboot.h> #define BITS_PER_PAGE (PAGE_SIZE*8) @@ -168,13 +169,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) while (nr > 0) { rcu_read_lock(); - /* - * Any nested-container's init processes won't ignore the - * SEND_SIG_NOINFO signal, see send_signal()->si_fromuser(). - */ task = pid_task(find_vpid(nr), PIDTYPE_PID); - if (task) - send_sig_info(SIGKILL, SEND_SIG_NOINFO, task); + if (task && !__fatal_signal_pending(task)) + send_sig_info(SIGKILL, SEND_SIG_FORCED, task); rcu_read_unlock(); @@ -187,6 +184,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) rc = sys_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); + if (pid_ns->reboot) + current->signal->group_exit_code = pid_ns->reboot; + acct_exit_ns(pid_ns); return; } @@ -221,6 +221,35 @@ static struct ctl_table pid_ns_ctl_table[] = { static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; +int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) +{ + if (pid_ns == &init_pid_ns) + return 0; + + switch (cmd) { + case LINUX_REBOOT_CMD_RESTART2: + case LINUX_REBOOT_CMD_RESTART: + pid_ns->reboot = SIGHUP; + break; + + case LINUX_REBOOT_CMD_POWER_OFF: + case LINUX_REBOOT_CMD_HALT: + pid_ns->reboot = SIGINT; + break; + default: + return -EINVAL; + } + + read_lock(&tasklist_lock); + force_sig(SIGKILL, pid_ns->child_reaper); + read_unlock(&tasklist_lock); + + do_exit(0); + + /* Not reached */ + return 0; +} + static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 07e0e28ffba7..66d808ec5252 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -1,7 +1,8 @@ ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG -obj-$(CONFIG_PM) += main.o qos.o +obj-y += qos.o +obj-$(CONFIG_PM) += main.o obj-$(CONFIG_VT_CONSOLE_SLEEP) += console.o obj-$(CONFIG_FREEZER) += process.o obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 6d6d28870335..0a186cfde788 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -245,8 +245,8 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop, * create_image - Create a hibernation image. * @platform_mode: Whether or not to use the platform driver. * - * Execute device drivers' .freeze_noirq() callbacks, create a hibernation image - * and execute the drivers' .thaw_noirq() callbacks. + * Execute device drivers' "late" and "noirq" freeze callbacks, create a + * hibernation image and run the drivers' "noirq" and "early" thaw callbacks. * * Control reappears in this routine after the subsequent restore. */ @@ -254,7 +254,7 @@ static int create_image(int platform_mode) { int error; - error = dpm_suspend_noirq(PMSG_FREEZE); + error = dpm_suspend_end(PMSG_FREEZE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting hibernation\n"); @@ -306,7 +306,7 @@ static int create_image(int platform_mode) Platform_finish: platform_finish(platform_mode); - dpm_resume_noirq(in_suspend ? + dpm_resume_start(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); return error; @@ -343,13 +343,13 @@ int hibernation_snapshot(int platform_mode) * successful freezer test. */ freezer_test_done = true; - goto Cleanup; + goto Thaw; } error = dpm_prepare(PMSG_FREEZE); if (error) { dpm_complete(PMSG_RECOVER); - goto Cleanup; + goto Thaw; } suspend_console(); @@ -385,6 +385,8 @@ int hibernation_snapshot(int platform_mode) platform_end(platform_mode); return error; + Thaw: + thaw_kernel_threads(); Cleanup: swsusp_free(); goto Close; @@ -394,16 +396,16 @@ int hibernation_snapshot(int platform_mode) * resume_target_kernel - Restore system state from a hibernation image. * @platform_mode: Whether or not to use the platform driver. * - * Execute device drivers' .freeze_noirq() callbacks, restore the contents of - * highmem that have not been restored yet from the image and run the low-level - * code that will restore the remaining contents of memory and switch to the - * just restored target kernel. + * Execute device drivers' "noirq" and "late" freeze callbacks, restore the + * contents of highmem that have not been restored yet from the image and run + * the low-level code that will restore the remaining contents of memory and + * switch to the just restored target kernel. */ static int resume_target_kernel(bool platform_mode) { int error; - error = dpm_suspend_noirq(PMSG_QUIESCE); + error = dpm_suspend_end(PMSG_QUIESCE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting resume\n"); @@ -460,7 +462,7 @@ static int resume_target_kernel(bool platform_mode) Cleanup: platform_restore_cleanup(platform_mode); - dpm_resume_noirq(PMSG_RECOVER); + dpm_resume_start(PMSG_RECOVER); return error; } @@ -518,7 +520,7 @@ int hibernation_platform_enter(void) goto Resume_devices; } - error = dpm_suspend_noirq(PMSG_HIBERNATE); + error = dpm_suspend_end(PMSG_HIBERNATE); if (error) goto Resume_devices; @@ -549,7 +551,7 @@ int hibernation_platform_enter(void) Platform_finish: hibernation_ops->finish(); - dpm_resume_noirq(PMSG_RESTORE); + dpm_resume_start(PMSG_RESTORE); Resume_devices: entering_platform_hibernation = false; @@ -616,7 +618,7 @@ int hibernate(void) /* Allocate memory management structures */ error = create_basic_memory_bitmaps(); if (error) - goto Exit; + goto Enable_umh; printk(KERN_INFO "PM: Syncing filesystems ... "); sys_sync(); @@ -624,15 +626,11 @@ int hibernate(void) error = freeze_processes(); if (error) - goto Finish; + goto Free_bitmaps; error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM); - if (error) - goto Thaw; - if (freezer_test_done) { - freezer_test_done = false; + if (error || freezer_test_done) goto Thaw; - } if (in_suspend) { unsigned int flags = 0; @@ -657,8 +655,13 @@ int hibernate(void) Thaw: thaw_processes(); - Finish: + + /* Don't bother checking whether freezer_test_done is true */ + freezer_test_done = false; + + Free_bitmaps: free_basic_memory_bitmaps(); + Enable_umh: usermodehelper_enable(); Exit: pm_notifier_call_chain(PM_POST_HIBERNATION); diff --git a/kernel/power/main.c b/kernel/power/main.c index 9824b41e5a18..1c12581f1c62 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -165,16 +165,20 @@ static int suspend_stats_show(struct seq_file *s, void *unused) last_errno %= REC_FAILED_NUM; last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1; last_step %= REC_FAILED_NUM; - seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n" - "%s: %d\n%s: %d\n%s: %d\n%s: %d\n", + seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n" + "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n", "success", suspend_stats.success, "fail", suspend_stats.fail, "failed_freeze", suspend_stats.failed_freeze, "failed_prepare", suspend_stats.failed_prepare, "failed_suspend", suspend_stats.failed_suspend, + "failed_suspend_late", + suspend_stats.failed_suspend_late, "failed_suspend_noirq", suspend_stats.failed_suspend_noirq, "failed_resume", suspend_stats.failed_resume, + "failed_resume_early", + suspend_stats.failed_resume_early, "failed_resume_noirq", suspend_stats.failed_resume_noirq); seq_printf(s, "failures:\n last_failed_dev:\t%-s\n", @@ -287,16 +291,10 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, #ifdef CONFIG_SUSPEND for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) { - if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) + if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) { + error = pm_suspend(state); break; - } - if (state < PM_SUSPEND_MAX && *s) { - error = enter_state(state); - if (error) { - suspend_stats.fail++; - dpm_save_failed_errno(error); - } else - suspend_stats.success++; + } } #endif diff --git a/kernel/power/power.h b/kernel/power/power.h index 21724eee5206..98f3622d7407 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -177,13 +177,11 @@ extern const char *const pm_states[]; extern bool valid_state(suspend_state_t state); extern int suspend_devices_and_enter(suspend_state_t state); -extern int enter_state(suspend_state_t state); #else /* !CONFIG_SUSPEND */ static inline int suspend_devices_and_enter(suspend_state_t state) { return -ENOSYS; } -static inline int enter_state(suspend_state_t state) { return -ENOSYS; } static inline bool valid_state(suspend_state_t state) { return false; } #endif /* !CONFIG_SUSPEND */ @@ -234,16 +232,14 @@ static inline int suspend_freeze_processes(void) int error; error = freeze_processes(); - /* * freeze_processes() automatically thaws every task if freezing * fails. So we need not do anything extra upon error. */ if (error) - goto Finish; + return error; error = freeze_kernel_threads(); - /* * freeze_kernel_threads() thaws only kernel threads upon freezing * failure. So we have to thaw the userspace tasks ourselves. @@ -251,7 +247,6 @@ static inline int suspend_freeze_processes(void) if (error) thaw_processes(); - Finish: return error; } diff --git a/kernel/power/process.c b/kernel/power/process.c index 7e426459e60a..0d2aeb226108 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -53,11 +53,9 @@ static int try_to_freeze_tasks(bool user_only) * It is "frozen enough". If the task does wake * up, it will immediately call try_to_freeze. * - * Because freeze_task() goes through p's - * scheduler lock after setting TIF_FREEZE, it's - * guaranteed that either we see TASK_RUNNING or - * try_to_stop() after schedule() in ptrace/signal - * stop sees TIF_FREEZE. + * Because freeze_task() goes through p's scheduler lock, it's + * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING + * transition can't race with task state testing here. */ if (!task_is_stopped_or_traced(p) && !freezer_should_skip(p)) @@ -98,13 +96,15 @@ static int try_to_freeze_tasks(bool user_only) elapsed_csecs / 100, elapsed_csecs % 100, todo - wq_busy, wq_busy); - read_lock(&tasklist_lock); - do_each_thread(g, p) { - if (!wakeup && !freezer_should_skip(p) && - p != current && freezing(p) && !frozen(p)) - sched_show_task(p); - } while_each_thread(g, p); - read_unlock(&tasklist_lock); + if (!wakeup) { + read_lock(&tasklist_lock); + do_each_thread(g, p) { + if (p != current && !freezer_should_skip(p) + && freezing(p) && !frozen(p)) + sched_show_task(p); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); + } } else { printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100, elapsed_csecs % 100); diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 995e3bd3417b..d6d6dbd1ecc0 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -469,21 +469,18 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, static int __init pm_qos_power_init(void) { int ret = 0; + int i; - ret = register_pm_qos_misc(&cpu_dma_pm_qos); - if (ret < 0) { - printk(KERN_ERR "pm_qos_param: cpu_dma_latency setup failed\n"); - return ret; - } - ret = register_pm_qos_misc(&network_lat_pm_qos); - if (ret < 0) { - printk(KERN_ERR "pm_qos_param: network_latency setup failed\n"); - return ret; + BUILD_BUG_ON(ARRAY_SIZE(pm_qos_array) != PM_QOS_NUM_CLASSES); + + for (i = 1; i < PM_QOS_NUM_CLASSES; i++) { + ret = register_pm_qos_misc(pm_qos_array[i]); + if (ret < 0) { + printk(KERN_ERR "pm_qos_param: %s setup failed\n", + pm_qos_array[i]->name); + return ret; + } } - ret = register_pm_qos_misc(&network_throughput_pm_qos); - if (ret < 0) - printk(KERN_ERR - "pm_qos_param: network_throughput setup failed\n"); return ret; } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 6a768e537001..0de28576807d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -711,9 +711,10 @@ static void mark_nosave_pages(struct memory_bitmap *bm) list_for_each_entry(region, &nosave_regions, list) { unsigned long pfn; - pr_debug("PM: Marking nosave pages: %016lx - %016lx\n", - region->start_pfn << PAGE_SHIFT, - region->end_pfn << PAGE_SHIFT); + pr_debug("PM: Marking nosave pages: [mem %#010llx-%#010llx]\n", + (unsigned long long) region->start_pfn << PAGE_SHIFT, + ((unsigned long long) region->end_pfn << PAGE_SHIFT) + - 1); for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++) if (pfn_valid(pfn)) { @@ -1000,20 +1001,20 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) s_page = pfn_to_page(src_pfn); d_page = pfn_to_page(dst_pfn); if (PageHighMem(s_page)) { - src = kmap_atomic(s_page, KM_USER0); - dst = kmap_atomic(d_page, KM_USER1); + src = kmap_atomic(s_page); + dst = kmap_atomic(d_page); do_copy_page(dst, src); - kunmap_atomic(dst, KM_USER1); - kunmap_atomic(src, KM_USER0); + kunmap_atomic(dst); + kunmap_atomic(src); } else { if (PageHighMem(d_page)) { /* Page pointed to by src may contain some kernel * data modified by kmap_atomic() */ safe_copy_page(buffer, s_page); - dst = kmap_atomic(d_page, KM_USER0); + dst = kmap_atomic(d_page); copy_page(dst, buffer); - kunmap_atomic(dst, KM_USER0); + kunmap_atomic(dst); } else { safe_copy_page(page_address(d_page), s_page); } @@ -1728,9 +1729,9 @@ int snapshot_read_next(struct snapshot_handle *handle) */ void *kaddr; - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); copy_page(buffer, kaddr); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); handle->buffer = buffer; } else { handle->buffer = page_address(page); @@ -2014,9 +2015,9 @@ static void copy_last_highmem_page(void) if (last_highmem_page) { void *dst; - dst = kmap_atomic(last_highmem_page, KM_USER0); + dst = kmap_atomic(last_highmem_page); copy_page(dst, buffer); - kunmap_atomic(dst, KM_USER0); + kunmap_atomic(dst); last_highmem_page = NULL; } } @@ -2309,13 +2310,13 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf) { void *kaddr1, *kaddr2; - kaddr1 = kmap_atomic(p1, KM_USER0); - kaddr2 = kmap_atomic(p2, KM_USER1); + kaddr1 = kmap_atomic(p1); + kaddr2 = kmap_atomic(p2); copy_page(buf, kaddr1); copy_page(kaddr1, kaddr2); copy_page(kaddr2, buf); - kunmap_atomic(kaddr2, KM_USER1); - kunmap_atomic(kaddr1, KM_USER0); + kunmap_atomic(kaddr2); + kunmap_atomic(kaddr1); } /** diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 4fd51beed879..88e5c967370d 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -37,8 +37,8 @@ const char *const pm_states[PM_SUSPEND_MAX] = { static const struct platform_suspend_ops *suspend_ops; /** - * suspend_set_ops - Set the global suspend method table. - * @ops: Pointer to ops structure. + * suspend_set_ops - Set the global suspend method table. + * @ops: Suspend operations to use. */ void suspend_set_ops(const struct platform_suspend_ops *ops) { @@ -58,11 +58,11 @@ bool valid_state(suspend_state_t state) } /** - * suspend_valid_only_mem - generic memory-only valid callback + * suspend_valid_only_mem - Generic memory-only valid callback. * - * Platform drivers that implement mem suspend only and only need - * to check for that in their .valid callback can use this instead - * of rolling their own .valid callback. + * Platform drivers that implement mem suspend only and only need to check for + * that in their .valid() callback can use this instead of rolling their own + * .valid() callback. */ int suspend_valid_only_mem(suspend_state_t state) { @@ -83,10 +83,11 @@ static int suspend_test(int level) } /** - * suspend_prepare - Do prep work before entering low-power state. + * suspend_prepare - Prepare for entering system sleep state. * - * This is common code that is called for each state that we're entering. - * Run suspend notifiers, allocate a console and stop all processes. + * Common code run for every system sleep state that can be entered (except for + * hibernation). Run suspend notifiers, allocate the "suspend" console and + * freeze processes. */ static int suspend_prepare(void) { @@ -131,9 +132,9 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void) } /** - * suspend_enter - enter the desired system sleep state. - * @state: State to enter - * @wakeup: Returns information that suspend should not be entered again. + * suspend_enter - Make the system enter the given sleep state. + * @state: System sleep state to enter. + * @wakeup: Returns information that the sleep state should not be re-entered. * * This function should be called after devices have been suspended. */ @@ -147,7 +148,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) goto Platform_finish; } - error = dpm_suspend_noirq(PMSG_SUSPEND); + error = dpm_suspend_end(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to power down\n"); goto Platform_finish; @@ -189,7 +190,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (suspend_ops->wake) suspend_ops->wake(); - dpm_resume_noirq(PMSG_RESUME); + dpm_resume_start(PMSG_RESUME); Platform_finish: if (suspend_ops->finish) @@ -199,9 +200,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) } /** - * suspend_devices_and_enter - suspend devices and enter the desired system - * sleep state. - * @state: state to enter + * suspend_devices_and_enter - Suspend devices and enter system sleep state. + * @state: System sleep state to enter. */ int suspend_devices_and_enter(suspend_state_t state) { @@ -251,10 +251,10 @@ int suspend_devices_and_enter(suspend_state_t state) } /** - * suspend_finish - Do final work before exiting suspend sequence. + * suspend_finish - Clean up before finishing the suspend sequence. * - * Call platform code to clean up, restart processes, and free the - * console that we've allocated. This is not called for suspend-to-disk. + * Call platform code to clean up, restart processes, and free the console that + * we've allocated. This routine is not called for hibernation. */ static void suspend_finish(void) { @@ -265,16 +265,14 @@ static void suspend_finish(void) } /** - * enter_state - Do common work of entering low-power state. - * @state: pm_state structure for state we're entering. + * enter_state - Do common work needed to enter system sleep state. + * @state: System sleep state to enter. * - * Make sure we're the only ones trying to enter a sleep state. Fail - * if someone has beat us to it, since we don't want anything weird to - * happen when we wake up. - * Then, do the setup for suspend, enter the state, and cleaup (after - * we've woken up). + * Make sure that no one else is trying to put the system into a sleep state. + * Fail if that's not the case. Otherwise, prepare for system suspend, make the + * system enter the given sleep state and clean up after wakeup. */ -int enter_state(suspend_state_t state) +static int enter_state(suspend_state_t state) { int error; @@ -310,24 +308,26 @@ int enter_state(suspend_state_t state) } /** - * pm_suspend - Externally visible function for suspending system. - * @state: Enumerated value of state to enter. + * pm_suspend - Externally visible function for suspending the system. + * @state: System sleep state to enter. * - * Determine whether or not value is within range, get state - * structure, and enter (above). + * Check if the value of @state represents one of the supported states, + * execute enter_state() and update system suspend statistics. */ int pm_suspend(suspend_state_t state) { - int ret; - if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX) { - ret = enter_state(state); - if (ret) { - suspend_stats.fail++; - dpm_save_failed_errno(ret); - } else - suspend_stats.success++; - return ret; + int error; + + if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) + return -EINVAL; + + error = enter_state(state); + if (error) { + suspend_stats.fail++; + dpm_save_failed_errno(error); + } else { + suspend_stats.success++; } - return -EINVAL; + return error; } EXPORT_SYMBOL(pm_suspend); diff --git a/kernel/power/user.c b/kernel/power/user.c index 3e100075b13c..33c4329205af 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -249,16 +249,10 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, } pm_restore_gfp_mask(); error = hibernation_snapshot(data->platform_support); - if (error) { - thaw_kernel_threads(); - } else { + if (!error) { error = put_user(in_suspend, (int __user *)arg); - if (!error && !freezer_test_done) - data->ready = 1; - if (freezer_test_done) { - freezer_test_done = false; - thaw_kernel_threads(); - } + data->ready = !freezer_test_done && !error; + freezer_test_done = false; } break; diff --git a/kernel/printk.c b/kernel/printk.c index 13c0a1143f49..b663c2c95d39 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -44,6 +44,9 @@ #include <asm/uaccess.h> +#define CREATE_TRACE_POINTS +#include <trace/events/printk.h> + /* * Architectures can override it: */ @@ -542,6 +545,8 @@ MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" static void _call_console_drivers(unsigned start, unsigned end, int msg_log_level) { + trace_console(&LOG_BUF(0), start, end, log_buf_len); + if ((msg_log_level < console_loglevel || ignore_loglevel) && console_drivers && start != end) { if ((start & LOG_BUF_MASK) > (end & LOG_BUF_MASK)) { @@ -702,6 +707,9 @@ static bool printk_time = 0; #endif module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); +static bool always_kmsg_dump; +module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); + /* Check if we have any console registered that can be called early in boot. */ static int have_callable_console(void) { @@ -1208,13 +1216,27 @@ int is_console_locked(void) return console_locked; } +/* + * Delayed printk facility, for scheduler-internal messages: + */ +#define PRINTK_BUF_SIZE 512 + +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_SCHED 0x02 + static DEFINE_PER_CPU(int, printk_pending); +static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); void printk_tick(void) { if (__this_cpu_read(printk_pending)) { - __this_cpu_write(printk_pending, 0); - wake_up_interruptible(&log_wait); + int pending = __this_cpu_xchg(printk_pending, 0); + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); + } + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); } } @@ -1228,7 +1250,7 @@ int printk_needs_cpu(int cpu) void wake_up_klogd(void) { if (waitqueue_active(&log_wait)) - this_cpu_write(printk_pending, 1); + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); } /** @@ -1621,6 +1643,26 @@ late_initcall(printk_late_init); #if defined CONFIG_PRINTK +int printk_sched(const char *fmt, ...) +{ + unsigned long flags; + va_list args; + char *buf; + int r; + + local_irq_save(flags); + buf = __get_cpu_var(printk_sched_buf); + + va_start(args, fmt); + r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args); + va_end(args); + + __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); + local_irq_restore(flags); + + return r; +} + /* * printk rate limiting, lifted from the networking subsystem. * @@ -1732,6 +1774,9 @@ void kmsg_dump(enum kmsg_dump_reason reason) unsigned long l1, l2; unsigned long flags; + if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) + return; + /* Theoretically, the log could move on after we do this, but there's not a lot we can do about that. The new messages will overwrite the start of what we dump. */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 00ab2ca5ed11..ee8d49b9c309 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -231,26 +231,22 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) } static int ptrace_attach(struct task_struct *task, long request, + unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; - /* - * SEIZE will enable new ptrace behaviors which will be implemented - * gradually. SEIZE_DEVEL is used to prevent applications - * expecting full SEIZE behaviors trapping on kernel commits which - * are still in the process of implementing them. - * - * Only test programs for new ptrace behaviors being implemented - * should set SEIZE_DEVEL. If unset, SEIZE will fail with -EIO. - * - * Once SEIZE behaviors are completely implemented, this flag and - * the following test will be removed. - */ retval = -EIO; - if (seize && !(flags & PTRACE_SEIZE_DEVEL)) - goto out; + if (seize) { + if (addr != 0) + goto out; + if (flags & ~(unsigned long)PTRACE_O_MASK) + goto out; + flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); + } else { + flags = PT_PTRACED; + } audit_ptrace(task); @@ -262,7 +258,7 @@ static int ptrace_attach(struct task_struct *task, long request, /* * Protect exec's credential calculations against our interference; - * interference; SUID, SGID and LSM creds get determined differently + * SUID, SGID and LSM creds get determined differently * under ptrace. */ retval = -ERESTARTNOINTR; @@ -282,11 +278,11 @@ static int ptrace_attach(struct task_struct *task, long request, if (task->ptrace) goto unlock_tasklist; - task->ptrace = PT_PTRACED; if (seize) - task->ptrace |= PT_SEIZED; + flags |= PT_SEIZED; if (ns_capable(task_user_ns(task), CAP_SYS_PTRACE)) - task->ptrace |= PT_PTRACE_CAP; + flags |= PT_PTRACE_CAP; + task->ptrace = flags; __ptrace_link(task, current); @@ -528,30 +524,18 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds static int ptrace_setoptions(struct task_struct *child, unsigned long data) { - child->ptrace &= ~PT_TRACE_MASK; + unsigned flags; - if (data & PTRACE_O_TRACESYSGOOD) - child->ptrace |= PT_TRACESYSGOOD; - - if (data & PTRACE_O_TRACEFORK) - child->ptrace |= PT_TRACE_FORK; - - if (data & PTRACE_O_TRACEVFORK) - child->ptrace |= PT_TRACE_VFORK; - - if (data & PTRACE_O_TRACECLONE) - child->ptrace |= PT_TRACE_CLONE; - - if (data & PTRACE_O_TRACEEXEC) - child->ptrace |= PT_TRACE_EXEC; - - if (data & PTRACE_O_TRACEVFORKDONE) - child->ptrace |= PT_TRACE_VFORK_DONE; + if (data & ~(unsigned long)PTRACE_O_MASK) + return -EINVAL; - if (data & PTRACE_O_TRACEEXIT) - child->ptrace |= PT_TRACE_EXIT; + /* Avoid intermediate state when all opts are cleared */ + flags = child->ptrace; + flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); + flags |= (data << PT_OPT_FLAG_SHIFT); + child->ptrace = flags; - return (data & ~PTRACE_O_MASK) ? -EINVAL : 0; + return 0; } static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) @@ -891,7 +875,7 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { - ret = ptrace_attach(child, request, data); + ret = ptrace_attach(child, request, addr, data); /* * Some architectures need to do book-keeping after * a ptrace attach. @@ -1034,7 +1018,7 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { - ret = ptrace_attach(child, request, data); + ret = ptrace_attach(child, request, addr, data); /* * Some architectures need to do book-keeping after * a ptrace attach. diff --git a/kernel/rcu.h b/kernel/rcu.h index aa88baab5f78..8ba99cdc6515 100644 --- a/kernel/rcu.h +++ b/kernel/rcu.h @@ -33,8 +33,27 @@ * Process-level increment to ->dynticks_nesting field. This allows for * architectures that use half-interrupts and half-exceptions from * process context. + * + * DYNTICK_TASK_NEST_MASK defines a field of width DYNTICK_TASK_NEST_WIDTH + * that counts the number of process-based reasons why RCU cannot + * consider the corresponding CPU to be idle, and DYNTICK_TASK_NEST_VALUE + * is the value used to increment or decrement this field. + * + * The rest of the bits could in principle be used to count interrupts, + * but this would mean that a negative-one value in the interrupt + * field could incorrectly zero out the DYNTICK_TASK_NEST_MASK field. + * We therefore provide a two-bit guard field defined by DYNTICK_TASK_MASK + * that is set to DYNTICK_TASK_FLAG upon initial exit from idle. + * The DYNTICK_TASK_EXIT_IDLE value is thus the combined value used upon + * initial exit from idle. */ -#define DYNTICK_TASK_NESTING (LLONG_MAX / 2 - 1) +#define DYNTICK_TASK_NEST_WIDTH 7 +#define DYNTICK_TASK_NEST_VALUE ((LLONG_MAX >> DYNTICK_TASK_NEST_WIDTH) + 1) +#define DYNTICK_TASK_NEST_MASK (LLONG_MAX - DYNTICK_TASK_NEST_VALUE + 1) +#define DYNTICK_TASK_FLAG ((DYNTICK_TASK_NEST_VALUE / 8) * 2) +#define DYNTICK_TASK_MASK ((DYNTICK_TASK_NEST_VALUE / 8) * 3) +#define DYNTICK_TASK_EXIT_IDLE (DYNTICK_TASK_NEST_VALUE + \ + DYNTICK_TASK_FLAG) /* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally @@ -50,7 +69,6 @@ extern struct debug_obj_descr rcuhead_debug_descr; static inline void debug_rcu_head_queue(struct rcu_head *head) { - WARN_ON_ONCE((unsigned long)head & 0x3); debug_object_activate(head, &rcuhead_debug_descr); debug_object_active_state(head, &rcuhead_debug_descr, STATE_RCU_HEAD_READY, @@ -76,16 +94,18 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) extern void kfree(const void *); -static inline void __rcu_reclaim(char *rn, struct rcu_head *head) +static inline bool __rcu_reclaim(char *rn, struct rcu_head *head) { unsigned long offset = (unsigned long)head->func; if (__is_kfree_rcu_offset(offset)) { RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset)); kfree((void *)head - offset); + return 1; } else { RCU_TRACE(trace_rcu_invoke_callback(rn, head)); head->func(head); + return 0; } } diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 2bc4e135ff23..a86f1741cc27 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -88,6 +88,9 @@ EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); * section. * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. */ int rcu_read_lock_bh_held(void) { @@ -95,6 +98,8 @@ int rcu_read_lock_bh_held(void) return 1; if (rcu_is_cpu_idle()) return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 977296dca0a4..37a5444204d2 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -53,7 +53,7 @@ static void __call_rcu(struct rcu_head *head, #include "rcutiny_plugin.h" -static long long rcu_dynticks_nesting = DYNTICK_TASK_NESTING; +static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ static void rcu_idle_enter_common(long long oldval) @@ -88,10 +88,16 @@ void rcu_idle_enter(void) local_irq_save(flags); oldval = rcu_dynticks_nesting; - rcu_dynticks_nesting = 0; + WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0); + if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == + DYNTICK_TASK_NEST_VALUE) + rcu_dynticks_nesting = 0; + else + rcu_dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; rcu_idle_enter_common(oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_enter); /* * Exit an interrupt handler towards idle. @@ -140,11 +146,15 @@ void rcu_idle_exit(void) local_irq_save(flags); oldval = rcu_dynticks_nesting; - WARN_ON_ONCE(oldval != 0); - rcu_dynticks_nesting = DYNTICK_TASK_NESTING; + WARN_ON_ONCE(rcu_dynticks_nesting < 0); + if (rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) + rcu_dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + else + rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_idle_exit_common(oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_exit); /* * Enter an interrupt handler, moving away from idle. @@ -258,7 +268,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* If no RCU callbacks ready to invoke, just return. */ if (&rcp->rcucblist == rcp->donetail) { - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1)); RCU_TRACE(trace_rcu_batch_end(rcp->name, 0, ACCESS_ONCE(rcp->rcucblist), need_resched(), @@ -269,7 +279,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1)); list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; *rcp->donetail = NULL; @@ -319,6 +329,10 @@ static void rcu_process_callbacks(struct softirq_action *unused) */ void synchronize_sched(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU read-side critical