diff options
Diffstat (limited to 'kernel')
48 files changed, 2462 insertions, 966 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index e4791b3ba55..bab1dffe37e 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -93,6 +93,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o +obj-$(CONFIG_SLOW_WORK) += slow-work.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8cbddff6c28..2bfc6478676 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -66,6 +66,7 @@ #include <linux/syscalls.h> #include <linux/inotify.h> #include <linux/capability.h> +#include <linux/fs_struct.h> #include "audit.h" diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c500ca7239b..382109b5bae 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -94,7 +94,6 @@ struct cgroupfs_root { char release_agent_path[PATH_MAX]; }; - /* * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the * subsystems that are otherwise unattached - it never has more than a @@ -102,6 +101,39 @@ struct cgroupfs_root { */ static struct cgroupfs_root rootnode; +/* + * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when + * cgroup_subsys->use_id != 0. + */ +#define CSS_ID_MAX (65535) +struct css_id { + /* + * The css to which this ID points. This pointer is set to valid value + * after cgroup is populated. If cgroup is removed, this will be NULL. + * This pointer is expected to be RCU-safe because destroy() + * is called after synchronize_rcu(). But for safe use, css_is_removed() + * css_tryget() should be used for avoiding race. + */ + struct cgroup_subsys_state *css; + /* + * ID of this css. + */ + unsigned short id; + /* + * Depth in hierarchy which this ID belongs to. + */ + unsigned short depth; + /* + * ID is freed by RCU. (and lookup routine is RCU safe.) + */ + struct rcu_head rcu_head; + /* + * Hierarchy of CSS ID belongs to. + */ + unsigned short stack[0]; /* Array of Length (depth+1) */ +}; + + /* The list of hierarchy roots */ static LIST_HEAD(roots); @@ -185,6 +217,8 @@ struct cg_cgroup_link { static struct css_set init_css_set; static struct cg_cgroup_link init_css_set_link; +static int cgroup_subsys_init_idr(struct cgroup_subsys *ss); + /* css_set_lock protects the list of css_set objects, and the * chain of tasks off each css_set. Nests outside task->alloc_lock * due to cgroup_iter_start() */ @@ -567,6 +601,9 @@ static struct backing_dev_info cgroup_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; +static int alloc_css_id(struct cgroup_subsys *ss, + struct cgroup *parent, struct cgroup *child); + static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) { struct inode *inode = new_inode(sb); @@ -585,13 +622,18 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) * Call subsys's pre_destroy handler. * This is called before css refcnt check. */ -static void cgroup_call_pre_destroy(struct cgroup *cgrp) +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) - ss->pre_destroy(ss, cgrp); - return; + if (ss->pre_destroy) { + ret = ss->pre_destroy(ss, cgrp); + if (ret) + break; + } + return ret; } static void free_cgroup_rcu(struct rcu_head *obj) @@ -685,6 +727,22 @@ static void cgroup_d_remove_dir(struct dentry *dentry) remove_dir(dentry); } +/* + * A queue for waiters to do rmdir() cgroup. A tasks will sleep when + * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some + * reference to css->refcnt. In general, this refcnt is expected to goes down + * to zero, soon. + * + * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex; + */ +DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq); + +static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp) +{ + if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))) + wake_up_all(&cgroup_rmdir_waitq); +} + static int rebind_subsystems(struct cgroupfs_root *root, unsigned long final_bits) { @@ -857,16 +915,16 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) } ret = rebind_subsystems(root, opts.subsys_bits); + if (ret) + goto out_unlock; /* (re)populate subsystem files */ - if (!ret) - cgroup_populate_dir(cgrp); + cgroup_populate_dir(cgrp); if (opts.release_agent) strcpy(root->release_agent_path, opts.release_agent); out_unlock: - if (opts.release_agent) - kfree(opts.release_agent); + kfree(opts.release_agent); mutex_unlock(&cgroup_mutex); mutex_unlock(&cgrp->dentry->d_inode->i_mutex); return ret; @@ -969,15 +1027,13 @@ static int cgroup_get_sb(struct file_system_type *fs_type, /* First find the desired set of subsystems */ ret = parse_cgroupfs_options(data, &opts); if (ret) { - if (opts.release_agent) - kfree(opts.release_agent); + kfree(opts.release_agent); return ret; } root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) { - if (opts.release_agent) - kfree(opts.release_agent); + kfree(opts.release_agent); return -ENOMEM; } @@ -1280,6 +1336,12 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) set_bit(CGRP_RELEASABLE, &oldcgrp->flags); synchronize_rcu(); put_css_set(cg); + + /* + * wake up rmdir() waiter. the rmdir should fail since the cgroup + * is no longer empty. + */ + cgroup_wakeup_rmdir_waiters(cgrp); return 0; } @@ -1625,7 +1687,7 @@ static struct inode_operations cgroup_dir_inode_operations = { .rename = cgroup_rename, }; -static int cgroup_create_file(struct dentry *dentry, int mode, +static int cgroup_create_file(struct dentry *dentry, mode_t mode, struct super_block *sb) { static const struct dentry_operations cgroup_dops = { @@ -1671,7 +1733,7 @@ static int cgroup_create_file(struct dentry *dentry, int mode, * @mode: mode to set on new directory. */ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, - int mode) + mode_t mode) { struct dentry *parent; int error = 0; @@ -1689,6 +1751,33 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, return error; } +/** + * cgroup_file_mode - deduce file mode of a control file + * @cft: the control file in question + * + * returns cft->mode if ->mode is not 0 + * returns S_IRUGO|S_IWUSR if it has both a read and a write handler + * returns S_IRUGO if it has only a read handler + * returns S_IWUSR if it has only a write hander + */ +static mode_t cgroup_file_mode(const struct cftype *cft) +{ + mode_t mode = 0; + + if (cft->mode) + return cft->mode; + + if (cft->read || cft->read_u64 || cft->read_s64 || + cft->read_map || cft->read_seq_string) + mode |= S_IRUGO; + + if (cft->write || cft->write_u64 || cft->write_s64 || + cft->write_string || cft->trigger) + mode |= S_IWUSR; + + return mode; +} + int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype *cft) @@ -1696,6 +1785,7 @@ int cgroup_add_file(struct cgroup *cgrp, struct dentry *dir = cgrp->dentry; struct dentry *dentry; int error; + mode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) { @@ -1706,7 +1796,8 @@ int cgroup_add_file(struct cgroup *cgrp, BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex)); dentry = lookup_one_len(name, dir, strlen(name)); if (!IS_ERR(dentry)) { - error = cgroup_create_file(dentry, 0644 | S_IFREG, + mode = cgroup_file_mode(cft); + error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); if (!error) dentry->d_fsdata = (void *)cft; @@ -2288,6 +2379,7 @@ static struct cftype files[] = { .write_u64 = cgroup_tasks_write, .release = cgroup_tasks_release, .private = FILE_TASKLIST, + .mode = S_IRUGO | S_IWUSR, }, { @@ -2327,6 +2419,17 @@ static int cgroup_populate_dir(struct cgroup *cgrp) if (ss->populate && (err = ss->populate(ss, cgrp)) < 0) return err; } + /* This cgroup is ready now */ + for_each_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + /* + * Update id->css pointer and make this css visible from + * CSS ID functions. This pointer will be dereferened + * from RCU-read-side without locks. + */ + if (css->id) + rcu_assign_pointer(css->id->css, css); + } return 0; } @@ -2338,6 +2441,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, css->cgroup = cgrp; atomic_set(&css->refcnt, 1); css->flags = 0; + css->id = NULL; if (cgrp == dummytop) set_bit(CSS_ROOT, &css->flags); BUG_ON(cgrp->subsys[ss->subsys_id]); @@ -2376,7 +2480,7 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) * Must be called with the mutex on the parent inode held */ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, - int mode) + mode_t mode) { struct cgroup *cgrp; struct cgroupfs_root *root = parent->root; @@ -2413,6 +2517,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_destroy; } init_cgroup_css(css, ss, cgrp); + if (ss->use_id) + if (alloc_css_id(ss, parent, cgrp)) + goto err_destroy; + /* At error, ->destroy() callback has to free assigned ID. */ } cgroup_lock_hierarchy(root); @@ -2555,9 +2663,11 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cgroup *cgrp = dentry->d_fsdata; struct dentry *d; struct cgroup *parent; + DEFINE_WAIT(wait); + int ret; /* the vfs holds both inode->i_mutex already */ - +again: mutex_lock(&cgroup_mutex); if (atomic_read(&cgrp->count) != 0) { mutex_unlock(&cgroup_mutex); @@ -2573,17 +2683,39 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) * Call pre_destroy handlers of subsys. Notify subsystems * that rmdir() request comes. */ - cgroup_call_pre_destroy(cgrp); + ret = cgroup_call_pre_destroy(cgrp); + if (ret) + return ret; mutex_lock(&cgroup_mutex); parent = cgrp->parent; - - if (atomic_read(&cgrp->count) - || !list_empty(&cgrp->children) - || !cgroup_clear_css_refs(cgrp)) { + if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } + /* + * css_put/get is provided for subsys to grab refcnt to css. In typical + * case, subsystem has no reference after pre_destroy(). But, under + * hierarchy management, some *temporal* refcnt can be hold. + * To avoid returning -EBUSY to a user, waitqueue is used. If subsys + * is really busy, it should return -EBUSY at pre_destroy(). wake_up + * is called when css_put() is called and refcnt goes down to 0. + */ + set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); + prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE); + + if (!cgroup_clear_css_refs(cgrp)) { + mutex_unlock(&cgroup_mutex); + schedule(); + finish_wait(&cgroup_rmdir_waitq, &wait); + clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); + if (signal_pending(current)) + return -EINTR; + goto again; + } + /* NO css_tryget() can success after here. */ + finish_wait(&cgroup_rmdir_waitq, &wait); + clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); spin_lock(&release_list_lock); set_bit(CGRP_REMOVED, &cgrp->flags); @@ -2708,6 +2840,8 @@ int __init cgroup_init(void) struct cgroup_subsys *ss = subsys[i]; if (!ss->early_init) cgroup_init_subsys(ss); + if (ss->use_id) + cgroup_subsys_init_idr(ss); } /* Add init_css_set to the hash table */ @@ -3084,18 +3218,19 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, } /** - * cgroup_is_descendant - see if @cgrp is a descendant of current task's cgrp + * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp * @cgrp: the cgroup in question + * @task: the task in question * - * See if @cgrp is a descendant of the current task's cgroup in - * the appropriate hierarchy. + * See if @cgrp is a descendant of @task's cgroup in the appropriate + * hierarchy. * * If we are sending in dummytop, then presumably we are creating * the top cgroup in the subsystem. * * Called only by the ns (nsproxy) cgroup. */ -int cgroup_is_descendant(const struct cgroup *cgrp) +int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task) { int ret; struct cgroup *target; @@ -3105,7 +3240,7 @@ int cgroup_is_descendant(const struct cgroup *cgrp) return 1; get_first_subsys(cgrp, NULL, &subsys_id); - target = task_cgroup(current, subsys_id); + target = task_cgroup(task, subsys_id); while (cgrp != target && cgrp!= cgrp->top_cgroup) cgrp = cgrp->parent; ret = (cgrp == target); @@ -3138,10 +3273,12 @@ void __css_put(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; rcu_read_lock(); - if ((atomic_dec_return(&css->refcnt) == 1) && - notify_on_release(cgrp)) { - set_bit(CGRP_RELEASABLE, &cgrp->flags); - check_for_release(cgrp); + if (atomic_dec_return(&css->refcnt) == 1) { + if (notify_on_release(cgrp)) { + set_bit(CGRP_RELEASABLE, &cgrp->flags); + check_for_release(cgrp); + } + cgroup_wakeup_rmdir_waiters(cgrp); } rcu_read_unlock(); } @@ -3241,3 +3378,232 @@ static int __init cgroup_disable(char *str) return 1; } __setup("cgroup_disable=", cgroup_disable); + +/* + * Functons for CSS ID. + */ + +/* + *To get ID other than 0, this should be called when !cgroup_is_removed(). + */ +unsigned short css_id(struct cgroup_subsys_state *css) +{ + struct css_id *cssid = rcu_dereference(css->id); + + if (cssid) + return cssid->id; + return 0; +} + +unsigned short css_depth(struct cgroup_subsys_state *css) +{ + struct css_id *cssid = rcu_dereference(css->id); + + if (cssid) + return cssid->depth; + return 0; +} + +bool css_is_ancestor(struct cgroup_subsys_state *child, + const struct cgroup_subsys_state *root) +{ + struct css_id *child_id = rcu_dereference(child->id); + struct css_id *root_id = rcu_dereference(root->id); + + if (!child_id || !root_id || (child_id->depth < root_id->depth)) + return false; + return child_id->stack[root_id->depth] == root_id->id; +} + +static void __free_css_id_cb(struct rcu_head *head) +{ + struct css_id *id; + + id = container_of(head, struct css_id, rcu_head); + kfree(id); +} + +void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) +{ + struct css_id *id = css->id; + /* When this is called before css_id initialization, id can be NULL */ + if (!id) + return; + + BUG_ON(!ss->use_id); + + rcu_assign_pointer(id->css, NULL); + rcu_assign_pointer(css->id, NULL); + spin_lock(&ss->id_lock); + idr_remove(&ss->idr, id->id); + spin_unlock(&ss->id_lock); + call_rcu(&id->rcu_head, __free_css_id_cb); +} + +/* + * This is called by init or create(). Then, calls to this function are + * always serialized (By cgroup_mutex() at create()). + */ + +static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) +{ + struct css_id *newid; + int myid, error, size; + + BUG_ON(!ss->use_id); + + size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1); + newid = kzalloc(size, GFP_KERNEL); + if (!newid) + return ERR_PTR(-ENOMEM); + /* get id */ + if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) { + error = -ENOMEM; + goto err_out; + } + 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); + spin_unlock(&ss->id_lock); + + /* Returns error when there are no free spaces for new ID.*/ + if (error) { + error = -ENOSPC; + goto err_out; + } + if (myid > CSS_ID_MAX) + goto remove_idr; + + newid->id = myid; + newid->depth = depth; + return newid; +remove_idr: + error = -ENOSPC; + spin_lock(&ss->id_lock); + idr_remove(&ss->idr, myid); + spin_unlock(&ss->id_lock); +err_out: + kfree(newid); + return ERR_PTR(error); + +} + +static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss) +{ + struct css_id *newid; + struct cgroup_subsys_state *rootcss; + + spin_lock_init(&ss->id_lock); + idr_init(&ss->idr); + + rootcss = init_css_set.subsys[ss->subsys_id]; + newid = get_new_cssid(ss, 0); + if (IS_ERR(newid)) + return PTR_ERR(newid); + + newid->stack[0] = newid->id; + newid->css = rootcss; + rootcss->id = newid; + return 0; +} + +static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent, + struct cgroup *child) +{ + int subsys_id, i, depth = 0; + struct cgroup_subsys_state *parent_css, *child_css; + struct css_id *child_id, *parent_id = NULL; + + subsys_id = ss->subsys_id; + parent_css = parent->subsys[subsys_id]; + child_css = child->subsys[subsys_id]; + depth = css_depth(parent_css) + 1; + parent_id = parent_css->id; + + child_id = get_new_cssid(ss, depth); + if (IS_ERR(child_id)) + return PTR_ERR(child_id); + + for (i = 0; i < depth; i++) + child_id->stack[i] = parent_id->stack[i]; + child_id->stack[depth] = child_id->id; + /* + * child_id->css pointer will be set after this cgroup is available + * see cgroup_populate_dir() + */ + rcu_assign_pointer(child_css->id, child_id); + + return 0; +} + +/** + * css_lookup - lookup css by id + * @ss: cgroup subsys to be looked into. + * @id: the id + * + * Returns pointer to cgroup_subsys_state if there is valid one with id. + * NULL if not. Should be called under rcu_read_lock() + */ +struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id) +{ + struct css_id *cssid = NULL; + + BUG_ON(!ss->use_id); + cssid = idr_find(&ss->idr, id); + + if (unlikely(!cssid)) + return NULL; + + return rcu_dereference(cssid->css); +} + +/** + * css_get_next - lookup next cgroup under specified hierarchy. + * @ss: pointer to subsystem + * @id: current position of iteration. + * @root: pointer to css. search tree under this. + * @foundid: position of found object. + * + * Search next css under the specified hierarchy of rootid. Calling under + * rcu_read_lock() is necessary. Returns NULL if it reaches the end. + */ +struct cgroup_subsys_state * +css_get_next(struct cgroup_subsys *ss, int id, + struct cgroup_subsys_state *root, int *foundid) +{ + struct cgroup_subsys_state *ret = NULL; + struct css_id *tmp; + int tmpid; + int rootid = css_id(root); + int depth = css_depth(root); + + if (!rootid) + return NULL; + + BUG_ON(!ss->use_id); + /* fill start point for scan */ + tmpid = id; + while (1) { + /* + * scan next entry from bitmap(tree), tmpid is updated after + * idr_get_next(). + */ + spin_lock(&ss->id_lock); + tmp = idr_get_next(&ss->idr, &tmpid); + spin_unlock(&ss->id_lock); + + if (!tmp) + break; + if (tmp->depth >= depth && tmp->stack[depth] == rootid) { + ret = rcu_dereference(tmp->css); + if (ret) { + *foundid = tmpid; + break; + } + } + /* continue to scan from next id */ + tmpid = tmpid + 1; + } + return ret; +} + diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c index daca6209202..0c92d797baa 100644 --- a/kernel/cgroup_debug.c +++ b/kernel/cgroup_debug.c @@ -40,9 +40,7 @@ static u64 taskcount_read(struct cgroup *cont, struct cftype *cft) { u64 count; - cgroup_lock(); count = cgroup_task_count(cont); - cgroup_unlock(); return count; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 79e40f00dcb..395b6974dc8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -281,7 +281,7 @@ int __ref cpu_down(unsigned int cpu) goto out; } - cpu_clear(cpu, cpu_active_map); + set_cpu_active(cpu, false); /* * Make sure