diff options
Diffstat (limited to 'kernel')
97 files changed, 6804 insertions, 4804 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 2251882daf5..44511d100ea 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -87,6 +87,9 @@ config ARCH_INLINE_WRITE_UNLOCK_IRQ config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE bool +config UNINLINE_SPIN_UNLOCK + bool + # # lock_* functions are inlined when: # - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y @@ -103,100 +106,120 @@ config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE # - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y # +if !DEBUG_SPINLOCK + config INLINE_SPIN_TRYLOCK - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK + def_bool y + depends on ARCH_INLINE_SPIN_TRYLOCK config INLINE_SPIN_TRYLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH + def_bool y + depends on ARCH_INLINE_SPIN_TRYLOCK_BH config INLINE_SPIN_LOCK - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK config INLINE_SPIN_LOCK_BH - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_SPIN_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_BH config INLINE_SPIN_LOCK_IRQ - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_SPIN_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQ config INLINE_SPIN_LOCK_IRQSAVE - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_SPIN_LOCK_IRQSAVE - -config UNINLINE_SPIN_UNLOCK - bool + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQSAVE config INLINE_SPIN_UNLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_SPIN_UNLOCK_BH config INLINE_SPIN_UNLOCK_IRQ - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH) + def_bool y + depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH config INLINE_SPIN_UNLOCK_IRQRESTORE - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE config INLINE_READ_TRYLOCK - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK + def_bool y + depends on ARCH_INLINE_READ_TRYLOCK config INLINE_READ_LOCK - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK config INLINE_READ_LOCK_BH - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_READ_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_BH config INLINE_READ_LOCK_IRQ - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_READ_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQ config INLINE_READ_LOCK_IRQSAVE - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_READ_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQSAVE config INLINE_READ_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK) + def_bool y + depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK config INLINE_READ_UNLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_READ_UNLOCK_BH config INLINE_READ_UNLOCK_IRQ - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH) + def_bool y + depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_BH config INLINE_READ_UNLOCK_IRQRESTORE - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_READ_UNLOCK_IRQRESTORE config INLINE_WRITE_TRYLOCK - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK + def_bool y + depends on ARCH_INLINE_WRITE_TRYLOCK config INLINE_WRITE_LOCK - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK config INLINE_WRITE_LOCK_BH - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_WRITE_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_BH config INLINE_WRITE_LOCK_IRQ - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_WRITE_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQ config INLINE_WRITE_LOCK_IRQSAVE - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_WRITE_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQSAVE config INLINE_WRITE_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK) + def_bool y + depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK config INLINE_WRITE_UNLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_WRITE_UNLOCK_BH config INLINE_WRITE_UNLOCK_IRQ - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH) + def_bool y + depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH config INLINE_WRITE_UNLOCK_IRQRESTORE - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + +endif config MUTEX_SPIN_ON_OWNER - def_bool SMP && !DEBUG_MUTEXES + def_bool y + depends on SMP && !DEBUG_MUTEXES diff --git a/kernel/Makefile b/kernel/Makefile index c0cc67ad764..5404911eaee 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -10,7 +10,7 @@ obj-y = fork.o exec_domain.o panic.o printk.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o cred.o \ - async.o range.o groups.o lglock.o + async.o range.o groups.o lglock.o smpboot.