diff options
Diffstat (limited to 'kernel')
34 files changed, 1911 insertions, 818 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/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/extable.c b/kernel/extable.c index 384f0da8a03..81e99d1f0d5 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -41,6 +41,14 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } +static inline int init_kernel_text(unsigned long addr) +{ + if (addr >= (unsigned long)_sinittext && + addr <= (unsigned long)_einittext) + return 1; + return 0; +} + __notrace_funcgraph int core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && @@ -48,8 +56,7 @@ __notrace_funcgraph int core_kernel_text(unsigned long addr) return 1; if (system_state == SYSTEM_BOOTING && - addr >= (unsigned long)_sinittext && - addr <= (unsigned long)_einittext) + init_kernel_text(addr)) return 1; return 0; } @@ -58,7 +65,19 @@ __notrace_funcgraph int __kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) return 1; - return is_module_text_address(addr); + if (is_module_text_address(addr)) + return 1; + /* + * There might be init symbols in saved stacktraces. + * Give those symbols a chance to be printed in + * backtraces (such as lockdep traces). + * + * Since we are after the module-symbols check, there's + * no danger of address overlap: + */ + if (init_kernel_text(addr)) + return 1; + return 0; } int kernel_text_address(unsigned long addr) diff --git a/kernel/fork.c b/kernel/fork.c index 47c15840a38..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> @@ -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/kexec.c b/kernel/kexec.c index 93eed85fe01..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); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 3673a3f44d9..981cd485428 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -433,13 +433,6 @@ atomic_t nr_find_usage_forwards_checks; atomic_t nr_find_usage_forwards_recursions; atomic_t nr_find_usage_backwards_checks; atomic_t nr_find_usage_backwards_recursions; -# define debug_atomic_inc(ptr) atomic_inc(ptr) -# define debug_atomic_dec(ptr) atomic_dec(ptr) -# define debug_atomic_read(ptr) atomic_read(ptr) -#else -# define debug_atomic_inc(ptr) do { } while (0) -# define debug_atomic_dec(ptr) do { } while (0) -# define debug_atomic_read(ptr) 0 #endif /* @@ -1900,9 +1893,9 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other, curr->comm, task_pid_nr(curr)); print_lock(this); if (forwards) - printk("but this lock took another, %s-irq-unsafe lock in the past:\n", irqclass); + printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass); else - printk("but this lock was taken by another, %s-irq-safe lock in the past:\n", irqclass); + printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass); print_lock_name(other); printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); @@ -2015,7 +2008,8 @@ 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) +mark_lock_irq(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit) { int excl_bit = exclusive_bit(new_bit); int read = new_bit & 1; @@ -2043,7 +2037,7 @@ mark_lock_irq(struct task_struct *curr, struct held_lock *this, int new_bit) * states. */ if ((!read || !dir || STRICT_READ_CHECKS) && - !usage(curr, this, excl_bit, state_name(new_bit))) + !usage(curr, this, excl_bit, state_name(new_bit & ~1))) return 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/panic.c b/kernel/panic.c index 32fe4eff1b8..3fd8c5bf8b3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -8,19 +8,19 @@ * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ +#include <linux/debug_locks.h> +#include <linux/interrupt.h> +#include <linux/kallsyms.h> +#include <linux/notifier.h> #include <linux/module.h> -#include <linux/sched.h> -#include <linux/delay.h> +#include <linux/random.h> #include <linux/reboot.h> -#include <linux/notifier.h> -#include <linux/init.h> +#include <linux/delay.h> +#include <linux/kexec.h> +#include <linux/sched.h> #include <linux/sysrq.h> -#include <linux/interrupt.h> +#include <linux/init.h> #include <linux/nmi.h> -#include <linux/kexec.h> -#include <linux/debug_locks.h> -#include <linux/random.h> -#include <linux/kallsyms.h> #include <linux/dmi.h> int panic_on_oops; @@ -52,19 +52,15 @@ EXPORT_SYMBOL(panic_blink); * * This function never returns. */ - NORET_TYPE void panic(const char * fmt, ...) { - long i; static char buf[1024]; va_list args; -#if defined(CONFIG_S390) - unsigned long caller = (unsigned long) __builtin_return_address(0); -#endif + long i; /* - * It's possible to come here directly from a panic-assertion and not - * have preempt disabled. Some functions called from here want + * It's possible to come here directly from a panic-assertion and + * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... */ preempt_disable(); @@ -77,7 +73,6 @@ NORET_TYPE void panic(const char * fmt, ...) #ifdef CONFIG_DEBUG_BUGVERBOSE dump_stack(); #endif - bust_spinlocks(0); /* * If we have crashed and we have a crash kernel loaded let it handle @@ -86,14 +81,12 @@ NORET_TYPE void panic(const char * fmt, ...) */ crash_kexec(NULL); -#ifdef CONFIG_SMP /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic * situation. */ smp_send_stop(); -#endif atomic_notifier_call_chain(&panic_notifier_list, 0, buf); @@ -102,19 +95,21 @@ NORET_TYPE void panic(const char * fmt, ...) if (panic_timeout > 0) { /* - * Delay timeout seconds before rebooting the machine. - * We can't use the "normal" timers since we just panicked.. - */ - printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout); + * Delay timeout seconds before rebooting the machine. + * We can't use the "normal" timers since we just panicked. + */ + printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout); + for (i = 0; i < panic_timeout*1000; ) { touch_nmi_watchdog(); i += panic_blink(i); mdelay(1); i++; } - /* This will not be a clean reboot, with everything - * shutting down. But if there is a chance of - * rebooting the system it will be rebooted. + /* + * This will not be a clean reboot, with everything + * shutting down. But if there is a chance of + * rebooting the system it will be rebooted. */ emergency_restart(); } @@ -127,38 +122,44 @@ NORET_TYPE void panic(const char * fmt, ...) } #endif #if defined(CONFIG_S390) - disabled_wait(caller); + { + unsigned long caller; + + caller = (unsigned long)__builtin_return_address(0); + disabled_wait(caller); + } #endif local_irq_enable(); - for (i = 0;;) { + for (i = 0; ; ) { touch_softlockup_watchdog(); i += panic_blink(i); mdelay(1); i++; } + bust_spinlocks(0); } EXPORT_SYMBOL(panic); struct tnt { - u8 bit; - char true; - char false; + u8 bit; + char true; + char false; }; static const struct tnt tnts[] = { - { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, - { TAINT_FORCED_MODULE, 'F', ' ' }, - { TAINT_UNSAFE_SMP, 'S', ' ' }, - { TAINT_FORCED_RMMOD, 'R', ' ' }, - { TAINT_MACHINE_CHECK, 'M', ' ' }, - { TAINT_BAD_PAGE, 'B', ' ' }, - { TAINT_USER, 'U', ' ' }, - { TAINT_DIE, 'D', ' ' }, - { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, - { TAINT_WARN, 'W', ' ' }, - { TAINT_CRAP, 'C', ' ' }, + { TAINT_PROPRIETARY_MODULE, 'P', 'G' }, + { TAINT_FORCED_MODULE, 'F', ' ' }, + { TAINT_UNSAFE_SMP, 'S', ' ' }, + { TAINT_FORCED_RMMOD, 'R', ' ' }, + { TAINT_MACHINE_CHECK, 'M', ' ' }, + { TAINT_BAD_PAGE, 'B', ' ' }, + { TAINT_USER, 'U', ' ' }, + { TAINT_DIE, 'D', ' ' }, + { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' }, + { TAINT_WARN, 'W', ' ' }, + { TAINT_CRAP, 'C', ' ' }, }; /** @@ -195,7 +196,8 @@ const char *print_tainted(void) *s = 0; } else snprintf(buf, sizeof(buf), "Not tainted"); - return(buf); + + return buf; } int test_taint(unsigned flag) @@ -211,7 +213,8 @@ unsigned long get_taint(void) void add_taint(unsigned flag) { - debug_locks = 0; /* can't trust the integrity of the kernel anymore */ + /* can't trust the integrity of the kernel anymore: */ + debug_locks = 0; set_bit(flag, &tainted_mask); } EXPORT_SYMBOL(add_taint); @@ -266,8 +269,8 @@ static void do_oops_enter_exit(void) } /* - * Return true if the calling CPU is allowed to print oops-related info. This - * is a bit racy.. + * Return true if the calling CPU is allowed to print oops-related info. + * This is a bit racy.. */ int oops_may_print(void) { @@ -276,20 +279,22 @@ int oops_may_print(void) /* * Called when the architecture enters its oops handler, before it prints - * anything. If this is the first CPU to oops, and it's oopsing the first time - * then let it proceed. + * anything. If this is the first CPU to oops, and it's oopsing the first + * time then let it proceed. * - * This is all enabled by the pause_on_oops kernel boot option. We do all this - * to ensure that oopses don't scroll off the screen. It has the side-effect - * of preventing later-oopsing CPUs from mucking up the display, too. + * This is all enabled by the pause_on_oops kernel boot option. We do all + * this to ensure that oopses don't scroll off the screen. It has the + * side-effect of preventing later-oopsing CPUs from mucking up the display, + * too. * - * It turns out that the CPU which is allowed to print ends up pausing for the - * right duration, whereas all the other CPUs pause for twice as long: once in - * oops_enter(), once in oops_exit(). + * It turns out that the CPU which is allowed to print ends up pausing for + * the right duration, whereas all the other CPUs pause for twice as long: + * once in oops_enter(), once in oops_exit(). */ void oops_enter(void) { - debug_locks_off(); /* can't trust the integrity of the kernel anymore */ + /* can't trust the integrity of the kernel anymore: */ + debug_locks_off(); do_oops_enter_exit(); } 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 e886d1332a1..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" @@ -288,7 +289,7 @@ static int create_image(int platform_mode) * hibernation_snapshot - quiesce devices and create the hibernation * snapshot image. * @platform_mode - if set, use the platform driver, if available, to - * prepare the platform frimware for the power transition. + * prepare the platform firmware for the power transition. * * Must be called with pm_mutex held */ @@ -411,7 +412,7 @@ static int resume_target_kernel(bool platform_mode) * hibernation_restore - quiesce devices and restore the hibernation * snapshot image. If successful, control returns in hibernation_snaphot() * @platform_mode - if set, use the platform driver, if available, to - * prepare the platform frimware for the transition. + * prepare the platform firmware for the transition. * * Must be called with pm_mutex held */ 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..5052b5497c6 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); @@ -1292,8 +1311,11 @@ EXPORT_SYMBOL(printk_ratelimit); bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { - if (*caller_jiffies == 0 || time_after(jiffies, *caller_jiffies)) { - *caller_jiffies = jiffies + msecs_to_jiffies(interval_msecs); + if (*caller_jiffies == 0 + || !time_in_range(jiffies, *caller_jiffies, + *caller_jiffies + + msecs_to_jiffies(interval_msecs))) { + *caller_jiffies = jiffies; return true; } return false; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index c9cf48b21f0..aaad0ec3419 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; @@ -612,8 +687,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); - if (ret < 0) - goto out_put_task_struct; out_put_task_struct: put_task_struct(child); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index cae8a059cf4..2c7b8457d0d 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -122,6 +122,8 @@ static void rcu_barrier_func(void *type) } } +static inline void wait_migrated_callbacks(void); + /* * Orchestrate the specified type of RCU barrier, waiting for all * RCU callbacks of the specified type to complete. @@ -147,6 +149,7 @@ static void _rcu_barrier(enum rcu_barrier type) complete(&rcu_barrier_completion); wait_for_completion(&rcu_barrier_completion); mutex_unlock(&rcu_barrier_mutex); + wait_migrated_callbacks(); } /** @@ -176,9 +179,50 @@ void rcu_barrier_sched(void) } EXPORT_SYMBOL_GPL(rcu_barrier_sched); +static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0); +static struct rcu_head rcu_migrate_head[3]; +static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq); + +static void rcu_migrate_callback(struct rcu_head *notused) +{ + if (atomic_dec_and_test(&rcu_migrate_type_count)) + wake_up(&rcu_migrate_wq); +} + +static inline void wait_migrated_callbacks(void) +{ + wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count)); +} + +static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + if (action == CPU_DYING) { + /* + * preempt_disable() in on_each_cpu() prevents stop_machine(), + * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);" + * returns, all online cpus have queued rcu_barrier_func(), + * and the dead cpu(if it exist) queues rcu_migrate_callback()s. + * + * These callbacks ensure _rcu_barrier() waits for all + * RCU callbacks of the specified type to complete. + */ + atomic_set(&rcu_migrate_type_count, 3); + call_rcu_bh(rcu_migrate_head, rcu_migrate_callback); + call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback); + call_rcu(rcu_migrate_head + 2, rcu_migrate_callback); + } else if (action == CPU_POST_DEAD) { + /* rcu_migrate_head is protected by cpu_add_remove_lock */ + wait_migrated_callbacks(); + } + + return NOTIFY_OK; +} + void __init rcu_init(void) { __rcu_init(); + hotcpu_notifier(rcu_barrier_cpu_hotplug, 0); } void rcu_scheduler_starting(void) 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 196d48babbe..2325db2be31 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1110,7 +1110,7 @@ static void hrtick_start(struct rq *rq, u64 delay) if (rq == this_rq()) { hrtimer_restart(timer); } else if (!rq->hrtick_csd_pending) { - __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd); + __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); rq->hrtick_csd_pending = 1; } } @@ -5196,11 +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 @@ -5209,8 +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; @@ -5222,9 +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/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/smp.c b/kernel/smp.c index bbedbb7efe3..858baac568e 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -2,40 +2,82 @@ * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 - * */ -#include <linux/init.h> -#include <linux/module.h> -#include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/rculist.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/init.h> #include <linux/smp.h> +#include <linux/cpu.h> static DEFINE_PER_CPU(struct call_single_queue, call_single_queue); -static LIST_HEAD(call_function_queue); -__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock); + +static struct { + struct list_head queue; + spinlock_t lock; +} call_function __cacheline_aligned_in_smp = + { + .queue = LIST_HEAD_INIT(call_function.queue), + .lock = __SPIN_LOCK_UNLOCKED(call_function.lock), + }; enum { - CSD_FLAG_WAIT = 0x01, - CSD_FLAG_ALLOC = 0x02, - CSD_FLAG_LOCK = 0x04, + CSD_FLAG_LOCK = 0x01, }; struct call_function_data { - struct call_single_data csd; - spinlock_t lock; - unsigned int refs; - struct rcu_head rcu_head; - unsigned long cpumask_bits[]; + struct call_single_data csd; + spinlock_t lock; + unsigned int refs; + cpumask_var_t cpumask; }; struct call_single_queue { - struct list_head list; - spinlock_t lock; + struct list_head list; + spinlock_t lock; +}; + +static DEFINE_PER_CPU(struct call_function_data, cfd_data) = { + .lock = __SPIN_LOCK_UNLOCKED(cfd_data.lock), +}; + +static int +hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + struct call_function_data *cfd = &per_cpu(cfd_data, cpu); + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (!alloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, + cpu_to_node(cpu))) + return NOTIFY_BAD; + break; + +#ifdef CONFIG_CPU_HOTPLUG + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + free_cpumask_var(cfd->cpumask); + break; +#endif + }; + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata hotplug_cfd_notifier = { + .notifier_call = hotplug_cfd, }; static int __cpuinit init_call_single_data(void) { + void *cpu = (void *)(long)smp_processor_id(); int i; for_each_possible_cpu(i) { @@ -44,29 +86,63 @@ static int __cpuinit init_call_single_data(void) spin_lock_init(&q->lock); INIT_LIST_HEAD(&q->list); } + + hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); + register_cpu_notifier(&hotplug_cfd_notifier); + return 0; } early_initcall(init_call_single_data); -static void csd_flag_wait(struct call_single_data *data) +/* + * csd_lock/csd_unlock used to serialize access to per-cpu csd resources + * + * For non-synchronous ipi calls the csd can still be in use by the + * previous function call. For multi-cpu calls its even more interesting + * as we'll have to ensure no other cpu is observing our csd. + */ +static void csd_lock_wait(struct call_single_data *data) { - /* Wait for response */ - do { - if (!