the all cpus did the reschedule and are not @@ -296,7 +296,7 @@ int __ref cpu_down(unsigned int cpu) err = _cpu_down(cpu, 0); if (cpu_online(cpu)) - cpu_set(cpu, cpu_active_map); + set_cpu_active(cpu, true); out: cpu_maps_update_done(); @@ -333,7 +333,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); - cpu_set(cpu, cpu_active_map); + set_cpu_active(cpu, true); /* Now call notifier in preparation. */ raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f76db9dcaa0..026faccca86 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -128,10 +128,6 @@ static inline struct cpuset *task_cs(struct task_struct *task) return container_of(task_subsys_state(task, cpuset_subsys_id), struct cpuset, css); } -struct cpuset_hotplug_scanner { - struct cgroup_scanner scan; - struct cgroup *to; -}; /* bits in struct cpuset flags field */ typedef enum { @@ -521,6 +517,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) return 0; } +#ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping cpus_allowed masks? @@ -815,6 +812,18 @@ static void do_rebuild_sched_domains(struct work_struct *unused) put_online_cpus(); } +#else /* !CONFIG_SMP */ +static void do_rebuild_sched_domains(struct work_struct *unused) +{ +} + +static int generate_sched_domains(struct cpumask **domains, + struct sched_domain_attr **attributes) +{ + *domains = NULL; + return 1; +} +#endif /* CONFIG_SMP */ static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains); @@ -1026,101 +1035,70 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, mutex_unlock(&callback_mutex); } +/* + * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new + * nodes if memory_migrate flag is set. Called with cgroup_mutex held. + */ +static void cpuset_change_nodemask(struct task_struct *p, + struct cgroup_scanner *scan) +{ + struct mm_struct *mm; + struct cpuset *cs; + int migrate; + const nodemask_t *oldmem = scan->data; + + mm = get_task_mm(p); + if (!mm) + return; + + cs = cgroup_cs(scan->cg); + migrate = is_memory_migrate(cs); + + mpol_rebind_mm(mm, &cs->mems_allowed); + if (migrate) + cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed); + mmput(mm); +} + static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * @oldmem: old mems_allowed of cpuset cs + * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() * * Called with cgroup_mutex held - * Return 0 if successful, -errno if not. + * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 + * if @heap != NULL. */ -static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem) +static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, + struct ptr_heap *heap) { - struct task_struct *p; - struct mm_struct **mmarray; - int i, n, ntasks; - int migrate; - int fudge; - struct cgroup_iter it; - int retval; + struct cgroup_scanner scan; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ - fudge = 10; /* spare mmarray[] slots */ - fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */ - retval = -ENOMEM; - - /* - * Allocate mmarray[] to hold mm reference for each task - * in cpuset cs. Can't kmalloc GFP_KERNEL while holding - * tasklist_lock. We could use GFP_ATOMIC, but with a - * few more lines of code, we can retry until we get a big - * enough mmarray[] w/o using GFP_ATOMIC. - */ - while (1) { - ntasks = cgroup_task_count(cs->css.cgroup); /* guess */ - ntasks += fudge; - mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL); - if (!mmarray) - goto done; - read_lock(&tasklist_lock); /* block fork */ - if (cgroup_task_count(cs->css.cgroup) <= ntasks) - break; /* got enough */ - read_unlock(&tasklist_lock); /* try again */ - kfree(mmarray); - } - - n = 0; - - /* Load up mmarray[] with mm reference for each task in cpuset. */ - cgroup_iter_start(cs->css.cgroup, &it); - while ((p = cgroup_iter_next(cs->css.cgroup, &it))) { - struct mm_struct *mm; - - if (n >= ntasks) { - printk(KERN_WARNING - "Cpuset mempolicy rebind incomplete.\n"); - break; - } - mm = get_task_mm(p); - if (!mm) - continue; - mmarray[n++] = mm; - } - cgroup_iter_end(cs->css.cgroup, &it); - read_unlock(&tasklist_lock); + scan.cg = cs->css.cgroup; + scan.test_task = NULL; + scan.process_task = cpuset_change_nodemask; + scan.heap = heap; + scan.data = (nodemask_t *)oldmem; /* - * Now that we've dropped the tasklist spinlock, we can - * rebind the vma mempolicies of each mm in mmarray[] to their - * new cpuset, and release that mm. The mpol_rebind_mm() - * call takes mmap_sem, which we couldn't take while holding - * tasklist_lock. Forks can happen again now - the mpol_dup() - * cpuset_being_rebound check will catch such forks, and rebind - * their vma mempolicies too. Because we still hold the global - * cgroup_mutex, we know that no other rebind effort will - * be contending for the global variable cpuset_being_rebound. + * The mpol_rebind_mm() call takes mmap_sem, which we couldn't + * take while holding tasklist_lock. Forks can happen - the + * mpol_dup() cpuset_being_rebound check will catch such forks, + * and rebind their vma mempolicies too. Because we still hold + * the global cgroup_mutex, we know that no other rebind effort + * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ - migrate = is_memory_migrate(cs); - for (i = 0; i < n; i++) { - struct mm_struct *mm = mmarray[i]; - - mpol_rebind_mm(mm, &cs->mems_allowed); - if (migrate) - cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed); - mmput(mm); - } + cgroup_scan_tasks(&scan); /* We're done rebinding vmas to this cpuset's new mems_allowed. */ - kfree(mmarray); cpuset_being_rebound = NULL; - retval = 0; -done: - return retval; } /* @@ -1141,6 +1119,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, { nodemask_t oldmem; int retval; + struct ptr_heap heap; /* * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY]; @@ -1175,12 +1154,18 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; + retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); + if (retval < 0) + goto done; + mutex_lock(&callback_mutex); cs->mems_allowed = trialcs->mems_allowed; cs->mems_generation = cpuset_mems_generation++; mutex_unlock(&callback_mutex); - retval = update_tasks_nodemask(cs, &oldmem); + update_tasks_nodemask(cs, &oldmem, &heap); + + heap_free(&heap); done: return retval; } @@ -1192,8 +1177,10 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { +#ifdef CONFIG_SMP if (val < -1 || val >= SD_LV_MAX) return -EINVAL; +#endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; @@ -1355,19 +1342,22 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct task_struct *tsk) { struct cpuset *cs = cgroup_cs(cont); - int ret = 0; if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; - if (tsk->flags & PF_THREAD_BOUND) { - mutex_lock(&callback_mutex); - if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed)) - ret = -EINVAL; - mutex_unlock(&callback_mutex); - } + /* + * Kthreads bound to specific cpus cannot be moved to a new cpuset; we + * cannot change their cpu affinity and isolating such threads by their + * set of allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for success of + * set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may + * be changed. + */ + if (tsk->flags & PF_THREAD_BOUND) + return -EINVAL; - return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL); + return security_task_setscheduler(tsk, 0, NULL); } static void cpuset_attach(struct cgroup_subsys *ss, @@ -1706,6 +1696,7 @@ static struct cftype files[] = { .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE, + .mode = S_IRUGO, }, { @@ -1913,10 +1904,9 @@ int __init cpuset_init(void) static void cpuset_do_move_task(struct task_struct *tsk, struct cgroup_scanner *scan) { - struct cpuset_hotplug_scanner *chsp; + struct cgroup *new_cgroup = scan->data; - chsp = container_of(scan, struct cpuset_hotplug_scanner, scan); - cgroup_attach_task(chsp->to, tsk); + cgroup_attach_task(new_cgroup, tsk); } /** @@ -1932,15 +1922,15 @@ static void cpuset_do_move_task(struct task_struct *tsk, */ static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to) { - struct cpuset_hotplug_scanner scan; + struct cgroup_scanner scan; - scan.scan.cg = from->css.cgroup; - scan.scan.test_task = NULL; /* select all tasks in cgroup */ - scan.scan.process_task = cpuset_do_move_task; - scan.scan.heap = NULL; - scan.to = to->css.cgroup; + scan.cg = from->css.cgroup; + scan.test_task = NULL; /* select all tasks in cgroup */ + scan.process_task = cpuset_do_move_task; + scan.heap = NULL; + scan.data = to->css.cgroup; - if (cgroup_scan_tasks(&scan.scan)) + if (cgroup_scan_tasks(&scan)) printk(KERN_ERR "move_member_tasks_to_cpuset: " "cgroup_scan_tasks failed\n"); } @@ -2033,7 +2023,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) remove_tasks_in_empty_cpuset(cp); else { update_tasks_cpumask(cp, NULL); - update_tasks_nodemask(cp, &oldmems); + update_tasks_nodemask(cp, &oldmems, NULL); } } } @@ -2069,7 +2059,9 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, } cgroup_lock(); + mutex_lock(&callback_mutex); cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); + mutex_unlock(&callback_mutex); scan_for_empty_cpusets(&top_cpuset); ndoms = generate_sched_domains(&doms, &attr); cgroup_unlock(); @@ -2092,11 +2084,12 @@ static int cpuset_track_online_nodes(struct notifier_block *self, cgroup_lock(); switch (action) { case MEM_ONLINE: - top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; - break; case MEM_OFFLINE: + mutex_lock(&callback_mutex); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; - scan_for_empty_cpusets(&top_cpuset); + mutex_unlock(&callback_mutex); + if (action == MEM_OFFLINE) + scan_for_empty_cpusets(&top_cpuset); break; default: break; @@ -2206,26 +2199,24 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs) } /** - * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node? - * @z: is this zone on an allowed node? + * cpuset_node_allowed_softwall - Can we allocate on a memory node? + * @node: is this an allowed node? * @gfp_mask: memory allocation flags * - * If we're in interrupt, yes, we can always allocate. If - * __GFP_THISNODE is set, yes, we can always allocate. If zone - * z's node is in our tasks mems_allowed, yes. If it's not a - * __GFP_HARDWALL request and this zone's nodes is in the nearest - * hardwalled cpuset ancestor to this tasks cpuset, yes. - * If the task has been OOM killed and has access to memory reserves - * as specified by the TIF_MEMDIE flag, yes. + * If we're in interrupt, yes, we can always allocate. If __GFP_THISNODE is + * set, yes, we can always allocate. If node is in our task's mems_allowed, + * yes. If it's not a __GFP_HARDWALL request and this node is in the nearest + * hardwalled cpuset ancestor to this task's cpuset, yes. If the task has been + * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE + * flag, yes. * Otherwise, no. * - * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall() - * reduces to cpuset_zone_allowed_hardwall(). Otherwise, - * cpuset_zone_allowed_softwall() might sleep, and might allow a zone - * from an enclosing cpuset. + * If __GFP_HARDWALL is set, cpuset_node_allowed_softwall() reduces to + * cpuset_node_allowed_hardwall(). Otherwise, cpuset_node_allowed_softwall() + * might sleep, and might allow a node from an enclosing cpuset. * - * cpuset_zone_allowed_hardwall() only handles the simpler case of - * hardwall cpusets, and never sleeps. + * cpuset_node_allowed_hardwall() only handles the simpler case of hardwall + * cpusets, and never sleeps. * * The __GFP_THISNODE placement logic is really handled elsewhere, * by forcibly using a zonelist starting at a specified node, and by @@ -2264,20 +2255,17 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs) * GFP_USER - only nodes in current tasks mems allowed ok. * * Rule: - * Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you + * Don't call cpuset_node_allowed_softwall if you can't sleep, unless you * pass in the __GFP_HARDWALL flag set in gfp_flag, which disables * the code that might scan up ancestor cpusets and sleep. */ - -int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) +int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { - int node; /* node that zone z is on */ const struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; - node = zone_to_nid(z); might_sleep_if(!(gfp_mask & __GFP_HARDWALL)); if (node_isset(node, current->mems_allowed)) return 1; @@ -2306,15 +2294,15 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) } /* - * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node? - * @z: is this zone on an allowed node? + * cpuset_node_allowed_hardwall - Can we allocate on a memory node? + * @node: is this an allowed node? * @gfp_mask: memory allocation flags * - * If we're in interrupt, yes, we can always allocate. - * If __GFP_THISNODE is set, yes, we can always allocate. If zone - * z's node is in our tasks mems_allowed, yes. If the task has been - * OOM killed and has access to memory reserves as specified by the - * TIF_MEMDIE flag, yes. Otherwise, no. + * If we're in interrupt, yes, we can always allocate. If __GFP_THISNODE is + * set, yes, we can always allocate. If node is in our task's mems_allowed, + * yes. If the task has been OOM killed and has access to memory reserves as + * specified by the TIF_MEMDIE flag, yes. + * Otherwise, no. * * The __GFP_THISNODE placement logic is really handled elsewhere, * by forcibly using a zonelist starting at a specified node, and by @@ -2322,20 +2310,16 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) * any node on the zonelist except the first. By the time any such * calls get to this routine, we should just shut up and say 'yes'. * - * Unlike the cpuset_zone_allowed_softwall() variant, above, - * this variant requires that the zone be in the current tasks + * Unlike the cpuset_node_allowed_softwall() variant, above, + * this variant requires that the node be in the current task's * mems_allowed or that we're in interrupt. It does not scan up the * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset. * It never sleeps. */ - -int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) +int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { - int node; /* node that zone z is on */ - if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) return 1; - node = zone_to_nid(z); if (node_isset(node, current->mems_allowed)) return 1; /* diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index 667c841c295..c35452cadde 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -18,6 +18,7 @@ #include <linux/syscalls.h> #include <linux/sysctl.h> #include <linux/types.h> +#include <linux/fs_struct.h> static void default_handler(int, struct pt_regs *); @@ -145,28 +146,6 @@ __set_personality(u_long personality) return 0; } - if (atomic_read(¤t->fs->count) != 1) { - struct fs_struct *fsp, *ofsp; - - fsp = copy_fs_struct(current->fs); - if (fsp == NULL) { - module_put(ep->module); - return -ENOMEM; - } - - task_lock(current); - ofsp = current->fs; - current->fs = fsp; - task_unlock(current); - - put_fs_struct(ofsp); - } - - /* - * At that point we are guaranteed to be the sole owner of - * current->fs. - */ - current->personality = personality; oep = current_thread_info()->exec_domain; current_thread_info()->exec_domain = ep; diff --git a/kernel/exit.c b/kernel/exit.c index 167e1e3ad7c..6686ed1e4aa 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -46,6 +46,7 @@ #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> +#include <linux/fs_struct.h> #include <linux/init_task.h> #include <trace/sched.h> @@ -61,11 +62,6 @@ DEFINE_TRACE(sched_process_wait); static void exit_mm(struct task_struct * tsk); -static inline int task_detached(struct task_struct *p) -{ - return p->exit_signal == -1; -} - static void __unhash_process(struct task_struct *p) { nr_threads--; @@ -362,16 +358,12 @@ static void reparent_to_kthreadd(void) void __set_special_pids(struct pid *pid) { struct task_struct *curr = current->group_leader; - pid_t nr = pid_nr(pid); - if (task_session(curr) != pid) { + if (task_session(curr) != pid) change_pid(curr, PIDTYPE_SID, pid); - set_task_session(curr, nr); - } - if (task_pgrp(curr) != pid) { + + if (task_pgrp(curr) != pid) change_pid(curr, PIDTYPE_PGID, pid); - set_task_pgrp(curr, nr); - } } static void set_special_pids(struct pid *pid) @@ -429,7 +421,6 @@ EXPORT_SYMBOL(disallow_signal); void daemonize(const char *name, ...) { va_list args; - struct fs_struct *fs; sigset_t blocked; va_start(args, name); @@ -462,11 +453,7 @@ void daemonize(const char *name, ...) /* Become as one with the init task */ - exit_fs(current); /* current->fs->count--; */ - fs = init_task.fs; - current->fs = fs; - atomic_inc(&fs->count); - + daemonize_fs_struct(); exit_files(current); current->files = init_task.files; atomic_inc(¤t->files->count); @@ -565,30 +552,6 @@ void exit_files(struct task_struct *tsk) } } -void put_fs_struct(struct fs_struct *fs) -{ - /* No need to hold fs->lock if we are killing it */ - if (atomic_dec_and_test(&fs->count)) { - path_put(&fs->root); - path_put(&fs->pwd); - kmem_cache_free(fs_cachep, fs); - } -} - -void exit_fs(struct task_struct *tsk) -{ - struct fs_struct * fs = tsk->fs; - - if (fs) { - task_lock(tsk); - tsk->fs = NULL; - task_unlock(tsk); - put_fs_struct(fs); - } -} - -EXPORT_SYMBOL_GPL(exit_fs); - #ifdef CONFIG_MM_OWNER /* * Task p is exiting and it owned mm, lets find a new owner for it @@ -732,119 +695,6 @@ static void exit_mm(struct task_struct * tsk) } /* - * Return nonzero if @parent's children should reap themselves. - * - * Called with write_lock_irq(&tasklist_lock) held. - */ -static int ignoring_children(struct task_struct *parent) -{ - int ret; - struct sighand_struct *psig = parent->sighand; - unsigned long flags; - spin_lock_irqsave(&psig->siglock, flags); - ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || - (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT)); - spin_unlock_irqrestore(&psig->siglock, flags); - return ret; -} - -/* - * Detach all tasks we were using ptrace on. - * Any that need to be release_task'd are put on the @dead list. - * - * Called with write_lock(&tasklist_lock) held. - */ -static void ptrace_exit(struct task_struct *parent, struct list_head *dead) -{ - struct task_struct *p, *n; - int ign = -1; - - list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) { - __ptrace_unlink(p); - - if (p->exit_state != EXIT_ZOMBIE) - continue; - - /* - * If it's a zombie, our attachedness prevented normal - * parent notification or self-reaping. Do notification - * now if it would have happened earlier. If it should - * reap itself, add it to the @dead list. We can't call - * release_task() here because we already hold tasklist_lock. - * - * If it's our own child, there is no notification to do. - * But if our normal children self-reap, then this child - * was prevented by ptrace and we must reap it now. - */ - if (!task_detached(p) && thread_group_empty(p)) { - if (!same_thread_group(p->real_parent, parent)) - do_notify_parent(p, p->exit_signal); - else { - if (ign < 0) - ign = ignoring_children(parent); - if (ign) - p->exit_signal = -1; - } - } - - if (task_detached(p)) { - /* - * Mark it as in the process of being reaped. - */ - p->exit_state = EXIT_DEAD; - list_add(&p->ptrace_entry, dead); - } - } -} - -/* - * Finish up exit-time ptrace cleanup. - * - * Called without locks. - */ -static void ptrace_exit_finish(struct task_struct *parent, - struct list_head *dead) -{ - struct task_struct *p, *n; - - BUG_ON(!list_empty(&parent->ptraced)); - - list_for_each_entry_safe(p, n, dead, ptrace_entry) { - list_del_init(&p->ptrace_entry); - release_task(p); - } -} - -static void reparent_thread(struct task_struct *p, struct task_struct *father) -{ - if (p->pdeath_signal) - /* We already hold the tasklist_lock here. */ - group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p); - - list_move_tail(&p->sibling, &p->real_parent->children); - - /* If this is a threaded reparent there is no need to - * notify anyone anything has happened. - */ - if (same_thread_group(p->real_parent, father)) - return; - - /* We don't want people slaying init. */ - if (!task_detached(p)) - p->exit_signal = SIGCHLD; - - /* If we'd notified the old parent about this child's death, - * also notify the new parent. - */ - if (!ptrace_reparented(p) && - p->exit_state == EXIT_ZOMBIE && - !task_detached(p) && thread_group_empty(p)) - do_notify_parent(p, p->exit_signal); - - kill_orphaned_pgrp(p, father); -} - -/* * 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 @@ -883,17 +733,51 @@ static struct task_struct *find_new_reaper(struct task_struct *father) return pid_ns->child_reaper; } +/* +* Any that need to be release_task'd are put on the @dead list. + */ +static void reparent_thread(struct task_struct *father, struct task_struct *p, + struct list_head *dead) +{ + if (p->pdeath_signal) + group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p); + + list_move_tail(&p->sibling, &p->real_parent->children); + + if (task_detached(p)) + return; + /* + * If this is a threaded reparent there is no need to + * notify anyone anything has happened. + */ + if (same_thread_group(p->real_parent, father)) + return; + + /* We don't want people slaying init. */ + p->exit_signal = SIGCHLD; + + /* If it has exited notify the new parent about this child's death. */ + if (!p->ptrace && + p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { + do_notify_parent(p, p->exit_signal); + if (task_detached(p)) { + p->exit_state = EXIT_DEAD; + list_move_tail(&p->sibling, dead); + } + } + + kill_orphaned_pgrp(p, father); +} + static void forget_original_parent(struct task_struct *father) { struct task_struct *p, *n, *reaper; - LIST_HEAD(ptrace_dead); + LIST_HEAD(dead_children); + + exit_ptrace(father); write_lock_irq(&tasklist_lock); reaper = find_new_reaper(father); - /* - * First clean up ptrace if we were using it. - */ - ptrace_exit(father, &ptrace_dead); list_for_each_entry_safe(p, n, &father->children, sibling) { p->real_parent = reaper; @@ -901,13 +785,16 @@ static void forget_original_parent(struct task_struct *father) BUG_ON(p->ptrace); p->parent = p->real_parent; } - reparent_thread(p, father); + reparent_thread(father, p, &dead_children); } - write_unlock_irq(&tasklist_lock); + BUG_ON(!list_empty(&father->children)); - ptrace_exit_finish(father, &ptrace_dead); + list_for_each_entry_safe(p, n, &dead_children, sibling) { + list_del_init(&p->sibling); + release_task(p); + } } /* @@ -1417,6 +1304,18 @@ static int wait_task_zombie(struct task_struct *p, int options, return retval; } +static int *task_stopped_code(struct task_struct *p, bool ptrace) +{ + if (ptrace) { + if (task_is_stopped_or_traced(p)) + return &p->exit_code; + } else { + if (p->signal->flags & SIGNAL_STOP_STOPPED) + return &p->signal->group_exit_code; + } + return NULL; +} + /* * Handle sys_wait4 work for one task in state TASK_STOPPED. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold @@ -1427,7 +1326,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, int options, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { - int retval, exit_code, why; + int retval, exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; @@ -1437,22 +1336,16 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, exit_code = 0; spin_lock_irq(&p->sighand->siglock); - if (unlikely(!task_is_stopped_or_traced(p))) - goto unlock_sig; - - if (!ptrace && p->signal->group_stop_count > 0) - /* - * A group stop is in progress and this is the group leader. - * We won't report until all threads have stopped. - */ + p_code = task_stopped_code(p, ptrace); + if (unlikely(!p_code)) goto unlock_sig; - exit_code = p->exit_code; + exit_code = *p_code; if (!exit_code) goto unlock_sig; if (!unlikely(options & WNOWAIT)) - p->exit_code = 0; + *p_code = 0; /* don't need the RCU readlock here as we're holding a spinlock */ uid = __task_cred(p)->uid; @@ -1608,7 +1501,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace, */ *notask_error = 0; - if (task_is_stopped_or_traced(p)) + if (task_stopped_code(p, ptrace)) return wait_task_stopped(ptrace, p, options, infop, stat_addr, ru); @@ -1812,7 +1705,7 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; - pid = get_pid(task_pgrp(current)); + pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); diff --git a/kernel/fork.c b/kernel/fork.c index 6715ebc3761..660c2b8765b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -60,6 +60,7 @@ #include <linux/tty.h> #include <linux/proc_fs.h> #include <linux/blkdev.h> +#include <linux/fs_struct.h> #include <trace/sched.h> #include <linux/magic.h> @@ -284,7 +285,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->free_area_cache = oldmm->mmap_base; mm->cached_hole_size = ~0UL; mm->map_count = 0; - cpus_clear(mm->cpu_vm_mask); + cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; rb_link = &mm->mm_rb.rb_node; rb_parent = NULL; @@ -681,38 +682,21 @@ fail_nomem: return retval; } -static struct fs_struct *__copy_fs_struct(struct fs_struct *old) -{ - struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); - /* We don't need to lock fs - think why ;-) */ - if (fs) { - atomic_set(&fs->count, 1); - rwlock_init(&fs->lock); - fs->umask = old->umask; - read_lock(&old->lock); - fs->root = old->root; - path_get(&old->root); - fs->pwd = old->pwd; - path_get(&old->pwd); - read_unlock(&old->lock); - } - return fs; -} - -struct fs_struct *copy_fs_struct(struct fs_struct *old) -{ - return __copy_fs_struct(old); -} - -EXPORT_SYMBOL_GPL(copy_fs_struct); - static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { + struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { - atomic_inc(¤t->fs->count); + /* tsk->fs is already what we want */ + write_lock(&fs->lock); + if (fs->in_exec) { + write_unlock(&fs->lock); + return -EAGAIN; + } + fs->users++; + write_unlock(&fs->lock); return 0; } - tsk->fs = __copy_fs_struct(current->fs); + tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; @@ -841,6 +825,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) atomic_set(&sig->live, 1); init_waitqueue_head(&sig->wait_chldexit); sig->flags = 0; + if (clone_flags & CLONE_NEWPID) + sig->flags |= SIGNAL_UNKILLABLE; sig->group_exit_code = 0; sig->group_exit_task = NULL; sig->group_stop_count = 0; @@ -1125,7 +1111,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_mm; if ((retval = copy_io(clone_flags, p))) goto bad_fork_cleanup_namespaces; - retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); + retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) goto bad_fork_cleanup_io; @@ -1263,8 +1249,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->signal->leader_pid = pid; tty_kref_put(p->signal->tty); p->signal->tty = tty_kref_get(current->signal->tty); - set_task_pgrp(p, task_pgrp_nr(current)); - set_task_session(p, task_session_nr(current)); attach_pid(p, PIDTYPE_PGID, task_pgrp(current)); attach_pid(p, PIDTYPE_SID, task_session(current)); list_add_tail_rcu(&p->tasks, &init_task.tasks); @@ -1488,6 +1472,7 @@ void __init proc_caches_init(void) mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); mmap_init(); } @@ -1543,12 +1528,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; - if ((unshare_flags & CLONE_FS) && - (fs && atomic_read(&fs->count) > 1)) { - *new_fsp = __copy_fs_struct(current->fs); - if (!*new_fsp) - return -ENOMEM; - } + if (!(unshare_flags & CLONE_FS) || !fs) + return 0; + + /* don't need lock here; in the worst case we'll do useless copy */ + if (fs->users == 1) + return 0; + + *new_fsp = copy_fs_struct(fs); + if (!*new_fsp) + return -ENOMEM; return 0; } @@ -1664,8 +1653,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) if (new_fs) { fs = current->fs; + write_lock(&fs->lock); current->fs = new_fs; - new_fs = fs; + if (--fs->users) + new_fs = NULL; + else + new_fs = fs; + write_unlock(&fs->lock); } if (new_mm) { @@ -1704,7 +1698,7 @@ bad_unshare_cleanup_sigh: bad_unshare_cleanup_fs: if (new_fs) - put_fs_struct(new_fs); + free_fs_struct(new_fs); bad_unshare_cleanup_thread: bad_unshare_out: diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 4dd5b1edac9..3394f8f5296 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o +obj-$(CONFIG_PM_SLEEP) += pm.o diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ee1aa9f8e8b..01ce20eab38 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -12,6 +12,8 @@ extern void compat_irq_chip_set_default_handler(struct irq_desc *desc); extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, unsigned long flags); +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 struct lock_class_key irq_desc_lock_class; extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 6458e99984c..1516ab77355 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -162,6 +162,20 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) } #endif +void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend) +{ + if (suspend) { + if (!desc->action || (desc->action->flags & IRQF_TIMER)) + return; + desc->status |= IRQ_SUSPENDED; + } + + if (!desc->depth++) { + desc->status |= IRQ_DISABLED; + desc->chip->disable(irq); + } +} + /** * disable_irq_nosync - disable an irq without waiting * @irq: Interrupt to disable @@ -182,10 +196,7 @@ void disable_irq_nosync(unsigned int irq) return; spin_lock_irqsave(&desc->lock, flags); - if (!desc->depth++) { - desc->status |= IRQ_DISABLED; - desc->chip->disable(irq); - } + __disable_irq(desc, irq, false); spin_unlock_irqrestore(&desc->lock, flags); } EXPORT_SYMBOL(disable_irq_nosync); @@ -215,15 +226,21 @@ void disable_irq(unsigned int irq) } EXPORT_SYMBOL(disable_irq); -static void __enable_irq(struct irq_desc *desc, unsigned int irq) +void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) { + if (resume) + desc->status &= ~IRQ_SUSPENDED; + switch (desc->depth) { case 0: + err_out: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); break; case 1: { unsigned int status = desc->status & ~IRQ_DISABLED; + if (desc->status & IRQ_SUSPENDED) + goto err_out; /* Prevent probing on this irq: */ desc->status = status | IRQ_NOPROBE; check_irq_resend(desc, irq); @@ -253,7 +270,7 @@ void enable_irq(unsigned int irq) return; spin_lock_irqsave(&desc->lock, flags); - __enable_irq(desc, irq); + __enable_irq(desc, irq, false); spin_unlock_irqrestore(&desc->lock, flags); } EXPORT_SYMBOL(enable_irq); @@ -511,7 +528,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) { desc->status &= ~IRQ_SPURIOUS_DISABLED; - __enable_irq(desc, irq); + __enable_irq(desc, irq, false); } spin_unlock_irqrestore(&desc->lock, flags); diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c new file mode 100644 index 00000000000..638d8bedec1 --- /dev/null +++ b/kernel/irq/pm.c @@ -0,0 +1,79 @@ +/* + * linux/kernel/irq/pm.c + * + * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. + * + * This file contains power management functions related to interrupts. + */ + +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/interrupt.h> + +#include "internals.h" + +/** + * suspend_device_irqs - disable all currently enabled interrupt lines + * + * During system-wide suspend or hibernation device interrupts need to be + * disabled at the chip level and this function is provided for this purpose. + * It disables all interrupt lines that are enabled at the moment and sets the + * IRQ_SUSPENDED flag for them. + */ +void suspend_device_irqs(void) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) { + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + __disable_irq(desc, irq, true); + spin_unlock_irqrestore(&desc->lock, flags); + } + + for_each_irq_desc(irq, desc) + if (desc->status & IRQ_SUSPENDED) + synchronize_irq(irq); +} +EXPORT_SYMBOL_GPL(suspend_device_irqs); + +/** + * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() + * + * Enable all interrupt lines previously disabled by suspend_device_irqs() that + * have the IRQ_SUSPENDED flag set. + */ +void resume_device_irqs(void) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) { + unsigned long flags; + + if (!(desc->status & IRQ_SUSPENDED)) + continue; + + spin_lock_irqsave(&desc->lock, flags); + __enable_irq(desc, irq, true); + spin_unlock_irqrestore(&desc->lock, flags); + } +} +EXPORT_SYMBOL_GPL(resume_device_irqs); + +/** + * check_wakeup_irqs - check if any wake-up interrupts are pending + */ +int check_wakeup_irqs(void) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) + if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING)) + return -EBUSY; + + return 0; +} diff --git a/kernel/kexec.c b/kernel/kexec.c index c7fd6692939..5a758c6e495 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -42,7 +42,7 @@ note_buf_t* crash_notes; /* vmcoreinfo stuff */ -unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; +static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; size_t vmcoreinfo_size; size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); @@ -1409,6 +1409,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(list_head, prev); VMCOREINFO_OFFSET(vm_struct, addr); VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + log_buf_kexec_setup(); VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); VMCOREINFO_NUMBER(NR_FREE_PAGES); VMCOREINFO_NUMBER(PG_lru); @@ -1450,11 +1451,7 @@ int kernel_kexec(void) error = device_suspend(PMSG_FREEZE); if (error) goto Resume_console; - error = disable_nonboot_cpus(); - if (error) - goto Resume_devices; device_pm_lock(); - local_irq_disable(); /* At this point, device_suspend() has been called, * but *not* device_power_down(). We *must* * device_power_down() now. Otherwise, drivers for @@ -1464,12 +1461,15 @@ int kernel_kexec(void) */ error = device_power_down(PMSG_FREEZE); if (error) - goto Enable_irqs; - + goto Resume_devices; + error = disable_nonboot_cpus(); + if (error) + goto Enable_cpus; + local_irq_disable(); /* Suspend system devices */ error = sysdev_suspend(PMSG_FREEZE); if (error) - goto Power_up_devices; + goto Enable_irqs; } else #endif { @@ -1483,13 +1483,13 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { sysdev_resume(); - Power_up_devices: - device_power_up(PMSG_RESTORE); Enable_irqs: local_irq_enable(); - device_pm_unlock(); + Enable_cpus: enable_nonboot_cpus(); + device_power_up(PMSG_RESTORE); Resume_devices: + device_pm_unlock(); device_resume(PMSG_RESTORE); Resume_console: resume_console(); diff --git a/kernel/kmod.c b/kernel/kmod.c index a27a5f64443..f0c8f545180 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -167,7 +167,7 @@ static int ____call_usermodehelper(void *data) } /* We can run anywhere, unlike our parent keventd(). */ - set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR); + set_cpus_allowed_ptr(current, cpu_all_mask); /* * Our parent is keventd, which runs with elevated scheduling priority. diff --git a/kernel/kthread.c b/kernel/kthread.c index 4fbc456f393..84bbadd4d02 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -110,7 +110,7 @@ static void create_kthread(struct kthread_create_info *create) */ sched_setscheduler(create->result, SCHED_NORMAL, ¶m); set_user_nice(create->result, KTHREAD_NICE_LEVEL); - set_cpus_allowed_ptr(create->result, CPU_MASK_ALL_PTR); + set_cpus_allowed_ptr(create->result, cpu_all_mask); } complete(&create->done); } @@ -240,7 +240,7 @@ int kthreadd(void *unused) set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); set_user_nice(tsk, KTHREAD_NICE_LEVEL); - set_cpus_allowed_ptr(tsk, CPU_MASK_ALL_PTR); + set_cpus_allowed_ptr(tsk, cpu_all_mask); current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 06b0c3568f0..3673a3f44d9 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -41,6 +41,7 @@ #include <linux/utsname.h> #include <linux/hash.h> #include <linux/ftrace.h> +#include <linux/stringify.h> #include <asm/sections.h> @@ -310,12 +311,14 @@ EXPORT_SYMBOL(lockdep_on); #if VERBOSE # define HARDIRQ_VERBOSE 1 # define SOFTIRQ_VERBOSE 1 +# define RECLAIM_VERBOSE 1 #else # define HARDIRQ_VERBOSE 0 # define SOFTIRQ_VERBOSE 0 +# define RECLAIM_VERBOSE 0 #endif -#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE +#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE || RECLAIM_VERBOSE /* * Quick filtering for interesting events: */ @@ -443,17 +446,18 @@ atomic_t nr_find_usage_backwards_recursions; * Locking printouts: */ +#define __USAGE(__STATE) \ + [LOCK_USED_IN_##__STATE] = "IN-"__stringify(__STATE)"-W", \ + [LOCK_ENABLED_##__STATE] = __stringify(__STATE)"-ON-W", \ + [LOCK_USED_IN_##__STATE##_READ] = "IN-"__stringify(__STATE)"-R",\ + [LOCK_ENABLED_##__STATE##_READ] = __stringify(__STATE)"-ON-R", + static const char *usage_str[] = { - [LOCK_USED] = "initial-use ", - [LOCK_USED_IN_HARDIRQ] = "in-hardirq-W", - [LOCK_USED_IN_SOFTIRQ] = "in-softirq-W", - [LOCK_ENABLED_SOFTIRQS] = "softirq-on-W", - [LOCK_ENABLED_HARDIRQS] = "hardirq-on-W", - [LOCK_USED_IN_HARDIRQ_READ] = "in-hardirq-R", - [LOCK_USED_IN_SOFTIRQ_READ] = "in-softirq-R", - [LOCK_ENABLED_SOFTIRQS_READ] = "softirq-on-R", - [LOCK_ENABLED_HARDIRQS_READ] = "hardirq-on-R", +#define LOCKDEP_STATE(__STATE) __USAGE(__STATE) +#include "lockdep_states.h" +#undef LOCKDEP_STATE + [LOCK_USED] = "INITIAL USE", }; const char * __get_key_name(struct lockdep_subclass_key *key, char *str) @@ -461,46 +465,45 @@ const char * __get_key_name(struct lockdep_subclass_key *key, char *str) return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str); } -void -get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4) +static inline unsigned long lock_flag(enum lock_usage_bit bit) { - *c1 = '.', *c2 = '.', *c3 = '.', *c4 = '.'; - - if (class->usage_mask & LOCKF_USED_IN_HARDIRQ) - *c1 = '+'; - else - if (class->usage_mask & LOCKF_ENABLED_HARDIRQS) - *c1 = '-'; + return 1UL << bit; +} - if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ) - *c2 = '+'; - else - if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS) - *c2 = '-'; +static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit) +{ + char c = '.'; - if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) - *c3 = '-'; - if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ) { - *c3 = '+'; - if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) - *c3 = '?'; + if (class->usage_mask & lock_flag(bit + 2)) + c = '+'; + if (class->usage_mask & lock_flag(bit)) { + c = '-'; + if (class->usage_mask & lock_flag(bit + 2)) + c = '?'; } - if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ) - *c4 = '-'; - if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ) { - *c4 = '+'; - if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ) - *c4 = '?'; - } + return c; +} + +void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS]) +{ + int i = 0; + +#define LOCKDEP_STATE(__STATE) \ + usage[i++] = get_usage_char(class, LOCK_USED_IN_##__STATE); \ + usage[i++] = get_usage_char(class, LOCK_USED_IN_##__STATE##_READ); +#include "lockdep_states.h" +#undef LOCKDEP_STATE + + usage[i] = '\0'; } static void print_lock_name(struct lock_class *class) { - char str[KSYM_NAME_LEN], c1, c2, c3, c4; + char str[KSYM_NAME_LEN], usage[LOCK_USAGE_CHARS]; const char *name; - get_usage_chars(class, &c1, &c2, &c3, &c4); + get_usage_chars(class, usage); name = class->name; if (!name) { @@ -513,7 +516,7 @@ static void print_lock_name(struct lock_class *class) if (class->subclass) printk("/%d", class->subclass); } - printk("){%c%c%c%c}", c1, c2, c3, c4); + printk("){%s}", usage); } static void print_lockdep_cache(struct lockdep_map *lock) @@ -1263,9 +1266,49 @@ check_usage(struct task_struct *curr, struct held_lock *prev, bit_backwards, bit_forwards, irqclass); } -static int -check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next) +static const char *state_names[] = { +#define LOCKDEP_STATE(__STATE) \ + __stringify(__STATE), +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +static const char *state_rnames[] = { +#define LOCKDEP_STATE(__STATE) \ + __stringify(__STATE)"-READ", +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +static inline const char *state_name(enum lock_usage_bit bit) +{ + return (bit & 1) ? state_rnames[bit >> 2] : state_names[bit >> 2]; +} + +static int exclusive_bit(int new_bit) +{ + /* + * USED_IN + * USED_IN_READ + * ENABLED + * ENABLED_READ + * + * bit 0 - write/read + * bit 1 - used_in/enabled + * bit 2+ state + */ + + int state = new_bit & ~3; + int dir = new_bit & 2; + + /* + * keep state, bit flip the direction and strip read. + */ + return state | (dir ^ 2); +} + +static int check_irq_usage(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next, enum lock_usage_bit bit) { /* * Prove that the new dependency does not connect a hardirq-safe @@ -1273,38 +1316,34 @@ check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, * the backwards-subgraph starting at <prev>, and the * forwards-subgraph starting at <next>: */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ, - LOCK_ENABLED_HARDIRQS, "hard")) + if (!check_usage(curr, prev, next, bit, + exclusive_bit(bit), state_name(bit))) return 0; + bit++; /* _READ */ + /* * Prove that the new dependency does not connect a hardirq-safe-read * lock with a hardirq-unsafe lock - to achieve this we search * the backwards-subgraph starting at <prev>, and the * forwards-subgraph starting at <next>: */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_HARDIRQ_READ, - LOCK_ENABLED_HARDIRQS, "hard-read")) + if (!check_usage(curr, prev, next, bit, + exclusive_bit(bit), state_name(bit))) return 0; - /* - * Prove that the new dependency does not connect a softirq-safe - * lock with a softirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at <prev>, and the - * forwards-subgraph starting at <next>: - */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ, - LOCK_ENABLED_SOFTIRQS, "soft")) - return 0; - /* - * Prove that the new dependency does not connect a softirq-safe-read - * lock with a softirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at <prev>, and the - * forwards-subgraph starting at <next>: - */ - if (!check_usage(curr, prev, next, LOCK_USED_IN_SOFTIRQ_READ, - LOCK_ENABLED_SOFTIRQS, "soft")) + return 1; +} + +static int +check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, + struct held_lock *next) +{ +#define LOCKDEP_STATE(__STATE) \ + if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE)) \ return 0; +#include "lockdep_states.h" +#undef LOCKDEP_STATE return 1; } @@ -1933,7 +1972,7 @@ void print_irqtrace_events(struct task_struct *curr) print_ip_sym(curr->softirq_disable_ip); } -static int hardirq_verbose(struct lock_class *class) +static int HARDIRQ_verbose(struct lock_class *class) { #if HARDIRQ_VERBOSE return class_filter(class); @@ -1941,7 +1980,7 @@ static int hardirq_verbose(struct lock_class *class) return 0; } -static int softirq_verbose(struct lock_class *class) +static int SOFTIRQ_verbose(struct lock_class *class) { #if SOFTIRQ_VERBOSE return class_filter(class); @@ -1949,185 +1988,94 @@ static int softirq_verbose(struct lock_class *class) return 0; } +static int RECLAIM_FS_verbose(struct lock_class *class) +{ +#if RECLAIM_VERBOSE + return class_filter(class); +#endif + return 0; +} + #define STRICT_READ_CHECKS 1 -static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit new_bit) +static int (*state_verbose_f[])(struct lock_class *class) = { +#define LOCKDEP_STATE(__STATE) \ + __STATE##_verbose, +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + +static inline int state_verbose(enum lock_usage_bit bit, + struct lock_class *class) { - int ret = 1; + return state_verbose_f[bit >> 2](class); +} - switch(new_bit) { - case LOCK_USED_IN_HARDIRQ: - if (!valid_state(curr, this, new_bit, LOCK_ENABLED_HARDIRQS)) - return 0; - if (!valid_state(curr, this, new_bit, - LOCK_ENABLED_HARDIRQS_READ)) - return 0; - /* - * just marked it hardirq-safe, check that this lock - * took no hardirq-unsafe lock in the past: - */ - if (!check_usage_forwards(curr, this, - LOCK_ENABLED_HARDIRQS, "hard")) - return 0; -#if STRICT_READ_CHECKS - /* - * just marked it hardirq-safe, check that this lock - * took no hardirq-unsafe-read lock in the past: - */ - if (!check_usage_forwards(curr, this, - LOCK_ENABLED_HARDIRQS_READ, "hard-read")) - return 0; -#endif - if (hardirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_USED_IN_SOFTIRQ: - if (!valid_state(curr, this, new_bit, LOCK_ENABLED_SOFTIRQS)) - return 0; - if (!valid_state(curr, this, new_bit, - LOCK_ENABLED_SOFTIRQS_READ)) - return 0; - /* - * just marked it softirq-safe, check that this lock - * took no softirq-unsafe lock in the past: - */ - if (!check_usage_forwards(curr, this, - LOCK_ENABLED_SOFTIRQS, "soft")) - return 0; -#if STRICT_READ_CHECKS - /* - * just marked it softirq-safe, check that this lock - * took no softirq-unsafe-read lock in the past: - */ - if (!check_usage_forwards(curr, this, - LOCK_ENABLED_SOFTIRQS_READ, "soft-read")) - return 0; -#endif - if (softirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_USED_IN_HARDIRQ_READ: - if (!valid_state(curr, this, new_bit, LOCK_ENABLED_HARDIRQS)) - return 0; - /* - * just marked it hardirq-read-safe, check that this lock - * took no hardirq-unsafe lock in the past: - */ - if (!check_usage_forwards(curr, this, - LOCK_ENABLED_HARDIRQS, "hard")) - return 0; - if (hardirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_USED_IN_SOFTIRQ_READ: - if (!valid_state(curr, this, new_bit, LOCK_ENABLED_SOFTIRQS)) - return 0; - /* - * just marked it softirq-read-safe, check that this lock - * took no softirq-unsafe lock in the past: - */ - if (!check_usage_forwards(curr, this, - LOCK_ENABLED_SOFTIRQS, "soft")) - return 0; - if (softirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_ENABLED_HARDIRQS: - if (!valid_state(curr, this, new_bit, LOCK_USED_IN_HARDIRQ)) - return 0; - if (!valid_state(curr, this, new_bit, - LOCK_USED_IN_HARDIRQ_READ)) - return 0; - /* - * just marked it hardirq-unsafe, check that no hardirq-safe - * lock in the system ever took it in the past: - */ - if (!check_usage_backwards(curr, this, - LOCK_USED_IN_HARDIRQ, "hard")) - return 0; -#if STRICT_READ_CHECKS - /* - * just marked it hardirq-unsafe, check that no - * hardirq-safe-read lock in the system ever took - * it in the past: - */ - if (!check_usage_backwards(curr, this, - LOCK_USED_IN_HARDIRQ_READ, "hard-read")) - return 0; -#endif - if (hardirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_ENABLED_SOFTIRQS: - if (!valid_state(curr, this, new_bit, LOCK_USED_IN_SOFTIRQ)) - return 0; - if (!valid_state(curr, this, new_bit, - LOCK_USED_IN_SOFTIRQ_READ)) - return 0; - /* - * just marked it softirq-unsafe, check that no softirq-safe - * lock in the system ever took it in the past: - */ - if (!check_usage_backwards(curr, this, - LOCK_USED_IN_SOFTIRQ, "soft")) - return 0; -#if STRICT_READ_CHECKS - /* - * just marked it softirq-unsafe, check that no - * softirq-safe-read lock in the system ever took - * it in the past: - */ - if (!check_usage_backwards(curr, this, - LOCK_USED_IN_SOFTIRQ_READ, "soft-read")) - return 0; -#endif - if (softirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_ENABLED_HARDIRQS_READ: - if (!valid_state(curr, this, new_bit, LOCK_USED_IN_HARDIRQ)) - return 0; -#if STRICT_READ_CHECKS - /* - * just marked it hardirq-read-unsafe, check that no - * hardirq-safe lock in the system ever took it in the past: - */ - if (!check_usage_backwards(curr, this, - LOCK_USED_IN_HARDIRQ, "hard")) - return 0; -#endif - if (hardirq_verbose(hlock_class(this))) - ret = 2; - break; - case LOCK_ENABLED_SOFTIRQS_READ: - if (!valid_state(curr, this, new_bit, LOCK_USED_IN_SOFTIRQ)) +typedef int (*check_usage_f)(struct task_struct *, struct held_lock *, + enum lock_usage_bit bit, const char *name); + +static int +mark_lock_irq(struct task_struct *curr, struct held_lock *this, int new_bit) +{ + int excl_bit = exclusive_bit(new_bit); + int read = new_bit & 1; + int dir = new_bit & 2; + + /* + * mark USED_IN has to look forwards -- to ensure no dependency + * has ENABLED state, which would allow recursion deadlocks. + * + * mark ENABLED has to look backwards -- to ensure no dependee + * has USED_IN state, which, again, would allow recursion deadlocks. + */ + check_usage_f usage = dir ? + check_usage_backwards : check_usage_forwards; + + /* + * Validate that this particular lock does not have conflicting + * usage states. + */ + if (!valid_state(curr, this, new_bit, excl_bit)) + return 0; + + /* + * Validate that the lock dependencies don't have conflicting usage + * states. + */ + if ((!read || !dir || STRICT_READ_CHECKS) && + !usage(curr, this, excl_bit, state_name(new_bit))) + return 0; + + /* + * Check for read in write conflicts + */ + if (!read) { + if (!valid_state(curr, this, new_bit, excl_bit + 1)) return 0; -#if STRICT_READ_CHECKS - /* - * just marked it softirq-read-unsafe, check that no - * softirq-safe lock in the system ever took it in the past: - */ - if (!check_usage_backwards(curr, this, - LOCK_USED_IN_SOFTIRQ, "soft")) + + if (STRICT_READ_CHECKS && + !usage(curr, this, excl_bit + 1, + state_name(new_bit + 1))) return 0; -#endif - if (softirq_verbose(hlock_class(this))) - ret = 2; - break; - default: - WARN_ON(1); - break; } - return ret; + if (state_verbose(new_bit, hlock_class(this))) + return 2; + + return 1; } +enum mark_type { +#define LOCKDEP_STATE(__STATE) __STATE, +#include "lockdep_states.h" +#undef LOCKDEP_STATE +}; + /* * Mark all held locks with a usage bit: */ static int -mark_held_locks(struct task_struct *curr, int hardirq) +mark_held_locks(struct task_struct *curr, enum mark_type mark) { enum lock_usage_bit usage_bit; struct held_lock *hlock; @@ -2136,17 +2084,12 @@ mark_held_locks(struct task_struct *curr, int hardirq) for (i = 0; i < curr->lockdep_depth; i++) { hlock = curr->held_locks + i; - if (hardirq) { - if (hlock->read) - usage_bit = LOCK_ENABLED_HARDIRQS_READ; - else - usage_bit = LOCK_ENABLED_HARDIRQS; - } else { - if (hlock->read) - usage_bit = LOCK_ENABLED_SOFTIRQS_READ; - else - usage_bit = LOCK_ENABLED_SOFTIRQS; - } + usage_bit = 2 + (mark << 2); /* ENABLED */ + if (hlock->read) + usage_bit += 1; /* READ */ + + BUG_ON(usage_bit >= LOCK_USAGE_STATES); + if (!mark_lock(curr, hlock, usage_bit)) return 0; } @@ -2200,7 +2143,7 @@ void trace_hardirqs_on_caller(unsigned long ip) * We are going to turn hardirqs on, so set the * usage bit for all held locks: */ - if (!mark_held_locks(curr, 1)) + if (!mark_held_locks(curr, HARDIRQ)) return; /* * If we have softirqs enabled, then set the usage @@ -2208,7 +2151,7 @@ void trace_hardirqs_on_caller(unsigned long ip) * this bit from being set before) */ if (curr->softirqs_enabled) - if (!mark_held_locks(curr, 0)) + if (!mark_held_locks(curr, SOFTIRQ)) return; curr->hardirq_enable_ip = ip; @@ -2288,7 +2231,7 @@ void trace_softirqs_on(unsigned long ip) * enabled too: */ if (curr->hardirqs_enabled) - mark_held_locks(curr, 0); + mark_held_locks(curr, SOFTIRQ); } /* @@ -2317,6 +2260,48 @@ void trace_softirqs_off(unsigned long ip) debug_atomic_inc(&redundant_softirqs_off); } +static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) +{ + struct task_struct *curr = current; + + if (unlikely(!debug_locks)) + return; + + /* no reclaim without waiting on it */ + if (!(gfp_mask & __GFP_WAIT)) + return; + + /* this guy won't enter reclaim */ + if ((curr->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC)) + return; + + /* We're only interested __GFP_FS allocations for now */ + if (!(gfp_mask & __GFP_FS)) + return; + + if (DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))) + return; + + mark_held_locks(curr, RECLAIM_FS); +} + +static void check_flags(unsigned long flags); + +void lockdep_trace_alloc(gfp_t gfp_mask) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + check_flags(flags); + current->lockdep_recursion = 1; + __lockdep_trace_alloc(gfp_mask, flags); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} + static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) { /* @@ -2345,19 +2330,35 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) if (!hlock->hardirqs_off) { if (hlock->read) { if (!mark_lock(curr, hlock, - LOCK_ENABLED_HARDIRQS_READ)) + LOCK_ENABLED_HARDIRQ_READ)) return 0; if (curr->softirqs_enabled) if (!mark_lock(curr, hlock, - LOCK_ENABLED_SOFTIRQS_READ)) + LOCK_ENABLED_SOFTIRQ_READ)) return 0; } else { if (!mark_lock(curr, hlock, - LOCK_ENABLED_HARDIRQS)) + LOCK_ENABLED_HARDIRQ)) return 0; if (curr->softirqs_enabled) if (!mark_lock(curr, hlock, - LOCK_ENABLED_SOFTIRQS)) + LOCK_ENABLED_SOFTIRQ)) + return 0; + } + } + + /* + * We reuse the irq context infrastructure more broadly as a general + * context checking code. This tests GFP_FS recursion (a lock taken + * during reclaim for a GFP_FS allocation is held over a GFP_FS + * allocation). + */ + if (!hlock->trylock && (curr->lockdep_reclaim_gfp & __GFP_FS)) { + if (hlock->read) { + if (!mark_lock(curr, hlock, LOCK_USED_IN_RECLAIM_FS_READ)) + return 0; + } else { + if (!mark_lock(curr, hlock, LOCK_USED_IN_RECLAIM_FS)) return 0; } } @@ -2412,6 +2413,10 @@ static inline int separate_irq_context(struct task_struct *curr, return 0; } +void lockdep_trace_alloc(gfp_t gfp_mask) +{ +} + #endif /* @@ -2445,14 +2450,13 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, return 0; switch (new_bit) { - case LOCK_USED_IN_HARDIRQ: - case LOCK_USED_IN_SOFTIRQ: - case LOCK_USED_IN_HARDIRQ_READ: - case LOCK_USED_IN_SOFTIRQ_READ: - case LOCK_ENABLED_HARDIRQS: - case LOCK_ENABLED_SOFTIRQS: - case LOCK_ENABLED_HARDIRQS_READ: - case LOCK_ENABLED_SOFTIRQS_READ: +#define LOCKDEP_STATE(__STATE) \ + case LOCK_USED_IN_##__STATE: \ + case LOCK_USED_IN_##__STATE##_READ: \ + case LOCK_ENABLED_##__STATE: \ + case LOCK_ENABLED_##__STATE##_READ: +#include "lockdep_states.h" +#undef LOCKDEP_STATE ret = mark_lock_irq(curr, this, new_bit); if (!ret) return 0; @@ -2966,6 +2970,16 @@ void lock_release(struct lockdep_map *lock, int nested, } EXPORT_SYMBOL_GPL(lock_release); +void lockdep_set_current_reclaim_state(gfp_t gfp_mask) +{ + current->lockdep_reclaim_gfp = gfp_mask; +} + +void lockdep_clear_current_reclaim_state(void) +{ + current->lockdep_reclaim_gfp = 0; +} + #ifdef CONFIG_LOCK_STAT static int print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h index 56b196932c0..a2cc7e9a6e8 100644 --- a/kernel/lockdep_internals.h +++ b/kernel/lockdep_internals.h @@ -7,6 +7,45 @@ */ /* + * Lock-class usage-state bits: + */ +enum lock_usage_bit { +#define LOCKDEP_STATE(__STATE) \ + LOCK_USED_IN_##__STATE, \ + LOCK_USED_IN_##__STATE##_READ, \ + LOCK_ENABLED_##__STATE, \ + LOCK_ENABLED_##__STATE##_READ, +#include "lockdep_states.h" +#undef