section"); cond_resched(); } EXPORT_SYMBOL_GPL(synchronize_sched); diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 9cb1ae4aabdd..22ecea0dfb62 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,6 +132,7 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; +static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -146,6 +147,16 @@ static int rcu_cpu_blocking_cur_gp(void) /* * Check for a running RCU reader. Because there is only one CPU, * there can be but one running RCU reader at a time. ;-) + * + * Returns zero if there are no running readers. Returns a positive + * number if there is at least one reader within its RCU read-side + * critical section. Returns a negative number if an outermost reader + * is in the midst of exiting from its RCU read-side critical section + * + * Returns zero if there are no running readers. Returns a positive + * number if there is at least one reader within its RCU read-side + * critical section. Returns a negative number if an outermost reader + * is in the midst of exiting from its RCU read-side critical section. */ static int rcu_preempt_running_reader(void) { @@ -307,7 +318,6 @@ static int rcu_boost(void) t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; raw_local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ @@ -475,7 +485,7 @@ void rcu_preempt_note_context_switch(void) unsigned long flags; local_irq_save(flags); /* must exclude scheduler_tick(). */ - if (rcu_preempt_running_reader() && + if (rcu_preempt_running_reader() > 0 && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ @@ -494,6 +504,13 @@ void rcu_preempt_note_context_switch(void) list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks); if (rcu_cpu_blocking_cur_gp()) rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry; + } else if (rcu_preempt_running_reader() < 0 && + t->rcu_read_unlock_special) { + /* + * Complete exit from RCU read-side critical section on + * behalf of preempted instance of __rcu_read_unlock(). + */ + rcu_read_unlock_special(t); } /* @@ -526,12 +543,15 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock); * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static void rcu_read_unlock_special(struct task_struct *t) +static noinline void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; unsigned long flags; struct list_head *np; +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rbmp = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ int special; /* @@ -552,7 +572,7 @@ static void rcu_read_unlock_special(struct task_struct *t) rcu_preempt_cpu_qs(); /* Hardware IRQ handlers cannot block. */ - if (in_irq()) { + if (in_irq() || in_serving_softirq()) { local_irq_restore(flags); return; } @@ -597,10 +617,10 @@ static void rcu_read_unlock_special(struct task_struct *t) } #ifdef CONFIG_RCU_BOOST /* Unboost self if was boosted. */ - if (special & RCU_READ_UNLOCK_BOOSTED) { - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED; - rt_mutex_unlock(t->rcu_boost_mutex); + if (t->rcu_boost_mutex != NULL) { + rbmp = t->rcu_boost_mutex; t->rcu_boost_mutex = NULL; + rt_mutex_unlock(rbmp); } #endif /* #ifdef CONFIG_RCU_BOOST */ local_irq_restore(flags); @@ -618,13 +638,22 @@ void __rcu_read_unlock(void) struct task_struct *t = current; barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - --t->rcu_read_lock_nesting; - barrier(); /* decrement before load of ->rcu_read_unlock_special */ - if (t->rcu_read_lock_nesting == 0 && - unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); + if (t->rcu_read_lock_nesting != 1) + --t->rcu_read_lock_nesting; + else { + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(t->rcu_read_lock_nesting < 0); + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } #endif /* #ifdef CONFIG_PROVE_LOCKING */ } EXPORT_SYMBOL_GPL(__rcu_read_unlock); @@ -649,7 +678,7 @@ static void rcu_preempt_check_callbacks(void) invoke_rcu_callbacks(); if (rcu_preempt_gp_in_progress() && rcu_cpu_blocking_cur_gp() && - rcu_preempt_running_reader()) + rcu_preempt_running_reader() > 0) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } @@ -706,6 +735,11 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); + #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!rcu_scheduler_active) return; @@ -882,7 +916,8 @@ static void rcu_preempt_process_callbacks(void) static void invoke_rcu_callbacks(void) { have_rcu_kthread_work = 1; - wake_up(&rcu_kthread_wq); + if (rcu_kthread_task != NULL) + wake_up(&rcu_kthread_wq); } #ifdef CONFIG_RCU_TRACE @@ -943,12 +978,16 @@ early_initcall(rcu_spawn_kthreads); #else /* #ifdef CONFIG_RCU_BOOST */ +/* Hold off callback invocation until early_initcall() time. */ +static int rcu_scheduler_fully_active __read_mostly; + /* * Start up softirq processing of callbacks. */ void invoke_rcu_callbacks(void) { - raise_softirq(RCU_SOFTIRQ); + if (rcu_scheduler_fully_active) + raise_softirq(RCU_SOFTIRQ); } #ifdef CONFIG_RCU_TRACE @@ -963,10 +1002,14 @@ static bool rcu_is_callbacks_kthread(void) #endif /* #ifdef CONFIG_RCU_TRACE */ -void rcu_init(void) +static int __init rcu_scheduler_really_started(void) { + rcu_scheduler_fully_active = 1; open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + raise_softirq(RCU_SOFTIRQ); /* Invoke any callbacks from early boot. */ + return 0; } +early_initcall(rcu_scheduler_really_started); #endif /* #else #ifdef CONFIG_RCU_BOOST */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index a58ac285fc69..a89b381a8c6e 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -65,7 +65,10 @@ static int fqs_duration; /* Duration of bursts (us), 0 to disable. */ static int fqs_holdoff; /* Hold time within burst (us). */ static int fqs_stutter = 3; /* Wait time between bursts (s). */ static int onoff_interval; /* Wait time between CPU hotplugs, 0=disable. */ +static int onoff_holdoff; /* Seconds after boot before CPU hotplugs. */ static int shutdown_secs; /* Shutdown time (s). <=0 for no shutdown. */ +static int stall_cpu; /* CPU-stall duration (s). 0 for no stall. */ +static int stall_cpu_holdoff = 10; /* Time to wait until stall (s). */ static int test_boost = 1; /* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */ static int test_boost_interval = 7; /* Interval between boost tests, seconds. */ static int test_boost_duration = 4; /* Duration of each boost test, seconds. */ @@ -95,8 +98,14 @@ module_param(fqs_stutter, int, 0444); MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)"); module_param(onoff_interval, int, 0444); MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable"); +module_param(onoff_holdoff, int, 0444); +MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)"); module_param(shutdown_secs, int, 0444); MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), zero to disable."); +module_param(stall_cpu, int, 0444); +MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable."); +module_param(stall_cpu_holdoff, int, 0444); +MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s)."); module_param(test_boost, int, 0444); MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes."); module_param(test_boost_interval, int, 0444); @@ -129,6 +138,7 @@ static struct task_struct *shutdown_task; #ifdef CONFIG_HOTPLUG_CPU static struct task_struct *onoff_task; #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +static struct task_struct *stall_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -990,12 +1000,12 @@ static void rcu_torture_timer(unsigned long unused) rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p == NULL) { /* Leave because rcu_torture_writer is not yet underway */ cur_ops->readunlock(idx); return; } + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); spin_lock(&rand_lock); @@ -1053,13 +1063,13 @@ rcu_torture_reader(void *arg) rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ cur_ops->readunlock(idx); schedule_timeout_interruptible(HZ); continue; } + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); cur_ops->read_delay(&rand); @@ -1300,13 +1310,13 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag) "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " "test_boost=%d/%d test_boost_interval=%d " "test_boost_duration=%d shutdown_secs=%d " - "onoff_interval=%d\n", + "onoff_interval=%d onoff_holdoff=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, test_boost, cur_ops->can_boost, test_boost_interval, test_boost_duration, shutdown_secs, - onoff_interval); + onoff_interval, onoff_holdoff); } static struct notifier_block rcutorture_shutdown_nb = { @@ -1410,6 +1420,11 @@ rcu_torture_onoff(void *arg) for_each_online_cpu(cpu) maxcpu = cpu; WARN_ON(maxcpu < 0); + if (onoff_holdoff > 0) { + VERBOSE_PRINTK_STRING("rcu_torture_onoff begin holdoff"); + schedule_timeout_interruptible(onoff_holdoff * HZ); + VERBOSE_PRINTK_STRING("rcu_torture_onoff end holdoff"); + } while (!kthread_should_stop()) { cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1); if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { @@ -1450,12 +1465,15 @@ rcu_torture_onoff(void *arg) static int __cpuinit rcu_torture_onoff_init(void) { + int ret; + if (onoff_interval <= 0) return 0; onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff"); if (IS_ERR(onoff_task)) { + ret = PTR_ERR(onoff_task); onoff_task = NULL; - return PTR_ERR(onoff_task); + return ret; } return 0; } @@ -1481,6 +1499,63 @@ static void rcu_torture_onoff_cleanup(void) #endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ +/* + * CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then + * induces a CPU stall for the time specified by stall_cpu. + */ +static int __cpuinit rcu_torture_stall(void *args) +{ + unsigned long stop_at; + + VERBOSE_PRINTK_STRING("rcu_torture_stall task started"); + if (stall_cpu_holdoff > 0) { + VERBOSE_PRINTK_STRING("rcu_torture_stall begin holdoff"); + schedule_timeout_interruptible(stall_cpu_holdoff * HZ); + VERBOSE_PRINTK_STRING("rcu_torture_stall end holdoff"); + } + if (!kthread_should_stop()) { + stop_at = get_seconds() + stall_cpu; + /* RCU CPU stall is expected behavior in following code. */ + printk(KERN_ALERT "rcu_torture_stall start.\n"); + rcu_read_lock(); + preempt_disable(); + while (ULONG_CMP_LT(get_seconds(), stop_at)) + continue; /* Induce RCU CPU stall warning. */ + preempt_enable(); + rcu_read_unlock(); + printk(KERN_ALERT "rcu_torture_stall end.\n"); + } + rcutorture_shutdown_absorb("rcu_torture_stall"); + while (!kthread_should_stop()) + schedule_timeout_interruptible(10 * HZ); + return 0; +} + +/* Spawn CPU-stall kthread, if stall_cpu specified. */ +static int __init rcu_torture_stall_init(void) +{ + int ret; + + if (stall_cpu <= 0) + return 0; + stall_task = kthread_run(rcu_torture_stall, NULL, "rcu_torture_stall"); + if (IS_ERR(stall_task)) { + ret = PTR_ERR(stall_task); + stall_task = NULL; + return ret; + } + return 0; +} + +/* Clean up after the CPU-stall kthread, if one was spawned. */ +static void rcu_torture_stall_cleanup(void) +{ + if (stall_task == NULL) + return; + VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task."); + kthread_stop(stall_task); +} + static int rcutorture_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -1523,6 +1598,7 @@ rcu_torture_cleanup(void) fullstop = FULLSTOP_RMMOD; mutex_unlock(&fullstop_mutex); unregister_reboot_notifier(&rcutorture_shutdown_nb); + rcu_torture_stall_cleanup(); if (stutter_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); kthread_stop(stutter_task); @@ -1602,6 +1678,10 @@ rcu_torture_cleanup(void) cur_ops->cleanup(); if (atomic_read(&n_rcu_torture_error)) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); + else if (n_online_successes != n_online_attempts || + n_offline_successes != n_offline_attempts) + rcu_torture_print_module_parms(cur_ops, + "End of test: RCU_HOTPLUG"); else rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); } @@ -1819,6 +1899,7 @@ rcu_torture_init(void) } rcu_torture_onoff_init(); register_reboot_notifier(&rcutorture_shutdown_nb); + rcu_torture_stall_init(); rcutorture_record_test_transition(); mutex_unlock(&fullstop_mutex); return 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 6c4a6722abfd..1050d6d3922c 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -50,6 +50,8 @@ #include <linux/wait.h> #include <linux/kthread.h> #include <linux/prefetch.h> +#include <linux/delay.h> +#include <linux/stop_machine.h> #include "rcutree.h" #include <trace/events/rcu.h> @@ -196,7 +198,7 @@ void rcu_note_context_switch(int cpu) EXPORT_SYMBOL_GPL(rcu_note_context_switch); DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { - .dynticks_nesting = DYNTICK_TASK_NESTING, + .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(1), }; @@ -208,8 +210,11 @@ module_param(blimit, int, 0); module_param(qhimark, int, 0); module_param(qlowmark, int, 0); -int rcu_cpu_stall_suppress __read_mostly; +int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ +int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; + module_param(rcu_cpu_stall_suppress, int, 0644); +module_param(rcu_cpu_stall_timeout, int, 0644); static void force_quiescent_state(struct rcu_state *rsp, int relaxed); static int rcu_pending(int cpu); @@ -301,8 +306,6 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) return &rsp->node[0]; } -#ifdef CONFIG_SMP - /* * If the specified CPU is offline, tell the caller that it is in * a quiescent state. Otherwise, whack it with a reschedule IPI. @@ -317,30 +320,21 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) static int rcu_implicit_offline_qs(struct rcu_data *rdp) { /* - * If the CPU is offline, it is in a quiescent state. We can - * trust its state not to change because interrupts are disabled. + * If the CPU is offline for more than a jiffy, it is in a quiescent + * state. We can trust its state not to change because interrupts + * are disabled. The reason for the jiffy's worth of slack is to + * handle CPUs initializing on the way up and finding their way + * to the idle loop on the way down. */ - if (cpu_is_offline(rdp->cpu)) { + if (cpu_is_offline(rdp->cpu) && + ULONG_CMP_LT(rdp->rsp->gp_start + 2, jiffies)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); rdp->offline_fqs++; return 1; } - - /* - * The CPU is online, so send it a reschedule IPI. This forces - * it through the scheduler, and (inefficiently) also handles cases - * where idle loops fail to inform RCU about the CPU being idle. - */ - if (rdp->cpu != smp_processor_id()) - smp_send_reschedule(rdp->cpu); - else - set_need_resched(); - rdp->resched_ipi++; return 0; } -#endif /* #ifdef CONFIG_SMP */ - /* * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle * @@ -366,6 +360,17 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) atomic_inc(&rdtp->dynticks); smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + + /* + * The idle task is not permitted to enter the idle loop while + * in an RCU read-side critical section. + */ + rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), + "Illegal idle entry in RCU read-side critical section."); + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), + "Illegal idle entry in RCU-bh read-side critical section."); + rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), + "Illegal idle entry in RCU-sched read-side critical section."); } /** @@ -389,10 +394,15 @@ void rcu_idle_enter(void) local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); oldval = rdtp->dynticks_nesting; - rdtp->dynticks_nesting = 0; + WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) + rdtp->dynticks_nesting = 0; + else + rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; rcu_idle_enter_common(rdtp, oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_enter); /** * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle @@ -462,7 +472,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) * Exit idle mode, in other words, -enter- the mode in which RCU * read-side critical sections can occur. * - * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NESTING to + * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST to * allow for the possibility of usermode upcalls messing up our count * of interrupt nesting level during the busy period that is just * now starting. @@ -476,11 +486,15 @@ void rcu_idle_exit(void) local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE(oldval != 0); - rdtp->dynticks_nesting = DYNTICK_TASK_NESTING; + WARN_ON_ONCE(oldval < 0); + if (oldval & DYNTICK_TASK_NEST_MASK) + rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + else + rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_idle_exit_common(rdtp, oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_exit); /** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle @@ -581,6 +595,49 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Is the current CPU online? Disable preemption to avoid false positives + * that could otherwise happen due to the current CPU number being sampled, + * this task being preempted, its old CPU being taken offline, resuming + * on some other CPU, then determining that its old CPU is now offline. + * It is OK to use RCU on an offline processor during initial boot, hence + * the check for rcu_scheduler_fully_active. Note also that it is OK + * for a CPU coming online to use RCU for one jiffy prior to marking itself + * online in the cpu_online_mask. Similarly, it is OK for a CPU going + * offline to continue to use RCU for one jiffy after marking itself + * offline in the cpu_online_mask. This leniency is necessary given the + * non-atomic nature of the online and offline processing, for example, + * the fact that a CPU enters the scheduler after completing the CPU_DYING + * notifiers. + * + * This is also why RCU internally marks CPUs online during the + * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase. + * + * Disable checking if in an NMI handler because we cannot safely report + * errors from NMI handlers anyway. + */ +bool rcu_lockdep_current_cpu_online(void) +{ + struct rcu_data *rdp; + struct rcu_node *rnp; + bool ret; + + if (in_nmi()) + return 1; + preempt_disable(); + rdp = &__get_cpu_var(rcu_sched_data); + rnp = rdp->mynode; + ret = (rdp->grpmask & rnp->qsmaskinit) || + !rcu_scheduler_fully_active; + preempt_enable(); + return ret; +} +EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + #endif /* #ifdef CONFIG_PROVE_RCU */ /** @@ -595,8 +652,6 @@ int rcu_is_cpu_rrupt_from_idle(void) return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1; } -#ifdef CONFIG_SMP - /* * Snapshot the specified CPU's dynticks counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU @@ -640,12 +695,28 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return rcu_implicit_offline_qs(rdp); } -#endif /* #ifdef CONFIG_SMP */ +static int jiffies_till_stall_check(void) +{ + int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout); + + /* + * Limit check must be consistent with the Kconfig limits + * for CONFIG_RCU_CPU_STALL_TIMEOUT. + */ + if (till_stall_check < 3) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 3; + till_stall_check = 3; + } else if (till_stall_check > 300) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 300; + till_stall_check = 300; + } + return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; +} static void record_gp_stall_check_time(struct rcu_state *rsp) { rsp->gp_start = jiffies; - rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK; + rsp->jiffies_stall = jiffies + jiffies_till_stall_check(); } static void print_other_cpu_stall(struct rcu_state *rsp) @@ -664,13 +735,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } - rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK; - - /* - * Now rat on any tasks that got kicked up to the root rcu_node - * due to CPU offlining. - */ - ndetected = rcu_print_task_stall(rnp); + rsp->jiffies_stall = jiffies + 3 * jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -678,8 +743,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp) * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {", + printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks:", rsp->name); + print_cpu_stall_info_begin(); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave(&rnp->lock, flags); ndetected += rcu_print_task_stall(rnp); @@ -688,11 +754,22 @@ static void print_other_cpu_stall(struct rcu_state *rsp) continue; for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) if (rnp->qsmask & (1UL << cpu)) { - printk(" %d", rnp->grplo + cpu); + print_cpu_stall_info(rsp, rnp->grplo + cpu); ndetected++; } } - printk("} (detected by %d, t=%ld jiffies)\n", + + /* + * Now rat on any tasks that got kicked up to the root rcu_node + * due to CPU offlining. + */ + rnp = rcu_get_root(rsp); + raw_spin_lock_irqsave(&rnp->lock, flags); + ndetected = rcu_print_task_stall(rnp); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + print_cpu_stall_info_end(); + printk(KERN_CONT "(detected by %d, t=%ld jiffies)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start)); if (ndetected == 0) printk(KERN_ERR "INFO: Stall ended before state dump start\n"); @@ -716,15 +793,18 @@ static void print_cpu_stall(struct rcu_state *rsp) * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n", - rsp->name, smp_processor_id(), jiffies - rsp->gp_start); + printk(KERN_ERR "INFO: %s self-detected stall on CPU", rsp->name); + print_cpu_stall_info_begin(); + print_cpu_stall_info(rsp, smp_processor_id()); + print_cpu_stall_info_end(); + printk(KERN_CONT " (t=%lu jiffies)\n", jiffies - rsp->gp_start); if (!trigger_all_cpu_backtrace()) dump_stack(); raw_spin_lock_irqsave(&rnp->lock, flags); if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall)) - rsp->jiffies_stall = - jiffies + RCU_SECONDS_TILL_STALL_RECHECK; + rsp->jiffies_stall = jiffies + + 3 * jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); set_need_resched(); /* kick ourselves to get things going. */ @@ -807,6 +887,7 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rdp->passed_quiesce = 0; } else rdp->qs_pending = 0; + zero_cpu_stall_ticks(rdp); } } @@ -943,6 +1024,10 @@ rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat * in preparation for detecting the next grace period. The caller must hold * the root node's ->lock, which is released before return. Hard irqs must * be disabled. + * + * Note that it is legal for a dying CPU (which is marked as offline) to + * invoke this function. This can happen when the dying CPU reports its + * quiescent state. */ static void rcu_start_gp(struct rcu_state *rsp, unsigned long flags) @@ -980,26 +1065,8 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */ rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); - - /* Special-case the common single-level case. */ - if (NUM_RCU_NODES == 1) { - rcu_preempt_check_blocked_tasks(rnp); - rnp->qsmask = rnp->qsmaskinit; - rnp->gpnum = rsp->gpnum; - rnp->completed = rsp->completed; - rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state OK */ - rcu_start_gp_per_cpu(rsp, rnp, rdp); - rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, - rnp->level, rnp->grplo, - rnp->grphi, rnp->qsmask); - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - raw_spin_unlock(&rnp->lock); /* leave irqs disabled. */ - /* Exclude any concurrent CPU-hotplug operations. */ raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */ @@ -1245,53 +1312,115 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) /* * Move a dying CPU's RCU callbacks to online CPU's callback list. - * Synchronization is not required because this function executes - * in stop_machine() context. + * Also record a quiescent state for this CPU for the current grace period. + * Synchronization and interrupt disabling are not required because + * this function executes in stop_machine() context. Therefore, cleanup + * operations that might block must be done later from the CPU_DEAD + * notifier. + * + * Note that the outgoing CPU's bit has already been cleared in the + * cpu_online_mask. This allows us to randomly pick a callback + * destination from the bits set in that mask. */ -static void rcu_send_cbs_to_online(struct rcu_state *rsp) +static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { int i; - /* current DYING CPU is cleared in the cpu_online_mask */ + unsigned long mask; int receive_cpu = cpumask_any(cpu_online_mask); struct rcu_data *rdp = this_cpu_ptr(rsp->rda); struct rcu_data *receive_rdp = per_cpu_ptr(rsp->rda, receive_cpu); + RCU_TRACE(struct rcu_node *rnp = rdp->mynode); /* For dying CPU. */ + + /* First, adjust the counts. */ + if (rdp->nxtlist != NULL) { + receive_rdp->qlen_lazy += rdp->qlen_lazy; + receive_rdp->qlen += rdp->qlen; + rdp->qlen_lazy = 0; + rdp->qlen = 0; + } - if (rdp->nxtlist == NULL) - return; /* irqs disabled, so comparison is stable. */ + /* + * Next, move ready-to-invoke callbacks to be invoked on some + * other CPU. These will not be required to pass through another + * grace period: They are done, regardless of CPU. + */ + if (rdp->nxtlist != NULL && + rdp->nxttail[RCU_DONE_TAIL] != &rdp->nxtlist) { + struct rcu_head *oldhead; + struct rcu_head **oldtail; + struct rcu_head **newtail; + + oldhead = rdp->nxtlist; + oldtail = receive_rdp->nxttail[RCU_DONE_TAIL]; + rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = *oldtail; + *receive_rdp->nxttail[RCU_DONE_TAIL] = oldhead; + newtail = rdp->nxttail[RCU_DONE_TAIL]; + for (i = RCU_DONE_TAIL; i < RCU_NEXT_SIZE; i++) { + if (receive_rdp->nxttail[i] == oldtail) + receive_rdp->nxttail[i] = newtail; + if (rdp->nxttail[i] == newtail) + rdp->nxttail[i] = &rdp->nxtlist; + } + } - *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; - receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - receive_rdp->qlen += rdp->qlen; - receive_rdp->n_cbs_adopted += rdp->qlen; - rdp->n_cbs_orphaned += rdp->qlen; + /* + * Finally, put the rest of the callbacks at the end of the list. + * The ones that made it partway through get to start over: We + * cannot assume that grace periods are synchronized across CPUs. + * (We could splice RCU_WAIT_TAIL into RCU_NEXT_READY_TAIL, but + * this does not seem compelling. Not yet, anyway.) + */ + if (rdp->nxtlist != NULL) { + *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; + receive_rdp->nxttail[RCU_NEXT_TAIL] = + rdp->nxttail[RCU_NEXT_TAIL]; + receive_rdp->n_cbs_adopted += rdp->qlen; + rdp->n_cbs_orphaned += rdp->qlen; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; + } - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; - rdp->qlen = 0; + /* + * Record a quiescent state for the dying CPU. This is safe + * only because we have already cleared out the callbacks. + * (Otherwise, the RCU core might try to schedule the invocation + * of callbacks on this now-offline CPU, which would be bad.) + */ + mask = rdp->grpmask; /* rnp->grplo is constant. */ + trace_rcu_grace_period(rsp->name, + rnp->gpnum + 1 - !!(rnp->qsmask & mask), + "cpuofl"); + rcu_report_qs_rdp(smp_processor_id(), rsp, rdp, rsp->gpnum); + /* Note that rcu_report_qs_rdp() might call trace_rcu_grace_period(). */ } /* - * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy - * and move all callbacks from the outgoing CPU to the current one. + * The CPU has been completely removed, and some other CPU is reporting + * this fact from process context. Do the remainder of the cleanup. * There can only be one CPU hotplug operation at a time, so no other * CPU can be attempting to update rcu_cpu_kthread_task. */ -static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) +static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { unsigned long flags; unsigned long mask; int need_report = 0; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp; + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rnp. */ + /* Adjust any no-longer-needed kthreads. */ rcu_stop_cpu_kthread(cpu); + rcu_node_kthread_setaffinity(rnp, -1); + + /* Remove the dying CPU from the bitmasks in the rcu_node hierarchy. */ /* Exclude any attempts to start a new grace period. */ raw_spin_lock_irqsave(&rsp->onofflock, flags); /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */ - rnp = rdp->mynode; /* this is the outgoing CPU's rnp. */ mask = rdp->grpmask; /* rnp->grplo is constant. */ do { raw_spin_lock(&rnp->lock); /* irqs already disabled. */ @@ -1299,20 +1428,11 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) if (rnp->qsmaskinit != 0) { if (rnp != rdp->mynode) raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - else - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - - !!(rnp->qsmask & mask), - "cpuofl"); break; } - if (rnp == rdp->mynode) { - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - - !!(rnp->qsmask & mask), - "cpuofl"); + if (rnp == rdp->mynode) need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp); - } else + else raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ mask = rnp->grpmask; rnp = rnp->parent; @@ -1332,29 +1452,15 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); - rcu_node_kthread_setaffinity(rnp, -1); -} - -/* - * Remove the specified CPU from the RCU hierarchy and move any pending - * callbacks that it might have to the current CPU. This code assumes - * that at least one CPU in the system will remain running at all times. - * Any attempt to offline -all- CPUs is likely to strand RCU callbacks. - */ -static void rcu_offline_cpu(int cpu) -{ - __rcu_offline_cpu(cpu, &rcu_sched_state); - __rcu_offline_cpu(cpu, &rcu_bh_state); - rcu_preempt_offline_cpu(cpu); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_send_cbs_to_online(struct rcu_state *rsp) +static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { } -static void rcu_offline_cpu(int cpu) +static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { } @@ -1368,11 +1474,11 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; struct rcu_head *next, *list, **tail; - int bl, count; + int bl, count, count_lazy; /* If no callbacks are ready, just return.