(data->flags & CSD_FLAG_WAIT)) - break; + while (data->flags & CSD_FLAG_LOCK) cpu_relax(); - } while (1); +} + +static void csd_lock(struct call_single_data *data) +{ + csd_lock_wait(data); + data->flags = CSD_FLAG_LOCK; + + /* + * prevent CPU from reordering the above assignment + * to ->flags with any subsequent assignments to other + * fields of the specified call_single_data structure: + */ + smp_mb(); +} + +static void csd_unlock(struct call_single_data *data) +{ + WARN_ON(!(data->flags & CSD_FLAG_LOCK)); + + /* + * ensure we're all done before releasing data: + */ + smp_mb(); + + data->flags &= ~CSD_FLAG_LOCK; } /* - * Insert a previously allocated call_single_data element for execution - * on the given CPU. data must already have ->func, ->info, and ->flags set. + * Insert a previously allocated call_single_data element + * for execution on the given CPU. data must already have + * ->func, ->info, and ->flags set. */ -static void generic_exec_single(int cpu, struct call_single_data *data) +static +void generic_exec_single(int cpu, struct call_single_data *data, int wait) { struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); - int wait = data->flags & CSD_FLAG_WAIT, ipi; unsigned long flags; + int ipi; spin_lock_irqsave(&dst->lock, flags); ipi = list_empty(&dst->list); @@ -74,24 +150,21 @@ static void generic_exec_single(int cpu, struct call_single_data *data) spin_unlock_irqrestore(&dst->lock, flags); /* - * Make the list addition visible before sending the ipi. + * The list addition should be visible before sending the IPI + * handler locks the list to pull the entry off it because of + * normal cache coherency rules implied by spinlocks. + * + * If IPIs can go out of order to the cache coherency protocol + * in an architecture, sufficient synchronisation should be added + * to arch code to make it appear to obey cache coherency WRT + * locking and barrier primitives. Generic code isn't really + * equipped to do the right thing... */ - smp_mb(); - if (ipi) arch_send_call_function_single_ipi(cpu); if (wait) - csd_flag_wait(data); -} - -static void rcu_free_call_data(struct rcu_head *head) -{ - struct call_function_data *data; - - data = container_of(head, struct call_function_data, rcu_head); - - kfree(data); + csd_lock_wait(data); } /* @@ -104,99 +177,83 @@ void generic_smp_call_function_interrupt(void) int cpu = get_cpu(); /* - * It's ok to use list_for_each_rcu() here even though we may delete - * 'pos', since list_del_rcu() doesn't clear ->next + * Ensure entry is visible on call_function_queue after we have + * entered the IPI. See comment in smp_call_function_many. + * If we don't have this, then we may miss an entry on the list + * and never get another IPI to process it. + */ + smp_mb(); + + /* + * It's ok to use list_for_each_rcu() here even though we may + * delete 'pos', since list_del_rcu() doesn't clear ->next */ - rcu_read_lock(); - list_for_each_entry_rcu(data, &call_function_queue, csd.list) { + list_for_each_entry_rcu(data, &call_function.queue, csd.list) { int refs; - if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits))) + spin_lock(&data->lock); + if (!cpumask_test_cpu(cpu, data->cpumask)) { + spin_unlock(&data->lock); continue; + } + cpumask_clear_cpu(cpu, data->cpumask); + spin_unlock(&data->lock); data->csd.func(data->csd.info); spin_lock(&data->lock); - cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits)); WARN_ON(data->refs == 0); - data->refs--; - refs = data->refs; + refs = --data->refs; + if (!refs) { + spin_lock(&call_function.lock); + list_del_rcu(&data->csd.list); + spin_unlock(&call_function.lock); + } spin_unlock(&data->lock); if (refs) continue; - spin_lock(&call_function_lock); - list_del_rcu(&data->csd.list); - spin_unlock(&call_function_lock); - - if (data->csd.flags & CSD_FLAG_WAIT) { - /* - * serialize stores to data with the flag clear - * and wakeup - */ - smp_wmb(); - data->csd.flags &= ~CSD_FLAG_WAIT; - } - if (data->csd.flags & CSD_FLAG_ALLOC) - call_rcu(&data->rcu_head, rcu_free_call_data); + csd_unlock(&data->csd); } - rcu_read_unlock(); put_cpu(); } /* - * Invoked by arch to handle an IPI for call function single. Must be called - * from the arch with interrupts disabled. + * Invoked by arch to handle an IPI for call function single. Must be + * called from the arch with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { struct call_single_queue *q = &__get_cpu_var(call_single_queue); + unsigned int data_flags; LIST_HEAD(list); - /* - * Need to see other stores to list head for checking whether - * list is empty without holding q->lock - */ - smp_read_barrier_depends(); - while (!list_empty(&q->list)) { - unsigned int data_flags; - - spin_lock(&q->lock); - list_replace_init(&q->list, &list); - spin_unlock(&q->lock); - - while (!list_empty(&list)) { - struct call_single_data *data; - - data = list_entry(list.next, struct call_single_data, - list); - list_del(&data->list); - - /* - * 'data' can be invalid after this call if - * flags == 0 (when called through - * generic_exec_single(), so save them away before - * making the call. - */ - data_flags = data->flags; - - data->func(data->info); - - if (data_flags & CSD_FLAG_WAIT) { - smp_wmb(); - data->flags &= ~CSD_FLAG_WAIT; - } else if (data_flags & CSD_FLAG_LOCK) { - smp_wmb(); - data->flags &= ~CSD_FLAG_LOCK; - } else if (data_flags & CSD_FLAG_ALLOC) - kfree(data); - } + spin_lock(&q->lock); + list_replace_init(&q->list, &list); + spin_unlock(&q->lock); + + while (!list_empty(&list)) { + struct call_single_data *data; + + data = list_entry(list.next, struct call_single_data, list); + list_del(&data->list); + + /* + * 'data' can be invalid after this call if flags == 0 + * (when called through generic_exec_single()), + * so save them away before making the call: + */ + data_flags = data->flags; + + data->func(data->info); + /* - * See comment on outer loop + * Unlocked CSDs are valid through generic_exec_single(): */ - smp_read_barrier_depends(); + if (data_flags & CSD_FLAG_LOCK) + csd_unlock(data); } } @@ -215,65 +272,45 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data); int smp_call_function_single(int cpu, void (*func) (void *info), void *info, int wait) { - struct call_single_data d; + struct call_single_data d = { + .flags = 0, + }; unsigned long flags; - /* prevent preemption and reschedule on another processor, - as well as CPU removal */ - int me = get_cpu(); + int this_cpu; int err = 0; + /* + * prevent preemption and reschedule on another processor, + * as well as CPU removal + */ + this_cpu = get_cpu(); + /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); + WARN_ON_ONCE(irqs_disabled() && !oops_in_progress); - if (cpu == me) { + if (cpu == this_cpu) { local_irq_save(flags); func(info); local_irq_restore(flags); - } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { - struct call_single_data *data; + } else { + if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { + struct call_single_data *data = &d; + + if (!wait) + data = &__get_cpu_var(csd_data); - if (!wait) { - /* - * We are calling a function on a single CPU - * and we are not going to wait for it to finish. - * We first try to allocate the data, but if we - * fail, we fall back to use a per cpu data to pass - * the information to that CPU. Since all callers - * of this code will use the same data, we must - * synchronize the callers to prevent a new caller - * from corrupting the data before the callee - * can access it. - * - * The CSD_FLAG_LOCK is used to let us know when - * the IPI handler is done with the data. - * The first caller will set it, and the callee - * will clear it. The next caller must wait for - * it to clear before we set it again. This - * will make sure the callee is done with the - * data before a new caller will use it. - */ - data = kmalloc(sizeof(*data), GFP_ATOMIC); - if (data) - data->flags = CSD_FLAG_ALLOC; - else { - data = &per_cpu(csd_data, me); - while (data->flags & CSD_FLAG_LOCK) - cpu_relax(); - data->flags = CSD_FLAG_LOCK; - } + csd_lock(data); + + data->func = func; + data->info = info; + generic_exec_single(cpu, data, wait); } else { - data = &d; - data->flags = CSD_FLAG_WAIT; + err = -ENXIO; /* CPU not online */ } - - data->func = func; - data->info = info; - generic_exec_single(cpu, data); - } else { - err = -ENXIO; /* CPU not online */ } put_cpu(); + return err; } EXPORT_SYMBOL(smp_call_function_single); @@ -283,23 +320,26 @@ EXPORT_SYMBOL(smp_call_function_single); * @cpu: The CPU to run on. * @data: Pre-allocated and setup data structure * - * Like smp_call_function_single(), but allow caller to pass in a pre-allocated - * data structure. Useful for embedding @data inside other structures, for - * instance. - * + * Like smp_call_function_single(), but allow caller to pass in a + * pre-allocated data structure. Useful for embedding @data inside + * other structures, for instance. */ -void __smp_call_function_single(int cpu, struct call_single_data *data) +void __smp_call_function_single(int cpu, struct call_single_data *data, + int wait) { + csd_lock(data); + /* Can deadlock when called with interrupts disabled */ - WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled()); + WARN_ON_ONCE(wait && irqs_disabled() && !oops_in_progress); - generic_exec_single(cpu, data); + generic_exec_single(cpu, data, wait); } -/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */ +/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */ + #ifndef arch_send_call_function_ipi_mask -#define arch_send_call_function_ipi_mask(maskp) \ - arch_send_call_function_ipi(*(maskp)) +# define arch_send_call_function_ipi_mask(maskp) \ + arch_send_call_function_ipi(*(maskp)) #endif /** @@ -307,7 +347,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data) * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed on other CPUs. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. * * If @wait is true, then returns once @func has returned. Note that @wait * will be implicitly turned on in case of allocation failures, since @@ -318,27 +359,27 @@ void __smp_call_function_single(int cpu, struct call_single_data *data) * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, - void (*func)(void *), void *info, - bool wait) + void (*func)(void *), void *info, bool wait) { struct call_function_data *data; unsigned long flags; - int cpu, next_cpu; + int cpu, next_cpu, this_cpu = smp_processor_id(); /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); + WARN_ON_ONCE(irqs_disabled() && !oops_in_progress); - /* So, what's a CPU they want? Ignoring this one. */ + /* So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); - if (cpu == smp_processor_id()) + if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); + /* No online cpus? We're done. */ if (cpu >= nr_cpu_ids) return; /* Do we have another CPU which isn't us? */ next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); - if (next_cpu == smp_processor_id()) + if (next_cpu == this_cpu) next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); /* Fastpath: do that cpu by itself. */ @@ -347,43 +388,40 @@ void smp_call_function_many(const struct cpumask *mask, return; } - data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC); - if (unlikely(!data)) { - /* Slow path. */ - for_each_online_cpu(cpu) { - if (cpu == smp_processor_id()) - continue; - if (cpumask_test_cpu(cpu, mask)) - smp_call_function_single(cpu, func, info, wait); - } - return; - } + data = &__get_cpu_var(cfd_data); + csd_lock(&data->csd); - spin_lock_init(&data->lock); - data->csd.flags = CSD_FLAG_ALLOC; - if (wait) - data->csd.flags |= CSD_FLAG_WAIT; + spin_lock_irqsave(&data->lock, flags); data->csd.func = func; data->csd.info = info; - cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits)); - data->refs = cpumask_weight(to_cpumask(data->cpumask_bits)); + cpumask_and(data->cpumask, mask, cpu_online_mask); + cpumask_clear_cpu(this_cpu, data->cpumask); + data->refs = cpumask_weight(data->cpumask); - spin_lock_irqsave(&call_function_lock, flags); - list_add_tail_rcu(&data->csd.list, &call_function_queue); - spin_unlock_irqrestore(&call_function_lock, flags); + spin_lock(&call_function.lock); + /* + * Place entry at the _HEAD_ of the list, so that any cpu still + * observing the entry in generic_smp_call_function_interrupt() + * will not miss any other list entries: + */ + list_add_rcu(&data->csd.list, &call_function.queue); + spin_unlock(&call_function.lock); + + spin_unlock_irqrestore(&data->lock, flags); /* * Make the list addition visible before sending the ipi. + * (IPIs must obey or appear to obey normal Linux cache + * coherency rules -- see comment in generic_exec_single). */ smp_mb(); /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits)); + arch_send_call_function_ipi_mask(data->cpumask); - /* optionally wait for the CPUs to complete */ + /* Optionally wait for the CPUs to complete */ if (wait) - csd_flag_wait(&data->csd); + csd_lock_wait(&data->csd); } EXPORT_SYMBOL(smp_call_function_many); @@ -391,7 +429,8 @@ EXPORT_SYMBOL(smp_call_function_many); * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed on other CPUs. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. * * Returns 0. * @@ -407,26 +446,27 @@ int smp_call_function(void (*func)(void *), void *info, int wait) preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); + return 0; } EXPORT_SYMBOL(smp_call_function); void ipi_call_lock(void) { - spin_lock(&call_function_lock); + spin_lock(&call_function.lock); } void ipi_call_unlock(void) { - spin_unlock(&call_function_lock); + spin_unlock(&call_function.lock); } void ipi_call_lock_irq(void) { - spin_lock_irq(&call_function_lock); + spin_lock_irq(&call_function.lock); } void ipi_call_unlock_irq(void) { - spin_unlock_irq(&call_function_lock); + spin_unlock_irq(&call_function.lock); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 57d3f67f6f3..ea23ec087ee 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -180,7 +180,7 @@ asmlinkage void __do_softirq(void) account_system_vtime(current); __local_bh_disable((unsigned long)__builtin_return_address(0)); - trace_softirq_enter(); + lockdep_softirq_enter(); cpu = smp_processor_id(); restart: @@ -220,7 +220,7 @@ restart: if (pending) wakeup_softirqd(); - trace_softirq_exit(); + lockdep_softirq_exit(); account_system_vtime(current); _local_bh_enable(); @@ -496,7 +496,7 @@ static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softir cp->flags = 0; cp->priv = softirq; - __smp_call_function_single(cpu, cp); + __smp_call_function_single(cpu, cp, 0); return 0; } return 1; 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/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/trace/Kconfig b/kernel/trace/Kconfig index 34e707e5ab8..504086ab444 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -72,11 +72,10 @@ config FUNCTION_GRAPH_TRACER help Enable the kernel to trace a function at both its return and its entry. - It's first purpose is to trace the duration of functions and - draw a call graph for each thread with some informations like - the return value. - This is done by setting the current return address on the current - task structure into a stack of calls. + Its first purpose is to trace the duration of functions and + draw a call graph for each thread with some information like + the return value. This is done by setting the current return + address on the current task structure into a stack of calls. config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fdf913dfc7e..53e8c8bc0c9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1908,7 +1908,7 @@ int register_ftrace_function(struct ftrace_ops *ops) } /** - * unregister_ftrace_function - unresgister a function for profiling. + * unregister_ftrace_function - unregister a function for profiling. * @ops - ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. 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 9aedd9fd825..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; } |