LOCKDEP_STATE + LOCK_USED, + LOCK_USAGE_STATES +}; + +/* + * Usage-state bitmasks: + */ +#define __LOCKF(__STATE) LOCKF_##__STATE = (1 << LOCK_##__STATE), + +enum { +#define LOCKDEP_STATE(__STATE) \ + __LOCKF(USED_IN_##__STATE) \ + __LOCKF(USED_IN_##__STATE##_READ) \ + __LOCKF(ENABLED_##__STATE) \ + __LOCKF(ENABLED_##__STATE##_READ) +#include "lockdep_states.h" +#undef LOCKDEP_STATE + __LOCKF(USED) +}; + +#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ) +#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ) + +#define LOCKF_ENABLED_IRQ_READ \ + (LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ) +#define LOCKF_USED_IN_IRQ_READ \ + (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) + +/* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. * @@ -31,8 +70,10 @@ extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; -extern void -get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4); +#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2) + +extern void get_usage_chars(struct lock_class *class, + char usage[LOCK_USAGE_CHARS]); extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str); diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index 13716b81389..d7135aa2d2c 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -84,7 +84,7 @@ static int l_show(struct seq_file *m, void *v) { struct lock_class *class = v; struct lock_list *entry; - char c1, c2, c3, c4; + char usage[LOCK_USAGE_CHARS]; if (v == SEQ_START_TOKEN) { seq_printf(m, "all lock classes:\n"); @@ -100,8 +100,8 @@ static int l_show(struct seq_file *m, void *v) seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class)); #endif - get_usage_chars(class, &c1, &c2, &c3, &c4); - seq_printf(m, " %c%c%c%c", c1, c2, c3, c4); + get_usage_chars(class, usage); + seq_printf(m, " %s", usage); seq_printf(m, ": "); print_name(m, class); @@ -300,27 +300,27 @@ static int lockdep_stats_show(struct seq_file *m, void *v) nr_uncategorized++; if (class->usage_mask & LOCKF_USED_IN_IRQ) nr_irq_safe++; - if (class->usage_mask & LOCKF_ENABLED_IRQS) + if (class->usage_mask & LOCKF_ENABLED_IRQ) nr_irq_unsafe++; if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ) nr_softirq_safe++; - if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS) + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ) nr_softirq_unsafe++; if (class->usage_mask & LOCKF_USED_IN_HARDIRQ) nr_hardirq_safe++; - if (class->usage_mask & LOCKF_ENABLED_HARDIRQS) + if (class->usage_mask & LOCKF_ENABLED_HARDIRQ) nr_hardirq_unsafe++; if (class->usage_mask & LOCKF_USED_IN_IRQ_READ) nr_irq_read_safe++; - if (class->usage_mask & LOCKF_ENABLED_IRQS_READ) + if (class->usage_mask & LOCKF_ENABLED_IRQ_READ) nr_irq_read_unsafe++; if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ) nr_softirq_read_safe++; - if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ) + if (class->usage_mask & LOCKF_ENABLED_SOFTIRQ_READ) nr_softirq_read_unsafe++; if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ) nr_hardirq_read_safe++; - if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) + if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ) nr_hardirq_read_unsafe++; #ifdef CONFIG_PROVE_LOCKING @@ -601,6 +601,10 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) static void seq_header(struct seq_file *m) { seq_printf(m, "lock_stat version 0.3\n"); + + if (unlikely(!debug_locks)) + seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n"); + seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1)); seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s " "%14s %14s\n", diff --git a/kernel/lockdep_states.h b/kernel/lockdep_states.h new file mode 100644 index 00000000000..995b0cc2b84 --- /dev/null +++ b/kernel/lockdep_states.h @@ -0,0 +1,9 @@ +/* + * Lockdep states, + * + * please update XXX_LOCK_USAGE_STATES in include/linux/lockdep.h whenever + * you add one, or come up with a nice dynamic solution. + */ +LOCKDEP_STATE(HARDIRQ) +LOCKDEP_STATE(SOFTIRQ) +LOCKDEP_STATE(RECLAIM_FS) diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index 1d94160eb53..50d022e5a56 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -26,11 +26,6 @@ /* * Must be called with lock->wait_lock held. */ -void debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner) -{ - lock->owner = new_owner; -} - void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter) { memset(waiter, MUTEX_DEBUG_INIT, sizeof(*waiter)); @@ -59,7 +54,6 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, /* Mark the current thread as blocked on the lock: */ ti->task->blocked_on = waiter; - waiter->lock = lock; } void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, @@ -82,7 +76,7 @@ void debug_mutex_unlock(struct mutex *lock) DEBUG_LOCKS_WARN_ON(lock->magic != lock); DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + mutex_clear_owner(lock); } void debug_mutex_init(struct mutex *lock, const char *name, @@ -95,7 +89,6 @@ void debug_mutex_init(struct mutex *lock, const char *name, debug_check_no_locks_freed((void *)lock, sizeof(*lock)); lockdep_init_map(&lock->dep_map, name, key, 0); #endif - lock->owner = NULL; lock->magic = lock; } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index babfbdfc534..6b2d735846a 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -13,14 +13,6 @@ /* * This must be called with lock->wait_lock held. */ -extern void -debug_mutex_set_owner(struct mutex *lock, struct thread_info *new_owner); - -static inline void debug_mutex_clear_owner(struct mutex *lock) -{ - lock->owner = NULL; -} - extern void debug_mutex_lock_common(struct mutex *lock, struct mutex_waiter *waiter); extern void debug_mutex_wake_waiter(struct mutex *lock, @@ -35,6 +27,16 @@ extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current_thread_info(); +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} + #define spin_lock_mutex(lock, flags) \ do { \ struct mutex *l = container_of(lock, struct mutex, wait_lock); \ diff --git a/kernel/mutex.c b/kernel/mutex.c index 4f45d4b658e..5d79781394a 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -10,6 +10,11 @@ * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and * David Howells for suggestions and improvements. * + * - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline + * from the -rt tree, where it was originally implemented for rtmutexes + * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale + * and Sven Dietrich. + * * Also see Documentation/mutex-design.txt. */ #include <linux/mutex.h> @@ -46,6 +51,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) atomic_set(&lock->count, 1); spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); + mutex_clear_owner(lock); debug_mutex_init(lock, name, key); } @@ -91,6 +97,7 @@ void inline __sched mutex_lock(struct mutex *lock) * 'unlocked' into 'locked' state. */ __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); + mutex_set_owner(lock); } EXPORT_SYMBOL(mutex_lock); @@ -115,6 +122,14 @@ void __sched mutex_unlock(struct mutex *lock) * The unlocking fastpath is the 0->1 transition from 'locked' * into 'unlocked' state: */ +#ifndef CONFIG_DEBUG_MUTEXES + /* + * When debugging is enabled we must not clear the owner before time, + * the slow path will always be taken, and that clears the owner field + * after verifying that it was indeed current. + */ + mutex_clear_owner(lock); +#endif __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); } @@ -129,21 +144,75 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, { struct task_struct *task = current; struct mutex_waiter waiter; - unsigned int old_val; unsigned long flags; + preempt_disable(); + mutex_acquire(&lock->dep_map, subclass, 0, ip); +#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) + /* + * Optimistic spinning. + * + * We try to spin for acquisition when we find that there are no + * pending waiters and the lock owner is currently running on a + * (different) CPU. + * + * The rationale is that if the lock owner is running, it is likely to + * release the lock soon. + * + * Since this needs the lock owner, and this mutex implementation + * doesn't track the owner atomically in the lock field, we need to + * track it non-atomically. + * + * We can't do this for DEBUG_MUTEXES because that relies on wait_lock + * to serialize everything. + */ + + for (;;) { + struct thread_info *owner; + + /* + * If there's an owner, wait for it to either + * release the lock or go to sleep. + */ + owner = ACCESS_ONCE(lock->owner); + if (owner && !mutex_spin_on_owner(lock, owner)) + break; + + if (atomic_cmpxchg(&lock->count, 1, 0) == 1) { + lock_acquired(&lock->dep_map, ip); + mutex_set_owner(lock); + preempt_enable(); + return 0; + } + + /* + * When there's no owner, we might have preempted between the + * owner acquiring the lock and setting the owner field. If + * we're an RT task that will live-lock because we won't let + * the owner complete. + */ + if (!owner && (need_resched() || rt_task(task))) + break; + + /* + * The cpu_relax() call is a compiler barrier which forces + * everything in this loop to be re-loaded. We don't need + * memory barriers as we'll eventually observe the right + * values at the cost of a few extra spins. + */ + cpu_relax(); + } +#endif spin_lock_mutex(&lock->wait_lock, flags); debug_mutex_lock_common(lock, &waiter); - mutex_acquire(&lock->dep_map, subclass, 0, ip); debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); /* add waiting tasks to the end of the waitqueue (FIFO): */ list_add_tail(&waiter.list, &lock->wait_list); waiter.task = task; - old_val = atomic_xchg(&lock->count, -1); - if (old_val == 1) + if (atomic_xchg(&lock->count, -1) == 1) goto done; lock_contended(&lock->dep_map, ip); @@ -158,8 +227,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * that when we release the lock, we properly wake up the * other waiters: */ - old_val = atomic_xchg(&lock->count, -1); - if (old_val == 1) + if (atomic_xchg(&lock->count, -1) == 1) break; /* @@ -173,21 +241,22 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); + preempt_enable(); return -EINTR; } __set_task_state(task, state); /* didnt get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - schedule(); + __schedule(); spin_lock_mutex(&lock->wait_lock, flags); } done: lock_acquired(&lock->dep_map, ip); /* got the lock - rejoice! */ - mutex_remove_waiter(lock, &waiter, task_thread_info(task)); - debug_mutex_set_owner(lock, task_thread_info(task)); + mutex_remove_waiter(lock, &waiter, current_thread_info()); + mutex_set_owner(lock); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) @@ -196,6 +265,7 @@ done: spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); + preempt_enable(); return 0; } @@ -222,7 +292,8 @@ int __sched mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, _RET_IP_); + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, + subclass, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); @@ -260,8 +331,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) wake_up_process(waiter->task); } - debug_mutex_clear_owner(lock); - spin_unlock_mutex(&lock->wait_lock, flags); } @@ -298,18 +367,30 @@ __mutex_lock_interruptible_slowpath(atomic_t *lock_count); */ int __sched mutex_lock_interruptible(struct mutex *lock) { + int ret; + might_sleep(); - return __mutex_fastpath_lock_retval + ret = __mutex_fastpath_lock_retval (&lock->count, __mutex_lock_interruptible_slowpath); + if (!ret) + mutex_set_owner(lock); + + return ret; } EXPORT_SYMBOL(mutex_lock_interruptible); int __sched mutex_lock_killable(struct mutex *lock) { + int ret; + might_sleep(); - return __mutex_fastpath_lock_retval + ret = __mutex_fastpath_lock_retval (&lock->count, __mutex_lock_killable_slowpath); + if (!ret) + mutex_set_owner(lock); + + return ret; } EXPORT_SYMBOL(mutex_lock_killable); @@ -352,9 +433,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) prev = atomic_xchg(&lock->count, -1); if (likely(prev == 1)) { - debug_mutex_set_owner(lock, current_thread_info()); + mutex_set_owner(lock); mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); } + /* Set it back to 0 if there are no waiters: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); @@ -380,8 +462,13 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) */ int __sched mutex_trylock(struct mutex *lock) { - return __mutex_fastpath_trylock(&lock->count, - __mutex_trylock_slowpath); + int ret; + + ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); + if (ret) + mutex_set_owner(lock); + + return ret; } EXPORT_SYMBOL(mutex_trylock); diff --git a/kernel/mutex.h b/kernel/mutex.h index a075dafbb29..67578ca48f9 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -16,8 +16,26 @@ #define mutex_remove_waiter(lock, waiter, ti) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#define debug_mutex_set_owner(lock, new_owner) do { } while (0) -#define debug_mutex_clear_owner(lock) do { } while (0) +#ifdef CONFIG_SMP +static inline void mutex_set_owner(struct mutex *lock) +{ + lock->owner = current_thread_info(); +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ + lock->owner = NULL; +} +#else +static inline void mutex_set_owner(struct mutex *lock) +{ +} + +static inline void mutex_clear_owner(struct mutex *lock) +{ +} +#endif + #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 78bc3fdac0d..5aa854f9e5a 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -34,7 +34,7 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid) /* * Rules: - * 1. you can only enter a cgroup which is a child of your current + * 1. you can only enter a cgroup which is a descendant of your current * cgroup * 2. you can only place another process into a cgroup if * a. you have CAP_SYS_ADMIN @@ -45,21 +45,15 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid) static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, struct task_struct *task) { - struct cgroup *orig; - if (current != task) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!cgroup_is_descendant(new_cgroup)) + if (!cgroup_is_descendant(new_cgroup, current)) return -EPERM; } - if (atomic_read(&new_cgroup->count) != 0) - return -EPERM; - - orig = task_cgroup(task, ns_subsys_id); - if (orig && orig != new_cgroup->parent) + if (!cgroup_is_descendant(new_cgroup, task)) return -EPERM; return 0; @@ -77,7 +71,7 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (!cgroup_is_descendant(cgroup)) + if (!cgroup_is_descendant(cgroup, current)) return ERR_PTR(-EPERM); ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); diff --git a/kernel/pid.c b/kernel/pid.c index 1b3586fe753..b2e5f78fd28 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -403,6 +403,8 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); + if (type != PIDTYPE_PID) + task = task->group_leader; pid = get_pid(task->pids[type].pid); rcu_read_unlock(); return pid; @@ -450,11 +452,24 @@ pid_t pid_vnr(struct pid *pid) } EXPORT_SYMBOL_GPL(pid_vnr); -pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, + struct pid_namespace *ns) { - return pid_nr_ns(task_pid(tsk), ns); + pid_t nr = 0; + + rcu_read_lock(); + if (!ns) + ns = current->nsproxy->pid_ns; + if (likely(pid_alive(task))) { + if (type != PIDTYPE_PID) + task = task->group_leader; + nr = pid_nr_ns(task->pids[type].pid, ns); + } + rcu_read_unlock(); + + return nr; } -EXPORT_SYMBOL(task_pid_nr_ns); +EXPORT_SYMBOL(__task_pid_nr_ns); pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -462,18 +477,6 @@ pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) } EXPORT_SYMBOL(task_tgid_nr_ns); -pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_pgrp(tsk), ns); -} -EXPORT_SYMBOL(task_pgrp_nr_ns); - -pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_session(tsk), ns); -} -EXPORT_SYMBOL(task_session_nr_ns); - struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index fab8ea86fac..2d1001b4858 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -152,6 +152,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) { int nr; int rc; + struct task_struct *task; /* * The last thread in the cgroup-init thread group is terminating. @@ -169,7 +170,19 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) read_lock(&tasklist_lock); nr = next_pidmap(pid_ns, 1); while (nr > 0) { - kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr); + rcu_read_lock(); + + /* + * Use force_sig() since it clears SIGNAL_UNKILLABLE ensuring + * any nested-container's init processes don't ignore the + * signal + */ + task = pid_task(find_vpid(nr), PIDTYPE_PID); + if (task) + force_sig(SIGKILL, task); + + rcu_read_unlock(); + nr = next_pidmap(pid_ns, nr); } read_unlock(&tasklist_lock); diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 9d1c1a0de35..5f21ab2bbcd 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -22,6 +22,7 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> +#include <asm/suspend.h> #include "power.h" @@ -214,7 +215,7 @@ static int create_image(int platform_mode) return error; device_pm_lock(); - local_irq_disable(); + /* At this point, device_suspend() has been called, but *not* * device_power_down(). We *must* call device_power_down() now. * Otherwise, drivers for some devices (e.g. interrupt controllers) @@ -225,13 +226,25 @@ static int create_image(int platform_mode) if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting hibernation\n"); - goto Enable_irqs; + goto Unlock; } + + error = platform_pre_snapshot(platform_mode); + if (error || hibernation_test(TEST_PLATFORM)) + goto Platform_finish; + + error = disable_nonboot_cpus(); + if (error || hibernation_test(TEST_CPUS) + || hibernation_testmode(HIBERNATION_TEST)) + goto Enable_cpus; + + local_irq_disable(); + sysdev_suspend(PMSG_FREEZE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting hibernation\n"); - goto Power_up_devices; + goto Enable_irqs; } if (hibernation_test(TEST_CORE)) @@ -247,17 +260,28 @@ static int create_image(int platform_mode) restore_processor_state(); if (!in_suspend) platform_leave(platform_mode); + Power_up: sysdev_resume(); /* NOTE: device_power_up() is just a resume() for devices * that suspended with irqs off ... no overall powerup. */ - Power_up_devices: - device_power_up(in_suspend ? - (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); + Enable_irqs: local_irq_enable(); + + Enable_cpus: + enable_nonboot_cpus(); + + Platform_finish: + platform_finish(platform_mode); + + device_power_up(in_suspend ? + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); + + Unlock: device_pm_unlock(); + return error; } @@ -291,25 +315,9 @@ int hibernation_snapshot(int platform_mode) if (hibernation_test(TEST_DEVICES)) goto Recover_platform; - error = platform_pre_snapshot(platform_mode); - if (error || hibernation_test(TEST_PLATFORM)) - goto Finish; - - error = disable_nonboot_cpus(); - if (!error) { - if (hibernation_test(TEST_CPUS)) - goto Enable_cpus; - - if (hibernation_testmode(HIBERNATION_TEST)) - goto Enable_cpus; + error = create_image(platform_mode); + /* Control returns here after successful restore */ - error = create_image(platform_mode); - /* Control returns here after successful restore */ - } - Enable_cpus: - enable_nonboot_cpus(); - Finish: - platform_finish(platform_mode); Resume_devices: device_resume(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); @@ -331,19 +339,33 @@ int hibernation_snapshot(int platform_mode) * kernel. */ -static int resume_target_kernel(void) +static int resume_target_kernel(bool platform_mode) { int error; device_pm_lock(); - local_irq_disable(); + error = device_power_down(PMSG_QUIESCE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting resume\n"); - goto Enable_irqs; + goto Unlock; } - sysdev_suspend(PMSG_QUIESCE); + + error = platform_pre_restore(platform_mode); + if (error) + goto Cleanup; + + error = disable_nonboot_cpus(); + if (error) + goto Enable_cpus; + + local_irq_disable(); + + error = sysdev_suspend(PMSG_QUIESCE); + if (error) + goto Enable_irqs; + /* We'll ignore saved state, but this gets preempt count (etc) right */ save_processor_state(); error = restore_highmem(); @@ -366,11 +388,23 @@ static int resume_target_kernel(void) swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); + sysdev_resume(); - device_power_up(PMSG_RECOVER); + Enable_irqs: local_irq_enable(); + + Enable_cpus: + enable_nonboot_cpus(); + + Cleanup: + platform_restore_cleanup(platform_mode); + + device_power_up(PMSG_RECOVER); + + Unlock: device_pm_unlock(); + return error; } @@ -390,19 +424,10 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); error = device_suspend(PMSG_QUIESCE); - if (error) - goto Finish; - - error = platform_pre_restore(platform_mode); if (!error) { - error = disable_nonboot_cpus(); - if (!error) - error = resume_target_kernel(); - enable_nonboot_cpus(); + error = resume_target_kernel(platform_mode); + device_resume(PMSG_RECOVER); } - platform_restore_cleanup(platform_mode); - device_resume(PMSG_RECOVER); - Finish: resume_console(); pm_restore_console(); return error; @@ -438,38 +463,46 @@ int hibernation_platform_enter(void) goto Resume_devices; } + device_pm_lock(); + + error = device_power_down(PMSG_HIBERNATE); + if (error) + goto Unlock; + error = hibernation_ops->prepare(); if (error) - goto Resume_devices; + goto Platofrm_finish; error = disable_nonboot_cpus(); if (error) - goto Finish; + goto Platofrm_finish; - device_pm_lock(); local_irq_disable(); - error = device_power_down(PMSG_HIBERNATE); - if (!error) { - sysdev_suspend(PMSG_HIBERNATE); - hibernation_ops->enter(); - /* We should never get here */ - while (1); - } - local_irq_enable(); - device_pm_unlock(); + sysdev_suspend(PMSG_HIBERNATE); + hibernation_ops->enter(); + /* We should never get here */ + while (1); /* * We don't need to reenable the nonboot CPUs or resume consoles, since * the system is going to be halted anyway. */ - Finish: + Platofrm_finish: hibernation_ops->finish(); + + device_power_up(PMSG_RESTORE); + + Unlock: + device_pm_unlock(); + Resume_devices: entering_platform_hibernation = false; device_resume(PMSG_RESTORE); resume_console(); + Close: hibernation_ops->end(); + return error; } diff --git a/kernel/power/main.c b/kernel/power/main.c index c9632f841f6..f172f41858b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -287,17 +287,32 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void) */ static int suspend_enter(suspend_state_t state) { - int error = 0; + int error; device_pm_lock(); - arch_suspend_disable_irqs(); - BUG_ON(!irqs_disabled()); - if ((error = device_power_down(PMSG_SUSPEND))) { + error = device_power_down(PMSG_SUSPEND); + if (error) { printk(KERN_ERR "PM: Some devices failed to power down\n"); goto Done; } + if (suspend_ops->prepare) { + error = suspend_ops->prepare(); + if (error) + goto Power_up_devices; + } + + if (suspend_test(TEST_PLATFORM)) + goto Platfrom_finish; + + error = disable_nonboot_cpus(); + if (error || suspend_test(TEST_CPUS)) + goto Enable_cpus; + + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + error = sysdev_suspend(PMSG_SUSPEND); if (!error) { if (!suspend_test(TEST_CORE)) @@ -305,11 +320,22 @@ static int suspend_enter(suspend_state_t state) sysdev_resume(); } - device_power_up(PMSG_RESUME); - Done: arch_suspend_enable_irqs(); BUG_ON(irqs_disabled()); + + Enable_cpus: + enable_nonboot_cpus(); + + Platfrom_finish: + if (suspend_ops->finish) + suspend_ops->finish(); + + Power_up_devices: + device_power_up(PMSG_RESUME); + + Done: device_pm_unlock(); + return error; } @@ -341,23 +367,8 @@ int suspend_devices_and_enter(suspend_state_t state) if (suspend_test(TEST_DEVICES)) goto Recover_platform; - if (suspend_ops->prepare) { - error = suspend_ops->prepare(); - if (error) - goto Resume_devices; - } - - if (suspend_test(TEST_PLATFORM)) - goto Finish; - - error = disable_nonboot_cpus(); - if (!error && !suspend_test(TEST_CPUS)) - suspend_enter(state); + suspend_enter(state); - enable_nonboot_cpus(); - Finish: - if (suspend_ops->finish) - suspend_ops->finish(); Resume_devices: suspend_test_start(); device_resume(PMSG_RESUME); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f5fc2d7680f..33e2e4a819f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -321,13 +321,10 @@ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) INIT_LIST_HEAD(list); - for_each_zone(zone) { + for_each_populated_zone(zone) { unsigned long zone_start, zone_end; struct mem_extent *ext, *cur, *aux; - if (!populated_zone(zone)) - continue; - zone_start = zone->zone_start_pfn; zone_end = zone->zone_start_pfn + zone->spanned_pages; @@ -804,8 +801,8 @@ static unsigned int count_free_highmem_pages(void) struct zone *zone; unsigned int cnt = 0; - for_each_zone(zone) - if (populated_zone(zone) && is_highmem(zone)) + for_each_populated_zone(zone) + if (is_highmem(zone)) cnt += zone_page_state(zone, NR_FREE_PAGES); return cnt; diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index a92c9145155..78c35047586 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -51,6 +51,7 @@ #include <linux/highmem.h> #include <linux/time.h> #include <linux/rbtree.h> +#include <linux/io.h> #include "power.h" @@ -229,17 +230,16 @@ int swsusp_shrink_memory(void) size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES; tmp = size; size += highmem_size; - for_each_zone (zone) - if (populated_zone(zone)) { - tmp += snapshot_additional_pages(zone); - if (is_highmem(zone)) { - highmem_size -= + for_each_populated_zone(zone) { + tmp += snapshot_additional_pages(zone); + if (is_highmem(zone)) { + highmem_size -= zone_page_state(zone, NR_FREE_PAGES); - } else { - tmp -= zone_page_state(zone, NR_FREE_PAGES); - tmp += zone->lowmem_reserve[ZONE_NORMAL]; - } + } else { + tmp -= zone_page_state(zone, NR_FREE_PAGES); + tmp += zone->lowmem_reserve[ZONE_NORMAL]; } + } if (highmem_size < 0) highmem_size = 0; diff --git a/kernel/printk.c b/kernel/printk.c index e3602d0755b..a5f61a9aced 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -32,6 +32,7 @@ #include <linux/security.h> #include <linux/bootmem.h> #include <linux/syscalls.h> +#include <linux/kexec.h> #include <asm/uaccess.h> @@ -135,6 +136,24 @@ static char *log_buf = __log_buf; static int log_buf_len = __LOG_BUF_LEN; static unsigned logged_chars; /* Number of chars produced since last read+clear operation */ +#ifdef CONFIG_KEXEC +/* + * This appends the listed symbols to /proc/vmcoreinfo + * + * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to + * obtain access to symbols that are otherwise very difficult to locate. These + * symbols are specifically used so that utilities can access and extract the + * dmesg log from a vmcore file after a crash. + */ +void log_buf_kexec_setup(void) +{ + VMCOREINFO_SYMBOL(log_buf); + VMCOREINFO_SYMBOL(log_end); + VMCOREINFO_SYMBOL(log_buf_len); + VMCOREINFO_SYMBOL(logged_chars); +} +#endif + static int __init log_buf_len_setup(char *str) { unsigned size = memparse(str, &str); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index c9cf48b21f0..5105f5a6a2c 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -60,11 +60,15 @@ static void ptrace_untrace(struct task_struct *child) { spin_lock(&child->sighand->siglock); if (task_is_traced(child)) { - if (child->signal->flags & SIGNAL_STOP_STOPPED) { + /* + * If the group stop is completed or in progress, + * this thread was already counted as stopped. + */ + if (child->signal->flags & SIGNAL_STOP_STOPPED || + child->signal->group_stop_count) __set_task_state(child, TASK_STOPPED); - } else { + else signal_wake_up(child, 1); - } } spin_unlock(&child->sighand->siglock); } @@ -235,18 +239,58 @@ out: return retval; } -static inline void __ptrace_detach(struct task_struct *child, unsigned int data) +/* + * Called with irqs disabled, returns true if childs should reap themselves. + */ +static int ignoring_children(struct sighand_struct *sigh) { - child->exit_code = data; - /* .. re-parent .. */ - __ptrace_unlink(child); - /* .. and wake it up. */ - if (child->exit_state != EXIT_ZOMBIE) - wake_up_process(child); + int ret; + spin_lock(&sigh->siglock); + ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || + (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); + spin_unlock(&sigh->siglock); + return ret; +} + +/* + * Called with tasklist_lock held for writing. + * Unlink a traced task, and clean it up if it was a traced zombie. + * Return true if it needs to be reaped with release_task(). + * (We can't call release_task() here because we already hold tasklist_lock.) + * + * If it's a zombie, our attachedness prevented normal parent notification + * or self-reaping. Do notification now if it would have happened earlier. + * If it should reap itself, return true. + * + * If it's our own child, there is no notification to do. + * But if our normal children self-reap, then this child + * was prevented by ptrace and we must reap it now. + */ +static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) +{ + __ptrace_unlink(p); + + if (p->exit_state == EXIT_ZOMBIE) { + if (!task_detached(p) && thread_group_empty(p)) { + if (!same_thread_group(p->real_parent, tracer)) + do_notify_parent(p, p->exit_signal); + else if (ignoring_children(tracer->sighand)) + p->exit_signal = -1; + } + if (task_detached(p)) { + /* Mark it as in the process of being reaped. */ + p->exit_state = EXIT_DEAD; + return true; + } + } + + return false; } int ptrace_detach(struct task_struct *child, unsigned int data) { + bool dead = false; + if (!valid_signal(data)) return -EIO; @@ -255,14 +299,45 @@ int ptrace_detach(struct task_struct *child, unsigned int data) clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); write_lock_irq(&tasklist_lock); - /* protect against de_thread()->release_task() */ - if (child->ptrace) - __ptrace_detach(child, data); + /* + * This child can be already killed. Make sure de_thread() or + * our sub-thread doing do_wait() didn't do release_task() yet. + */ + if (child->ptrace) { + child->exit_code = data; + dead = __ptrace_detach(current, child); + } write_unlock_irq(&tasklist_lock); + if (unlikely(dead)) + release_task(child); + return 0; } +/* + * Detach all tasks we were using ptrace on. + */ +void exit_ptrace(struct task_struct *tracer) +{ + struct task_struct *p, *n; + LIST_HEAD(ptrace_dead); + + write_lock_irq(&tasklist_lock); + list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { + if (__ptrace_detach(tracer, p)) + list_add(&p->ptrace_entry, &ptrace_dead); + } + write_unlock_irq(&tasklist_lock); + + BUG_ON(!list_empty(&tracer->ptraced)); + + list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } +} + int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 7c4142a79f0..9b4a975a4b4 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -126,6 +126,7 @@ static atomic_t n_rcu_torture_mberror; static atomic_t n_rcu_torture_error; static long n_rcu_torture_timers = 0; static struct list_head rcu_torture_removed; +static cpumask_var_t shuffle_tmp_mask; static int stutter_pause_test = 0; @@ -889,10 +890,9 @@ static int rcu_idle_cpu; /* Force all torture tasks off this CPU */ */ static void rcu_torture_shuffle_tasks(void) { - cpumask_t tmp_mask; int i; - cpus_setall(tmp_mask); + cpumask_setall(shuffle_tmp_mask); get_online_cpus(); /* No point in shuffling if there is only one online CPU (ex: UP) */ @@ -902,29 +902,29 @@ static void rcu_torture_shuffle_tasks(void) } if (rcu_idle_cpu != -1) - cpu_clear(rcu_idle_cpu, tmp_mask); + cpumask_clear_cpu(rcu_idle_cpu, shuffle_tmp_mask); - set_cpus_allowed_ptr(current, &tmp_mask); + set_cpus_allowed_ptr(current, shuffle_tmp_mask); if (reader_tasks) { for (i = 0; i < nrealreaders; i++) if (reader_tasks[i]) set_cpus_allowed_ptr(reader_tasks[i], - &tmp_mask); + shuffle_tmp_mask); } if (fakewriter_tasks) { for (i = 0; i < nfakewriters; i++) if (fakewriter_tasks[i]) set_cpus_allowed_ptr(fakewriter_tasks[i], - &tmp_mask); + shuffle_tmp_mask); } if (writer_task) - set_cpus_allowed_ptr(writer_task, &tmp_mask); + set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask); if (stats_task) - set_cpus_allowed_ptr(stats_task, &tmp_mask); + set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask); if (rcu_idle_cpu == -1) rcu_idle_cpu = num_online_cpus() - 1; @@ -1012,6 +1012,7 @@ rcu_torture_cleanup(void) if (shuffler_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task"); kthread_stop(shuffler_task); + free_cpumask_var(shuffle_tmp_mask); } shuffler_task = NULL; @@ -1190,10 +1191,18 @@ rcu_torture_init(void) } if (test_no_idle_hz) { rcu_idle_cpu = num_online_cpus() - 1; + + if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) { + firsterr = -ENOMEM; + VERBOSE_PRINTK_ERRSTRING("Failed to alloc mask"); + goto unwind; + } + /* Create the shuffler thread */ shuffler_task = kthread_run(rcu_torture_shuffle, NULL, "rcu_torture_shuffle"); if (IS_ERR(shuffler_task)) { + free_cpumask_var(shuffle_tmp_mask); firsterr = PTR_ERR(shuffler_task); VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler"); shuffler_task = NULL; diff --git a/kernel/relay.c b/kernel/relay.c index 8f2179c8056..e92db8c06ac 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -797,13 +797,15 @@ void relay_subbufs_consumed(struct rchan *chan, if (!chan) return; - if (cpu >= NR_CPUS || !chan->buf[cpu]) + if (cpu >= NR_CPUS || !chan->buf[cpu] || + subbufs_consumed > chan->n_subbufs) return; buf = chan->buf[cpu]; - buf->subbufs_consumed += subbufs_consumed; - if (buf->subbufs_consumed > buf->subbufs_produced) + if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed) buf->subbufs_consumed = buf->subbufs_produced; + else + buf->subbufs_consumed += subbufs_consumed; } EXPORT_SYMBOL_GPL(relay_subbufs_consumed); diff --git a/kernel/sched.c b/kernel/sched.c index 5757e03cfac..73513f4e19d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4942,15 +4942,13 @@ pick_next_task(struct rq *rq) /* * schedule() is the main scheduler function. */ -asmlinkage void __sched schedule(void) +asmlinkage void __sched __schedule(void) { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; -need_resched: - preempt_disable(); cpu = smp_processor_id(); rq = cpu_rq(cpu); rcu_qsctr_inc(cpu); @@ -5007,13 +5005,80 @@ need_resched_nonpreemptible: if (unlikely(reacquire_kernel_lock(current) < 0)) goto need_resched_nonpreemptible; +} +asmlinkage void __sched schedule(void) +{ +need_resched: + preempt_disable(); + __schedule(); preempt_enable_no_resched(); if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) goto need_resched; } EXPORT_SYMBOL(schedule); +#ifdef CONFIG_SMP +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) +{ + unsigned int cpu; + struct rq *rq; + + if (!sched_feat(OWNER_SPIN)) + return 0; + +#ifdef CONFIG_DEBUG_PAGEALLOC + /* + * Need to access the cpu field knowing that + * DEBUG_PAGEALLOC could have unmapped it if + * the mutex owner just released it and exited. + */ + if (probe_kernel_address(&owner->cpu, cpu)) + goto out; +#else + cpu = owner->cpu; +#endif + + /* + * Even if the access succeeded (likely case), + * the cpu field may no longer be valid. + */ + if (cpu >= nr_cpumask_bits) + goto out; + + /* + * We need to validate that we can do a + * get_cpu() and that we have the percpu area. + */ + if (!cpu_online(cpu)) + goto out; + + rq = cpu_rq(cpu); + + for (;;) { + /* + * Owner changed, break to re-assess state. + */ + if (lock->owner != owner) + break; + + /* + * Is that owner really running on that cpu? + */ + if (task_thread_info(rq->curr) != owner || need_resched()) + return 0; + + cpu_relax(); + } +out: + return 1; +} +#endif + #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption @@ -5131,11 +5196,17 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) __wake_up_common(q, mode, 1, 0, NULL); } +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +{ + __wake_up_common(q, mode, 1, 0, key); +} + /** - * __wake_up_sync - wake up threads blocked on a waitqueue. + * __wake_up_sync_key - wake up threads blocked on a waitqueue. * @q: the waitqueue * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: opaque value to be passed to wakeup targets * * The sync wakeup differs that the waker knows that it will schedule * away soon, so while the target thread will be woken up, it will not @@ -5144,8 +5215,8 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) * * On UP it can prevent extra preemption. */ -void -__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) { unsigned long flags; int sync = 1; @@ -5157,9 +5228,18 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) sync = 0; spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, sync, NULL); + __wake_up_common(q, mode, nr_exclusive, sync, key); spin_unlock_irqrestore(&q->lock, flags); } +EXPORT_SYMBOL_GPL(__wake_up_sync_key); + +/* + * __wake_up_sync - see __wake_up_sync_key() + */ +void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +{ + __wake_up_sync_key(q, mode, nr_exclusive, NULL); +} EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ /** diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h index 642a94ef8a0..9a7e859b8fb 100644 --- a/kernel/sched_cpupri.h +++ b/kernel/sched_cpupri.h @@ -25,7 +25,7 @@ struct cpupri { #ifdef CONFIG_SMP int cpupri_find(struct cpupri *cp, - struct task_struct *p, cpumask_t *lowest_mask); + struct task_struct *p, struct cpumask *lowest_mask); void cpupri_set(struct cpupri *cp, int cpu, int pri); int cpupri_init(struct cpupri *cp, bool bootmem); void cpupri_cleanup(struct cpupri *cp); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 76f61756e67..4569bfa7df9 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -14,3 +14,4 @@ SCHED_FEAT(LB_WAKEUP_UPDATE, 1) SCHED_FEAT(ASYM_EFF_LOAD, 1) SCHED_FEAT(WAKEUP_OVERLAP, 0) SCHED_FEAT(LAST_BUDDY, 1) +SCHED_FEAT(OWNER_SPIN, 1) diff --git a/kernel/signal.c b/kernel/signal.c index 1c8814481a1..d8034737db4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -55,10 +55,22 @@ static int sig_handler_ignored(void __user *handler, int sig) (handler == SIG_DFL && sig_kernel_ignore(sig)); } -static int sig_ignored(struct task_struct *t, int sig) +static int sig_task_ignored(struct task_struct *t, int sig, + int from_ancestor_ns) { void __user *handler; + handler = sig_handler(t, sig); + + if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && + handler == SIG_DFL && !from_ancestor_ns) + return 1; + + return sig_handler_ignored(handler, sig); +} + +static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns) +{ /* * Blocked signals are never ignored, since the * signal handler may change by the time it is @@ -67,14 +79,13 @@ static int sig_ignored(struct task_struct *t, int sig) if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return 0; - handler = sig_handler(t, sig); - if (!sig_handler_ignored(handler, sig)) + if (!sig_task_ignored(t, sig, from_ancestor_ns)) return 0; /* * Tracers may want to know about even ignored signals. */ - return !tracehook_consider_ignored_signal(t, sig, handler); + return !tracehook_consider_ignored_signal(t, sig); } /* @@ -318,7 +329,7 @@ int unhandled_signal(struct task_struct *tsk, int sig) return 1; if (handler != SIG_IGN && handler != SIG_DFL) return 0; - return !tracehook_consider_fatal_signal(tsk, sig, handler); + return !tracehook_consider_fatal_signal(tsk, sig); } @@ -624,7 +635,7 @@ static int check_kill_permission(int sig, struct siginfo *info, * Returns true if the signal should be actually delivered, otherwise * it should be dropped. */ -static int prepare_signal(int sig, struct task_struct *p) +static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) { struct signal_struct *signal = p->signal; struct task_struct *t; @@ -708,7 +719,7 @@ static int prepare_signal(int sig, struct task_struct *p) } } - return !sig_ignored(p, sig); + return !sig_ignored(p, sig, from_ancestor_ns); } /* @@ -777,7 +788,7 @@ static void complete_signal(int sig, struct task_struct *p, int group) !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || - !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) { + !tracehook_consider_fatal_signal(t, sig))) { /* * This signal will be fatal to the whole group. */ @@ -813,8 +824,8 @@ static inline int legacy_queue(struct sigpending *signals, int sig) return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); } -static int send_signal(int sig, struct siginfo *info, struct task_struct *t, - int group) +static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, + int group, int from_ancestor_ns) { struct sigpending *pending; struct sigqueue *q; @@ -822,7 +833,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, trace_sched_signal_send(sig, t); assert_spin_locked(&t->sighand->siglock); - if (!prepare_signal(sig, t)) + + if (!prepare_signal(sig, t, from_ancestor_ns)) return 0; pending = group ? &t->signal->shared_pending : &t->pending; @@ -871,6 +883,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, break; default: copy_siginfo(&q->info, info); + if (from_ancestor_ns) + q->info.si_pid = 0; break; } } else if (!is_si_special(info)) { @@ -889,6 +903,20 @@ out_set: return 0; } +static int send_signal(int sig, struct siginfo *info, struct task_struct *t, + int group) +{ + int from_ancestor_ns = 0; + +#ifdef CONFIG_PID_NS + if (!is_si_special(info) && SI_FROMUSER(info) && + task_pid_nr_ns(current, task_active_pid_ns(t)) <= 0) + from_ancestor_ns = 1; +#endif + + return __send_signal(sig, info, t, group, from_ancestor_ns); +} + int print_fatal_signals; static void print_fatal_signal(struct pt_regs *regs, int signr) @@ -1133,7 +1161,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, if (sig && p->sighand) { unsigned long flags; spin_lock_irqsave(&p->sighand->siglock, flags); - ret = __group_send_sig_info(sig, info, p); + ret = __send_signal(sig, info, p, 1, 0); spin_unlock_irqrestore(&p->sighand->siglock, flags); } out_unlock: @@ -1320,7 +1348,7 @@ 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)) + if (!prepare_signal(sig, t, 0)) goto out; ret = 0; @@ -1844,9 +1872,16 @@ relock: /* * Global init gets no signals it doesn't want. + * Container-init gets no signals it doesn't want from same + * container. + * + * Note that if global/container-init sees a sig_kernel_only() + * signal here, the signal must have been generated internally + * or must have come from an ancestor namespace. In either + * case, the signal cannot be dropped. */ if (unlikely(signal->flags & SIGNAL_UNKILLABLE) && - !signal_group_exit(signal)) + !sig_kernel_only(signr)) continue; if (sig_kernel_stop(signr)) { diff --git a/kernel/slow-work.c b/kernel/slow-work.c new file mode 100644 index 00000000000..cf2bc01186e --- /dev/null +++ b/kernel/slow-work.c @@ -0,0 +1,640 @@ +/* Worker thread pool for slow items, such as filesystem lookups or mkdirs + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + * + * See Documentation/slow-work.txt + */ + +#include <linux/module.h> +#include <linux/slow-work.h> +#include <linux/kthread.h> +#include <linux/freezer.h> +#include <linux/wait.h> + +#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of + * things to do */ +#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after + * OOM */ + +static void slow_work_cull_timeout(unsigned long); +static void slow_work_oom_timeout(unsigned long); + +#ifdef CONFIG_SYSCTL +static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *, + void __user *, size_t *, loff_t *); + +static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *, + void __user *, size_t *, loff_t *); +#endif + +/* + * The pool of threads has at least min threads in it as long as someone is + * using the facility, and may have as many as max. + * + * A portion of the pool may be processing very slow operations. + */ +static unsigned slow_work_min_threads = 2; +static unsigned slow_work_max_threads = 4; +static unsigned vslow_work_proportion = 50; /* % of threads that may process + * very slow work */ + +#ifdef CONFIG_SYSCTL +static const int slow_work_min_min_threads = 2; +static int slow_work_max_max_threads = 255; +static const int slow_work_min_vslow = 1; +static const int slow_work_max_vslow = 99; + +ctl_table slow_work_sysctls[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "min-threads", + .data = &slow_work_min_threads, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = slow_work_min_threads_sysctl, + .extra1 = (void *) &slow_work_min_min_threads, + .extra2 = &slow_work_max_threads, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "max-threads", + .data = &slow_work_max_threads, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = slow_work_max_threads_sysctl, + .extra1 = &slow_work_min_threads, + .extra2 = (void *) &slow_work_max_max_threads, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "vslow-percentage", + .data = &vslow_work_proportion, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = (void *) &slow_work_min_vslow, + .extra2 = (void *) &slow_work_max_vslow, + }, + { .ctl_name = 0 } +}; +#endif + +/* + * The active state of the thread pool + */ +static atomic_t slow_work_thread_count; +static atomic_t vslow_work_executing_count; + +static bool slow_work_may_not_start_new_thread; +static bool slow_work_cull; /* cull a thread due to lack of activity */ +static DEFINE_TIMER(slow_work_cull_timer, slow_work_cull_timeout, 0, 0); +static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0); +static struct slow_work slow_work_new_thread; /* new thread starter */ + +/* + * The queues of work items and the lock governing access to them. These are + * shared between all the CPUs. It doesn't make sense to have per-CPU queues + * as the number of threads bears no relation to the number of CPUs. + * + * There are two queues of work items: one for slow work items, and one for + * very slow work items. + */ +static LIST_HEAD(slow_work_queue); +static LIST_HEAD(vslow_work_queue); +static DEFINE_SPINLOCK(slow_work_queue_lock); + +/* + * The thread controls. A variable used to signal to the threads that they + * should exit when the queue is empty, a waitqueue used by the threads to wait + * for signals, and a completion set by the last thread to exit. + */ +static bool slow_work_threads_should_exit; +static DECLARE_WAIT_QUEUE_HEAD(slow_work_thread_wq); +static DECLARE_COMPLETION(slow_work_last_thread_exited); + +/* + * The number of users of the thread pool and its lock. Whilst this is zero we + * have no threads hanging around, and when this reaches zero, we wait for all + * active or queued work items to complete and kill all the threads we do have. + */ +static int slow_work_user_count; +static DEFINE_MUTEX(slow_work_user_lock); + +/* + * Calculate the maximum number of active threads in the pool that are + * permitted to process very slow work items. + * + * The answer is rounded up to at least 1, but may not equal or exceed the + * maximum number of the threads in the pool. This means we always have at + * least one thread that can process slow work items, and we always have at + * least one thread that won't get tied up doing so. + */ +static unsigned slow_work_calc_vsmax(void) +{ + unsigned vsmax; + + vsmax = atomic_read(&slow_work_thread_count) * vslow_work_proportion; + vsmax /= 100; + vsmax = max(vsmax, 1U); + return min(vsmax, slow_work_max_threads - 1); +} + +/* + * Attempt to execute stuff queued on a slow thread. Return true if we managed + * it, false if there was nothing to do. + */ +static bool slow_work_execute(void) +{ + struct slow_work *work = NULL; + unsigned vsmax; + bool very_slow; + + vsmax = slow_work_calc_vsmax(); + + /* see if we can schedule a new thread to be started if we're not + * keeping up with the work */ + if (!waitqueue_active(&slow_work_thread_wq) && + (!list_empty(&slow_work_queue) || !list_empty(&vslow_work_queue)) && + atomic_read(&slow_work_thread_count) < slow_work_max_threads && + !slow_work_may_not_start_new_thread) + slow_work_enqueue(&slow_work_new_thread); + + /* find something to execute */ + spin_lock_irq(&slow_work_queue_lock); + if (!list_empty(&vslow_work_queue) && + atomic_read(&vslow_work_executing_count) < vsmax) { + work = list_entry(vslow_work_queue.next, + struct slow_work, link); + if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags)) + BUG(); + list_del_init(&work->link); + atomic_inc(&vslow_work_executing_count); + very_slow = true; + } else if (!list_empty(&slow_work_queue)) { + work = list_entry(slow_work_queue.next, + struct slow_work, link); + if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags)) + BUG(); + list_del_init(&work->link); + very_slow = false; + } else { + very_slow = false; /* avoid the compiler warning */ + } + spin_unlock_irq(&slow_work_queue_lock); + + if (!work) + return false; + + if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags)) + BUG(); + + work->ops->execute(work); + + if (very_slow) + atomic_dec(&vslow_work_executing_count); + clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags); + + /* if someone tried to enqueue the item whilst we were executing it, + * then it'll be left unenqueued to avoid multiple threads trying to + * execute it simultaneously + * + * there is, however, a race between us testing the pending flag and + * getting the spinlock, and between the enqueuer setting the pending + * flag and getting the spinlock, so we use a deferral bit to tell us + * if the enqueuer got there first + */ + if (test_bit(SLOW_WORK_PENDING, &work->flags)) { + spin_lock_irq(&slow_work_queue_lock); + + if (!test_bit(SLOW_WORK_EXECUTING, &work->flags) && + test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) + goto auto_requeue; + + spin_unlock_irq(&slow_work_queue_lock); + } + + work->ops->put_ref(work); + return true; + +auto_requeue: + /* we must complete the enqueue operation + * - we transfer our ref on the item back to the appropriate queue + * - don't wake another thread up as we're awake already + */ + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) + list_add_tail(&work->link, &vslow_work_queue); + else + list_add_tail(&work->link, &slow_work_queue); + spin_unlock_irq(&slow_work_queue_lock); + return true; +} + +/** + * slow_work_enqueue - Schedule a slow work item for processing + * @work: The work item to queue + * + * Schedule a slow work item for processing. If the item is already undergoing + * execution, this guarantees not to re-enter the execution routine until the + * first execution finishes. + * + * The item is pinned by this function as it retains a reference to it, managed + * through the item operations. The item is unpinned once it has been + * executed. + * + * An item may hog the thread that is running it for a relatively large amount + * of time, sufficient, for example, to perform several lookup, mkdir, create + * and setxattr operations. It may sleep on I/O and may sleep to obtain locks. + * + * Conversely, if a number of items are awaiting processing, it may take some + * time before any given item is given attention. The number of threads in the + * pool may be increased to deal with demand, but only up to a limit. + * + * If SLOW_WORK_VERY_SLOW is set on the work item, then it will be placed in + * the very slow queue, from which only a portion of the threads will be + * allowed to pick items to execute. This ensures that very slow items won't + * overly block ones that are just ordinarily slow. + * + * Returns 0 if successful, -EAGAIN if not. + */ +int slow_work_enqueue(struct slow_work *work) +{ + unsigned long flags; + + BUG_ON(slow_work_user_count <= 0); + BUG_ON(!work); + BUG_ON(!work->ops); + BUG_ON(!work->ops->get_ref); + + /* when honouring an enqueue request, we only promise that we will run + * the work function in the future; we do not promise to run it once + * per enqueue request + * + * we use the PENDING bit to merge together repeat requests without + * having to disable IRQs and take the spinlock, whilst still + * maintaining our promise + */ + if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { + spin_lock_irqsave(&slow_work_queue_lock, flags); + + /* we promise that we will not attempt to execute the work + * function in more than one thread simultaneously + * + * this, however, leaves us with a problem if we're asked to + * enqueue the work whilst someone is executing the work + * function as simply queueing the work immediately means that + * another thread may try executing it whilst it is already + * under execution + * + * to deal with this, we set the ENQ_DEFERRED bit instead of + * enqueueing, and the thread currently executing the work + * function will enqueue the work item when the work function + * returns and it has cleared the EXECUTING bit + */ + if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { + set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); + } else { + if (work->ops->get_ref(work) < 0) + goto cant_get_ref; + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) + list_add_tail(&work->link, &vslow_work_queue); + else + list_add_tail(&work->link, &slow_work_queue); + wake_up(&slow_work_thread_wq); + } + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + } + return 0; + +cant_get_ref: + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + return -EAGAIN; +} +EXPORT_SYMBOL(slow_work_enqueue); + +/* + * Worker thread culling algorithm + */ +static bool slow_work_cull_thread(void) +{ + unsigned long flags; + bool do_cull = false; + + spin_lock_irqsave(&slow_work_queue_lock, flags); + + if (slow_work_cull) { + slow_work_cull = false; + + if (list_empty(&slow_work_queue) && + list_empty(&vslow_work_queue) && + atomic_read(&slow_work_thread_count) > + slow_work_min_threads) { + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + do_cull = true; + } + } + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + return do_cull; +} + +/* + * Determine if there is slow work available for dispatch + */ +static inline bool slow_work_available(int vsmax) +{ + return !list_empty(&slow_work_queue) || + (!list_empty(&vslow_work_queue) && + atomic_read(&vslow_work_executing_count) < vsmax); +} + +/* + * Worker thread dispatcher + */ +static int slow_work_thread(void *_data) +{ + int vsmax; + + DEFINE_WAIT(wait); + + set_freezable(); + set_user_nice(current, -5); + + for (;;) { + vsmax = vslow_work_proportion; + vsmax *= atomic_read(&slow_work_thread_count); + vsmax /= 100; + + prepare_to_wait(&slow_work_thread_wq, &wait, + TASK_INTERRUPTIBLE); + if (!freezing(current) && + !slow_work_threads_should_exit && + !slow_work_available(vsmax) && + !slow_work_cull) + schedule(); + finish_wait(&slow_work_thread_wq, &wait); + + try_to_freeze(); + + vsmax = vslow_work_proportion; + vsmax *= atomic_read(&slow_work_thread_count); + vsmax /= 100; + + if (slow_work_available(vsmax) && slow_work_execute()) { + cond_resched(); + if (list_empty(&slow_work_queue) && + list_empty(&vslow_work_queue) && + atomic_read(&slow_work_thread_count) > + slow_work_min_threads) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + continue; + } + + if (slow_work_threads_should_exit) + break; + + if (slow_work_cull && slow_work_cull_thread()) + break; + } + + if (atomic_dec_and_test(&slow_work_thread_count)) + complete_and_exit(&slow_work_last_thread_exited, 0); + return 0; +} + +/* + * Handle thread cull timer expiration + */ +static void slow_work_cull_timeout(unsigned long data) +{ + slow_work_cull = true; + wake_up(&slow_work_thread_wq); +} + +/* + * Get a reference on slow work thread starter + */ +static int slow_work_new_thread_get_ref(struct slow_work *work) +{ + return 0; +} + +/* + * Drop a reference on slow work thread starter + */ +static void slow_work_new_thread_put_ref(struct slow_work *work) +{ +} + +/* + * Start a new slow work thread + */ +static void slow_work_new_thread_execute(struct slow_work *work) +{ + struct task_struct *p; + + if (slow_work_threads_should_exit) + return; + + if (atomic_read(&slow_work_thread_count) >= slow_work_max_threads) + return; + + if (!mutex_trylock(&slow_work_user_lock)) + return; + + slow_work_may_not_start_new_thread = true; + atomic_inc(&slow_work_thread_count); + p = kthread_run(slow_work_thread, NULL, "kslowd"); + if (IS_ERR(p)) { + printk(KERN_DEBUG "Slow work thread pool: OOM\n"); + if (atomic_dec_and_test(&slow_work_thread_count)) + BUG(); /* we're running on a slow work thread... */ + mod_timer(&slow_work_oom_timer, + jiffies + SLOW_WORK_OOM_TIMEOUT); + } else { + /* ratelimit the starting of new threads */ + mod_timer(&slow_work_oom_timer, jiffies + 1); + } + + mutex_unlock(&slow_work_user_lock); +} + +static const struct slow_work_ops slow_work_new_thread_ops = { + .get_ref = slow_work_new_thread_get_ref, + .put_ref = slow_work_new_thread_put_ref, + .execute = slow_work_new_thread_execute, +}; + +/* + * post-OOM new thread start suppression expiration + */ +static void slow_work_oom_timeout(unsigned long data) +{ + slow_work_may_not_start_new_thread = false; +} + +#ifdef CONFIG_SYSCTL +/* + * Handle adjustment of the minimum number of threads + */ +static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int n; + + if (ret == 0) { + mutex_lock(&slow_work_user_lock); + if (slow_work_user_count > 0) { + /* see if we need to start or stop threads */ + n = atomic_read(&slow_work_thread_count) - + slow_work_min_threads; + + if (n < 0 && !slow_work_may_not_start_new_thread) + slow_work_enqueue(&slow_work_new_thread); + else if (n > 0) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + } + mutex_unlock(&slow_work_user_lock); + } + + return ret; +} + +/* + * Handle adjustment of the maximum number of threads + */ +static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int n; + + if (ret == 0) { + mutex_lock(&slow_work_user_lock); + if (slow_work_user_count > 0) { + /* see if we need to stop threads */ + n = slow_work_max_threads - + atomic_read(&slow_work_thread_count); + + if (n < 0) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + } + mutex_unlock(&slow_work_user_lock); + } + + return ret; +} +#endif /* CONFIG_SYSCTL */ + +/** + * slow_work_register_user - Register a user of the facility + * + * Register a user of the facility, starting up the initial threads if there + * aren't any other users at this point. This will return 0 if successful, or + * an error if not. + */ +int slow_work_register_user(void) +{ + struct task_struct *p; + int loop; + + mutex_lock(&slow_work_user_lock); + + if (slow_work_user_count == 0) { + printk(KERN_NOTICE "Slow work thread pool: Starting up\n"); + init_completion(&slow_work_last_thread_exited); + + slow_work_threads_should_exit = false; + slow_work_init(&slow_work_new_thread, + &slow_work_new_thread_ops); + slow_work_may_not_start_new_thread = false; + slow_work_cull = false; + + /* start the minimum number of threads */ + for (loop = 0; loop < slow_work_min_threads; loop++) { + atomic_inc(&slow_work_thread_count); + p = kthread_run(slow_work_thread, NULL, "kslowd"); + if (IS_ERR(p)) + goto error; + } + printk(KERN_NOTICE "Slow work thread pool: Ready\n"); + } + + slow_work_user_count++; + mutex_unlock(&slow_work_user_lock); + return 0; + +error: + if (atomic_dec_and_test(&slow_work_thread_count)) + complete(&slow_work_last_thread_exited); + if (loop > 0) { + printk(KERN_ERR "Slow work thread pool:" + " Aborting startup on ENOMEM\n"); + slow_work_threads_should_exit = true; + wake_up_all(&slow_work_thread_wq); + wait_for_completion(&slow_work_last_thread_exited); + printk(KERN_ERR "Slow work thread pool: Aborted\n"); + } + mutex_unlock(&slow_work_user_lock); + return PTR_ERR(p); +} +EXPORT_SYMBOL(slow_work_register_user); + +/** + * slow_work_unregister_user - Unregister a user of the facility + * + * Unregister a user of the facility, killing all the threads if this was the + * last one. + */ +void slow_work_unregister_user(void) +{ + mutex_lock(&slow_work_user_lock); + + BUG_ON(slow_work_user_count <= 0); + + slow_work_user_count--; + if (slow_work_user_count == 0) { + printk(KERN_NOTICE "Slow work thread pool: Shutting down\n"); + slow_work_threads_should_exit = true; + wake_up_all(&slow_work_thread_wq); + wait_for_completion(&slow_work_last_thread_exited); + printk(KERN_NOTICE "Slow work thread pool:" + " Shut down complete\n"); + } + + del_timer_sync(&slow_work_cull_timer); + + mutex_unlock(&slow_work_user_lock); +} +EXPORT_SYMBOL(slow_work_unregister_user); + +/* + * Initialise the slow work facility + */ +static int __init init_slow_work(void) +{ + unsigned nr_cpus = num_possible_cpus(); + + if (slow_work_max_threads < nr_cpus) + slow_work_max_threads = nr_cpus; +#ifdef CONFIG_SYSCTL + if (slow_work_max_max_threads < nr_cpus * 2) + slow_work_max_max_threads = nr_cpus * 2; +#endif + return 0; +} + +subsys_initcall(init_slow_work); diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 29ab20749dd..7932653c4eb 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -121,7 +121,8 @@ unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock); + LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock, + _raw_read_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_read_lock_irqsave); @@ -151,7 +152,8 @@ unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock); + LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock, + _raw_write_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_write_lock_irqsave); @@ -299,16 +301,8 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas local_irq_save(flags); preempt_disable(); spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - /* - * On lockdep we dont want the hand-coded irq-enable of - * _raw_spin_lock_flags() code, because lockdep assumes - * that interrupts are not re-enabled during lock-acquire: - */ -#ifdef CONFIG_LOCKDEP - LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock); -#else - _raw_spin_lock_flags(lock, &flags); -#endif + LOCK_CONTENDED_FLAGS(lock, _raw_spin_trylock, _raw_spin_lock, + _raw_spin_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_spin_lock_irqsave_nested); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 74541ca4953..912823e2a11 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -44,7 +44,7 @@ static DEFINE_MUTEX(setup_lock); static int refcount; static struct workqueue_struct *stop_machine_wq; static struct stop_machine_data active, idle; -static const cpumask_t *active_cpus; +static const struct cpumask *active_cpus; static void *stop_machine_work; static void set_state(enum stopmachine_state newstate) diff --git a/kernel/sys.c b/kernel/sys.c index 37f458e6882..51dbb55604e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -34,6 +34,7 @@ #include <linux/seccomp.h> #include <linux/cpu.h> #include <linux/ptrace.h> +#include <linux/fs_struct.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -1013,10 +1014,8 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) if (err) goto out; - if (task_pgrp(p) != pgrp) { + if (task_pgrp(p) != pgrp) change_pid(p, PIDTYPE_PGID, pgrp); - set_task_pgrp(p, pid_nr(pgrp)); - } err = 0; out: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c5ef44ff850..82350f8f04f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -48,6 +48,7 @@ #include <linux/acpi.h> #include <linux/reboot.h> #include <linux/ftrace.h> +#include <linux/slow-work.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -95,12 +96,9 @@ static int sixty = 60; static int neg_one = -1; #endif -#if defined(CONFIG_MMU) && defined(CONFIG_FILE_LOCKING) -static int two = 2; -#endif - static int zero; static int one = 1; +static int two = 2; static unsigned long one_ul = 1; static int one_hundred = 100; @@ -900,6 +898,14 @@ static struct ctl_table kern_table[] = { .proc_handler = &scan_unevictable_handler, }, #endif +#ifdef CONFIG_SLOW_WORK + { + .ctl_name = CTL_UNNUMBERED, + .procname = "slow-work", + .mode = 0555, + .child = slow_work_sysctls, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt @@ -1010,7 +1016,7 @@ static struct ctl_table vm_table[] = { .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, + .proc_handler = &proc_dointvec, }, { .ctl_name = VM_NR_PDFLUSH_THREADS, @@ -1373,10 +1379,7 @@ static struct ctl_table fs_table[] = { .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &zero, - .extra2 = &two, + .proc_handler = &proc_dointvec, }, #endif #ifdef CONFIG_AIO @@ -1417,7 +1420,10 @@ static struct ctl_table fs_table[] = { .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &two, }, #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) { diff --git a/kernel/timer.c b/kernel/timer.c index 9b77fc9a9ac..b4555568b4e 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -491,14 +491,18 @@ static inline void debug_timer_free(struct timer_list *timer) debug_object_free(timer, &timer_debug_descr); } -static void __init_timer(struct timer_list *timer); +static void __init_timer(struct timer_list *timer, + const char *name, + struct lock_class_key *key); -void init_timer_on_stack(struct timer_list *timer) +void init_timer_on_stack_key(struct timer_list *timer, + const char *name, + struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); - __init_timer(timer); + __init_timer(timer, name, key); } -EXPORT_SYMBOL_GPL(init_timer_on_stack); +EXPORT_SYMBOL_GPL(init_timer_on_stack_key); void destroy_timer_on_stack(struct timer_list *timer) { @@ -512,7 +516,9 @@ static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } #endif -static void __init_timer(struct timer_list *timer) +static void __init_timer(struct timer_list *timer, + const char *name, + struct lock_class_key *key) { timer->entry.next = NULL; timer->base = __raw_get_cpu_var(tvec_bases); @@ -521,6 +527,7 @@ static void __init_timer(struct timer_list *timer) timer->start_pid = -1; memset(timer->start_comm, 0, TASK_COMM_LEN); #endif + lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** @@ -530,19 +537,23 @@ static void __init_timer(struct timer_list *timer) * init_timer() must be done to a timer prior calling *any* of the * other timer functions. */ -void init_timer(struct timer_list *timer) +void init_timer_key(struct timer_list *timer, + const char *name, + struct lock_class_key *key) { debug_timer_init(timer); - __init_timer(timer); + __init_timer(timer, name, key); } -EXPORT_SYMBOL(init_timer); +EXPORT_SYMBOL(init_timer_key); -void init_timer_deferrable(struct timer_list *timer) +void init_timer_deferrable_key(struct timer_list *timer, + const char *name, + struct lock_class_key *key) { - init_timer(timer); + init_timer_key(timer, name, key); timer_set_deferrable(timer); } -EXPORT_SYMBOL(init_timer_deferrable); +EXPORT_SYMBOL(init_timer_deferrable_key); static inline void detach_timer(struct timer_list *timer, int clear_pending) @@ -826,6 +837,15 @@ EXPORT_SYMBOL(try_to_del_timer_sync); */ int del_timer_sync(struct timer_list *timer) { +#ifdef CONFIG_LOCKDEP + unsigned long flags; + + local_irq_save(flags); + lock_map_acquire(&timer->lockdep_map); + lock_map_release(&timer->lockdep_map); + local_irq_restore(flags); +#endif + for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) @@ -897,10 +917,36 @@ static inline void __run_timers(struct tvec_base *base) set_running_timer(base, timer); detach_timer(timer, 1); + spin_unlock_irq(&base->lock); { int preempt_count = preempt_count(); + +#ifdef CONFIG_LOCKDEP + /* + * It is permissible to free the timer from + * inside the function that is called from + * it, this we need to take into account for + * lockdep too. To avoid bogus "held lock + * freed" warnings as well as problems when + * looking into timer->lockdep_map, make a + * copy and use that here. + */ + struct lockdep_map lockdep_map = + timer->lockdep_map; +#endif + /* + * Couple the lock chain with the lock chain at + * del_timer_sync() by acquiring the lock_map + * around the fn() call here and in + * del_timer_sync(). + */ + lock_map_acquire(&lockdep_map); + fn(data); + + lock_map_release(&lockdep_map); + if (preempt_count != preempt_count()) { printk(KERN_ERR "huh, entered %p " "with preempt_count %08x, exited" diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 930c08e5b38..dce71a5b51b 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -42,6 +42,81 @@ static struct tracer_flags tracer_flags = { /* pid on the last trace processed */ static pid_t last_pid[NR_CPUS] = { [0 ... NR_CPUS-1] = -1 }; +/* Add a function return address to the trace stack on thread info.*/ +int +ftrace_push_return_trace(unsigned long ret, unsigned long long time, + unsigned long func, int *depth) +{ + int index; + + if (!current->ret_stack) + return -EBUSY; + + /* The return trace stack is full */ + if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { + atomic_inc(¤t->trace_overrun); + return -EBUSY; + } + + index = ++current->curr_ret_stack; + barrier(); + current->ret_stack[index].ret = ret; + current->ret_stack[index].func = func; + current->ret_stack[index].calltime = time; + *depth = index; + + return 0; +} + +/* Retrieve a function return address to the trace stack on thread info.*/ +void +ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) +{ + int index; + + index = current->curr_ret_stack; + + if (unlikely(index < 0)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic, otherwise we have no where to go */ + *ret = (unsigned long)panic; + return; + } + + *ret = current->ret_stack[index].ret; + trace->func = current->ret_stack[index].func; + trace->calltime = current->ret_stack[index].calltime; + trace->overrun = atomic_read(¤t->trace_overrun); + trace->depth = index; + barrier(); + current->curr_ret_stack--; + +} + +/* + * Send the trace to the ring-buffer. + * @return the original return address. + */ +unsigned long ftrace_return_to_handler(void) +{ + struct ftrace_graph_ret trace; + unsigned long ret; + + ftrace_pop_return_trace(&trace, &ret); + trace.rettime = cpu_clock(raw_smp_processor_id()); + ftrace_graph_return(&trace); + + if (unlikely(!ret)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic. What else to do? */ + ret = (unsigned long)panic; + } + + return ret; +} + static int graph_trace_init(struct trace_array *tr) { int cpu, ret; diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 3b34b354593..92359cc747a 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -37,7 +37,7 @@ static void put_uts(ctl_table *table, int write, void *which) up_write(&uts_sem); } -#ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_SYSCTL /* * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1f0c509b40d..32f8e0d2bf5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -48,8 +48,6 @@ struct cpu_workqueue_struct { struct workqueue_struct *wq; struct task_struct *thread; - - int run_depth; /* Detect run_workqueue() recursion depth */ } ____cacheline_aligned; /* @@ -262,13 +260,6 @@ EXPORT_SYMBOL_GPL(queue_delayed_work_on); static void run_workqueue(struct cpu_workqueue_struct *cwq) { spin_lock_irq(&cwq->lock); - cwq->run_depth++; - if (cwq->run_depth > 3) { - /* morton gets to eat his hat */ - printk("%s: recursion depth exceeded: %d\n", - __func__, cwq->run_depth); - dump_stack(); - } while (!list_empty(&cwq->worklist)) { struct work_struct *work = list_entry(cwq->worklist.next, struct work_struct, entry); @@ -311,7 +302,6 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) spin_lock_irq(&cwq->lock); cwq->current_work = NULL; } - cwq->run_depth--; spin_unlock_irq(&cwq->lock); } @@ -368,29 +358,20 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) { - int active; + int active = 0; + struct wq_barrier barr; - if (cwq->thread == current) { - /* - * Probably keventd trying to flush its own queue. So simply run - * it by hand rather than deadlocking. - */ - run_workqueue(cwq); - active = 1; - } else { - struct wq_barrier barr; + WARN_ON(cwq->thread == current); - active = 0; - spin_lock_irq(&cwq->lock); - if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) { - insert_wq_barrier(cwq, &barr, &cwq->worklist); - active = 1; - } - spin_unlock_irq(&cwq->lock); - - if (active) - wait_for_completion(&barr.done); + spin_lock_irq(&cwq->lock); + if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) { + insert_wq_barrier(cwq, &barr, &cwq->worklist); + active = 1; } + spin_unlock_irq(&cwq->lock); + + if (active) + wait_for_completion(&barr.done); return active; } @@ -416,7 +397,7 @@ void flush_workqueue(struct workqueue_struct *wq) might_sleep(); lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); - for_each_cpu_mask_nr(cpu, *cpu_map) + for_each_cpu(cpu, cpu_map) flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu)); } EXPORT_SYMBOL_GPL(flush_workqueue); @@ -547,7 +528,7 @@ static void wait_on_work(struct work_struct *work) wq = cwq->wq; cpu_map = wq_cpu_map(wq); - for_each_cpu_mask_nr(cpu, *cpu_map) + for_each_cpu(cpu, cpu_map) wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work); } @@ -911,7 +892,7 @@ void destroy_workqueue(struct workqueue_struct *wq) list_del(&wq->list); spin_unlock(&workqueue_lock); - for_each_cpu_mask_nr(cpu, *cpu_map) + for_each_cpu(cpu, cpu_map) cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu)); cpu_maps_update_done(); |