*/ if (!cpu_has_callbacks_ready_to_invoke(rdp)) { - trace_rcu_batch_start(rsp->name, 0, 0); + trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0); trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist), need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); @@ -1384,8 +1490,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) * races with call_rcu() from interrupt handlers. */ local_irq_save(flags); + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); bl = rdp->blimit; - trace_rcu_batch_start(rsp->name, rdp->qlen, bl); + trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl); list = rdp->nxtlist; rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; *rdp->nxttail[RCU_DONE_TAIL] = NULL; @@ -1396,12 +1503,13 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_restore(flags); /* Invoke callbacks. */ - count = 0; + count = count_lazy = 0; while (list) { next = list->next; prefetch(next); debug_rcu_head_unqueue(list); - __rcu_reclaim(rsp->name, list); + if (__rcu_reclaim(rsp->name, list)) + count_lazy++; list = next; /* Stop only if limit reached and CPU has something to do. */ if (++count >= bl && @@ -1416,6 +1524,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rcu_is_callbacks_kthread()); /* Update count, and requeue any remaining callbacks. */ + rdp->qlen_lazy -= count_lazy; rdp->qlen -= count; rdp->n_cbs_invoked += count; if (list != NULL) { @@ -1458,6 +1567,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) void rcu_check_callbacks(int cpu, int user) { trace_rcu_utilization("Start scheduler-tick"); + increment_cpu_stall_ticks(); if (user || rcu_is_cpu_rrupt_from_idle()) { /* @@ -1492,8 +1602,6 @@ void rcu_check_callbacks(int cpu, int user) trace_rcu_utilization("End scheduler-tick"); } -#ifdef CONFIG_SMP - /* * Scan the leaf rcu_node structures, processing dyntick state for any that * have not yet encountered a quiescent state, using the function specified. @@ -1616,15 +1724,6 @@ unlock_fqs_ret: trace_rcu_utilization("End fqs"); } -#else /* #ifdef CONFIG_SMP */ - -static void force_quiescent_state(struct rcu_state *rsp, int relaxed) -{ - set_need_resched(); -} - -#endif /* #else #ifdef CONFIG_SMP */ - /* * This does the RCU core processing work for the specified rcu_state * and rcu_data structures. This may be called only from the CPU to @@ -1702,11 +1801,12 @@ static void invoke_rcu_core(void) static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), - struct rcu_state *rsp) + struct rcu_state *rsp, bool lazy) { unsigned long flags; struct rcu_data *rdp; + WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */ debug_rcu_head_queue(head); head->func = func; head->next = NULL; @@ -1720,18 +1820,21 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), * a quiescent state betweentimes. */ local_irq_save(flags); + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ *rdp->nxttail[RCU_NEXT_TAIL] = head; rdp->nxttail[RCU_NEXT_TAIL] = &head->next; rdp->qlen++; + if (lazy) + rdp->qlen_lazy++; if (__is_kfree_rcu_offset((unsigned long)func)) trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, - rdp->qlen); + rdp->qlen_lazy, rdp->qlen); else - trace_rcu_callback(rsp->name, head, rdp->qlen); + trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); /* If interrupts were disabled, don't dive into RCU core. */ if (irqs_disabled_flags(flags)) { @@ -1778,16 +1881,16 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), */ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_sched_state); + __call_rcu(head, func, &rcu_sched_state, 0); } EXPORT_SYMBOL_GPL(call_rcu_sched); /* - * Queue an RCU for invocation after a quicker grace period. + * Queue an RCU callback for invocation after a quicker grace period. */ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_bh_state); + __call_rcu(head, func, &rcu_bh_state, 0); } EXPORT_SYMBOL_GPL(call_rcu_bh); @@ -1816,6 +1919,10 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); */ void synchronize_sched(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU-sched read-side critical section"); if (rcu_blocking_is_gp()) return; wait_rcu_gp(call_rcu_sched); @@ -1833,12 +1940,137 @@ EXPORT_SYMBOL_GPL(synchronize_sched); */ void synchronize_rcu_bh(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); if (rcu_blocking_is_gp()) return; wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0); +static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0); + +static int synchronize_sched_expedited_cpu_stop(void *data) +{ + /* + * There must be a full memory barrier on each affected CPU + * between the time that try_stop_cpus() is called and the + * time that it returns. + * + * In the current initial implementation of cpu_stop, the + * above condition is already met when the control reaches + * this point and the following smp_mb() is not strictly + * necessary. Do smp_mb() anyway for documentation and + * robustness against future implementation changes. + */ + smp_mb(); /* See above comment block. */ + return 0; +} + +/** + * synchronize_sched_expedited - Brute-force RCU-sched grace period + * + * Wait for an RCU-sched grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_sched_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_sched() instead. + * + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. + * + * This implementation can be thought of as an application of ticket + * locking to RCU, with sync_sched_expedited_started and + * sync_sched_expedited_done taking on the roles of the halves + * of the ticket-lock word. Each task atomically increments + * sync_sched_expedited_started upon entry, snapshotting the old value, + * then attempts to stop all the CPUs. If this succeeds, then each + * CPU will have executed a context switch, resulting in an RCU-sched + * grace period. We are then done, so we use atomic_cmpxchg() to + * update sync_sched_expedited_done to match our snapshot -- but + * only if someone else has not already advanced past our snapshot. + * + * On the other hand, if try_stop_cpus() fails, we check the value + * of sync_sched_expedited_done. If it has advanced past our + * initial snapshot, then someone else must have forced a grace period + * some time after we took our snapshot. In this case, our work is + * done for us, and we can simply return. Otherwise, we try again, + * but keep our initial snapshot for purposes of checking for someone + * doing our work for us. + * + * If we fail too many times in a row, we fall back to synchronize_sched(). + */ +void synchronize_sched_expedited(void) +{ + int firstsnap, s, snap, trycount = 0; + + /* Note that atomic_inc_return() implies full memory barrier. */ + firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started); + get_online_cpus(); + WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); + + /* + * Each pass through the following loop attempts to force a + * context switch on each CPU. + */ + while (try_stop_cpus(cpu_online_mask, + synchronize_sched_expedited_cpu_stop, + NULL) == -EAGAIN) { + put_online_cpus(); + + /* No joy, try again later. Or just synchronize_sched(). */ + if (trycount++ < 10) + udelay(trycount * num_online_cpus()); + else { + synchronize_sched(); + return; + } + + /* Check to see if someone else did our work for us. */ + s = atomic_read(&sync_sched_expedited_done); + if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) { + smp_mb(); /* ensure test happens before caller kfree */ + return; + } + + /* + * Refetching sync_sched_expedited_started allows later + * callers to piggyback on our grace period. We subtract + * 1 to get the same token that the last incrementer got. + * We retry after they started, so our grace period works + * for them, and they started after our first try, so their + * grace period works for us. + */ + get_online_cpus(); + snap = atomic_read(&sync_sched_expedited_started); + smp_mb(); /* ensure read is before try_stop_cpus(). */ + } + + /* + * Everyone up to our most recent fetch is covered by our grace + * period. Update the counter, but only if our work is still + * relevant -- which it won't be if someone who started later + * than we did beat us to the punch. + */ + do { + s = atomic_read(&sync_sched_expedited_done); + if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) { + smp_mb(); /* ensure test happens before caller kfree */ + break; + } + } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s); + + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); + /* * Check to see if there is any immediate RCU-related work to be done * by the current CPU, for the specified type of RCU, returning 1 if so. @@ -1932,7 +2164,7 @@ static int rcu_cpu_has_callbacks(int cpu) /* RCU callbacks either ready or pending? */ return per_cpu(rcu_sched_data, cpu).nxtlist || per_cpu(rcu_bh_data, cpu).nxtlist || - rcu_preempt_needs_cpu(cpu); + rcu_preempt_cpu_has_callbacks(cpu); } static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; @@ -2027,9 +2259,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->nxtlist = NULL; for (i = 0; i < RCU_NEXT_SIZE; i++) rdp->nxttail[i] = &rdp->nxtlist; + rdp->qlen_lazy = 0; rdp->qlen = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); - WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_NESTING); + WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); rdp->cpu = cpu; rdp->rsp = rsp; @@ -2057,7 +2290,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; - rdp->dynticks->dynticks_nesting = DYNTICK_TASK_NESTING; + rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); rcu_prepare_for_idle_init(cpu); @@ -2139,16 +2372,18 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, * touch any data without introducing corruption. We send the * dying CPU's callbacks to an arbitrarily chosen online CPU. */ - rcu_send_cbs_to_online(&rcu_bh_state); - rcu_send_cbs_to_online(&rcu_sched_state); - rcu_preempt_send_cbs_to_online(); + rcu_cleanup_dying_cpu(&rcu_bh_state); + rcu_cleanup_dying_cpu(&rcu_sched_state); + rcu_preempt_cleanup_dying_cpu(); rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - rcu_offline_cpu(cpu); + rcu_cleanup_dead_cpu(cpu, &rcu_bh_state); + rcu_cleanup_dead_cpu(cpu, &rcu_sched_state); + rcu_preempt_cleanup_dead_cpu(cpu); break; default: break; diff --git a/kernel/rcutree.h b/kernel/rcutree.h index fddff92d6676..cdd1be0a4072 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -239,6 +239,12 @@ struct rcu_data { bool preemptible; /* Preemptible RCU? */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ +#ifdef CONFIG_RCU_CPU_STALL_INFO + unsigned long ticks_this_gp; /* The number of scheduling-clock */ + /* ticks this CPU has handled */ + /* during and after the last grace */ + /* period it is aware of. */ +#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ /* 2) batch handling */ /* @@ -265,7 +271,8 @@ struct rcu_data { */ struct rcu_head *nxtlist; struct rcu_head **nxttail[RCU_NEXT_SIZE]; - long qlen; /* # of queued callbacks */ + long qlen_lazy; /* # of lazy queued callbacks */ + long qlen; /* # of queued callbacks, incl lazy */ long qlen_last_fqs_check; /* qlen at last check for QS forcing */ unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */ @@ -282,7 +289,6 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ unsigned long offline_fqs; /* Kicked due to being offline. */ - unsigned long resched_ipi; /* Sent a resched IPI. */ /* 5) __rcu_pending() statistics. */ unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ @@ -313,12 +319,6 @@ struct rcu_data { #else #define RCU_STALL_DELAY_DELTA 0 #endif - -#define RCU_SECONDS_TILL_STALL_CHECK (CONFIG_RCU_CPU_STALL_TIMEOUT * HZ + \ - RCU_STALL_DELAY_DELTA) - /* for rsp->jiffies_stall */ -#define RCU_SECONDS_TILL_STALL_RECHECK (3 * RCU_SECONDS_TILL_STALL_CHECK + 30) - /* for rsp->jiffies_stall */ #define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */ /* to take at least one */ /* scheduling clock irq */ @@ -438,8 +438,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); -static void rcu_preempt_offline_cpu(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +static void rcu_preempt_cleanup_dead_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); @@ -448,9 +448,9 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); -static int rcu_preempt_needs_cpu(int cpu); +static int rcu_preempt_cpu_has_callbacks(int cpu); static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void rcu_preempt_send_cbs_to_online(void); +static void rcu_preempt_cleanup_dying_cpu(void); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); @@ -471,5 +471,10 @@ static void __cpuinit rcu_prepare_kthreads(int cpu); static void rcu_prepare_for_idle_init(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); +static void print_cpu_stall_info_begin(void); +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); +static void print_cpu_stall_info_end(void); +static void zero_cpu_stall_ticks(struct rcu_data *rdp); +static void increment_cpu_stall_ticks(void); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 8bb35d73e1f9..c023464816be 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -25,7 +25,6 @@ */ #include <linux/delay.h> -#include <linux/stop_machine.h> #define RCU_KTHREAD_PRIO 1 @@ -63,7 +62,10 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tRCU torture testing starts during boot.\n"); #endif #if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE) - printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n"); + printk(KERN_INFO "\tDump stacks of tasks blocking RCU-preempt GP.\n"); +#endif +#if defined(CONFIG_RCU_CPU_STALL_INFO) + printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n"); #endif #if NUM_RCU_LVL_4 != 0 printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); @@ -490,6 +492,31 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ +#ifdef CONFIG_RCU_CPU_STALL_INFO + +static void rcu_print_task_stall_begin(struct rcu_node *rnp) +{ + printk(KERN_ERR "\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", + rnp->level, rnp->grplo, rnp->grphi); +} + +static void rcu_print_task_stall_end(void) +{ + printk(KERN_CONT "\n"); +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +static void rcu_print_task_stall_begin(struct rcu_node *rnp) +{ +} + +static void rcu_print_task_stall_end(void) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ + /* * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. @@ -501,12 +528,14 @@ static int rcu_print_task_stall(struct rcu_node *rnp) if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; + rcu_print_task_stall_begin(rnp); t = list_entry(rnp->gp_tasks, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { - printk(" P%d", t->pid); + printk(KERN_CONT " P%d", t->pid); ndetected++; } + rcu_print_task_stall_end(); return ndetected; } @@ -581,7 +610,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, * absolutely necessary, but this is a good performance/complexity * tradeoff. */ - if (rcu_preempt_blocked_readers_cgp(rnp)) + if (rcu_preempt_blocked_readers_cgp(rnp) && rnp->qsmask == 0) retval |= RCU_OFL_TASKS_NORM_GP; if (rcu_preempted_readers_exp(rnp)) retval |= RCU_OFL_TASKS_EXP_GP; @@ -618,16 +647,16 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, return retval; } +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + /* * Do CPU-offline processing for preemptible RCU. */ -static void rcu_preempt_offline_cpu(int cpu) +static void rcu_preempt_cleanup_dead_cpu(int cpu) { - __rcu_offline_cpu(cpu, &rcu_preempt_state); + rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state); } -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, @@ -671,10 +700,24 @@ static void rcu_preempt_do_callbacks(void) */ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_preempt_state); + __call_rcu(head, func, &rcu_preempt_state, 0); } EXPORT_SYMBOL_GPL(call_rcu); +/* + * Queue an RCU callback for lazy invocation after a grace period. + * This will likely be later named something like "call_rcu_lazy()", + * but this change will require some way of tagging the lazy RCU + * callbacks in the list of pending callbacks. Until then, this + * function may only be called from __kfree_rcu(). + */ +void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_preempt_state, 1); +} +EXPORT_SYMBOL_GPL(kfree_call_rcu); + /** * synchronize_rcu - wait until a grace period has elapsed. * @@ -688,6 +731,10 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); if (!rcu_scheduler_active) return; wait_rcu_gp(call_rcu); @@ -788,10 +835,22 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */ } -/* - * Wait for an rcu-preempt grace period, but expedite it. The basic idea - * is to invoke synchronize_sched_expedited() to push all the tasks to - * the ->blkd_tasks lists and wait for this list to drain. +/** + * synchronize_rcu_expedited - Brute-force RCU grace period + * + * Wait for an RCU-preempt grace period, but expedite it. The basic + * idea is to invoke synchronize_sched_expedited() to push all the tasks to + * the ->blkd_tasks lists and wait for this list to drain. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. + * In fact, if you are using synchronize_rcu_expedited() in a loop, + * please restructure your code to batch your updates, and then Use a + * single synchronize_rcu() instead. + * + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. */ void synchronize_rcu_expedited(void) { @@ -869,9 +928,9 @@ static int rcu_preempt_pending(int cpu) } /* - * Does preemptible RCU need the CPU to stay out of dynticks mode? + * Does preemptible RCU have callbacks on this CPU? */ -static int rcu_preempt_needs_cpu(int cpu) +static int rcu_preempt_cpu_has_callbacks(int cpu) { return !!per_cpu(rcu_preempt_data, cpu).nxtlist; } @@ -894,11 +953,12 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) } /* - * Move preemptible RCU's callbacks from dying CPU to other online CPU. + * Move preemptible RCU's callbacks from dying CPU to other online CPU + * and record a quiescent state. */ -static void rcu_preempt_send_cbs_to_online(void) +static void rcu_preempt_cleanup_dying_cpu(void) { - rcu_send_cbs_to_online(&rcu_preempt_state); + rcu_cleanup_dying_cpu(&rcu_preempt_state); } /* @@ -1034,16 +1094,16 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, return 0; } +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + /* * Because preemptible RCU does not exist, it never needs CPU-offline * processing. */ -static void rcu_preempt_offline_cpu(int cpu) +static void rcu_preempt_cleanup_dead_cpu(int cpu) { } -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Because preemptible RCU does not exist, it never has any callbacks * to check. @@ -1061,6 +1121,22 @@ static void rcu_preempt_process_callbacks(void) } /* + * Queue an RCU callback for lazy invocation after a grace period. + * This will likely be later named something like "call_rcu_lazy()", + * but this change will require some way of tagging the lazy RCU + * callbacks in the list of pending callbacks. Until then, this + * function may only be called from __kfree_rcu(). + * + * Because there is no preemptible RCU, we use RCU-sched instead. + */ +void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_sched_state, 1); +} +EXPORT_SYMBOL_GPL(kfree_call_rcu); + +/* * Wait for an rcu-preempt grace period, but make it happen quickly. * But because preemptible RCU does not exist, map to rcu-sched. */ @@ -1093,9 +1169,9 @@ static int rcu_preempt_pending(int cpu) } /* - * Because preemptible RCU does not exist, it never needs any CPU. + * Because preemptible RCU does not exist, it never has callbacks */ -static int rcu_preempt_needs_cpu(int cpu) +static int rcu_preempt_cpu_has_callbacks(int cpu) { return 0; } @@ -1119,9 +1195,9 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) } /* - * Because there is no preemptible RCU, there are no callbacks to move. + * Because there is no preemptible RCU, there is no cleanup to do. */ -static void rcu_preempt_send_cbs_to_online(void) +static void rcu_preempt_cleanup_dying_cpu(void) { } @@ -1823,132 +1899,6 @@ static void __cpuinit rcu_prepare_kthreads(int cpu) #endif /* #else #ifdef CONFIG_RCU_BOOST */ -#ifndef CONFIG_SMP - -void synchronize_sched_expedited(void) -{ - cond_resched(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#else /* #ifndef CONFIG_SMP */ - -static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0); -static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0); - -static int synchronize_sched_expedited_cpu_stop(void *data) -{ - /* - * There must be a full memory barrier on each affected CPU - * between the time that try_stop_cpus() is called and the - * time that it returns. - * - * In the current initial implementation of cpu_stop, the - * above condition is already met when the control reaches - * this point and the following smp_mb() is not strictly - * necessary. Do smp_mb() anyway for documentation and - * robustness against future implementation changes. - */ - smp_mb(); /* See above comment block. */ - return 0; -} - -/* - * Wait for an rcu-sched grace period to elapse, but use "big hammer" - * approach to force grace period to end quickly. This consumes - * significant time on all CPUs, and is thus not recommended for - * any sort of common-case code. - * - * Note that it is illegal to call this function while holding any - * lock that is acquired by a CPU-hotplug notifier. Failing to - * observe this restriction will result in deadlock. - * - * This implementation can be thought of as an application of ticket - * locking to RCU, with sync_sched_expedited_started and - * sync_sched_expedited_done taking on the roles of the halves - * of the ticket-lock word. Each task atomically increments - * sync_sched_expedited_started upon entry, snapshotting the old value, - * then attempts to stop all the CPUs. If this succeeds, then each - * CPU will have executed a context switch, resulting in an RCU-sched - * grace period. We are then done, so we use atomic_cmpxchg() to - * update sync_sched_expedited_done to match our snapshot -- but - * only if someone else has not already advanced past our snapshot. - * - * On the other hand, if try_stop_cpus() fails, we check the value - * of sync_sched_expedited_done. If it has advanced past our - * initial snapshot, then someone else must have forced a grace period - * some time after we took our snapshot. In this case, our work is - * done for us, and we can simply return. Otherwise, we try again, - * but keep our initial snapshot for purposes of checking for someone - * doing our work for us. - * - * If we fail too many times in a row, we fall back to synchronize_sched(). - */ -void synchronize_sched_expedited(void) -{ - int firstsnap, s, snap, trycount = 0; - - /* Note that atomic_inc_return() implies full memory barrier. */ - firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started); - get_online_cpus(); - - /* - * Each pass through the following loop attempts to force a - * context switch on each CPU. - */ - while (try_stop_cpus(cpu_online_mask, - synchronize_sched_expedited_cpu_stop, - NULL) == -EAGAIN) { - put_online_cpus(); - - /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) - udelay(trycount * num_online_cpus()); - else { - synchronize_sched(); - return; - } - - /* Check to see if someone else did our work for us. */ - s = atomic_read(&sync_sched_expedited_done); - if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) { - smp_mb(); /* ensure test happens before caller kfree */ - return; - } - - /* - * Refetching sync_sched_expedited_started allows later - * callers to piggyback on our grace period. We subtract - * 1 to get the same token that the last incrementer got. - * We retry after they started, so our grace period works - * for them, and they started after our first try, so their - * grace period works for us. - */ - get_online_cpus(); - snap = atomic_read(&sync_sched_expedited_started); - smp_mb(); /* ensure read is before try_stop_cpus(). */ - } - - /* - * Everyone up to our most recent fetch is covered by our grace - * period. Update the counter, but only if our work is still - * relevant -- which it won't be if someone who started later - * than we did beat us to the punch. - */ - do { - s = atomic_read(&sync_sched_expedited_done); - if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) { - smp_mb(); /* ensure test happens before caller kfree */ - break; - } - } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s); - - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#endif /* #else #ifndef CONFIG_SMP */ - #if !defined(CONFIG_RCU_FAST_NO_HZ) /* @@ -1981,7 +1931,7 @@ static void rcu_cleanup_after_idle(int cpu) } /* - * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=y, + * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n, * is nothing. */ static void rcu_prepare_for_idle(int cpu) @@ -2015,6 +1965,9 @@ static void rcu_prepare_for_idle(int cpu) * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your * system. And if you are -that- concerned about energy efficiency, * just power the system down and be done with it! + * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is + * permitted to sleep in dyntick-idle mode with only lazy RCU + * callbacks pending. Setting this too high can OOM your system. * * The values below work well in practice. If future workloads require * adjustment, they can be converted into kernel config parameters, though @@ -2023,11 +1976,13 @@ static void rcu_prepare_for_idle(int cpu) #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ #define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ static DEFINE_PER_CPU(int, rcu_dyntick_drain); static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer); -static ktime_t rcu_idle_gp_wait; +static ktime_t rcu_idle_gp_wait; /* If some non-lazy callbacks. */ +static ktime_t rcu_idle_lazy_gp_wait; /* If only lazy callbacks. */ /* * Allow the CPU to enter dyntick-idle mode if either: (1) There are no @@ -2048,6 +2003,48 @@ int rcu_needs_cpu(int cpu) } /* + * Does the specified flavor of RCU have non-lazy callbacks pending on + * the specified CPU? Both RCU flavor and CPU are specified by the + * rcu_data structure. + */ +static bool __rcu_cpu_has_nonlazy_callbacks(struct rcu_data *rdp) +{ + return rdp->qlen != rdp->qlen_lazy; +} + +#ifdef CONFIG_TREE_PREEMPT_RCU + +/* + * Are there non-lazy RCU-preempt callbacks? (There cannot be if there + * is no RCU-preempt in the kernel.) + */ +static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); + + return __rcu_cpu_has_nonlazy_callbacks(rdp); +} + +#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ + +static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu) +{ + return 0; +} + +#endif /* else #ifdef CONFIG_TREE_PREEMPT_RCU */ + +/* + * Does any flavor of RCU have non-lazy callbacks on the specified CPU? + */ +static bool rcu_cpu_has_nonlazy_callbacks(int cpu) +{ + return __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_sched_data, cpu)) || + __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_bh_data, cpu)) || + rcu_preempt_cpu_has_nonlazy_callbacks(cpu); +} + +/* * Timer handler used to force CPU to start pushing its remaining RCU * callbacks in the case where it entered dyntick-idle mode with callbacks * pending. The hander doesn't really need to do anything because the @@ -2074,6 +2071,8 @@ static void rcu_prepare_for_idle_init(int cpu) unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY); rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000); + upj = jiffies_to_usecs(RCU_IDLE_LAZY_GP_DELAY); + rcu_idle_lazy_gp_wait = ns_to_ktime(upj * (u64)1000); firsttime = 0; } } @@ -2109,10 +2108,6 @@ static void rcu_cleanup_after_idle(int cpu) */ static void rcu_prepare_for_idle(int cpu) { - unsigned long flags; - - local_irq_save(flags); - /* * If there are no callbacks on this CPU, enter dyntick-idle mode. * Also reset state to avoid prejudicing later attempts. @@ -2120,7 +2115,6 @@ static void rcu_prepare_for_idle(int cpu) if (!rcu_cpu_has_callbacks(cpu)) { per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; per_cpu(rcu_dyntick_drain, cpu) = 0; - local_irq_restore(flags); trace_rcu_prep_idle("No callbacks"); return; } @@ -2130,7 +2124,6 @@ static void rcu_prepare_for_idle(int cpu) * refrained from disabling the scheduling-clock tick. */ if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) { - local_irq_restore(flags); trace_rcu_prep_idle("In holdoff"); return; } @@ -2140,18 +2133,22 @@ static void rcu_prepare_for_idle(int cpu) /* First time through, initialize the counter. */ per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES; } else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES && - !rcu_pending(cpu)) { + !rcu_pending(cpu) && + !local_softirq_pending()) { /* Can we go dyntick-idle despite still having callbacks? */ trace_rcu_prep_idle("Dyntick with callbacks"); per_cpu(rcu_dyntick_drain, cpu) = 0; - per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; - hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), - rcu_idle_gp_wait, HRTIMER_MODE_REL); + per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) + hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), + rcu_idle_gp_wait, HRTIMER_MODE_REL); + else + hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), + rcu_idle_lazy_gp_wait, HRTIMER_MODE_REL); return; /* Nothing more to do immediately. */ } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) { /* We have hit the limit, so time to give up. */ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; - local_irq_restore(flags); trace_rcu_prep_idle("Begin holdoff"); invoke_rcu_core(); /* Force the CPU out of dyntick-idle. */ return; @@ -2163,23 +2160,17 @@ static void rcu_prepare_for_idle(int cpu) */ #ifdef CONFIG_TREE_PREEMPT_RCU if (per_cpu(rcu_preempt_data, cpu).nxtlist) { - local_irq_restore(flags); rcu_preempt_qs(cpu); force_quiescent_state(&rcu_preempt_state, 0); - local_irq_save(flags); } #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ if (per_cpu(rcu_sched_data, cpu).nxtlist) { - local_irq_restore(flags); rcu_sched_qs(cpu); force_quiescent_state(&rcu_sched_state, 0); - local_irq_save(flags); } if (per_cpu(rcu_bh_data, cpu).nxtlist) { - local_irq_restore(flags); rcu_bh_qs(cpu); force_quiescent_state(&rcu_bh_state, 0); - local_irq_save(flags); } /* @@ -2187,13 +2178,124 @@ static void rcu_prepare_for_idle(int cpu) * So try forcing the callbacks through the grace period. */ if (rcu_cpu_has_callbacks(cpu)) { - local_irq_restore(flags); trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - } else { - local_irq_restore(flags); + } else trace_rcu_prep_idle("Callbacks drained"); - } } #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ + +#ifdef CONFIG_RCU_CPU_STALL_INFO + +#ifdef CONFIG_RCU_FAST_NO_HZ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ + struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu); + + sprintf(cp, "drain=%d %c timer=%lld", + per_cpu(rcu_dyntick_drain, cpu), + per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.', + hrtimer_active(hrtp) + ? ktime_to_us(hrtimer_get_remaining(hrtp)) + : -1); +} + +#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ + +/* Initiate the stall-info list. */ +static void print_cpu_stall_info_begin(void) +{ + printk(KERN_CONT "\n"); +} + +/* + * Print out diagnostic information for the specified stalled CPU. + * + * If the specified CPU is aware of the current RCU grace period + * (flavor specified by rsp), then print the number of scheduling + * clock interrupts the CPU has taken during the time that it has + * been aware. Otherwise, print the number of RCU grace periods + * that this CPU is ignorant of, for example, "1" if the CPU was + * aware of the previous grace period. + * + * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info. + */ +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +{ + char fast_no_hz[72]; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = rdp->dynticks; + char *ticks_title; + unsigned long ticks_value; + + if (rsp->gpnum == rdp->gpnum) { + ticks_title = "ticks this GP"; + ticks_value = rdp->ticks_this_gp; + } else { + ticks_title = "GPs behind"; + ticks_value = rsp->gpnum - rdp->gpnum; + } + print_cpu_stall_fast_no_hz(fast_no_hz, cpu); + printk(KERN_ERR "\t%d: (%lu %s) idle=%03x/%llx/%d %s\n", + cpu, ticks_value, ticks_title, + atomic_read(&rdtp->dynticks) & 0xfff, + rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, + fast_no_hz); +} + +/* Terminate the stall-info list. */ +static void print_cpu_stall_info_end(void) +{ + printk(KERN_ERR "\t"); +} + +/* Zero ->ticks_this_gp for all flavors of RCU. */ +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ + rdp->ticks_this_gp = 0; +} + +/* Increment ->ticks_this_gp for all flavors of RCU. */ +static void increment_cpu_stall_ticks(void) +{ + __get_cpu_var(rcu_sched_data).ticks_this_gp++; + __get_cpu_var(rcu_bh_data).ticks_this_gp++; +#ifdef CONFIG_TREE_PREEMPT_RCU + __get_cpu_var(rcu_preempt_data).ticks_this_gp++; +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +static void print_cpu_stall_info_begin(void) +{ + printk(KERN_CONT " {"); +} + +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +{ + printk(KERN_CONT " %d", cpu); +} + +static void print_cpu_stall_info_end(void) +{ + printk(KERN_CONT "} "); +} + +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ +} + +static void increment_cpu_stall_ticks(void) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 654cfe67f0d1..ed459edeff43 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -72,9 +72,9 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); - seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, " ql=%ld qs=%c%c%c%c", - rdp->qlen, + seq_printf(m, " of=%lu", rdp->offline_fqs); + seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c", + rdp->qlen_lazy, rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], ".R"[rdp->nxttail[RCU_WAIT_TAIL] != @@ -144,8 +144,8 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); - seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen, + seq_printf(m, ",%lu", rdp->offline_fqs); + seq_printf(m, ",%ld,%ld,\"%c%c%c%c\"", rdp->qlen_lazy, rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], ".R"[rdp->nxttail[RCU_WAIT_TAIL] != @@ -168,7 +168,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) { seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); - seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\""); + seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); #ifdef CONFIG_RCU_BOOST seq_puts(m, "\"kt\",\"ktl\""); #endif /* #ifdef CONFIG_RCU_BOOST */ diff --git a/kernel/resource.c b/kernel/resource.c index 7640b3a947d0..7e8ea66a8c01 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -749,6 +749,7 @@ int adjust_resource(struct resource *res, resource_size_t start, resource_size_t write_unlock(&resource_lock); return result; } +EXPORT_SYMBOL(adjust_resource); static void __init __reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, @@ -792,8 +793,6 @@ void __init reserve_region_with_split(struct resource *root, write_unlock(&resource_lock); } -EXPORT_SYMBOL(adjust_resource); - /** * resource_alignment - calculate resource's alignment * @res: resource pointer diff --git a/kernel/rwsem.c b/kernel/rwsem.c index b152f74f02de..6850f53e02d8 100644 --- a/kernel/rwsem.c +++ b/kernel/rwsem.c @@ -10,7 +10,6 @@ #include <linux/export.h> #include <linux/rwsem.h> -#include <asm/system.h> #include <linux/atomic.h> /* diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index e8a1f83ee0e7..0984a21076a3 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -195,20 +195,20 @@ __setup("noautogroup", setup_autogroup); #ifdef CONFIG_PROC_FS -int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) +int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) { static unsigned long next = INITIAL_JIFFIES; struct autogroup *ag; int err; - if (*nice < -20 || *nice > 19) + if (nice < -20 || nice > 19) return -EINVAL; - err = security_task_setnice(current, *nice); + err = security_task_setnice(current, nice); if (err) return err; - if (*nice < 0 && !can_nice(current, *nice)) + if (nice < 0 && !can_nice(current, nice)) return -EPERM; /* this is a heavy operation taking global locks.. */ @@ -219,9 +219,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) ag = autogroup_task_get(p); down_write(&ag->lock); - err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]); + err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]); if (!err) - ag->nice = *nice; + ag->nice = nice; up_write(&ag->lock); autogroup_kref_put(ag); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5255c9d2e053..afc6d7e71557 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -71,7 +71,9 @@ #include <linux/ftrace.h> #include <linux/slab.h> #include <linux/init_task.h> +#include <linux/binfmts.h> +#include <asm/switch_to.h> #include <asm/tlb.h> #include <asm/irq_regs.h> #include <asm/mutex.h> @@ -162,13 +164,13 @@ static int sched_feat_show(struct seq_file *m, void *v) #ifdef HAVE_JUMP_LABEL -#define jump_label_key__true jump_label_key_enabled -#define jump_label_key__false jump_label_key_disabled +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE #define SCHED_FEAT(name, enabled) \ jump_label_key__##enabled , -struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = { +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { #include "features.h" }; @@ -176,14 +178,14 @@ struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = { static void sched_feat_disable(int i) { - if (jump_label_enabled(&sched_feat_keys[i])) - jump_label_dec(&sched_feat_keys[i]); + if (static_key_enabled(&sched_feat_keys[i])) + static_key_slow_dec(&sched_feat_keys[i]); } static void sched_feat_enable(int i) { - if (!jump_label_enabled(&sched_feat_keys[i])) - jump_label_inc(&sched_feat_keys[i]); + if (!static_key_enabled(&sched_feat_keys[i])) + static_key_slow_inc(&sched_feat_keys[i]); } #else static void sched_feat_disable(int i) { }; @@ -894,7 +896,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) delta -= irq_delta; #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING - if (static_branch((¶virt_steal_rq_enabled))) { + if (static_key_false((¶virt_steal_rq_enabled))) { u64 st; steal = paravirt_steal_clock(cpu_of(rq)); @@ -1263,29 +1265,59 @@ EXPORT_SYMBOL_GPL(kick_process); */ static int select_fallback_rq(int cpu, struct task_struct *p) { - int dest_cpu; const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); + enum { cpuset, possible, fail } state = cpuset; + int dest_cpu; /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) return dest_cpu; + } - /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask); - if (dest_cpu < nr_cpu_ids) - return dest_cpu; + for (;;) { + /* Any allowed, online CPU? */ + for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + goto out; + } - /* No more Mr. Nice Guy. */ - dest_cpu = cpuset_cpus_allowed_fallback(p); - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", - task_pid_nr(p), p->comm, cpu); + switch (state) { + case cpuset: + /* No more Mr. Nice Guy. */ + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + + case possible: + do_set_cpus_allowed(p, cpu_possible_mask); + state = fail; + break; + + case fail: + BUG(); + break; + } + } + +out: + if (state != cpuset) { + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk_sched("process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } } return dest_cpu; @@ -1507,7 +1539,7 @@ static int ttwu_activate_remote(struct task_struct *p, int wake_flags) } #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ -static inline int ttwu_share_cache(int this_cpu, int that_cpu) +bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } @@ -1518,7 +1550,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) struct rq *rq = cpu_rq(cpu); #if defined(CONFIG_SMP) - if (sched_feat(TTWU_QUEUE) && !ttwu_share_cache(smp_processor_id(), cpu)) { + if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { sched_clock_cpu(cpu); /* sync clocks x-cpu */ ttwu_queue_remote(p, cpu); return; @@ -1932,7 +1964,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) local_irq_enable(); #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); - trace_sched_stat_sleeptime(current, rq->clock); + finish_arch_post_lock_switch(); fire_sched_in_preempt_notifiers(current); if (mm) @@ -2267,13 +2299,10 @@ calc_load_n(unsigned long load, unsigned long exp, * 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) +static void calc_global_nohz(void) { 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 @@ -2285,31 +2314,25 @@ static void calc_global_nohz(unsigned long ticks) atomic_long_add(delta, &calc_load_tasks); /* - * If we were idle for multiple load cycles, apply them. + * It could be the one fold was all it took, we done! */ - if (ticks >= LOAD_FREQ) { - n = ticks / LOAD_FREQ; + if (time_before(jiffies, calc_load_update + 10)) + return; - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; + /* + * Catch-up, fold however many we are behind still + */ + delta = jiffies - calc_load_update - 10; + n = 1 + (delta / LOAD_FREQ); - 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); + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; - calc_load_update += n * LOAD_FREQ; - } + 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); - /* - * 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. - */ + calc_load_update += n * LOAD_FREQ; } #else void calc_load_account_idle(struct rq *this_rq) @@ -2321,7 +2344,7 @@ static inline long calc_load_fold_idle(void) return 0; } -static void calc_global_nohz(unsigned long ticks) +static void calc_global_nohz(void) { } #endif @@ -2349,8 +2372,6 @@ void calc_global_load(unsigned long ticks) { long active; - calc_global_nohz(ticks); - if (time_before(jiffies, calc_load_update + 10)) return; @@ -2362,6 +2383,16 @@ void calc_global_load(unsigned long ticks) avenrun[2] = calc_load(avenrun[2], EXP_15, active); calc_load_update += LOAD_FREQ; + + /* + * Account one period with whatever state we found before + * folding in the nohz state and ageing the entire idle period. + * + * This avoids loosing a sample when we go idle between + * calc_load_account_active() (10 ticks ago) and now and thus + * under-accounting. + */ + calc_global_nohz(); } /* @@ -2756,7 +2787,7 @@ void account_idle_time(cputime_t cputime) static __always_inline bool steal_account_process_tick(void) { #ifdef CONFIG_PARAVIRT - if (static_branch(¶virt_steal_enabled)) { + if (static_key_false(¶virt_steal_enabled)) { u64 steal, st = 0; steal = paravirt_steal_clock(smp_processor_id()); @@ -3071,8 +3102,6 @@ EXPORT_SYMBOL(sub_preempt_count); */ static noinline void __schedule_bug(struct task_struct *prev) { - struct pt_regs *regs = get_irq_regs(); - if (oops_in_progress) return; @@ -3083,11 +3112,7 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); - - if (regs) - show_regs(regs); - else - dump_stack(); + dump_stack(); } /* @@ -3221,14 +3246,14 @@ need_resched: post_schedule(rq); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); if (need_resched()) goto need_resched; } static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + if (!tsk->state || tsk_is_pi_blocked(tsk)) return; /* * If we are going to sleep and we have plugged IO queued, @@ -3247,6 +3272,18 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline bool owner_running(struct mutex *lock, struct task_struct *owner) @@ -3407,9 +3444,9 @@ EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) { - __wake_up_common(q, mode, 1, 0, NULL); + __wake_up_common(q, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); @@ -3768,6 +3805,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio) rq = __task_rq_lock(p); + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; @@ -3791,11 +3846,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); +out_unlock: __task_rq_unlock(rq); } - #endif - void set_user_nice(struct task_struct *p, long nice) { int old_prio, delta, on_rq; @@ -4475,7 +4529,7 @@ SYSCALL_DEFINE0(sched_yield) __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); do_raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); schedule(); @@ -4549,8 +4603,24 @@ EXPORT_SYMBOL(__cond_resched_softirq); /** * yield - yield the current processor to other threads. * - * This is a shortcut for kernel-space yielding - it marks the - * thread runnable and calls sys_sched_yield(). + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! */ void __sched yield(void) { @@ -5382,7 +5452,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: + case CPU_STARTING: case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -5754,7 +5824,7 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) * * Also keep a unique ID per domain (we use the first cpu number in * the cpumask of the domain), this allows us to quickly tell if - * two cpus are in the same cache domain, see ttwu_share_cache(). + * two cpus are in the same cache domain, see cpus_share_cache(). */ DEFINE_PER_CPU(struct sched_domain *, sd_llc); DEFINE_PER_CPU(int, sd_llc_id); @@ -6931,6 +7001,9 @@ void __init sched_init(void) rq->online = 0; rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; + + INIT_LIST_HEAD(&rq->cfs_tasks); + rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ rq->nohz_flags = 0; @@ -7525,8 +7598,7 @@ static inline struct task_group *cgroup_tg(struct cgroup *cgrp) struct task_group, css); } -static struct cgroup_subsys_state * -cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) +static struct cgroup_subsys_state *cpu_cgroup_create(struct cgroup *cgrp) { struct task_group *tg, *parent; @@ -7543,15 +7615,14 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) return &tg->css; } -static void -cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +static void cpu_cgroup_destroy(struct cgroup *cgrp) { struct task_group *tg = cgroup_tg(cgrp); sched_destroy_group(tg); } -static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, +static int cpu_cgroup_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *task; @@ -7569,7 +7640,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, return 0; } -static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, +static void cpu_cgroup_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *task; @@ -7579,8 +7650,8 @@ static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, } static void -cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task) +cpu_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp, + struct task_struct *task) { /* * cgroup_exit() is called in the copy_process() failure path. @@ -7899,13 +7970,9 @@ static struct cftype cpu_files[] = { .write_u64 = cpu_rt_period_write_uint, }, #endif + { } /* terminate */ }; -static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) -{ - return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files)); -} - struct cgroup_subsys cpu_cgroup_subsys = { .name = "cpu", .create = cpu_cgroup_create, @@ -7913,8 +7980,8 @@ struct cgroup_subsys cpu_cgroup_subsys = { .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, .exit = cpu_cgroup_exit, - .populate = cpu_cgroup_populate, .subsys_id = cpu_cgroup_subsys_id, + .base_cftypes = cpu_files, .early_init = 1, }; @@ -7930,8 +7997,7 @@ struct cgroup_subsys cpu_cgroup_subsys = { */ /* create a new cpu accounting group */ -static struct cgroup_subsys_state *cpuacct_create( - struct cgroup_subsys *ss, struct cgroup *cgrp) +static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp) { struct cpuacct *ca; @@ -7961,8 +8027,7 @@ out: } /* destroy an existing cpu accounting group */ -static void -cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +static void cpuacct_destroy(struct cgroup *cgrp) { struct cpuacct *ca = cgroup_ca(cgrp); @@ -8101,13 +8166,9 @@ static struct cftype files[] = { .name = "stat", .read_map = cpuacct_stats_show, }, + { } /* terminate */ }; -static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) -{ - return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files)); -} - /* * charge this task's execution time to its accounting group. * @@ -8139,7 +8200,7 @@ struct cgroup_subsys cpuacct_subsys = { .name = "cpuacct", .create = cpuacct_create, .destroy = cpuacct_destroy, - .populate = cpuacct_populate, .subsys_id = cpuacct_subsys_id, + .base_cftypes = files, }; #endif /* CONFIG_CGROUP_CPUACCT */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 2a075e10004b..09acaa15161d 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -288,7 +288,6 @@ static void print_cpu(struct seq_file *m, int cpu) P(yld_count); - P(sched_switch); P(sched_count); P(sched_goidle); #ifdef CONFIG_SMP diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7c6414fc669d..0d97ebdc58f0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -416,8 +416,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) #endif /* CONFIG_FAIR_GROUP_SCHED */ -static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec); +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -776,29 +776,16 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ -#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ - cfs_rq->task_weight += weight; -} -#else -static inline void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ -} -#endif - static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); if (!parent_entity(se)) update_load_add(&rq_of(cfs_rq)->load, se->load.weight); - if (entity_is_task(se)) { - add_cfs_task_weight(cfs_rq, se->load.weight); - list_add(&se->group_node, &cfs_rq->tasks); - } +#ifdef CONFIG_SMP + if (entity_is_task(se)) + list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks); +#endif cfs_rq->nr_running++; } @@ -808,10 +795,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_sub(&cfs_rq->load, se->load.weight); if (!parent_entity(se)) update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); - if (entity_is_task(se)) { - add_cfs_task_weight(cfs_rq, -se->load.weight); + if (entity_is_task(se)) list_del_init(&se->group_node); - } cfs_rq->nr_running--; } @@ -1003,6 +988,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) if (unlikely(delta > se->statistics.sleep_max)) se->statistics.sleep_max = delta; + se->statistics.sleep_start = 0; se->statistics.sum_sleep_runtime += delta; if (tsk) { @@ -1019,6 +1005,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) if (unlikely(delta > se->statistics.block_max)) se->statistics.block_max = delta; + se->statistics.block_start = 0; se->statistics.sum_sleep_runtime += delta; if (tsk) { @@ -1175,7 +1162,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) __clear_buddies_skip(se); } -static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) @@ -1399,20 +1386,20 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) #ifdef CONFIG_CFS_BANDWIDTH #ifdef HAVE_JUMP_LABEL -static struct jump_label_key __cfs_bandwidth_used; +static struct static_key __cfs_bandwidth_used; static inline bool cfs_bandwidth_used(void) { - return static_branch(&__cfs_bandwidth_used); + return static_key_false(&__cfs_bandwidth_used); } void account_cfs_bandwidth_used(int enabled, int was_enabled) { /* only need to count groups transitioning between enabled/!enabled */ if (enabled && !was_enabled) - jump_label_inc(&__cfs_bandwidth_used); + static_key_slow_inc(&__cfs_bandwidth_used); else if (!enabled && was_enabled) - jump_label_dec(&__cfs_bandwidth_used); + static_key_slow_dec(&__cfs_bandwidth_used); } #else /* HAVE_JUMP_LABEL */ static bool cfs_bandwidth_used(void) @@ -1559,8 +1546,8 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, resched_task(rq_of(cfs_rq)->curr); } -static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) { if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) return; @@ -2086,11 +2073,11 @@ void unthrottle_offline_cfs_rqs(struct rq *rq) } #else /* CONFIG_CFS_BANDWIDTH */ -static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) {} +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) {} static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} -static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) { @@ -2670,8 +2657,6 @@ static int select_idle_sibling(struct task_struct *p, int target) /* * Otherwise, iterate the domains and find an elegible idle cpu. */ - rcu_read_lock(); - sd = rcu_dereference(per_cpu(sd_llc, target)); for_each_lower_domain(sd) { sg = sd->groups; @@ -2693,8 +2678,6 @@ next: } while (sg != sd->groups); } done: - rcu_read_unlock(); - return target; } @@ -2920,7 +2903,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; /* - * This is possible from callers such as pull_task(), in which we + * This is possible from callers such as move_task(), in which we * unconditionally check_prempt_curr() after an enqueue (which may have * lead to a throttle). This both saves work and prevents false * next-buddy nomination below. @@ -3084,17 +3067,39 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * Fair scheduling class load-balancing methods: */ +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + +#define LBF_ALL_PINNED 0x01 +#define LBF_NEED_BREAK 0x02 + +struct lb_env { + struct sched_domain *sd; + + int src_cpu; + struct rq *src_rq; + + int dst_cpu; + struct rq *dst_rq; + + enum cpu_idle_type idle; + long load_move; + unsigned int flags; + + unsigned int loop; + unsigned int loop_break; + unsigned int loop_max; +}; + /* - * pull_task - move a task from a remote runqueue to the local runqueue. + * move_task - move a task from one runqueue to another runqueue. * Both runqueues must be locked. */ -static void pull_task(struct rq *src_rq, struct task_struct *p, - struct rq *this_rq, int this_cpu) +static void move_task(struct task_struct *p, struct lb_env *env) { - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); - check_preempt_curr(this_rq, p, 0); + deactivate_task(env->src_rq, p, 0); + set_task_cpu(p, env->dst_cpu); + activate_task(env->dst_rq, p, 0); + check_preempt_curr(env->dst_rq, p, 0); } /* @@ -3129,19 +3134,11 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) return delta < (s64)sysctl_sched_migration_cost; } -#define LBF_ALL_PINNED 0x01 -#define LBF_NEED_BREAK 0x02 /* clears into HAD_BREAK */ -#define LBF_HAD_BREAK 0x04 -#define LBF_HAD_BREAKS 0x0C /* count HAD_BREAKs overflows into ABORT */ -#define LBF_ABORT 0x10 - /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ static -int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +int can_migrate_task(struct task_struct *p, struct lb_env *env) { int tsk_cache_hot = 0; /* @@ -3150,13 +3147,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) cannot be migrated to this CPU due to cpus_allowed, or * 3) are cache-hot on their current CPU. */ - if (!cpumask_test_cpu(this_cpu, tsk_cpus_allowed(p))) { + if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { schedstat_inc(p, se.statistics.nr_failed_migrations_affine); return 0; } - *lb_flags &= ~LBF_ALL_PINNED; + env->flags &= ~LBF_ALL_PINNED; - if (task_running(rq, p)) { + if (task_running(env->src_rq, p)) { schedstat_inc(p, se.statistics.nr_failed_migrations_running); return 0; } @@ -3167,12 +3164,12 @@ 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_task, sd); + tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); if (!tsk_cache_hot || - sd->nr_balance_failed > sd->cache_nice_tries) { + env->sd->nr_balance_failed > env->sd->cache_nice_tries) { #ifdef CONFIG_SCHEDSTATS if (tsk_cache_hot) { - schedstat_inc(sd, lb_hot_gained[idle]); + schedstat_inc(env->sd, lb_hot_gained[env->idle]); schedstat_inc(p, se.statistics.nr_forced_migrations); } #endif @@ -3193,65 +3190,80 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * * Called with both runqueues locked. */ -static int -move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) +static int move_one_task(struct lb_env *env) { struct task_struct *p, *n; - struct cfs_rq *cfs_rq; - int pinned = 0; - for_each_leaf_cfs_rq(busiest, cfs_rq) { - list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) { - if (throttled_lb_pair(task_group(p), - busiest->cpu, this_cpu)) - break; + list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { + if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu)) + continue; - if (!can_migrate_task(p, busiest, this_cpu, - sd, idle, &pinned)) - continue; + if (!can_migrate_task(p, env)) + continue; - pull_task(busiest, p, this_rq, this_cpu); - /* - * Right now, this is only the second place pull_task() - * is called, so we can safely collect pull_task() - * stats here rather than inside pull_task(). - */ - schedstat_inc(sd, lb_gained[idle]); - return 1; - } + move_task(p, env); + /* + * Right now, this is only the second place move_task() + * is called, so we can safely collect move_task() + * stats here rather than inside move_task(). + */ + schedstat_inc(env->sd, lb_gained[env->idle]); + return 1; } - return 0; } -static unsigned long -balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, struct sched_domain *sd, - enum cpu_idle_type idle, int *lb_flags, - struct cfs_rq *busiest_cfs_rq) +static unsigned long task_h_load(struct task_struct *p); + +/* + * move_tasks tries to move up to load_move weighted load from busiest to + * this_rq, as part of a balancing operation within domain "sd". + * Returns 1 if successful and 0 otherwise. + * + * Called with both runqueues locked. + */ +static int move_tasks(struct lb_env *env) { - int loops = 0, pulled = 0; - long rem_load_move = max_load_move; - struct task_struct *p, *n; + struct list_head *tasks = &env->src_rq->cfs_tasks; + struct task_struct *p; + unsigned long load; + int pulled = 0; + + if (env->load_move <= 0) + return 0; - if (max_load_move == 0) - goto out; + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); - list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) { - if (loops++ > sysctl_sched_nr_migrate) { - *lb_flags |= LBF_NEED_BREAK; + env->loop++; + /* We've more or less seen every task there is, call it quits */ + if (env->loop > env->loop_max) + break; + + /* take a breather every nr_migrate tasks */ + if (env->loop > env->loop_break) { + env->loop_break += sysctl_sched_nr_migrate; + env->flags |= LBF_NEED_BREAK; break; } - if ((p->se.load.weight >> 1) > rem_load_move || - !can_migrate_task(p, busiest, this_cpu, sd, idle, - lb_flags)) - continue; + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + goto next; + + load = task_h_load(p); + + if (load < 16 && !env->sd->nr_balance_failed) + goto next; + + if ((load / 2) > env->load_move) + goto next; - pull_task(busiest, p, this_rq, this_cpu); + if (!can_migrate_task(p, env)) + goto next; + + move_task(p, env); pulled++; - rem_load_move -= p->se.load.weight; + env->load_move -= load; #ifdef CONFIG_PREEMPT /* @@ -3259,28 +3271,30 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, * kernels will stop after the first task is pulled to minimize * the critical section. */ - if (idle == CPU_NEWLY_IDLE) { - *lb_flags |= LBF_ABORT; + if (env->idle == CPU_NEWLY_IDLE) break; - } #endif /* * We only want to steal up to the prescribed amount of * weighted load. */ - if (rem_load_move <= 0) + if (env->load_move <= 0) break; + + continue; +next: + list_move_tail(&p->se.group_node, tasks); } -out: + /* - * Right now, this is one of only two places pull_task() is called, - * so we can safely collect pull_task() stats here rather than - * inside pull_task(). + * Right now, this is one of only two places move_task() is called, + * so we can safely collect move_task() stats here rather than + * inside move_task(). */ - schedstat_add(sd, lb_gained[idle], pulled); + schedstat_add(env->sd, lb_gained[env->idle], pulled); - return max_load_move - rem_load_move; + return pulled; } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -3360,113 +3374,35 @@ static int tg_load_down(struct task_group *tg, void *data) static void update_h_load(long cpu) { + rcu_read_lock(); walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); + rcu_read_unlock(); } -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +static unsigned long task_h_load(struct task_struct *p) { - long rem_load_move = max_load_move; - struct cfs_rq *busiest_cfs_rq; - - rcu_read_lock(); - update_h_load(cpu_of(busiest)); - - for_each_leaf_cfs_rq(busiest, busiest_cfs_rq) { - unsigned long busiest_h_load = busiest_cfs_rq->h_load; - unsigned long busiest_weight = busiest_cfs_rq->load.weight; - u64 rem_load, moved_load; - - if (*lb_flags & (LBF_NEED_BREAK|LBF_ABORT)) - break; - - /* - * empty group or part of a throttled hierarchy - */ - if (!busiest_cfs_rq->task_weight || - throttled_lb_pair(busiest_cfs_rq->tg, cpu_of(busiest), this_cpu)) - continue; - - rem_load = (u64)rem_load_move * busiest_weight; - rem_load = div_u64(rem_load, busiest_h_load + 1); - - moved_load = balance_tasks(this_rq, this_cpu, busiest, - rem_load, sd, idle, lb_flags, - busiest_cfs_rq); - - if (!moved_load) - continue; + struct cfs_rq *cfs_rq = task_cfs_rq(p); + unsigned long load; - moved_load *= busiest_h_load; - moved_load = div_u64(moved_load, busiest_weight + 1); + load = p->se.load.weight; + load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1); - rem_load_move -= moved_load; - if (rem_load_move < 0) - break; - } - rcu_read_unlock(); - - return max_load_move - rem_load_move; + return load; } #else static inline void update_shares(int cpu) { } -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +static inline void update_h_load(long cpu) { - return balance_tasks(this_rq, this_cpu, busiest, - max_load_move, sd, idle, lb_flags, - &busiest->cfs); } -#endif -/* - * move_tasks tries to move up to max_load_move weighted load from busiest to - * this_rq, as part of a balancing operation within domain "sd". - * Returns 1 if successful and 0 otherwise. - * - * Called with both runqueues locked. - */ -static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +static unsigned long task_h_load(struct task_struct *p) { - unsigned long total_load_moved = 0, load_moved; - - do { - load_moved = load_balance_fair(this_rq, this_cpu, busiest, - max_load_move - total_load_moved, - sd, idle, lb_flags); - - total_load_moved += load_moved; - - if (*lb_flags & (LBF_NEED_BREAK|LBF_ABORT)) - break; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible - * kernels will stop after the first task is pulled to minimize - * the critical section. - */ - if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) { - *lb_flags |= LBF_ABORT; - break; - } -#endif - } while (load_moved && max_load_move > total_load_moved); - - return total_load_moved > 0; + return p->se.load.weight; } +#endif /********** Helpers for find_busiest_group ************************/ /* @@ -3776,6 +3712,11 @@ void update_group_power(struct sched_domain *sd, int cpu) struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; unsigned long power; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgp->next_update = jiffies + interval; if (!child) { update_cpu_power(sd, cpu); @@ -3883,12 +3824,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * domains. In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ - if (idle != CPU_NEWLY_IDLE && local_group) { - if (balance_cpu != this_cpu) { - *balance = 0; - return; - } - update_group_power(sd, this_cpu); + if (local_group) { + if (idle != CPU_NEWLY_IDLE) { + if (balance_cpu != this_cpu) { + *balance = 0; + return; + } + update_group_power(sd, this_cpu); + } else if (time_after_eq(jiffies, group->sgp->next_update)) + update_group_power(sd, this_cpu); } /* Adjust by relative CPU power of the group */ @@ -4451,13 +4395,21 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, int *balance) { - int ld_moved, lb_flags = 0, active_balance = 0; + int ld_moved, active_balance = 0; struct sched_group *group; unsigned long imbalance; struct rq *busiest; unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); + struct lb_env env = { + .sd = sd, + .dst_cpu = this_cpu, + .dst_rq = this_rq, + .idle = idle, + .loop_break = sysctl_sched_nr_migrate, + }; + cpumask_copy(cpus, cpu_active_mask); schedstat_inc(sd, lb_count[idle]); @@ -4492,32 +4444,34 @@ redo: * still unbalanced. ld_moved simply stays zero, so it is * correctly treated as an imbalance. */ - lb_flags |= LBF_ALL_PINNED; + env.flags |= LBF_ALL_PINNED; + env.load_move = imbalance; + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + env.loop_max = busiest->nr_running; + +more_balance: local_irq_save(flags); double_rq_lock(this_rq, busiest); - ld_moved = move_tasks(this_rq, this_cpu, busiest, - imbalance, sd, idle, &lb_flags); + if (!env.loop) + update_h_load(env.src_cpu); + ld_moved += move_tasks(&env); double_rq_unlock(this_rq, busiest); local_irq_restore(flags); + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + goto more_balance; + } + /* * some other cpu did the load balance for us. */ if (ld_moved && this_cpu != smp_processor_id()) resched_cpu(this_cpu); - if (lb_flags & LBF_ABORT) - goto out_balanced; - - if (lb_flags & LBF_NEED_BREAK) { - lb_flags += LBF_HAD_BREAK - LBF_NEED_BREAK; - if (lb_flags & LBF_ABORT) - goto out_balanced; - goto redo; - } - /* All tasks on this runqueue were pinned by CPU affinity */ - if (unlikely(lb_flags & LBF_ALL_PINNED)) { + if (unlikely(env.flags & LBF_ALL_PINNED)) { cpumask_clear_cpu(cpu_of(busiest), cpus); if (!cpumask_empty(cpus)) goto redo; @@ -4547,7 +4501,7 @@ redo: tsk_cpus_allowed(busiest->curr))) { raw_spin_unlock_irqrestore(&busiest->lock, flags); - lb_flags |= LBF_ALL_PINNED; + env.flags |= LBF_ALL_PINNED; goto out_one_pinned; } @@ -4600,7 +4554,7 @@ out_balanced: out_one_pinned: /* tune up the balancing interval */ - if (((lb_flags & LBF_ALL_PINNED) && + if (((env.flags & LBF_ALL_PINNED) && sd->balance_interval < MAX_PINNED_INTERVAL) || (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; @@ -4710,10 +4664,18 @@ static int active_load_balance_cpu_stop(void *data) } if (likely(sd)) { + struct lb_env env = { + .sd = sd, + .dst_cpu = target_cpu, + .dst_rq = target_rq, + .src_cpu = busiest_rq->cpu, + .src_rq = busiest_rq, + .idle = CPU_IDLE, + }; + schedstat_inc(sd, alb_count); - if (move_one_task(target_rq, target_cpu, busiest_rq, - sd, CPU_IDLE)) + if (move_one_task(&env)) schedstat_inc(sd, alb_pushed); else schedstat_inc(sd, alb_failed); @@ -4945,8 +4907,6 @@ static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, static DEFINE_SPINLOCK(balancing); -static unsigned long __read_mostly max_load_balance_interval = HZ/10; - /* * Scale the max load_balance interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. @@ -5340,7 +5300,6 @@ static void set_curr_task_fair(struct rq *rq) void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT; - INIT_LIST_HEAD(&cfs_rq->tasks); cfs_rq->min_vruntime = (u64)(-(1LL << 20)); #ifndef CONFIG_64BIT cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; @@ -5612,6 +5571,7 @@ __init void init_sched_fair_class(void) open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); #ifdef CONFIG_NO_HZ + nohz.next_balance = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); cpu_notifier(sched_ilb_notifier, 0); #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f42ae7fb5ec5..44af55e6d5d0 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -778,12 +778,9 @@ static inline int balance_runtime(struct rt_rq *rt_rq) static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) { - int i, idle = 1; + int i, idle = 1, throttled = 0; const struct cpumask *span; - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return 1; - span = sched_rt_period_mask(); for_each_cpu(i, span) { int enqueue = 0; @@ -818,12 +815,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (!rt_rq_throttled(rt_rq)) enqueue = 1; } + if (rt_rq->rt_throttled) + throttled = 1; if (enqueue) sched_rt_rq_enqueue(rt_rq); raw_spin_unlock(&rq->lock); } + if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) + return 1; + return idle; } @@ -855,8 +857,30 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) return 0; if (rt_rq->rt_time > runtime) { - rt_rq->rt_throttled = 1; - printk_once(KERN_WARNING "sched: RT throttling activated\n"); + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + /* + * Don't actually throttle groups that have no runtime assigned + * but accrue some time due to boosting. + */ + if (likely(rt_b->rt_runtime)) { + static bool once = false; + + rt_rq->rt_throttled = 1; + + if (!once) { + once = true; + printk_sched("sched: RT throttling activated\n"); + } + } else { + /* + * In case we did anyway, make it go away, + * replenishment is a joke, since it will replenish us + * with exactly 0 ns. + */ + rt_rq->rt_time = 0; + } + if (rt_rq_throttled(rt_rq)) { sched_rt_rq_dequeue(rt_rq); return 1; @@ -884,7 +908,8 @@ static void update_curr_rt(struct rq *rq) if (unlikely((s64)delta_exec < 0)) delta_exec = 0; - schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); @@ -1403,7 +1428,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) next_idx: if (idx >= MAX_RT_PRIO) continue; - if (next && next->prio < idx) + if (next && next->prio <= idx) continue; list_for_each_entry(rt_se, array->queue + idx, run_list) { struct task_struct *p; @@ -1972,7 +1997,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) if (--p->rt.time_slice) return; - p->rt.time_slice = DEF_TIMESLICE; + p->rt.time_slice = RR_TIMESLICE; /* * Requeue to the end of queue if we are not the only element @@ -2000,7 +2025,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) * Time slice is 0 for SCHED_FIFO tasks */ if (task->policy == SCHED_RR) - return DEF_TIMESLICE; + return RR_TIMESLICE; else return 0; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 98c0c2623db8..fb3acba4d52e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -36,11 +36,7 @@ extern __read_mostly int scheduler_running; /* * These are the 'tuning knobs' of the scheduler: - * - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. */ -#define DEF_TIMESLICE (100 * HZ / 1000) /* * single value that denotes runtime == period, ie unlimited time. @@ -216,9 +212,6 @@ struct cfs_rq { struct rb_root tasks_timeline; struct rb_node *rb_leftmost; - struct list_head tasks; - struct list_head *balance_iterator; - /* * 'curr' points to currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). @@ -246,11 +239,6 @@ struct cfs_rq { #ifdef CONFIG_SMP /* - * the part of load.weight contributed by tasks - */ - unsigned long task_weight; - - /* * h_load = weight * f(tg) * * Where f(tg) is the recursive weight fraction assigned to @@ -424,6 +412,8 @@ struct rq { int cpu; int online; + struct list_head cfs_tasks; + u64 rt_avg; u64 age_stamp; u64 idle_stamp; @@ -462,7 +452,6 @@ struct rq { unsigned int yld_count; /* schedule() stats */ - unsigned int sched_switch; unsigned int sched_count; unsigned int sched_goidle; @@ -611,7 +600,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) * Tunables that become constants when CONFIG_SCHED_DEBUG is off: */ #ifdef CONFIG_SCHED_DEBUG -# include <linux/jump_label.h> +# include <linux/static_key.h> # define const_debug __read_mostly #else # define const_debug const @@ -630,18 +619,18 @@ enum { #undef SCHED_FEAT #if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) -static __always_inline bool static_branch__true(struct jump_label_key *key) +static __always_inline bool static_branch__true(struct static_key *key) { - return likely(static_branch(key)); /* Not out of line branch. */ + return static_key_true(key); /* Not out of line branch. */ } -static __always_inline bool static_branch__false(struct jump_label_key *key) +static __always_inline bool static_branch__false(struct static_key *key) { - return unlikely(static_branch(key)); /* Out of line branch. */ + return static_key_false(key); /* Out of line branch. */ } #define SCHED_FEAT(name, enabled) \ -static __always_inline bool static_branch_##name(struct jump_label_key *key) \ +static __always_inline bool static_branch_##name(struct static_key *key) \ { \ return static_branch__##enabled(key); \ } @@ -650,7 +639,7 @@ static __always_inline bool static_branch_##name(struct jump_label_key *key) \ #undef SCHED_FEAT -extern struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR]; +extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) #else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */ #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) @@ -692,6 +681,9 @@ static inline int task_running(struct rq *rq, struct task_struct *p) #ifndef finish_arch_switch # define finish_arch_switch(prev) do { } while (0) #endif +#ifndef finish_arch_post_lock_switch +# define finish_arch_post_lock_switch() do { } while (0) +#endif #ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 2a581ba8e190..903ffa9e8872 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -32,9 +32,9 @@ static int show_schedstat(struct seq_file *seq, void *v) /* runqueue-specific stats */ seq_printf(seq, - "cpu%d %u %u %u %u %u %u %llu %llu %lu", + "cpu%d %u 0 %u %u %u %u %llu %llu %lu", cpu, rq->yld_count, - rq->sched_switch, rq->sched_count, rq->sched_goidle, + rq->sched_count, rq->sched_goidle, rq->ttwu_count, rq->ttwu_local, rq->rq_cpu_time, rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount); diff --git a/kernel/signal.c b/kernel/signal.c index c73c4284160e..17afcaf582d0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -36,6 +36,7 @@ #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/siginfo.h> +#include <asm/cacheflush.h> #include "audit.h" /* audit_signal_info() */ /* @@ -58,21 +59,20 @@ static int sig_handler_ignored(void __user *handler, int sig) (handler == SIG_DFL && sig_kernel_ignore(sig)); } -static int sig_task_ignored(struct task_struct *t, int sig, - int from_ancestor_ns) +static int sig_task_ignored(struct task_struct *t, int sig, bool force) { void __user *handler; handler = sig_handler(t, sig); if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && - handler == SIG_DFL && !from_ancestor_ns) + handler == SIG_DFL && !force) return 1; return sig_handler_ignored(handler, sig); } -static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns) +static int sig_ignored(struct task_struct *t, int sig, bool force) { /* * Blocked signals are never ignored, since the @@ -82,7 +82,7 @@ static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns) if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return 0; - if (!sig_task_ignored(t, sig, from_ancestor_ns)) + if (!sig_task_ignored(t, sig, force)) return 0; /* @@ -855,7 +855,7 @@ static void ptrace_trap_notify(struct task_struct *t) * Returns true if the signal should be actually delivered, otherwise * it should be dropped. */ -static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) +static int prepare_signal(int sig, struct task_struct *p, bool force) { struct signal_struct *signal = p->signal; struct task_struct *t; @@ -915,7 +915,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) } } - return !sig_ignored(p, sig, from_ancestor_ns); + return !sig_ignored(p, sig, force); } /* @@ -1054,13 +1054,14 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, struct sigpending *pending; struct sigqueue *q; int override_rlimit; - - trace_signal_generate(sig, info, t); + int ret = 0, result; assert_spin_locked(&t->sighand->siglock); - if (!prepare_signal(sig, t, from_ancestor_ns)) - return 0; + result = TRACE_SIGNAL_IGNORED; + if (!prepare_signal(sig, t, + from_ancestor_ns || (info == SEND_SIG_FORCED))) + goto ret; pending = group ? &t->signal->shared_pending : &t->pending; /* @@ -1068,8 +1069,11 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, * exactly one non-rt signal, so that we can get more * detailed information about the cause of the signal. */ + result = TRACE_SIGNAL_ALREADY_PENDING; if (legacy_queue(pending, sig)) - return 0; + goto ret; + + result = TRACE_SIGNAL_DELIVERED; /* * fast-pathed signals for kernel-internal things like SIGSTOP * or SIGKILL. @@ -1127,14 +1131,15 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, * signal was rt and sent by user using something * other than kill(). */ - trace_signal_overflow_fail(sig, group, info); - return -EAGAIN; + result = TRACE_SIGNAL_OVERFLOW_FAIL; + ret = -EAGAIN; + goto ret; } else { /* * This is a silent loss of information. We still * send the signal, but the *info bits are lost. */ - trace_signal_lose_info(sig, group, info); + result = TRACE_SIGNAL_LOSE_INFO; } } @@ -1142,7 +1147,9 @@ out_set: signalfd_notify(t, sig); sigaddset(&pending->signal, sig); complete_signal(sig, t, group); - return 0; +ret: + trace_signal_generate(sig, info, t, group, result); + return ret; } static int send_signal(int sig, struct siginfo *info, struct task_struct *t, @@ -1585,7 +1592,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) int sig = q->info.si_signo; struct sigpending *pending; unsigned long flags; - int ret; + int ret, result; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); @@ -1594,7 +1601,8 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) goto ret; ret = 1; /* the signal is ignored */ - if (!prepare_signal(sig, t, 0)) + result = TRACE_SIGNAL_IGNORED; + if (!prepare_signal(sig, t, false)) goto out; ret = 0; @@ -1605,6 +1613,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) */ BUG_ON(q->info.si_code != SI_TIMER); q->info.si_overrun++; + result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } q->info.si_overrun = 0; @@ -1614,7 +1623,9 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) list_add_tail(&q->list, &pending->list); sigaddset(&pending->signal, sig); complete_signal(sig, t, group); + result = TRACE_SIGNAL_DELIVERED; out: + trace_signal_generate(sig, &q->info, t, group, result); unlock_task_sighand(t, &flags); ret: return ret; @@ -1642,6 +1653,15 @@ bool do_notify_parent(struct task_struct *tsk, int sig) BUG_ON(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); + if (sig != SIGCHLD) { + /* + * This is only possible if parent == real_parent. + * Check if it has changed security domain. + */ + if (tsk->parent_exec_id != tsk->parent->self_exec_id) + sig = SIGCHLD; + } + info.si_signo = sig; info.si_errno = 0; /* diff --git a/kernel/smp.c b/kernel/smp.c index db197d60489b..2f8b10ecf759 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -701,3 +701,93 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait) return ret; } EXPORT_SYMBOL(on_each_cpu); + +/** + * on_each_cpu_mask(): Run a function on processors specified by + * cpumask, which may include the local processor. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or + * from a hardware interrupt handler or from a bottom half handler. + */ +void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, + void *info, bool wait) +{ + int cpu = get_cpu(); + + smp_call_function_many(mask, func, info, wait); + if (cpumask_test_cpu(cpu, mask)) { + local_irq_disable(); + func(info); + local_irq_enable(); + } + put_cpu(); +} +EXPORT_SYMBOL(on_each_cpu_mask); + +/* + * on_each_cpu_cond(): Call a function on each processor for which + * the supplied function cond_func returns true, optionally waiting + * for all the required CPUs to finish. This may include the local + * processor. + * @cond_func: A callback function that is passed a cpu id and + * the the info parameter. The function is called + * with preemption disabled. The function should + * return a blooean value indicating whether to IPI + * the specified CPU. + * @func: The function to run on all applicable CPUs. + * This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to both functions. + * @wait: If true, wait (atomically) until function has + * completed on other CPUs. + * @gfp_flags: GFP flags to use when allocating the cpumask + * used internally by the function. + * + * The function might sleep if the GFP flags indicates a non + * atomic allocation is allowed. + * + * Preemption is disabled to protect against CPUs going offline but not online. + * CPUs going online during the call will not be seen or sent an IPI. + * + * You must not call this function with disabled interrupts or + * from a hardware interrupt handler or from a bottom half handler. + */ +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags) +{ + cpumask_var_t cpus; + int cpu, ret; + + might_sleep_if(gfp_flags & __GFP_WAIT); + + if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { + preempt_disable(); + for_each_online_cpu(cpu) + if (cond_func(cpu, info)) + cpumask_set_cpu(cpu, cpus); + on_each_cpu_mask(cpus, func, info, wait); + preempt_enable(); + free_cpumask_var(cpus); + } else { + /* + * No free cpumask, bother. No matter, we'll + * just have to IPI them one by one. + */ + preempt_disable(); + for_each_online_cpu(cpu) + if (cond_func(cpu, info)) { + ret = smp_call_function_single(cpu, func, + info, wait); + WARN_ON_ONCE(!ret); + } + preempt_enable(); + } +} +EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/softirq.c b/kernel/softirq.c index 4eb3a0fa351e..671f9594e368 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -297,7 +297,7 @@ void irq_enter(void) int cpu = smp_processor_id(); rcu_irq_enter(); - if (idle_cpu(cpu) && !in_interrupt()) { + if (is_idle_task(current) && !in_interrupt()) { /* * Prevent raise_softirq from needlessly waking up ksoftirqd * here, as softirq will be serviced on return from interrupt. @@ -310,31 +310,21 @@ void irq_enter(void) __irq_enter(); } -#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED static inline void invoke_softirq(void) { - if (!force_irqthreads) + if (!force_irqthreads) { +#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED __do_softirq(); - else { - __local_bh_disable((unsigned long)__builtin_return_address(0), - SOFTIRQ_OFFSET); - wakeup_softirqd(); - __local_bh_enable(SOFTIRQ_OFFSET); - } -} #else -static inline void invoke_softirq(void) -{ - if (!force_irqthreads) do_softirq(); - else { +#endif + } else { __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); wakeup_softirqd(); __local_bh_enable(SOFTIRQ_OFFSET); } } -#endif /* * Exit an interrupt context. Process softirqs if needed and possible: @@ -353,7 +343,7 @@ void irq_exit(void) tick_nohz_irq_exit(); #endif rcu_irq_exit(); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); } /* @@ -385,6 +375,12 @@ void raise_softirq(unsigned int nr) local_irq_restore(flags); } +void __raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); +} + void open_softirq(int nr, void (*action)(struct softirq_action *)) { softirq_vec[nr].action = action; @@ -744,9 +740,7 @@ static int run_ksoftirqd(void * __bind_cpu) while (!kthread_should_stop()) { preempt_disable(); if (!local_softirq_pending()) { - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } __set_current_state(TASK_RUNNING); @@ -761,7 +755,7 @@ static int run_ksoftirqd(void * __bind_cpu) if (local_softirq_pending()) __do_softirq(); local_irq_enable(); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); cond_resched(); preempt_disable(); rcu_note_context_switch((long)__bind_cpu); diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 84c7d96918bf..5cdd8065a3ce 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -163,7 +163,7 @@ void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock) EXPORT_SYMBOL(_raw_spin_lock_bh); #endif -#ifndef CONFIG_INLINE_SPIN_UNLOCK +#ifdef CONFIG_UNINLINE_SPIN_UNLOCK void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock) { __raw_spin_unlock(lock); diff --git a/kernel/srcu.c b/kernel/srcu.c index 0febf61e1aa3..ba35f3a4a1f4 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -172,6 +172,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) { int idx; + rcu_lockdep_assert(!lock_is_held(&sp->dep_map) && + !lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section"); + idx = sp->completed; mutex_lock(&sp->mutex); @@ -280,19 +286,26 @@ void synchronize_srcu(struct srcu_struct *sp) EXPORT_SYMBOL_GPL(synchronize_srcu); /** - * synchronize_srcu_expedited - like synchronize_srcu, but less patient + * synchronize_srcu_expedited - Brute-force SRCU grace period * @sp: srcu_struct with which to synchronize. * - * Flip the completed counter, and wait for the old count to drain to zero. - * As with classic RCU, the updater must use some separate means of - * synchronizing concurrent updates. Can block; must be called from - * process context. + * Wait for an SRCU grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_srcu_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_srcu() instead. * - * Note that it is illegal to call synchronize_srcu_expedited() - * from the corresponding SRCU read-side critical section; doing so - * will result in deadlock. However, it is perfectly legal to call - * synchronize_srcu_expedited() on one srcu_struct from some other - * srcu_struct's read-side critical section. + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. It is also illegal to call + * synchronize_srcu_expedited() from the corresponding SRCU read-side + * critical section; doing so will result in deadlock. However, it is + * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct + * from some other srcu_struct's read-side critical section, as long as + * the resulting graph of srcu_structs is acyclic. */ void synchronize_srcu_expedited(struct srcu_struct *sp) { diff --git a/kernel/sys.c b/kernel/sys.c index 40701538fbd1..e7006eb6c1e4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -444,6 +444,15 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, magic2 != LINUX_REBOOT_MAGIC2C)) return -EINVAL; + /* + * If pid namespaces are enabled and the current task is in a child + * pid_namespace, the command is handled by reboot_pid_ns() which will + * call do_exit(). + */ + ret = reboot_pid_ns(task_active_pid_ns(current), cmd); + if (ret) + return ret; + /* Instead of trying to make the power_off code look like * halt when pm_power_off is not set do it the easy way. */ @@ -1706,7 +1715,7 @@ static int prctl_set_mm(int opt, unsigned long addr, if (arg4 | arg5) return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (addr >= TASK_SIZE) @@ -1962,6 +1971,14 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_MM: error = prctl_set_mm(arg2, arg3, arg4, arg5); break; + case PR_SET_CHILD_SUBREAPER: + me->signal->is_child_subreaper = !!arg2; + error = 0; + break; + case PR_GET_CHILD_SUBREAPER: + error = put_user(me->signal->is_child_subreaper, + (int __user *) arg2); + break; default: error = -EINVAL; break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f487f257e05e..52b3a06a02f8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -23,6 +23,7 @@ #include <linux/swap.h> #include <linux/slab.h> #include <linux/sysctl.h> +#include <linux/bitmap.h> #include <linux/signal.h> #include <linux/printk.h> #include <linux/proc_fs.h> @@ -58,6 +59,7 @@ #include <linux/oom.h> #include <linux/kmod.h> #include <linux/capability.h> +#include <linux/binfmts.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -67,6 +69,9 @@ #include <asm/stacktrace.h> #include <asm/io.h> #endif +#ifdef CONFIG_SPARC +#include <asm/setup.h> +#endif #ifdef CONFIG_BSD_PROCESS_ACCT #include <linux/acct.h> #endif @@ -141,7 +146,6 @@ static const int cap_last_cap = CAP_LAST_CAP; #include <linux/inotify.h> #endif #ifdef CONFIG_SPARC -#include <asm/system.h> #endif #ifdef CONFIG_SPARC64 @@ -192,20 +196,6 @@ static int sysrq_sysctl_handler(ctl_table *table, int write, #endif -static struct ctl_table root_table[]; -static struct ctl_table_root sysctl_table_root; -static struct ctl_table_header root_table_header = { - {{.count = 1, - .ctl_table = root_table, - .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}}, - .root = &sysctl_table_root, - .set = &sysctl_table_root.default_set, -}; -static struct ctl_table_root sysctl_table_root = { - .root_list = LIST_HEAD_INIT(sysctl_table_root.root_list), - .default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry), -}; - static struct ctl_table kern_table[]; static struct ctl_table vm_table[]; static struct ctl_table fs_table[]; @@ -222,7 +212,7 @@ int sysctl_legacy_va_layout; /* The default sysctl tables: */ -static struct ctl_table root_table[] = { +static struct ctl_table sysctl_base_table[] = { { .procname = "kernel", .mode = 0555, @@ -1559,490 +1549,12 @@ static struct ctl_table dev_table[] = { { } }; -static DEFINE_SPINLOCK(sysctl_lock); - -/* called under sysctl_lock */ -static int use_table(struct ctl_table_header *p) +int __init sysctl_init(void) { - if (unlikely(p->unregistering)) - return 0; - p->used++; - return 1; -} - -/* called under sysctl_lock */ -static void unuse_table(struct ctl_table_header *p) -{ - if (!--p->used) - if (unlikely(p->unregistering)) - complete(p->unregistering); -} - -/* called under sysctl_lock, will reacquire if has to wait */ -static void start_unregistering(struct ctl_table_header *p) -{ - /* - * if p->used is 0, nobody will ever touch that entry again; - * we'll eliminate all paths to it before dropping sysctl_lock - */ - if (unlikely(p->used)) { - struct completion wait; - init_completion(&wait); - p->unregistering = &wait; - spin_unlock(&sysctl_lock); - wait_for_completion(&wait); - spin_lock(&sysctl_lock); - } else { - /* anything non-NULL; we'll never dereference it */ - p->unregistering = ERR_PTR(-EINVAL); - } - /* - * do not remove from the list until nobody holds it; walking the - * list in do_sysctl() relies on that. - */ - list_del_init(&p->ctl_entry); -} - -void sysctl_head_get(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - head->count++; - spin_unlock(&sysctl_lock); -} - -void sysctl_head_put(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - if (!--head->count) - kfree_rcu(head, rcu); - spin_unlock(&sysctl_lock); -} - -struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) -{ - if (!head) - BUG(); - spin_lock(&sysctl_lock); - if (!use_table(head)) - head = ERR_PTR(-ENOENT); - spin_unlock(&sysctl_lock); - return head; -} - -void sysctl_head_finish(struct ctl_table_header *head) -{ - if (!head) - return; - spin_lock(&sysctl_lock); - unuse_table(head); - spin_unlock(&sysctl_lock); -} - -static struct ctl_table_set * -lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces) -{ - struct ctl_table_set *set = &root->default_set; - if (root->lookup) - set = root->lookup(root, namespaces); - return set; -} - -static struct list_head * -lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces) -{ - struct ctl_table_set *set = lookup_header_set(root, namespaces); - return &set->list; -} - -struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces, - struct ctl_table_header *prev) -{ - struct ctl_table_root *root; - struct list_head *header_list; - struct ctl_table_header *head; - struct list_head *tmp; - - spin_lock(&sysctl_lock); - if (prev) { - head = prev; - tmp = &prev->ctl_entry; - unuse_table(prev); - goto next; - } - tmp = &root_table_header.ctl_entry; - for (;;) { - head = list_entry(tmp, struct ctl_table_header, ctl_entry); - - if (!use_table(head)) - goto next; - spin_unlock(&sysctl_lock); - return head; - next: - root = head->root; - tmp = tmp->next; - header_list = lookup_header_list(root, namespaces); - if (tmp != header_list) - continue; - - do { - root = list_entry(root->root_list.next, - struct ctl_table_root, root_list); - if (root == &sysctl_table_root) - goto out; - header_list = lookup_header_list(root, namespaces); - } while (list_empty(header_list)); - tmp = header_list->next; - } -out: - spin_unlock(&sysctl_lock); - return NULL; -} - -struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev) -{ - return __sysctl_head_next(current->nsproxy, prev); -} - -void register_sysctl_root(struct ctl_table_root *root) -{ - spin_lock(&sysctl_lock); - list_add_tail(&root->root_list, &sysctl_table_root.root_list); - spin_unlock(&sysctl_lock); -} - -/* - * sysctl_perm does NOT grant the superuser all rights automatically, because - * some sysctl variables are readonly even to root. - */ - -static int test_perm(int mode, int op) -{ - if (!current_euid()) - mode >>= 6; - else if (in_egroup_p(0)) - mode >>= 3; - if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) - return 0; - return -EACCES; -} - -int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op) -{ - int mode; - - if (root->permissions) - mode = root->permissions(root, current->nsproxy, table); - else - mode = table->mode; - - return test_perm(mode, op); -} - -static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table) -{ - for (; table->procname; table++) { - table->parent = parent; - if (table->child) - sysctl_set_parent(table, table->child); - } -} - -static __init int sysctl_init(void) -{ - sysctl_set_parent(NULL, root_table); -#ifdef CONFIG_SYSCTL_SYSCALL_CHECK - sysctl_check_table(current->nsproxy, root_table); -#endif + register_sysctl_table(sysctl_base_table); return 0; } -core_initcall(sysctl_init); - -static struct ctl_table *is_branch_in(struct ctl_table *branch, - struct ctl_table *table) -{ - struct ctl_table *p; - const char *s = branch->procname; - - /* branch should have named subdirectory as its first element */ - if (!s || !branch->child) - return NULL; - - /* ... and nothing else */ - if (branch[1].procname) - return NULL; - - /* table should contain subdirectory with the same name */ - for (p = table; p->procname; p++) { - if (!p->child) - continue; - if (p->procname && strcmp(p->procname, s) == 0) - return p; - } - return NULL; -} - -/* see if attaching q to p would be an improvement */ -static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q) -{ - struct ctl_table *to = p->ctl_table, *by = q->ctl_table; - struct ctl_table *next; - int is_better = 0; - int not_in_parent = !p->attached_by; - - while ((next = is_branch_in(by, to)) != NULL) { - if (by == q->attached_by) - is_better = 1; - if (to == p->attached_by) - not_in_parent = 1; - by = by->child; - to = next->child; - } - - if (is_better && not_in_parent) { - q->attached_by = by; - q->attached_to = to; - q->parent = p; - } -} - -/** - * __register_sysctl_paths - register a sysctl hierarchy - * @root: List of sysctl headers to register on - * @namespaces: Data to compute which lists of sysctl entries are visible - * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * - * The members of the &struct ctl_table structure are used as follows: - * - * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not - * enter a sysctl file - * - * data - a pointer to data for use by proc_handler - * - * maxlen - the maximum size in bytes of the data - * - * mode - the file permissions for the /proc/sys file, and for sysctl(2) - * - * child - a pointer to the child sysctl table if this entry is a directory, or - * %NULL. - * - * proc_handler - the text handler routine (described below) - * - * de - for internal use by the sysctl routines - * - * extra1, extra2 - extra pointers usable by the proc handler routines - * - * Leaf nodes in the sysctl tree will be represented by a single file - * under /proc; non-leaf nodes will be represented by directories. - * - * sysctl(2) can automatically manage read and write requests through - * the sysctl table. The data and maxlen fields of the ctl_table - * struct enable minimal validation of the values being written to be - * performed, and the mode field allows minimal authentication. - * - * There must be a proc_handler routine for any terminal nodes - * mirrored under /proc/sys (non-terminals are handled by a built-in - * directory handler). Several default handlers are available to - * cover common cases - - * - * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(), - * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(), - * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax() - * - * It is the handler's job to read the input buffer from user memory - * and process it. The handler should return 0 on success. - * - * This routine returns %NULL on a failure to register, and a pointer - * to the table header on success. - */ -struct ctl_table_header *__register_sysctl_paths( - struct ctl_table_root *root, - struct nsproxy *namespaces, - const struct ctl_path *path, struct ctl_table *table) -{ - struct ctl_table_header *header; - struct ctl_table *new, **prevp; - unsigned int n, npath; - struct ctl_table_set *set; - - /* Count the path components */ - for (npath = 0; path[npath].procname; ++npath) - ; - - /* - * For each path component, allocate a 2-element ctl_table array. - * The first array element will be filled with the sysctl entry - * for this, the second will be the sentinel (procname == 0). - * - * We allocate everything in one go so that we don't have to - * worry about freeing additional memory in unregister_sysctl_table. - */ - header = kzalloc(sizeof(struct ctl_table_header) + - (2 * npath * sizeof(struct ctl_table)), GFP_KERNEL); - if (!header) - return NULL; - - new = (struct ctl_table *) (header + 1); - - /* Now connect the dots */ - prevp = &header->ctl_table; - for (n = 0; n < npath; ++n, ++path) { - /* Copy the procname */ - new->procname = path->procname; - new->mode = 0555; - - *prevp = new; - prevp = &new->child; - - new += 2; - } - *prevp = table; - header->ctl_table_arg = table; - - INIT_LIST_HEAD(&header->ctl_entry); - header->used = 0; - header->unregistering = NULL; - header->root = root; - sysctl_set_parent(NULL, header->ctl_table); - header->count = 1; -#ifdef CONFIG_SYSCTL_SYSCALL_CHECK - if (sysctl_check_table(namespaces, header->ctl_table)) { - kfree(header); - return NULL; - } -#endif - spin_lock(&sysctl_lock); - header->set = lookup_header_set(root, namespaces); - header->attached_by = header->ctl_table; - header->attached_to = root_table; - header->parent = &root_table_header; - for (set = header->set; set; set = set->parent) { - struct ctl_table_header *p; - list_for_each_entry(p, &set->list, ctl_entry) { - if (p->unregistering) - continue; - try_attach(p, header); - } - } - header->parent->count++; - list_add_tail(&header->ctl_entry, &header->set->list); - spin_unlock(&sysctl_lock); - - return header; -} - -/** - * register_sysctl_table_path - register a sysctl table hierarchy - * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * - * See __register_sysctl_paths for more details. - */ -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table) -{ - return __register_sysctl_paths(&sysctl_table_root, current->nsproxy, - path, table); -} - -/** - * register_sysctl_table - register a sysctl table hierarchy - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * - * See register_sysctl_paths for more details. - */ -struct ctl_table_header *register_sysctl_table(struct ctl_table *table) -{ - static const struct ctl_path null_path[] = { {} }; - - return register_sysctl_paths(null_path, table); -} - -/** - * unregister_sysctl_table - unregister a sysctl table hierarchy - * @header: the header returned from register_sysctl_table - * - * Unregisters the sysctl table and all children. proc entries may not - * actually be removed until they are no longer used by anyone. - */ -void unregister_sysctl_table(struct ctl_table_header * header) -{ - might_sleep(); - - if (header == NULL) - return; - - spin_lock(&sysctl_lock); - start_unregistering(header); - if (!--header->parent->count) { - WARN_ON(1); - kfree_rcu(header->parent, rcu); - } - if (!--header->count) - kfree_rcu(header, rcu); - spin_unlock(&sysctl_lock); -} - -int sysctl_is_seen(struct ctl_table_header *p) -{ - struct ctl_table_set *set = p->set; - int res; - spin_lock(&sysctl_lock); - if (p->unregistering) - res = 0; - else if (!set->is_seen) - res = 1; - else - res = set->is_seen(set); - spin_unlock(&sysctl_lock); - return res; -} - -void setup_sysctl_set(struct ctl_table_set *p, - struct ctl_table_set *parent, - int (*is_seen)(struct ctl_table_set *)) -{ - INIT_LIST_HEAD(&p->list); - p->parent = parent ? parent : &sysctl_table_root.default_set; - p->is_seen = is_seen; -} - -#else /* !CONFIG_SYSCTL */ -struct ctl_table_header *register_sysctl_table(struct ctl_table * table) -{ - return NULL; -} - -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table) -{ - return NULL; -} - -void unregister_sysctl_table(struct ctl_table_header * table) -{ -} - -void setup_sysctl_set(struct ctl_table_set *p, - struct ctl_table_set *parent, - int (*is_seen)(struct ctl_table_set *)) -{ -} - -void sysctl_head_put(struct ctl_table_header *head) -{ -} - #endif /* CONFIG_SYSCTL */ /* @@ -2884,9 +2396,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, } } - while (val_a <= val_b) - set_bit(val_a++, tmp_bitmap); - + bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1); first = 0; proc_skip_char(&kbuf, &left, '\n'); } @@ -2929,8 +2439,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, if (*ppos) bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len); else - memcpy(bitmap, tmp_bitmap, - BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long)); + bitmap_copy(bitmap, tmp_bitmap, bitmap_len); } kfree(tmp_bitmap); *lenp -= left; @@ -3008,6 +2517,3 @@ EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); EXPORT_SYMBOL(proc_doulongvec_minmax); EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); -EXPORT_SYMBOL(register_sysctl_table); -EXPORT_SYMBOL(register_sysctl_paths); -EXPORT_SYMBOL(unregister_sysctl_table); diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c deleted file mode 100644 index 362da653813d..000000000000 --- a/kernel/sysctl_check.c +++ /dev/null @@ -1,160 +0,0 @@ -#include <linux/stat.h> -#include <linux/sysctl.h> -#include "../fs/xfs/xfs_sysctl.h" -#include <linux/sunrpc/debug.h> -#include <linux/string.h> -#include <net/ip_vs.h> - - -static int sysctl_depth(struct ctl_table *table) -{ - struct ctl_table *tmp; - int depth; - - depth = 0; - for (tmp = table; tmp->parent; tmp = tmp->parent) - depth++; - - return depth; -} - -static struct ctl_table *sysctl_parent(struct ctl_table *table, int n) -{ - int i; - - for (i = 0; table && i < n; i++) - table = table->parent; - - return table; -} - - -static void sysctl_print_path(struct ctl_table *table) -{ - struct ctl_table *tmp; - int depth, i; - depth = sysctl_depth(table); - if (table->procname) { - for (i = depth; i >= 0; i--) { - tmp = sysctl_parent(table, i); - printk("/%s", tmp->procname?tmp->procname:""); - } - } - printk(" "); -} - -static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces, - struct ctl_table *table) -{ - struct ctl_table_header *head; - struct ctl_table *ref, *test; - int depth, cur_depth; - - depth = sysctl_depth(table); - - for (head = __sysctl_head_next(namespaces, NULL); head; - head = __sysctl_head_next(namespaces, head)) { - cur_depth = depth; - ref = head->ctl_table; -repeat: - test = sysctl_parent(table, cur_depth); - for (; ref->procname; ref++) { - int match = 0; - if (cur_depth && !ref->child) - continue; - - if (test->procname && ref->procname && - (strcmp(test->procname, ref->procname) == 0)) - match++; - - if (match) { - if (cur_depth != 0) { - cur_depth--; - ref = ref->child; - goto repeat; - } - goto out; - } - } - } - ref = NULL; -out: - sysctl_head_finish(head); - return ref; -} - -static void set_fail(const char **fail, struct ctl_table *table, const char *str) -{ - if (*fail) { - printk(KERN_ERR "sysctl table check failed: "); - sysctl_print_path(table); - printk(" %s\n", *fail); - dump_stack(); - } - *fail = str; -} - -static void sysctl_check_leaf(struct nsproxy *namespaces, - struct ctl_table *table, const char **fail) -{ - struct ctl_table *ref; - - ref = sysctl_check_lookup(namespaces, table); - if (ref && (ref != table)) - set_fail(fail, table, "Sysctl already exists"); -} - -int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table) -{ - int error = 0; - for (; table->procname; table++) { - const char *fail = NULL; - - if (table->parent) { - if (!table->parent->procname) - set_fail(&fail, table, "Parent without procname"); - } - if (table->child) { - if (table->data) - set_fail(&fail, table, "Directory with data?"); - if (table->maxlen) - set_fail(&fail, table, "Directory with maxlen?"); - if ((table->mode & (S_IRUGO|S_IXUGO)) != table->mode) - set_fail(&fail, table, "Writable sysctl directory"); - if (table->proc_handler) - set_fail(&fail, table, "Directory with proc_handler"); - if (table->extra1) - set_fail(&fail, table, "Directory with extra1"); - if (table->extra2) - set_fail(&fail, table, "Directory with extra2"); - } else { - if ((table->proc_handler == proc_dostring) || - (table->proc_handler == proc_dointvec) || - (table->proc_handler == proc_dointvec_minmax) || - (table->proc_handler == proc_dointvec_jiffies) || - (table->proc_handler == proc_dointvec_userhz_jiffies) || - (table->proc_handler == proc_dointvec_ms_jiffies) || - (table->proc_handler == proc_doulongvec_minmax) || - (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { - if (!table->data) - set_fail(&fail, table, "No data"); - if (!table->maxlen) - set_fail(&fail, table, "No maxlen"); - } -#ifdef CONFIG_PROC_SYSCTL - if (!table->proc_handler) - set_fail(&fail, table, "No proc_handler"); -#endif - sysctl_check_leaf(namespaces, table, &fail); - } - if (table->mode > 0777) - set_fail(&fail, table, "bogus .mode"); - if (fail) { - set_fail(&fail, table, NULL); - error = -EINVAL; - } - if (table->child) - error |= sysctl_check_table(namespaces, table->child); - } - return error; -} diff --git a/kernel/time.c b/kernel/time.c index 73e416db0a1e..ba744cf80696 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -163,7 +163,6 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz) return error; if (tz) { - /* SMP safe, global irq locking makes it work. */ sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { @@ -173,12 +172,7 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz) } } if (tv) - { - /* SMP safe, again the code in arch/foo/time.c should - * globally block out interrupts when it runs. - */ return do_settimeofday(tv); - } return 0; } diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 8a46f5d64504..8a538c55fc7b 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -96,6 +96,11 @@ static int alarmtimer_rtc_add_device(struct device *dev, return 0; } +static inline void alarmtimer_rtc_timer_init(void) +{ + rtc_timer_init(&rtctimer, NULL, NULL); +} + static struct class_interface alarmtimer_rtc_interface = { .add_dev = &alarmtimer_rtc_add_device, }; @@ -117,6 +122,7 @@ static inline struct rtc_device *alarmtimer_get_rtcdev(void) #define rtcdev (NULL) static inline int alarmtimer_rtc_interface_setup(void) { return 0; } static inline void alarmtimer_rtc_interface_remove(void) { } +static inline void alarmtimer_rtc_timer_init(void) { } #endif /** @@ -783,6 +789,8 @@ static int __init alarmtimer_init(void) .nsleep = alarm_timer_nsleep, }; + alarmtimer_rtc_timer_init(); + posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock); posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index a45ca167ab24..c9583382141a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -500,7 +500,7 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) { u64 ret; /* - * We won't try to correct for more then 11% adjustments (110,000 ppm), + * We won't try to correct for more than 11% adjustments (110,000 ppm), */ ret = (u64)cs->mult * 11; do_div(ret,100); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index f6117a4c7cb8..f03fd83b170b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -22,17 +22,18 @@ * NTP timekeeping variables: */ +DEFINE_SPINLOCK(ntp_lock); + + /* USER_HZ period (usecs): */ unsigned long tick_usec = TICK_USEC; /* ACTHZ period (nsecs): */ unsigned long tick_nsec; -u64 tick_length; +static u64 tick_length; static u64 tick_length_base; -static struct hrtimer leap_timer; - #define MAX_TICKADJ 500LL /* usecs */ #define MAX_TICKADJ_SCALED \ (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) @@ -49,7 +50,7 @@ static struct hrtimer leap_timer; static int time_state = TIME_OK; /* clock status bits: */ -int time_status = STA_UNSYNC; +static int time_status = STA_UNSYNC; /* TAI offset (secs): */ static long time_tai; @@ -133,7 +134,7 @@ static inline void pps_reset_freq_interval(void) /** * pps_clear - Clears the PPS state variables * - * Must be called while holding a write on the xtime_lock + * Must be called while holding a write on the ntp_lock */ static inline void pps_clear(void) { @@ -149,7 +150,7 @@ static inline void pps_clear(void) * the last PPS signal. When it reaches 0, indicate that PPS signal is * missing. * - * Must be called while holding a write on the xtime_lock + * Must be called while holding a write on the ntp_lock */ static inline void pps_dec_valid(void) { @@ -233,6 +234,17 @@ static inline void pps_fill_timex(struct timex *txc) #endif /* CONFIG_NTP_PPS */ + +/** + * ntp_synced - Returns 1 if the NTP status is not UNSYNC + * + */ +static inline int ntp_synced(void) +{ + return !(time_status & STA_UNSYNC); +} + + /* * NTP methods: */ @@ -275,7 +287,7 @@ static inline s64 ntp_update_offset_fll(s64 offset64, long secs) time_status |= STA_MODE; - return div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); + return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); } static void ntp_update_offset(long offset) @@ -330,11 +342,13 @@ static void ntp_update_offset(long offset) /** * ntp_clear - Clears the NTP state variables - * - * Must be called while holding a write on the xtime_lock */ void ntp_clear(void) { + unsigned long flags; + + spin_lock_irqsave(&ntp_lock, flags); + time_adjust = 0; /* stop active adjtime() */ time_status |= STA_UNSYNC; time_maxerror = NTP_PHASE_LIMIT; @@ -347,63 +361,81 @@ void ntp_clear(void) /* Clear PPS state variables */ pps_clear(); + spin_unlock_irqrestore(&ntp_lock, flags); + +} + + +u64 ntp_tick_length(void) +{ + unsigned long flags; + s64 ret; + + spin_lock_irqsave(&ntp_lock, flags); + ret = tick_length; + spin_unlock_irqrestore(&ntp_lock, flags); + return ret; } + /* - * Leap second processing. If in leap-insert state at the end of the - * day, the system clock is set back one second; if in leap-delete - * state, the system clock is set ahead one second. + * this routine handles the overflow of the microsecond field + * + * The tricky bits of code to handle the accurate clock support + * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. + * They were originally developed for SUN and DEC kernels. + * All the kudos should go to Dave for this stuff. + * + * Also handles leap second processing, and returns leap offset */ -static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) +int second_overflow(unsigned long secs) { - enum hrtimer_restart res = HRTIMER_NORESTART; + s64 delta; + int leap = 0; + unsigned long flags; - write_seqlock(&xtime_lock); + spin_lock_irqsave(&ntp_lock, flags); + /* + * Leap second processing. If in leap-insert state at the end of the + * day, the system clock is set back one second; if in leap-delete + * state, the system clock is set ahead one second. + */ switch (time_state) { case TIME_OK: + if (time_status & STA_INS) + time_state = TIME_INS; + else if (time_status & STA_DEL) + time_state = TIME_DEL; break; case TIME_INS: - timekeeping_leap_insert(-1); - time_state = TIME_OOP; - printk(KERN_NOTICE - "Clock: inserting leap second 23:59:60 UTC\n"); - hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); - res = HRTIMER_RESTART; + if (secs % 86400 == 0) { + leap = -1; + time_state = TIME_OOP; + printk(KERN_NOTICE + "Clock: inserting leap second 23:59:60 UTC\n"); + } break; case TIME_DEL: - timekeeping_leap_insert(1); - time_tai--; - time_state = TIME_WAIT; - printk(KERN_NOTICE - "Clock: deleting leap second 23:59:59 UTC\n"); + if ((secs + 1) % 86400 == 0) { + leap = 1; + time_tai--; + time_state = TIME_WAIT; + printk(KERN_NOTICE + "Clock: deleting leap second 23:59:59 UTC\n"); + } break; case TIME_OOP: time_tai++; time_state = TIME_WAIT; - /* fall through */ + break; + case TIME_WAIT: if (!(time_status & (STA_INS | STA_DEL))) time_state = TIME_OK; break; } - write_sequnlock(&xtime_lock); - - return res; -} - -/* - * this routine handles the overflow of the microsecond field - * - * The tricky bits of code to handle the accurate clock support - * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. - * They were originally developed for SUN and DEC kernels. - * All the kudos should go to Dave for this stuff. - */ -void second_overflow(void) -{ - s64 delta; /* Bump the maxerror field */ time_maxerror += MAXFREQ / NSEC_PER_USEC; @@ -423,30 +455,34 @@ void second_overflow(void) pps_dec_valid(); if (!time_adjust) - return; + goto out; if (time_adjust > MAX_TICKADJ) { time_adjust -= MAX_TICKADJ; tick_length += MAX_TICKADJ_SCALED; - return; + goto out; } if (time_adjust < -MAX_TICKADJ) { time_adjust += MAX_TICKADJ; tick_length -= MAX_TICKADJ_SCALED; - return; + goto out; } tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT; time_adjust = 0; + + + +out: + spin_unlock_irqrestore(&ntp_lock, flags); + + return leap; } #ifdef CONFIG_GENERIC_CMOS_UPDATE -/* Disable the cmos update - used by virtualization and embedded */ -int no_sync_cmos_clock __read_mostly; - static void sync_cmos_clock(struct work_struct *work); static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); @@ -493,35 +529,13 @@ static void sync_cmos_clock(struct work_struct *work) static void notify_cmos_timer(void) { - if (!no_sync_cmos_clock) - schedule_delayed_work(&sync_cmos_work, 0); + schedule_delayed_work(&sync_cmos_work, 0); } #else static inline void notify_cmos_timer(void) { } #endif -/* - * Start the leap seconds timer: - */ -static inline void ntp_start_leap_timer(struct timespec *ts) -{ - long now = ts->tv_sec; - - if (time_status & STA_INS) { - time_state = TIME_INS; - now += 86400 - now % 86400; - hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); - - return; - } - - if (time_status & STA_DEL) { - time_state = TIME_DEL; - now += 86400 - (now + 1) % 86400; - hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); - } -} /* * Propagate a new txc->status value into the NTP state: @@ -546,22 +560,6 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) time_status &= STA_RONLY; time_status |= txc->status & ~STA_RONLY; - switch (time_state) { - case TIME_OK: - ntp_start_leap_timer(ts); - break; - case TIME_INS: - case TIME_DEL: - time_state = TIME_OK; - ntp_start_leap_timer(ts); - case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; - break; - case TIME_OOP: - hrtimer_restart(&leap_timer); - break; - } } /* * Called with the xtime lock held, so we can access and modify @@ -643,9 +641,6 @@ int do_adjtimex(struct timex *txc) (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; - - if (txc->modes & ADJ_STATUS && time_state != TIME_OK) - hrtimer_cancel(&leap_timer); } if (txc->modes & ADJ_SETOFFSET) { @@ -663,7 +658,7 @@ int do_adjtimex(struct timex *txc) getnstimeofday(&ts); - write_seqlock_irq(&xtime_lock); + spin_lock_irq(&ntp_lock); if (txc->modes & ADJ_ADJTIME) { long save_adjust = time_adjust; @@ -705,7 +700,7 @@ int do_adjtimex(struct timex *txc) /* fill PPS status fields */ pps_fill_timex(txc); - write_sequnlock_irq(&xtime_lock); + spin_unlock_irq(&ntp_lock); txc->time.tv_sec = ts.tv_sec; txc->time.tv_usec = ts.tv_nsec; @@ -903,7 +898,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) pts_norm = pps_normalize_ts(*phase_ts); - write_seqlock_irqsave(&xtime_lock, flags); + spin_lock_irqsave(&ntp_lock, flags); /* clear the error bits, they will be set again if needed */ time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); @@ -916,7 +911,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) * just start the frequency interval */ if (unlikely(pps_fbase.tv_sec == 0)) { pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + spin_unlock_irqrestore(&ntp_lock, flags); return; } @@ -931,7 +926,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) time_status |= STA_PPSJITTER; /* restart the frequency calibration interval */ pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + spin_unlock_irqrestore(&ntp_lock, flags); pr_err("hardpps: PPSJITTER: bad pulse\n"); return; } @@ -948,7 +943,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) hardpps_update_phase(pts_norm.nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); + spin_unlock_irqrestore(&ntp_lock, flags); } EXPORT_SYMBOL(hardpps); @@ -967,6 +962,4 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup); void __init ntp_init(void) { ntp_clear(); - hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); - leap_timer.function = ntp_leap_second; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index fd4a7b1625a2..e883f57a3cd3 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -575,11 +575,15 @@ void tick_broadcast_switch_to_oneshot(void) unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + if (cpumask_empty(tick_get_broadcast_mask())) + goto end; tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) tick_broadcast_setup_oneshot(bc); + +end: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7656642e4b8e..3526038f2836 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -182,11 +182,7 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now) static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts) { - ktime_t now; - - now = ktime_get(); - - update_ts_time_stats(cpu, ts, now, NULL); + ktime_t now = ktime_get(); ts->idle_entrytime = now; ts->idle_active = 1; @@ -562,20 +558,21 @@ void tick_nohz_idle_exit(void) local_irq_disable(); - if (ts->idle_active || (ts->inidle && ts->tick_stopped)) + WARN_ON_ONCE(!ts->inidle); + + ts->inidle = 0; + + if (ts->idle_active || ts->tick_stopped) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(cpu, now); - if (!ts->inidle || !ts->tick_stopped) { - ts->inidle = 0; + if (!ts->tick_stopped) { local_irq_enable(); return; } - ts->inidle = 0; - /* Update jiffies first */ select_nohz_load_balancer(0); tick_do_update_jiffies64(now); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0c6358186401..d66b21308f7c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -25,6 +25,8 @@ struct timekeeper { /* Current clocksource used for timekeeping. */ struct clocksource *clock; + /* NTP adjusted clock multiplier */ + u32 mult; /* The shift value of the current clocksource. */ int shift; @@ -45,12 +47,47 @@ struct timekeeper { /* Shift conversion between clock shifted nano seconds and * ntp shifted nano seconds. */ int ntp_error_shift; - /* NTP adjusted clock multiplier */ - u32 mult; + + /* The current time */ + struct timespec xtime; + /* + * wall_to_monotonic is what we need to add to xtime (or xtime corrected + * for sub jiffie times) to get to monotonic time. Monotonic is pegged + * at zero at system boot time, so wall_to_monotonic will be negative, + * however, we will ALWAYS keep the tv_nsec part positive so we can use + * the usual normalization. + * + * wall_to_monotonic is moved after resume from suspend for the + * monotonic time not to jump. We need to add total_sleep_time to + * wall_to_monotonic to get the real boot based time offset. + * + * - wall_to_monotonic is no longer the boot time, getboottime must be + * used instead. + */ + struct timespec wall_to_monotonic; + /* time spent in suspend */ + struct timespec total_sleep_time; + /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ + struct timespec raw_time; + + /* Seqlock for all timekeeper values */ + seqlock_t lock; }; static struct timekeeper timekeeper; +/* + * This read-write spinlock protects us from races in SMP while + * playing with xtime. + */ +__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); + + +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; + + + /** * timekeeper_setup_internals - Set up internals to use clocksource clock. * @@ -135,49 +172,18 @@ static inline s64 timekeeping_get_ns_raw(void) return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); } -/* - * This read-write spinlock protects us from races in SMP while - * playing with xtime. - */ -__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); - - -/* - * The current time - * wall_to_monotonic is what we need to add to xtime (or xtime corrected - * for sub jiffie times) to get to monotonic time. Monotonic is pegged - * at zero at system boot time, so wall_to_monotonic will be negative, - * however, we will ALWAYS keep the tv_nsec part positive so we can use - * the usual normalization. - * - * wall_to_monotonic is moved after resume from suspend for the monotonic - * time not to jump. We need to add total_sleep_time to wall_to_monotonic - * to get the real boot based time offset. - * - * - wall_to_monotonic is no longer the boot time, getboottime must be - * used instead. - */ -static struct timespec xtime __attribute__ ((aligned (16))); -static struct timespec wall_to_monotonic __attribute__ ((aligned (16))); -static struct timespec total_sleep_time; - -/* - * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. - */ -static struct timespec raw_time; - -/* flag for if timekeeping is suspended */ -int __read_mostly timekeeping_suspended; - -/* must hold xtime_lock */ -void timekeeping_leap_insert(int leapsecond) +/* must hold write on timekeeper.lock */ +static void timekeeping_update(bool clearntp) { - xtime.tv_sec += leapsecond; - wall_to_monotonic.tv_sec -= leapsecond; - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + if (clearntp) { + timekeeper.ntp_error = 0; + ntp_clear(); + } + update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic, + timekeeper.clock, timekeeper.mult); } + /** * timekeeping_forward_now - update clock to the current time * @@ -202,10 +208,10 @@ static void timekeeping_forward_now(void) /* If arch requires, add in gettimeoffset() */ nsec += arch_gettimeoffset(); - timespec_add_ns(&xtime, nsec); + timespec_add_ns(&timekeeper.xtime, nsec); nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); - timespec_add_ns(&raw_time, nsec); + timespec_add_ns(&timekeeper.raw_time, nsec); } /** @@ -222,15 +228,15 @@ void getnstimeofday(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - *ts = xtime; + *ts = timekeeper.xtime; nsecs = timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); timespec_add_ns(ts, nsecs); } @@ -245,14 +251,16 @@ ktime_t ktime_get(void) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); - secs = xtime.tv_sec + wall_to_monotonic.tv_sec; - nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec; + seq = read_seqbegin(&timekeeper.lock); + secs = timekeeper.xtime.tv_sec + + timekeeper.wall_to_monotonic.tv_sec; + nsecs = timekeeper.xtime.tv_nsec + + timekeeper.wall_to_monotonic.tv_nsec; nsecs += timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); /* * Use ktime_set/ktime_add_ns to create a proper ktime on * 32-bit architectures without CONFIG_KTIME_SCALAR. @@ -278,14 +286,14 @@ void ktime_get_ts(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); - *ts = xtime; - tomono = wall_to_monotonic; + seq = read_seqbegin(&timekeeper.lock); + *ts = timekeeper.xtime; + tomono = timekeeper.wall_to_monotonic; nsecs = timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, ts->tv_nsec + tomono.tv_nsec + nsecs); @@ -313,10 +321,10 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) do { u32 arch_offset; - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - *ts_raw = raw_time; - *ts_real = xtime; + *ts_raw = timekeeper.raw_time; + *ts_real = timekeeper.xtime; nsecs_raw = timekeeping_get_ns_raw(); nsecs_real = timekeeping_get_ns(); @@ -326,7 +334,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) nsecs_raw += arch_offset; nsecs_real += arch_offset; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -365,23 +373,19 @@ int do_settimeofday(const struct timespec *tv) if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); timekeeping_forward_now(); - ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec; - ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec; - wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta); + ts_delta.tv_sec = tv->tv_sec - timekeeper.xtime.tv_sec; + ts_delta.tv_nsec = tv->tv_nsec - timekeeper.xtime.tv_nsec; + timekeeper.wall_to_monotonic = + timespec_sub(timekeeper.wall_to_monotonic, ts_delta); - xtime = *tv; - - timekeeper.ntp_error = 0; - ntp_clear(); + timekeeper.xtime = *tv; + timekeeping_update(true); - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); - - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -405,20 +409,17 @@ int timekeeping_inject_offset(struct timespec *ts) if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); timekeeping_forward_now(); - xtime = timespec_add(xtime, *ts); - wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts); - - timekeeper.ntp_error = 0; - ntp_clear(); + timekeeper.xtime = timespec_add(timekeeper.xtime, *ts); + timekeeper.wall_to_monotonic = + timespec_sub(timekeeper.wall_to_monotonic, *ts); - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -435,9 +436,12 @@ EXPORT_SYMBOL(timekeeping_inject_offset); static int change_clocksource(void *data) { struct clocksource *new, *old; + unsigned long flags; new = (struct clocksource *) data; + write_seqlock_irqsave(&timekeeper.lock, flags); + timekeeping_forward_now(); if (!new->enable || new->enable(new) == 0) { old = timekeeper.clock; @@ -445,6 +449,10 @@ static int change_clocksource(void *data) if (old->disable) old->disable(old); } + timekeeping_update(true); + + write_sequnlock_irqrestore(&timekeeper.lock, flags); + return 0; } @@ -490,11 +498,11 @@ void getrawmonotonic(struct timespec *ts) s64 nsecs; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); nsecs = timekeeping_get_ns_raw(); - *ts = raw_time; + *ts = timekeeper.raw_time; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); timespec_add_ns(ts, nsecs); } @@ -510,24 +518,30 @@ int timekeeping_valid_for_hres(void) int ret; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred - * - * Caller must observe xtime_lock via read_seqbegin/read_seqretry to - * ensure that the clocksource does not change! */ u64 timekeeping_max_deferment(void) { - return timekeeper.clock->max_idle_ns; + unsigned long seq; + u64 ret; + do { + seq = read_seqbegin(&timekeeper.lock); + + ret = timekeeper.clock->max_idle_ns; + + } while (read_seqretry(&timekeeper.lock, seq)); + + return ret; } /** @@ -572,28 +586,29 @@ void __init timekeeping_init(void) read_persistent_clock(&now); read_boot_clock(&boot); - write_seqlock_irqsave(&xtime_lock, flags); + seqlock_init(&timekeeper.lock); ntp_init(); + write_seqlock_irqsave(&timekeeper.lock, flags); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); timekeeper_setup_internals(clock); - xtime.tv_sec = now.tv_sec; - xtime.tv_nsec = now.tv_nsec; - raw_time.tv_sec = 0; - raw_time.tv_nsec = 0; + timekeeper.xtime.tv_sec = now.tv_sec; + timekeeper.xtime.tv_nsec = now.tv_nsec; + timekeeper.raw_time.tv_sec = 0; + timekeeper.raw_time.tv_nsec = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) { - boot.tv_sec = xtime.tv_sec; - boot.tv_nsec = xtime.tv_nsec; + boot.tv_sec = timekeeper.xtime.tv_sec; + boot.tv_nsec = timekeeper.xtime.tv_nsec; } - set_normalized_timespec(&wall_to_monotonic, + set_normalized_timespec(&timekeeper.wall_to_monotonic, -boot.tv_sec, -boot.tv_nsec); - total_sleep_time.tv_sec = 0; - total_sleep_time.tv_nsec = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + timekeeper.total_sleep_time.tv_sec = 0; + timekeeper.total_sleep_time.tv_nsec = 0; + write_sequnlock_irqrestore(&timekeeper.lock, flags); } /* time in seconds when suspend began */ @@ -614,9 +629,11 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta) return; } - xtime = timespec_add(xtime, *delta); - wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta); - total_sleep_time = timespec_add(total_sleep_time, *delta); + timekeeper.xtime = timespec_add(timekeeper.xtime, *delta); + timekeeper.wall_to_monotonic = + timespec_sub(timekeeper.wall_to_monotonic, *delta); + timekeeper.total_sleep_time = timespec_add( + timekeeper.total_sleep_time, *delta); } @@ -640,17 +657,15 @@ void timekeeping_inject_sleeptime(struct timespec *delta) if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) return; - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); + timekeeping_forward_now(); __timekeeping_inject_sleeptime(delta); - timekeeper.ntp_error = 0; - ntp_clear(); - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -673,7 +688,7 @@ static void timekeeping_resume(void) clocksource_resume(); - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); @@ -683,7 +698,7 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); touch_softlockup_watchdog(); @@ -701,7 +716,7 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); timekeeping_forward_now(); timekeeping_suspended = 1; @@ -711,7 +726,7 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(xtime, timekeeping_suspend_time); + delta = timespec_sub(timekeeper.xtime, timekeeping_suspend_time); delta_delta = timespec_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* @@ -724,7 +739,7 @@ static int timekeeping_suspend(void) timekeeping_suspend_time = timespec_add(timekeeping_suspend_time, delta_delta); } - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); clocksource_suspend(); @@ -775,7 +790,7 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, * Now calculate the error in (1 << look_ahead) ticks, but first * remove the single look ahead already included in the error. */ - tick_error = tick_length >> (timekeeper.ntp_error_shift + 1); + tick_error = ntp_tick_length() >> (timekeeper.ntp_error_shift + 1); tick_error -= timekeeper.xtime_interval >> 1; error = ((error - tick_error) >> look_ahead) + tick_error; @@ -807,7 +822,7 @@ static void timekeeping_adjust(s64 offset) int adj; /* - * The point of this is to check if the error is greater then half + * The point of this is to check if the error is greater than half * an interval. * * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs. @@ -815,7 +830,7 @@ static void timekeeping_adjust(s64 offset) * Note we subtract one in the shift, so that error is really error*2. * This "saves" dividing(shifting) interval twice, but keeps the * (error > interval) comparison as still measuring if error is - * larger then half an interval. + * larger than half an interval. * * Note: It does not "save" on aggravation when reading the code. */ @@ -823,7 +838,7 @@ static void timekeeping_adjust(s64 offset) if (error > interval) { /* * We now divide error by 4(via shift), which checks if - * the error is greater then twice the interval. + * the error is greater than twice the interval. * If it is greater, we need a bigadjust, if its smaller, * we can adjust by 1. */ @@ -854,13 +869,15 @@ static void timekeeping_adjust(s64 offset) } else /* No adjustment needed */ return; - WARN_ONCE(timekeeper.clock->maxadj && - (timekeeper.mult + adj > timekeeper.clock->mult + - timekeeper.clock->maxadj), - "Adjusting %s more then 11%% (%ld vs %ld)\n", + if (unlikely(timekeeper.clock->maxadj && + (timekeeper.mult + adj > + timekeeper.clock->mult + timekeeper.clock->maxadj))) { + printk_once(KERN_WARNING + "Adjusting %s more than 11%% (%ld vs %ld)\n", timekeeper.clock->name, (long)timekeeper.mult + adj, (long)timekeeper.clock->mult + timekeeper.clock->maxadj); + } /* * So the following can be confusing. * @@ -932,7 +949,7 @@ 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 the offset is smaller than a shifted interval, do nothing */ if (offset < timekeeper.cycle_interval<<shift) return offset; @@ -942,23 +959,25 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) timekeeper.xtime_nsec += timekeeper.xtime_interval << shift; while (timekeeper.xtime_nsec >= nsecps) { + int leap; timekeeper.xtime_nsec -= nsecps; - xtime.tv_sec++; - second_overflow(); + timekeeper.xtime.tv_sec++; + leap = second_overflow(timekeeper.xtime.tv_sec); + timekeeper.xtime.tv_sec += leap; } /* Accumulate raw time */ raw_nsecs = timekeeper.raw_interval << shift; - raw_nsecs += raw_time.tv_nsec; + raw_nsecs += timekeeper.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; + timekeeper.raw_time.tv_sec += raw_secs; } - raw_time.tv_nsec = raw_nsecs; + timekeeper.raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ - timekeeper.ntp_error += tick_length << shift; + timekeeper.ntp_error += ntp_tick_length() << shift; timekeeper.ntp_error -= (timekeeper.xtime_interval + timekeeper.xtime_remainder) << (timekeeper.ntp_error_shift + shift); @@ -970,17 +989,19 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) /** * update_wall_time - Uses the current clocksource to increment the wall time * - * Called from the timer interrupt, must hold a write on xtime_lock. */ static void update_wall_time(void) { struct clocksource *clock; cycle_t offset; int shift = 0, maxshift; + unsigned long flags; + + write_seqlock_irqsave(&timekeeper.lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) - return; + goto out; clock = timekeeper.clock; @@ -989,20 +1010,21 @@ static void update_wall_time(void) #else offset = (clock->read(clock) - clock->cycle_last) & clock->mask; #endif - timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift; + timekeeper.xtime_nsec = (s64)timekeeper.xtime.tv_nsec << + timekeeper.shift; /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals - * that is smaller then the offset. We then accumulate that + * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(timekeeper.cycle_interval); shift = max(0, shift); - /* Bound shift to one less then what overflows tick_length */ - maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1; + /* Bound shift to one less than what overflows tick_length */ + maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= timekeeper.cycle_interval) { offset = logarithmic_accumulation(offset, shift); @@ -1040,24 +1062,30 @@ static void update_wall_time(void) * Store full nanoseconds into xtime after rounding it up and * add the remainder to the error difference. */ - xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1; - timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift; + timekeeper.xtime.tv_nsec = ((s64)timekeeper.xtime_nsec >> + timekeeper.shift) + 1; + timekeeper.xtime_nsec -= (s64)timekeeper.xtime.tv_nsec << + timekeeper.shift; timekeeper.ntp_error += timekeeper.xtime_nsec << timekeeper.ntp_error_shift; /* * Finally, make sure that after the rounding - * xtime.tv_nsec isn't larger then NSEC_PER_SEC + * xtime.tv_nsec isn't larger than NSEC_PER_SEC */ - if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) { - xtime.tv_nsec -= NSEC_PER_SEC; - xtime.tv_sec++; - second_overflow(); + if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) { + int leap; + timekeeper.xtime.tv_nsec -= NSEC_PER_SEC; + timekeeper.xtime.tv_sec++; + leap = second_overflow(timekeeper.xtime.tv_sec); + timekeeper.xtime.tv_sec += leap; } - /* check to see if there is a new clocksource to use */ - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(false); + +out: + write_sequnlock_irqrestore(&timekeeper.lock, flags); + } /** @@ -1074,8 +1102,10 @@ static void update_wall_time(void) void getboottime(struct timespec *ts) { struct timespec boottime = { - .tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec, - .tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec + .tv_sec = timekeeper.wall_to_monotonic.tv_sec + + timekeeper.total_sleep_time.tv_sec, + .tv_nsec = timekeeper.wall_to_monotonic.tv_nsec + + timekeeper.total_sleep_time.tv_nsec }; set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); @@ -1101,13 +1131,13 @@ void get_monotonic_boottime(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); - *ts = xtime; - tomono = wall_to_monotonic; - sleep = total_sleep_time; + seq = read_seqbegin(&timekeeper.lock); + *ts = timekeeper.xtime; + tomono = timekeeper.wall_to_monotonic; + sleep = timekeeper.total_sleep_time; nsecs = timekeeping_get_ns(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs); @@ -1137,19 +1167,19 @@ EXPORT_SYMBOL_GPL(ktime_get_boottime); */ void monotonic_to_bootbased(struct timespec *ts) { - *ts = timespec_add(*ts, total_sleep_time); + *ts = timespec_add(*ts, timekeeper.total_sleep_time); } EXPORT_SYMBOL_GPL(monotonic_to_bootbased); unsigned long get_seconds(void) { - return xtime.tv_sec; + return timekeeper.xtime.tv_sec; } EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - return xtime; + return timekeeper.xtime; } struct timespec current_kernel_time(void) @@ -1158,10 +1188,10 @@ struct timespec current_kernel_time(void) unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - now = xtime; - } while (read_seqretry(&xtime_lock, seq)); + now = timekeeper.xtime; + } while (read_seqretry(&timekeeper.lock, seq)); return now; } @@ -1173,11 +1203,11 @@ struct timespec get_monotonic_coarse(void) unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - now = xtime; - mono = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); + now = timekeeper.xtime; + mono = timekeeper.wall_to_monotonic; + } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); @@ -1209,11 +1239,11 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); - *xtim = xtime; - *wtom = wall_to_monotonic; - *sleep = total_sleep_time; - } while (read_seqretry(&xtime_lock, seq)); + seq = read_seqbegin(&timekeeper.lock); + *xtim = timekeeper.xtime; + *wtom = timekeeper.wall_to_monotonic; + *sleep = timekeeper.total_sleep_time; + } while (read_seqretry(&timekeeper.lock, seq)); } /** @@ -1225,11 +1255,14 @@ ktime_t ktime_get_monotonic_offset(void) struct timespec wtom; do { - seq = read_seqbegin(&xtime_lock); - wtom = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); + seq = read_seqbegin(&timekeeper.lock); + wtom = timekeeper.wall_to_monotonic; + } while (read_seqretry(&timekeeper.lock, seq)); + return timespec_to_ktime(wtom); } +EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); + /** * xtime_update() - advances the timekeeping infrastructure diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index cd3134510f3d..a1d2849f2473 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,7 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE + select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 683d559a0eef..0fa92f677c92 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -62,6 +62,8 @@ #define FTRACE_HASH_DEFAULT_BITS 10 #define FTRACE_HASH_MAX_BITS 12 +#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL) + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; @@ -89,12 +91,14 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { }; static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; +static struct ftrace_ops control_ops; static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); @@ -168,6 +172,32 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) } #endif +static void control_ops_disable_all(struct ftrace_ops *ops) +{ + int cpu; + + for_each_possible_cpu(cpu) + *per_cpu_ptr(ops->disabled, cpu) = 1; +} + +static int control_ops_alloc(struct ftrace_ops *ops) +{ + int __percpu *disabled; + + disabled = alloc_percpu(int); + if (!disabled) + return -ENOMEM; + + ops->disabled = disabled; + control_ops_disable_all(ops); + return 0; +} + +static void control_ops_free(struct ftrace_ops *ops) +{ + free_percpu(ops->disabled); +} + static void update_global_ops(void) { ftrace_func_t func; @@ -219,7 +249,8 @@ static void update_ftrace_function(void) #else __ftrace_trace_function = func; #endif - ftrace_trace_function = ftrace_test_stop_func; + ftrace_trace_function = + (func == ftrace_stub) ? func : ftrace_test_stop_func; #endif } @@ -259,6 +290,26 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) return 0; } +static void add_ftrace_list_ops(struct ftrace_ops **list, + struct ftrace_ops *main_ops, + struct ftrace_ops *ops) +{ + int first = *list == &ftrace_list_end; + add_ftrace_ops(list, ops); + if (first) + add_ftrace_ops(&ftrace_ops_list, main_ops); +} + +static int remove_ftrace_list_ops(struct ftrace_ops **list, + struct ftrace_ops *main_ops, + struct ftrace_ops *ops) +{ + int ret = remove_ftrace_ops(list, ops); + if (!ret && *list == &ftrace_list_end) + ret = remove_ftrace_ops(&ftrace_ops_list, main_ops); + return ret; +} + static int __register_ftrace_function(struct ftrace_ops *ops) { if (ftrace_disabled) @@ -270,15 +321,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) return -EBUSY; + /* We don't support both control and global flags set. */ + if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) + return -EINVAL; + if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; if (ops->flags & FTRACE_OPS_FL_GLOBAL) { - int first = ftrace_global_list == &ftrace_list_end; - add_ftrace_ops(&ftrace_global_list, ops); + add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops); ops->flags |= FTRACE_OPS_FL_ENABLED; - if (first) - add_ftrace_ops(&ftrace_ops_list, &global_ops); + } else if (ops->flags & FTRACE_OPS_FL_CONTROL) { + if (control_ops_alloc(ops)) + return -ENOMEM; + add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops); } else add_ftrace_ops(&ftrace_ops_list, ops); @@ -302,11 +358,23 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) return -EINVAL; if (ops->flags & FTRACE_OPS_FL_GLOBAL) { - ret = remove_ftrace_ops(&ftrace_global_list, ops); - if (!ret && ftrace_global_list == &ftrace_list_end) - ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops); + ret = remove_ftrace_list_ops(&ftrace_global_list, + &global_ops, ops); if (!ret) ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } else if (ops->flags & FTRACE_OPS_FL_CONTROL) { + ret = remove_ftrace_list_ops(&ftrace_control_list, + &control_ops, ops); + if (!ret) { + /* + * The ftrace_ops is now removed from the list, + * so there'll be no new users. We must ensure + * all current users are done before we free + * the control data. + */ + synchronize_sched(); + control_ops_free(ops); + } } else ret = remove_ftrace_ops(&ftrace_ops_list, ops); @@ -1119,6 +1187,12 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); } +void ftrace_free_filter(struct ftrace_ops *ops) +{ + free_ftrace_hash(ops->filter_hash); + free_ftrace_hash(ops->notrace_hash); +} + static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { struct ftrace_hash *hash; @@ -1129,7 +1203,7 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits) return NULL; size = 1 << size_bits; - hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL); + hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL); if (!hash->buckets) { kfree(hash); @@ -3146,8 +3220,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_lock(&ftrace_regex_lock); if (reset) ftrace_filter_reset(hash); - if (buf) - ftrace_match_records(hash, buf, len); + if (buf && !ftrace_match_records(hash, buf, len)) { + ret = -EINVAL; + goto out_regex_unlock; + } mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); @@ -3157,6 +3233,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_unlock(&ftrace_lock); + out_regex_unlock: mutex_unlock(&ftrace_regex_lock); free_ftrace_hash(hash); @@ -3173,10 +3250,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. */ -void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, +int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) { - ftrace_set_regex(ops, buf, len, reset, 1); + return ftrace_set_regex(ops, buf, len, reset, 1); } EXPORT_SYMBOL_GPL(ftrace_set_filter); @@ -3191,10 +3268,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter); * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. */ -void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, +int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) { - ftrace_set_regex(ops, buf, len, reset, 0); + return ftrace_set_regex(ops, buf, len, reset, 0); } EXPORT_SYMBOL_GPL(ftrace_set_notrace); /** @@ -3871,6 +3948,36 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) #endif /* CONFIG_DYNAMIC_FTRACE */ static void +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_ops *op; + + if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) + return; + + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + trace_recursion_set(TRACE_CONTROL_BIT); + op = rcu_dereference_raw(ftrace_control_list); + while (op != &ftrace_list_end) { + if (!ftrace_function_local_disabled(op) && + ftrace_ops_test(op, ip)) + op->func(ip, parent_ip); + + op = rcu_dereference_raw(op->next); + }; + trace_recursion_clear(TRACE_CONTROL_BIT); + preempt_enable_notrace(); +} + +static struct ftrace_ops control_ops = { + .func = ftrace_ops_control_func, +}; + +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { struct ftrace_ops *op; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f5b7b5c1195b..cf8d11e91efd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -154,33 +154,10 @@ enum { static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; -#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) - -/** - * tracing_on - enable all tracing buffers - * - * This function enables all tracing buffers that may have been - * disabled with tracing_off. - */ -void tracing_on(void) -{ - set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); -} -EXPORT_SYMBOL_GPL(tracing_on); +/* Used for individual buffers (after the counter) */ +#define RB_BUFFER_OFF (1 << 20) -/** - * tracing_off - turn off all tracing buffers - * - * This function stops all tracing buffers from recording data. - * It does not disable any overhead the tracers themselves may - * be causing. This function simply causes all recording to - * the ring buffers to fail. - */ -void tracing_off(void) -{ - clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); -} -EXPORT_SYMBOL_GPL(tracing_off); +#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) /** * tracing_off_permanent - permanently disable ring buffers @@ -193,15 +170,6 @@ void tracing_off_permanent(void) set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); } -/** - * tracing_is_on - show state of ring buffers enabled - */ -int tracing_is_on(void) -{ - return ring_buffer_flags == RB_BUFFERS_ON; -} -EXPORT_SYMBOL_GPL(tracing_is_on); - #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) @@ -2619,6 +2587,63 @@ void ring_buffer_record_enable(struct ring_buffer *buffer) EXPORT_SYMBOL_GPL(ring_buffer_record_enable); /** + * ring_buffer_record_off - stop all writes into the buffer + * @buffer: The ring buffer to stop writes to. + * + * This prevents all writes to the buffer. Any attempt to write + * to the buffer after this will fail and return NULL. + * + * This is different than ring_buffer_record_disable() as + * it works like an on/off switch, where as the disable() verison + * must be paired with a enable(). + */ +void ring_buffer_record_off(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd | RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_off); + +/** + * ring_buffer_record_on - restart writes into the buffer + * @buffer: The ring buffer to start writes to. + * + * This enables all writes to the buffer that was disabled by + * ring_buffer_record_off(). + * + * This is different than ring_buffer_record_enable() as + * it works like an on/off switch, where as the enable() verison + * must be paired with a disable(). + */ +void ring_buffer_record_on(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd & ~RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_on); + +/** + * ring_buffer_record_is_on - return true if the ring buffer can write + * @buffer: The ring buffer to see if write is enabled + * + * Returns true if the ring buffer is in a state that it accepts writes. + */ +int ring_buffer_record_is_on(struct ring_buffer *buffer) +{ + return !atomic_read(&buffer->record_disabled); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop @@ -4039,68 +4064,6 @@ int ring_buffer_read_page(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); -#ifdef CONFIG_TRACING -static ssize_t -rb_simple_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long *p = filp->private_data; - char buf[64]; - int r; - - if (test_bit(RB_BUFFERS_DISABLED_BIT, p)) - r = sprintf(buf, "permanently disabled\n"); - else - r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p)); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static ssize_t -rb_simple_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long *p = filp->private_data; - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - if (val) - set_bit(RB_BUFFERS_ON_BIT, p); - else - clear_bit(RB_BUFFERS_ON_BIT, p); - - (*ppos)++; - - return cnt; -} - -static const struct file_operations rb_simple_fops = { - .open = tracing_open_generic, - .read = rb_simple_read, - .write = rb_simple_write, - .llseek = default_llseek, -}; - - -static __init int rb_init_debugfs(void) -{ - struct dentry *d_tracer; - - d_tracer = tracing_init_dentry(); - - trace_create_file("tracing_on", 0644, d_tracer, - &ring_buffer_flags, &rb_simple_fops); - - return 0; -} - -fs_initcall(rb_init_debugfs); -#endif - #ifdef CONFIG_HOTPLUG_CPU static int rb_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a3f1bc5d2a00..ed7b5d1e12f4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -36,6 +36,7 @@ #include <linux/ctype.h> #include <linux/init.h> #include <linux/poll.h> +#include <linux/nmi.h> #include <linux/fs.h> #include "trace.h" @@ -352,6 +353,59 @@ static void wakeup_work_handler(struct work_struct *work) static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); /** + * tracing_on - enable tracing buffers + * + * This function enables tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 0; +} +EXPORT_SYMBOL_GPL(tracing_on); + +/** + * tracing_off - turn off tracing buffers + * + * This function stops the tracing buffers from recording data. + * It does not disable any overhead the tracers themselves may + * be causing. This function simply causes all recording to + * the ring buffers to fail. + */ +void tracing_off(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 1; +} +EXPORT_SYMBOL_GPL(tracing_off); + +/** + * tracing_is_on - show state of ring buffers enabled + */ +int tracing_is_on(void) +{ + if (global_trace.buffer) + return ring_buffer_record_is_on(global_trace.buffer); + return !global_trace.buffer_disabled; +} +EXPORT_SYMBOL_GPL(tracing_is_on); + +/** * trace_wake_up - wake up tasks waiting for trace input * * Schedules a delayed work to wake up any task that is blocked on the @@ -1644,6 +1698,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; + int next_size = 0; int cpu; /* @@ -1675,9 +1730,12 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, next_cpu = cpu; next_ts = ts; next_lost = lost_events; + next_size = iter->ent_size; } } + iter->ent_size = next_size; + if (ent_cpu) *ent_cpu = next_cpu; @@ -2764,12 +2822,12 @@ static const char readme_msg[] = "tracing mini-HOWTO:\n\n" "# mount -t debugfs nodev /sys/kernel/debug\n\n" "# cat /sys/kernel/debug/tracing/available_tracers\n" - "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n" + "wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n" "# cat /sys/kernel/debug/tracing/current_tracer\n" "nop\n" - "# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n" + "# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n" "# cat /sys/kernel/debug/tracing/current_tracer\n" - "sched_switch\n" + "wakeup\n" "# cat /sys/kernel/debug/tracing/trace_options\n" "noprint-parent nosym-offset nosym-addr noverbose\n" "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n" @@ -4567,6 +4625,55 @@ static __init void create_trace_options_dir(void) create_trace_option_core_file(trace_options[i], i); } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + char buf[64]; + int r; + + if (buffer) + r = ring_buffer_record_is_on(buffer); + else + r = 0; + + r = sprintf(buf, "%d\n", r); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +rb_simple_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (buffer) { + if (val) + ring_buffer_record_on(buffer); + else + ring_buffer_record_off(buffer); + } + + (*ppos)++; + + return cnt; +} + +static const struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, + .llseek = default_llseek, +}; + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; @@ -4626,6 +4733,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("trace_clock", 0644, d_tracer, NULL, &trace_clock_fops); + trace_create_file("tracing_on", 0644, d_tracer, + global_trace.buffer, &rb_simple_fops); + #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); @@ -4798,6 +4908,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); } + touch_nmi_watchdog(); trace_printk_seq(&iter.seq); } @@ -4863,6 +4974,8 @@ __init static int tracer_alloc_buffers(void) goto out_free_cpumask; } global_trace.entries = ring_buffer_size(global_trace.buffer); + if (global_trace.buffer_disabled) + tracing_off(); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b93ecbadad6d..95059f091a24 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -56,17 +56,23 @@ enum trace_type { #define F_STRUCT(args...) args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ - struct struct_name { \ - struct trace_entry ent; \ - tstruct \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ + struct struct_name { \ + struct trace_entry ent; \ + tstruct \ } #undef TP_ARGS #define TP_ARGS(args...) args #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) + +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ + filter, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) #include "trace_entries.h" @@ -148,6 +154,7 @@ struct trace_array { struct ring_buffer *buffer; unsigned long entries; int cpu; + int buffer_disabled; cycle_t time_start; struct task_struct *waiter; struct trace_array_cpu *data[NR_CPUS]; @@ -288,6 +295,8 @@ struct tracer { /* for function tracing recursion */ #define TRACE_INTERNAL_BIT (1<<11) #define TRACE_GLOBAL_BIT (1<<12) +#define TRACE_CONTROL_BIT (1<<13) + /* * Abuse of the trace_recursion. * As we need a way to maintain state if we are tracing the function @@ -589,6 +598,8 @@ static inline int ftrace_trace_task(struct task_struct *task) static inline int ftrace_is_dead(void) { return 0; } #endif +int ftrace_event_is_function(struct ftrace_event_call *call); + /* * struct trace_parser - servers for reading the user input separated by spaces * @cont: set if the input is not complete - no final space char was found @@ -766,9 +777,7 @@ struct filter_pred { u64 val; struct regex regex; unsigned short *ops; -#ifdef CONFIG_FTRACE_STARTUP_TEST struct ftrace_event_field *field; -#endif int offset; int not; int op; @@ -818,12 +827,20 @@ extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ __attribute__((__aligned__(4))) event_##call; #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) #include "trace_entries.h" +#ifdef CONFIG_FUNCTION_TRACER +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data); +#else +#define perf_ftrace_event_register NULL +#endif /* CONFIG_FUNCTION_TRACER */ + #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 93365907f219..4108e1250ca2 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -55,7 +55,7 @@ /* * Function trace entry - function address and parent function address: */ -FTRACE_ENTRY(function, ftrace_entry, +FTRACE_ENTRY_REG(function, ftrace_entry, TRACE_FN, @@ -64,7 +64,11 @@ FTRACE_ENTRY(function, ftrace_entry, __field( unsigned long, parent_ip ) ), - F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip) + F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip), + + FILTER_TRACE_FN, + + perf_ftrace_event_register ); /* Function call entry */ @@ -78,7 +82,9 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, __field_desc( int, graph_ent, depth ) ), - F_printk("--> %lx (%d)", __entry->func, __entry->depth) + F_printk("--> %lx (%d)", __entry->func, __entry->depth), + + FILTER_OTHER ); /* Function return entry */ @@ -98,7 +104,9 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d", __entry->func, __entry->depth, __entry->calltime, __entry->rettime, - __entry->depth) + __entry->depth), + + FILTER_OTHER ); /* @@ -127,8 +135,9 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry, F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu - ) + __entry->next_cpu), + + FILTER_OTHER ); /* @@ -146,8 +155,9 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu - ) + __entry->next_cpu), + + FILTER_OTHER ); /* @@ -156,6 +166,12 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, #define FTRACE_STACK_ENTRIES 8 +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + FTRACE_ENTRY(kernel_stack, stack_entry, TRACE_STACK, @@ -165,11 +181,14 @@ FTRACE_ENTRY(kernel_stack, stack_entry, __dynamic_array(unsigned long, caller ) ), - F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" - "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n", __entry->caller[0], __entry->caller[1], __entry->caller[2], __entry->caller[3], __entry->caller[4], __entry->caller[5], - __entry->caller[6], __entry->caller[7]) + __entry->caller[6], __entry->caller[7]), + + FILTER_OTHER ); FTRACE_ENTRY(user_stack, userstack_entry, @@ -181,11 +200,14 @@ FTRACE_ENTRY(user_stack, userstack_entry, __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), - F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" - "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n", __entry->caller[0], __entry->caller[1], __entry->caller[2], __entry->caller[3], __entry->caller[4], __entry->caller[5], - __entry->caller[6], __entry->caller[7]) + __entry->caller[6], __entry->caller[7]), + + FILTER_OTHER ); /* @@ -202,7 +224,9 @@ FTRACE_ENTRY(bprint, bprint_entry, ), F_printk("%08lx fmt:%p", - __entry->ip, __entry->fmt) + __entry->ip, __entry->fmt), + + FILTER_OTHER ); FTRACE_ENTRY(print, print_entry, @@ -215,7 +239,9 @@ FTRACE_ENTRY(print, print_entry, ), F_printk("%08lx %s", - __entry->ip, __entry->buf) + __entry->ip, __entry->buf), + + FILTER_OTHER ); FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, @@ -234,7 +260,9 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, F_printk("%lx %lx %lx %d %x %x", (unsigned long)__entry->phys, __entry->value, __entry->pc, - __entry->map_id, __entry->opcode, __entry->width) + __entry->map_id, __entry->opcode, __entry->width), + + FILTER_OTHER ); FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, @@ -252,7 +280,9 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, F_printk("%lx %lx %lx %d %x", (unsigned long)__entry->phys, __entry->virt, __entry->len, - __entry->map_id, __entry->opcode) + __entry->map_id, __entry->opcode), + + FILTER_OTHER ); @@ -272,6 +302,8 @@ FTRACE_ENTRY(branch, trace_branch, F_printk("%u:%s:%s (%u)", __entry->line, - __entry->func, __entry->file, __entry->correct) + __entry->func, __entry->file, __entry->correct), + + FILTER_OTHER ); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 19a359d5e6d5..fee3752ae8f6 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -24,6 +24,11 @@ static int total_ref_count; static int perf_trace_event_perm(struct ftrace_event_call *tp_event, struct perf_event *p_event) { + /* The ftrace function trace is allowed only for root. */ + if (ftrace_event_is_function(tp_event) && + perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* No tracing, just counting, so no obvious leak */ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) return 0; @@ -44,23 +49,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event, return 0; } -static int perf_trace_event_init(struct ftrace_event_call *tp_event, - struct perf_event *p_event) +static int perf_trace_event_reg(struct ftrace_event_call *tp_event, + struct perf_event *p_event) { struct hlist_head __percpu *list; - int ret; + int ret = -ENOMEM; int cpu; - ret = perf_trace_event_perm(tp_event, p_event); - if (ret) - return ret; - p_event->tp_event = tp_event; if (tp_event->perf_refcount++ > 0) return 0; - ret = -ENOMEM; - list = alloc_percpu(struct hlist_head); if (!list) goto fail; @@ -83,7 +82,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event, } } - ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); + ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL); if (ret) goto fail; @@ -108,6 +107,69 @@ fail: return ret; } +static void perf_trace_event_unreg(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + int i; + + if (--tp_event->perf_refcount > 0) + goto out; + + tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL); + + /* + * Ensure our callback won't be called anymore. The buffers + * will be freed after that. + */ + tracepoint_synchronize_unregister(); + + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + + if (!--total_ref_count) { + for (i = 0; i < PERF_NR_CONTEXTS; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; + } + } +out: + module_put(tp_event->mod); +} + +static int perf_trace_event_open(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event); +} + +static void perf_trace_event_close(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event); +} + +static int perf_trace_event_init(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + int ret; + + ret = perf_trace_event_perm(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_reg(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_open(p_event); + if (ret) { + perf_trace_event_unreg(p_event); + return ret; + } + + return 0; +} + int perf_trace_init(struct perf_event *p_event) { struct ftrace_event_call *tp_event; @@ -130,6 +192,14 @@ int perf_trace_init(struct perf_event *p_event) return ret; } +void perf_trace_destroy(struct perf_event *p_event) +{ + mutex_lock(&event_mutex); + perf_trace_event_close(p_event); + perf_trace_event_unreg(p_event); + mutex_unlock(&event_mutex); +} + int perf_trace_add(struct perf_event *p_event, int flags) { struct ftrace_event_call *tp_event = p_event->tp_event; @@ -146,43 +216,14 @@ int perf_trace_add(struct perf_event *p_event, int flags) list = this_cpu_ptr(pcpu_list); hlist_add_head_rcu(&p_event->hlist_entry, list); - return 0; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event); } void perf_trace_del(struct perf_event *p_event, int flags) { - hlist_del_rcu(&p_event->hlist_entry); -} - -void perf_trace_destroy(struct perf_event *p_event) -{ struct ftrace_event_call *tp_event = p_event->tp_event; - int i; - - mutex_lock(&event_mutex); - if (--tp_event->perf_refcount > 0) - goto out; - - tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); - - /* - * Ensure our callback won't be called anymore. The buffers - * will be freed after that. - */ - tracepoint_synchronize_unregister(); - - free_percpu(tp_event->perf_events); - tp_event->perf_events = NULL; - - if (!--total_ref_count) { - for (i = 0; i < PERF_NR_CONTEXTS; i++) { - free_percpu(perf_trace_buf[i]); - perf_trace_buf[i] = NULL; - } - } -out: - module_put(tp_event->mod); - mutex_unlock(&event_mutex); + hlist_del_rcu(&p_event->hlist_entry); + tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event); } __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, @@ -214,3 +255,86 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, return raw_data; } EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); + +#ifdef CONFIG_FUNCTION_TRACER +static void +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_entry *entry; + struct hlist_head *head; + struct pt_regs regs; + int rctx; + +#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \ + sizeof(u64)) - sizeof(u32)) + + BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE); + + perf_fetch_caller_regs(®s); + + entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx); + if (!entry) + return; + + entry->ip = ip; + entry->parent_ip = parent_ip; + + head = this_cpu_ptr(event_function.perf_events); + perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, + 1, ®s, head); + +#undef ENTRY_SIZE +} + +static int perf_ftrace_function_register(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + + ops->flags |= FTRACE_OPS_FL_CONTROL; + ops->func = perf_ftrace_function_call; + return register_ftrace_function(ops); +} + +static int perf_ftrace_function_unregister(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + int ret = unregister_ftrace_function(ops); + ftrace_free_filter(ops); + return ret; +} + +static void perf_ftrace_function_enable(struct perf_event *event) +{ + ftrace_function_local_enable(&event->ftrace_ops); +} + +static void perf_ftrace_function_disable(struct perf_event *event) +{ + ftrace_function_local_disable(&event->ftrace_ops); +} + +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data) +{ + switch (type) { + case TRACE_REG_REGISTER: + case TRACE_REG_UNREGISTER: + break; + case TRACE_REG_PERF_REGISTER: + case TRACE_REG_PERF_UNREGISTER: + return 0; + case TRACE_REG_PERF_OPEN: + return perf_ftrace_function_register(data); + case TRACE_REG_PERF_CLOSE: + return perf_ftrace_function_unregister(data); + case TRACE_REG_PERF_ADD: + perf_ftrace_function_enable(data); + return 0; + case TRACE_REG_PERF_DEL: + perf_ftrace_function_disable(data); + return 0; + } + + return -EINVAL; +} +#endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c212a7f934ec..079a93ae8a9d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -147,7 +147,8 @@ int trace_event_raw_init(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_event_raw_init); -int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type) +int ftrace_event_reg(struct ftrace_event_call *call, + enum trace_reg type, void *data) { switch (type) { case TRACE_REG_REGISTER: @@ -170,6 +171,11 @@ int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type) call->class->perf_probe, call); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; #endif } return 0; @@ -209,7 +215,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, tracing_stop_cmdline_record(); call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD; } - call->class->reg(call, TRACE_REG_UNREGISTER); + call->class->reg(call, TRACE_REG_UNREGISTER, NULL); } break; case 1: @@ -218,7 +224,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, tracing_start_cmdline_record(); call->flags |= TRACE_EVENT_FL_RECORDED_CMD; } - ret = call->class->reg(call, TRACE_REG_REGISTER); + ret = call->class->reg(call, TRACE_REG_REGISTER, NULL); if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 24aee7127451..431dba8b7542 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -81,6 +81,7 @@ enum { FILT_ERR_TOO_MANY_PREDS, FILT_ERR_MISSING_FIELD, FILT_ERR_INVALID_FILTER, + FILT_ERR_IP_FIELD_ONLY, }; static char *err_text[] = { @@ -96,6 +97,7 @@ static char *err_text[] = { "Too many terms in predicate expression", "Missing field name and/or value", "Meaningless filter expression", + "Only 'ip' field is supported for function trace", }; struct opstack_op { @@ -685,7 +687,7 @@ find_event_field(struct ftrace_event_call *call, char *name) static int __alloc_pred_stack(struct pred_stack *stack, int n_preds) { - stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL); + stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL); if (!stack->preds) return -ENOMEM; stack->index = n_preds; @@ -826,8 +828,7 @@ static int __alloc_preds(struct event_filter *filter, int n_preds) if (filter->preds) __free_preds(filter); - filter->preds = - kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL); + filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL); if (!filter->preds) return -ENOMEM; @@ -900,6 +901,11 @@ int filter_assign_type(const char *type) return FILTER_OTHER; } +static bool is_function_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_TRACE_FN; +} + static bool is_string_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_DYN_STRING || @@ -987,6 +993,11 @@ static int init_pred(struct filter_parse_state *ps, fn = filter_pred_strloc; else fn = filter_pred_pchar; + } else if (is_function_field(field)) { + if (strcmp(field->name, "ip")) { + parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0); + return -EINVAL; + } } else { if (field->is_signed) ret = strict_strtoll(pred->regex.pattern, 0, &val); @@ -1334,10 +1345,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps, strcpy(pred.regex.pattern, operand2); pred.regex.len = strlen(pred.regex.pattern); - -#ifdef CONFIG_FTRACE_STARTUP_TEST pred.field = field; -#endif return init_pred(ps, field, &pred) ? NULL : &pred; } @@ -1486,7 +1494,7 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root) children = count_leafs(preds, &preds[root->left]); children += count_leafs(preds, &preds[root->right]); - root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL); + root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL); if (!root->ops) return -ENOMEM; @@ -1950,6 +1958,148 @@ void ftrace_profile_free_filter(struct perf_event *event) __free_filter(filter); } +struct function_filter_data { + struct ftrace_ops *ops; + int first_filter; + int first_notrace; +}; + +#ifdef CONFIG_FUNCTION_TRACER +static char ** +ftrace_function_filter_re(char *buf, int len, int *count) +{ + char *str, *sep, **re; + + str = kstrndup(buf, len, GFP_KERNEL); + if (!str) + return NULL; + + /* + * The argv_split function takes white space + * as a separator, so convert ',' into spaces. + */ + while ((sep = strchr(str, ','))) + *sep = ' '; + + re = argv_split(GFP_KERNEL, str, count); + kfree(str); + return re; +} + +static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, + int reset, char *re, int len) +{ + int ret; + + if (filter) + ret = ftrace_set_filter(ops, re, len, reset); + else + ret = ftrace_set_notrace(ops, re, len, reset); + + return ret; +} + +static int __ftrace_function_set_filter(int filter, char *buf, int len, + struct function_filter_data *data) +{ + int i, re_cnt, ret; + int *reset; + char **re; + + reset = filter ? &data->first_filter : &data->first_notrace; + + /* + * The 'ip' field could have multiple filters set, separated + * either by space or comma. We first cut the filter and apply + * all pieces separatelly. + */ + re = ftrace_function_filter_re(buf, len, &re_cnt); + if (!re) + return -EINVAL; + + for (i = 0; i < re_cnt; i++) { + ret = ftrace_function_set_regexp(data->ops, filter, *reset, + re[i], strlen(re[i])); + if (ret) + break; + + if (*reset) + *reset = 0; + } + + argv_free(re); + return ret; +} + +static int ftrace_function_check_pred(struct filter_pred *pred, int leaf) +{ + struct ftrace_event_field *field = pred->field; + + if (leaf) { + /* + * Check the leaf predicate for function trace, verify: + * - only '==' and '!=' is used + * - the 'ip' field is used + */ + if ((pred->op != OP_EQ) && (pred->op != OP_NE)) + return -EINVAL; + + if (strcmp(field->name, "ip")) + return -EINVAL; + } else { + /* + * Check the non leaf predicate for function trace, verify: + * - only '||' is used + */ + if (pred->op != OP_OR) + return -EINVAL; + } + + return 0; +} + +static int ftrace_function_set_filter_cb(enum move_type move, + struct filter_pred *pred, + int *err, void *data) +{ + /* Checking the node is valid for function trace. */ + if ((move != MOVE_DOWN) || + (pred->left != FILTER_PRED_INVALID)) { + *err = ftrace_function_check_pred(pred, 0); + } else { + *err = ftrace_function_check_pred(pred, 1); + if (*err) + return WALK_PRED_ABORT; + + *err = __ftrace_function_set_filter(pred->op == OP_EQ, + pred->regex.pattern, + pred->regex.len, + data); + } + + return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT; +} + +static int ftrace_function_set_filter(struct perf_event *event, + struct event_filter *filter) +{ + struct function_filter_data data = { + .first_filter = 1, + .first_notrace = 1, + .ops = &event->ftrace_ops, + }; + + return walk_pred_tree(filter->preds, filter->root, + ftrace_function_set_filter_cb, &data); +} +#else +static int ftrace_function_set_filter(struct perf_event *event, + struct event_filter *filter) +{ + return -ENODEV; +} +#endif /* CONFIG_FUNCTION_TRACER */ + int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str) { @@ -1970,9 +2120,16 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, goto out_unlock; err = create_filter(call, filter_str, false, &filter); - if (!err) - event->filter = filter; + if (err) + goto free_filter; + + if (ftrace_event_is_function(call)) + err = ftrace_function_set_filter(event, filter); else + event->filter = filter; + +free_filter: + if (err || ftrace_event_is_function(call)) __free_filter(filter); out_unlock: diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index bbeec31e0ae3..3dd15e8bc856 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -18,6 +18,16 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace +/* + * The FTRACE_ENTRY_REG macro allows ftrace entry to define register + * function and thus become accesible via perf. + */ +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ + filter, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) + /* not needed for this file */ #undef __field_struct #define __field_struct(type, item) @@ -44,21 +54,22 @@ #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ -struct ____ftrace_##name { \ - tstruct \ -}; \ -static void __always_unused ____ftrace_check_##name(void) \ -{ \ - struct ____ftrace_##name *__entry = NULL; \ - \ - /* force compile-time check on F_printk() */ \ - printk(print); \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +struct ____ftrace_##name { \ + tstruct \ +}; \ +static void __always_unused ____ftrace_check_##name(void) \ +{ \ + struct ____ftrace_##name *__entry = NULL; \ + \ + /* force compile-time check on F_printk() */ \ + printk(print); \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) #include "trace_entries.h" @@ -67,7 +78,7 @@ static void __always_unused ____ftrace_check_##name(void) \ ret = trace_define_field(event_call, #type, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; @@ -77,7 +88,7 @@ static void __always_unused ____ftrace_check_##name(void) \ offsetof(typeof(field), \ container.item), \ sizeof(field.container.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; @@ -91,7 +102,7 @@ static void __always_unused ____ftrace_check_##name(void) \ ret = trace_define_field(event_call, event_storage, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ mutex_unlock(&event_storage_mutex); \ if (ret) \ return ret; \ @@ -104,7 +115,7 @@ static void __always_unused ____ftrace_check_##name(void) \ offsetof(typeof(field), \ container.item), \ sizeof(field.container.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; @@ -112,17 +123,18 @@ static void __always_unused ____ftrace_check_##name(void) \ #define __dynamic_array(type, item) \ ret = trace_define_field(event_call, #type, #item, \ offsetof(typeof(field), item), \ - 0, is_signed_type(type), FILTER_OTHER);\ + 0, is_signed_type(type), filter_type);\ if (ret) \ return ret; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ int \ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ { \ struct struct_name field; \ int ret; \ + int filter_type = filter; \ \ tstruct; \ \ @@ -150,15 +162,17 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #define __dynamic_array(type, item) #undef F_printk -#define F_printk(fmt, args...) #fmt ", " __stringify(args) +#define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) -#undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ + regfn) \ \ struct ftrace_event_class event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .define_fields = ftrace_define_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ + .reg = regfn, \ }; \ \ struct ftrace_event_call __used event_##call = { \ @@ -170,4 +184,14 @@ struct ftrace_event_call __used event_##call = { \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ + FTRACE_ENTRY_REG(call, struct_name, etype, \ + PARAMS(tstruct), PARAMS(print), filter, NULL) + +int ftrace_event_is_function(struct ftrace_event_call *call) +{ + return call == &event_function; +} + #include "trace_entries.h" diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 00d527c945a4..580a05ec926b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1892,7 +1892,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, #endif /* CONFIG_PERF_EVENTS */ static __kprobes -int kprobe_register(struct ftrace_event_call *event, enum trace_reg type) +int kprobe_register(struct ftrace_event_call *event, + enum trace_reg type, void *data) { struct trace_probe *tp = (struct trace_probe *)event->data; @@ -1909,6 +1910,11 @@ int kprobe_register(struct ftrace_event_call *event, enum trace_reg type) case TRACE_REG_PERF_UNREGISTER: disable_trace_probe(tp, TP_FLAG_PROFILE); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; #endif } return 0; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 0d6ff3555942..859fae6b1825 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -264,7 +264,7 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len) return ret; } -int trace_seq_path(struct trace_seq *s, struct path *path) +int trace_seq_path(struct trace_seq *s, const struct path *path) { unsigned char *p; @@ -300,7 +300,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long mask; const char *str; const char *ret = p->buffer + p->len; - int i; + int i, first = 1; for (i = 0; flag_array[i].name && flags; i++) { @@ -310,14 +310,16 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim, str = flag_array[i].name; flags &= ~mask; - if (p->len && delim) + if (!first && delim) trace_seq_puts(p, delim); + else + first = 0; trace_seq_puts(p, str); } /* check for left over flags */ if (flags) { - if (p->len && delim) + if (!first && delim) trace_seq_puts(p, delim); trace_seq_printf(p, "0x%lx", flags); } @@ -344,7 +346,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, break; } - if (!p->len) + if (ret == (const char *)(p->buffer + p->len)) trace_seq_printf(p, "0x%lx", val); trace_seq_putc(p, 0); @@ -370,7 +372,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, break; } - if (!p->len) + if (ret == (const char *)(p->buffer + p->len)) trace_seq_printf(p, "0x%llx", val); trace_seq_putc(p, 0); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index cb654542c1a1..96fc73369099 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -17,9 +17,9 @@ static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); static int syscall_enter_register(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); static int syscall_exit_register(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); static int syscall_enter_define_fields(struct ftrace_event_call *call); static int syscall_exit_define_fields(struct ftrace_event_call *call); @@ -468,8 +468,8 @@ int __init init_ftrace_syscalls(void) unsigned long addr; int i; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * - NR_syscalls, GFP_KERNEL); + syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata), + GFP_KERNEL); if (!syscalls_metadata) { WARN_ON(1); return -ENOMEM; @@ -649,7 +649,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call) #endif /* CONFIG_PERF_EVENTS */ static int syscall_enter_register(struct ftrace_event_call *event, - enum trace_reg type) + enum trace_reg type, void *data) { switch (type) { case TRACE_REG_REGISTER: @@ -664,13 +664,18 @@ static int syscall_enter_register(struct ftrace_event_call *event, case TRACE_REG_PERF_UNREGISTER: perf_sysenter_disable(event); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; #endif } return 0; } static int syscall_exit_register(struct ftrace_event_call *event, - enum trace_reg type) + enum trace_reg type, void *data) { switch (type) { case TRACE_REG_REGISTER: @@ -685,6 +690,11 @@ static int syscall_exit_register(struct ftrace_event_call *event, case TRACE_REG_PERF_UNREGISTER: perf_sysexit_disable(event); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: + return 0; #endif } return 0; diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index f1539decd99d..d96ba22dabfa 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -25,7 +25,7 @@ #include <linux/err.h> #include <linux/slab.h> #include <linux/sched.h> -#include <linux/jump_label.h> +#include <linux/static_key.h> extern struct tracepoint * const __start___tracepoints_ptrs[]; extern struct tracepoint * const __stop___tracepoints_ptrs[]; @@ -256,9 +256,9 @@ static void set_tracepoint(struct tracepoint_entry **entry, { WARN_ON(strcmp((*entry)->name, elem->name) != 0); - if (elem->regfunc && !jump_label_enabled(&elem->key) && active) + if (elem->regfunc && !static_key_enabled(&elem->key) && active) elem->regfunc(); - else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active) + else if (elem->unregfunc && static_key_enabled(&elem->key) && !active) elem->unregfunc(); /* @@ -269,10 +269,10 @@ static void set_tracepoint(struct tracepoint_entry **entry, * is used. */ rcu_assign_pointer(elem->funcs, (*entry)->funcs); - if (active && !jump_label_enabled(&elem->key)) - jump_label_inc(&elem->key); - else if (!active && jump_label_enabled(&elem->key)) - jump_label_dec(&elem->key); + if (active && !static_key_enabled(&elem->key)) + static_key_slow_inc(&elem->key); + else if (!active && static_key_enabled(&elem->key)) + static_key_slow_dec(&elem->key); } /* @@ -283,11 +283,11 @@ static void set_tracepoint(struct tracepoint_entry **entry, */ static void disable_tracepoint(struct tracepoint *elem) { - if (elem->unregfunc && jump_label_enabled(&elem->key)) + if (elem->unregfunc && static_key_enabled(&elem->key)) elem->unregfunc(); - if (jump_label_enabled(&elem->key)) - jump_label_dec(&elem->key); + if (static_key_enabled(&elem->key)) + static_key_slow_dec(&elem->key); rcu_assign_pointer(elem->funcs, NULL); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d117262deba3..df30ee08bdd4 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -3,15 +3,14 @@ * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * - * this code detects hard lockups: incidents in where on a CPU - * the kernel does not respond to anything except NMI. - * - * Note: Most of this code is borrowed heavily from softlockup.c, - * so thanks to Ingo for the initial implementation. - * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks + * Note: Most of this code is borrowed heavily from the original softlockup + * detector, so thanks to Ingo for the initial implementation. + * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ +#define pr_fmt(fmt) "NMI watchdog: " fmt + #include <linux/mm.h> #include <linux/cpu.h> #include <linux/nmi.h> @@ -117,9 +116,10 @@ static unsigned long get_sample_period(void) { /* * convert watchdog_thresh from seconds to ns - * the divide by 5 is to give hrtimer 5 chances to - * increment before the hardlockup detector generates - * a warning + * the divide by 5 is to give hrtimer several chances (two + * or three with the current relation between the soft + * and hard thresholds) to increment before the + * hardlockup detector generates a warning */ return get_softlockup_thresh() * (NSEC_PER_SEC / 5); } @@ -321,11 +321,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ static int watchdog(void *unused) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + struct sched_param param = { .sched_priority = 0 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - sched_setscheduler(current, SCHED_FIFO, ¶m); - /* initialize timestamp */ __touch_watchdog(); @@ -336,9 +334,11 @@ static int watchdog(void *unused) set_current_state(TASK_INTERRUPTIBLE); /* - * Run briefly once per second to reset the softlockup timestamp. - * If this gets delayed for more than 60 seconds then the - * debug-printout triggers in watchdog_timer_fn(). + * Run briefly (kicked by the hrtimer callback function) once every + * get_sample_period() seconds (4 seconds by default) to reset the + * softlockup timestamp. If this gets delayed for more than + * 2*watchdog_thresh seconds then the debug-printout triggers in + * watchdog_timer_fn(). */ while (!kthread_should_stop()) { __touch_watchdog(); @@ -349,8 +349,11 @@ static int watchdog(void *unused) set_current_state(TASK_INTERRUPTIBLE); } + /* + * Drop the policy/priority elevation during thread exit to avoid a + * scheduling latency spike. + */ __set_current_state(TASK_RUNNING); - param.sched_priority = 0; sched_setscheduler(current, SCHED_NORMAL, ¶m); return 0; } @@ -376,18 +379,20 @@ static int watchdog_nmi_enable(int cpu) /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (!IS_ERR(event)) { - printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n"); + pr_info("enabled, takes one hw-pmu counter.\n"); goto out_save; } /* vary the KERN level based on the returned errno */ if (PTR_ERR(event) == -EOPNOTSUPP) - printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu); + pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); else if (PTR_ERR(event) == -ENOENT) - printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu); + pr_warning("disabled (cpu%i): hardware events not enabled\n", + cpu); else - printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event)); + pr_err("disabled (cpu%i): unable to create perf event: %ld\n", + cpu, PTR_ERR(event)); return PTR_ERR(event); /* success path */ @@ -439,9 +444,10 @@ static int watchdog_enable(int cpu) /* create the watchdog thread */ if (!p) { + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu); if (IS_ERR(p)) { - printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); + pr_err("softlockup watchdog for %i failed\n", cpu); if (!err) { /* if hardlockup hasn't already set this */ err = PTR_ERR(p); @@ -450,6 +456,7 @@ static int watchdog_enable(int cpu) } goto out; } + sched_setscheduler(p, SCHED_FIFO, ¶m); kthread_bind(p, cpu); per_cpu(watchdog_touch_ts, cpu) = 0; per_cpu(softlockup_watchdog, cpu) = p; @@ -496,7 +503,7 @@ static void watchdog_enable_all_cpus(void) watchdog_enabled = 1; if (!watchdog_enabled) - printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); + pr_err("failed to be enabled on some cpus\n"); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f2c5638bb5ab..5abf42f63c08 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -476,13 +476,8 @@ static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, struct workqueue_struct *wq) { if (!(wq->flags & WQ_UNBOUND)) { - if (likely(cpu < nr_cpu_ids)) { -#ifdef CONFIG_SMP + if (likely(cpu < nr_cpu_ids)) return per_cpu_ptr(wq->cpu_wq.pcpu, cpu); -#else - return wq->cpu_wq.single; -#endif - } } else if (likely(cpu == WORK_CPU_UNBOUND)) return wq->cpu_wq.single; return NULL; @@ -2899,13 +2894,8 @@ static int alloc_cwqs(struct workqueue_struct *wq) const size_t size = sizeof(struct cpu_workqueue_struct); const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long)); -#ifdef CONFIG_SMP - bool percpu = !(wq->flags & WQ_UNBOUND); -#else - bool percpu = false; -#endif - if (percpu) + if (!(wq->flags & WQ_UNBOUND)) wq->cpu_wq.pcpu = __alloc_percpu(size, align); else { void *ptr; @@ -2929,13 +2919,7 @@ static int alloc_cwqs(struct workqueue_struct *wq) static void free_cwqs(struct workqueue_struct *wq) { -#ifdef CONFIG_SMP - bool percpu = !(wq->flags & WQ_UNBOUND); -#else - bool percpu = false; -#endif - - if (percpu) + if (!(wq->flags & WQ_UNBOUND)) free_percpu(wq->cpu_wq.pcpu); else if (wq->cpu_wq.single) { /* the pointer to free is stored right after the cwq */ |