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files @@ -46,7 +46,6 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_SMP) += smpboot.o ifneq ($(CONFIG_SMP),y) obj-y += up.o endif @@ -98,7 +97,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ -obj-$(CONFIG_X86_DS) += trace/ +obj-$(CONFIG_TRACE_CLOCK) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_IRQ_WORK) += irq_work.o diff --git a/kernel/async.c b/kernel/async.c index bd0c168a3bb..9d311838485 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -62,8 +62,10 @@ static async_cookie_t next_cookie = 1; #define MAX_WORK 32768 static LIST_HEAD(async_pending); -static LIST_HEAD(async_running); +static ASYNC_DOMAIN(async_running); +static LIST_HEAD(async_domains); static DEFINE_SPINLOCK(async_lock); +static DEFINE_MUTEX(async_register_mutex); struct async_entry { struct list_head list; @@ -71,7 +73,7 @@ struct async_entry { async_cookie_t cookie; async_func_ptr *func; void *data; - struct list_head *running; + struct async_domain *running; }; static DECLARE_WAIT_QUEUE_HEAD(async_done); @@ -82,13 +84,12 @@ static atomic_t entry_count; /* * MUST be called with the lock held! */ -static async_cookie_t __lowest_in_progress(struct list_head *running) +static async_cookie_t __lowest_in_progress(struct async_domain *running) { struct async_entry *entry; - if (!list_empty(running)) { - entry = list_first_entry(running, - struct async_entry, list); + if (!list_empty(&running->domain)) { + entry = list_first_entry(&running->domain, typeof(*entry), list); return entry->cookie; } @@ -99,7 +100,7 @@ static async_cookie_t __lowest_in_progress(struct list_head *running) return next_cookie; /* "infinity" value */ } -static async_cookie_t lowest_in_progress(struct list_head *running) +static async_cookie_t lowest_in_progress(struct async_domain *running) { unsigned long flags; async_cookie_t ret; @@ -119,10 +120,11 @@ static void async_run_entry_fn(struct work_struct *work) container_of(work, struct async_entry, work); unsigned long flags; ktime_t uninitialized_var(calltime), delta, rettime; + struct async_domain *running = entry->running; /* 1) move self to the running queue */ spin_lock_irqsave(&async_lock, flags); - list_move_tail(&entry->list, entry->running); + list_move_tail(&entry->list, &running->domain); spin_unlock_irqrestore(&async_lock, flags); /* 2) run (and print duration) */ @@ -145,6 +147,8 @@ static void async_run_entry_fn(struct work_struct *work) /* 3) remove self from the running queue */ spin_lock_irqsave(&async_lock, flags); list_del(&entry->list); + if (running->registered && --running->count == 0) + list_del_init(&running->node); /* 4) free the entry */ kfree(entry); @@ -156,7 +160,7 @@ static void async_run_entry_fn(struct work_struct *work) wake_up(&async_done); } -static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running) +static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct async_domain *running) { struct async_entry *entry; unsigned long flags; @@ -187,6 +191,8 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l spin_lock_irqsave(&async_lock, flags); newcookie = entry->cookie = next_cookie++; list_add_tail(&entry->list, &async_pending); + if (running->registered && running->count++ == 0) + list_add_tail(&running->node, &async_domains); atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); @@ -223,7 +229,7 @@ EXPORT_SYMBOL_GPL(async_schedule); * Note: This function may be called from atomic or non-atomic contexts. */ async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data, - struct list_head *running) + struct async_domain *running) { return __async_schedule(ptr, data, running); } @@ -236,22 +242,52 @@ EXPORT_SYMBOL_GPL(async_schedule_domain); */ void async_synchronize_full(void) { + mutex_lock(&async_register_mutex); do { - async_synchronize_cookie(next_cookie); - } while (!list_empty(&async_running) || !list_empty(&async_pending)); + struct async_domain *domain = NULL; + + spin_lock_irq(&async_lock); + if (!list_empty(&async_domains)) + domain = list_first_entry(&async_domains, typeof(*domain), node); + spin_unlock_irq(&async_lock); + + async_synchronize_cookie_domain(next_cookie, domain); + } while (!list_empty(&async_domains)); + mutex_unlock(&async_register_mutex); } EXPORT_SYMBOL_GPL(async_synchronize_full); /** + * async_unregister_domain - ensure no more anonymous waiters on this domain + * @domain: idle domain to flush out of any async_synchronize_full instances + * + * async_synchronize_{cookie|full}_domain() are not flushed since callers + * of these routines should know the lifetime of @domain + * + * Prefer ASYNC_DOMAIN_EXCLUSIVE() declarations over flushing + */ +void async_unregister_domain(struct async_domain *domain) +{ + mutex_lock(&async_register_mutex); + spin_lock_irq(&async_lock); + WARN_ON(!domain->registered || !list_empty(&domain->node) || + !list_empty(&domain->domain)); + domain->registered = 0; + spin_unlock_irq(&async_lock); + mutex_unlock(&async_register_mutex); +} +EXPORT_SYMBOL_GPL(async_unregister_domain); + +/** * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain - * @list: running list to synchronize on + * @domain: running list to synchronize on * * This function waits until all asynchronous function calls for the - * synchronization domain specified by the running list @list have been done. + * synchronization domain specified by the running list @domain have been done. */ -void async_synchronize_full_domain(struct list_head *list) +void async_synchronize_full_domain(struct async_domain *domain) { - async_synchronize_cookie_domain(next_cookie, list); + async_synchronize_cookie_domain(next_cookie, domain); } EXPORT_SYMBOL_GPL(async_synchronize_full_domain); @@ -261,14 +297,16 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain); * @running: running list to synchronize on * * This function waits until all asynchronous function calls for the - * synchronization domain specified by the running list @list submitted + * synchronization domain specified by running list @running submitted * prior to @cookie have been done. */ -void async_synchronize_cookie_domain(async_cookie_t cookie, - struct list_head *running) +void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *running) { ktime_t uninitialized_var(starttime), delta, endtime; + if (!running) + return; + if (initcall_debug && system_state == SYSTEM_BOOTING) { printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); diff --git a/kernel/audit.c b/kernel/audit.c index 1c7f2c61416..ea3b7b6191c 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -384,7 +384,7 @@ static void audit_hold_skb(struct sk_buff *skb) static void audit_printk_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - char *data = NLMSG_DATA(nlh); + char *data = nlmsg_data(nlh); if (nlh->nlmsg_type != AUDIT_EOE) { if (printk_ratelimit()) @@ -516,14 +516,15 @@ struct sk_buff *audit_make_reply(int pid, int seq, int type, int done, if (!skb) return NULL; - nlh = NLMSG_NEW(skb, pid, seq, t, size, flags); - data = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, t, size, flags); + if (!nlh) + goto out_kfree_skb; + data = nlmsg_data(nlh); memcpy(data, payload, size); return skb; -nlmsg_failure: /* Used by NLMSG_NEW */ - if (skb) - kfree_skb(skb); +out_kfree_skb: + kfree_skb(skb); return NULL; } @@ -680,7 +681,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sessionid = audit_get_sessionid(current); security_task_getsecid(current, &sid); seq = nlh->nlmsg_seq; - data = NLMSG_DATA(nlh); + data = nlmsg_data(nlh); switch (msg_type) { case AUDIT_GET: @@ -961,14 +962,17 @@ static void audit_receive(struct sk_buff *skb) static int __init audit_init(void) { int i; + struct netlink_kernel_cfg cfg = { + .input = audit_receive, + }; if (audit_initialized == AUDIT_DISABLED) return 0; printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); - audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0, - audit_receive, NULL, THIS_MODULE); + audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, + THIS_MODULE, &cfg); if (!audit_sock) audit_panic("cannot initialize netlink socket"); else @@ -1060,13 +1064,15 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx, ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); if (!ab->skb) - goto nlmsg_failure; + goto err; - nlh = NLMSG_NEW(ab->skb, 0, 0, type, 0, 0); + nlh = nlmsg_put(ab->skb, 0, 0, type, 0, 0); + if (!nlh) + goto out_kfree_skb; return ab; -nlmsg_failure: /* Used by NLMSG_NEW */ +out_kfree_skb: kfree_skb(ab->skb); ab->skb = NULL; err: @@ -1450,6 +1456,27 @@ void audit_log_key(struct audit_buffer *ab, char *key) } /** + * audit_log_link_denied - report a link restriction denial + * @operation: specific link opreation + * @link: the path that triggered the restriction + */ +void audit_log_link_denied(const char *operation, struct path *link) +{ + struct audit_buffer *ab; + + ab = audit_log_start(current->audit_context, GFP_KERNEL, + AUDIT_ANOM_LINK); + audit_log_format(ab, "op=%s action=denied", operation); + audit_log_format(ab, " pid=%d comm=", current->pid); + audit_log_untrustedstring(ab, current->comm); + audit_log_d_path(ab, " path=", link); + audit_log_format(ab, " dev="); + audit_log_untrustedstring(ab, link->dentry->d_inode->i_sb->s_id); + audit_log_format(ab, " ino=%lu", link->dentry->d_inode->i_ino); + audit_log_end(ab); +} + +/** * audit_log_end - end one audit record * @ab: the audit_buffer * diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 5bf0790497e..ed206fd88cc 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -250,7 +250,6 @@ static void untag_chunk(struct node *p) spin_unlock(&hash_lock); spin_unlock(&entry->lock); fsnotify_destroy_mark(entry); - fsnotify_put_mark(entry); goto out; } @@ -259,7 +258,7 @@ static void untag_chunk(struct node *p) fsnotify_duplicate_mark(&new->mark, entry); if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) { - free_chunk(new); + fsnotify_put_mark(&new->mark); goto Fallback; } @@ -293,7 +292,7 @@ static void untag_chunk(struct node *p) spin_unlock(&hash_lock); spin_unlock(&entry->lock); fsnotify_destroy_mark(entry); - fsnotify_put_mark(entry); + fsnotify_put_mark(&new->mark); /* drop initial reference */ goto out; Fallback: @@ -322,7 +321,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) entry = &chunk->mark; if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) { - free_chunk(chunk); + fsnotify_put_mark(entry); return -ENOSPC; } @@ -347,6 +346,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) insert_hash(chunk); spin_unlock(&hash_lock); spin_unlock(&entry->lock); + fsnotify_put_mark(entry); /* drop initial reference */ return 0; } @@ -396,7 +396,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) fsnotify_duplicate_mark(chunk_entry, old_entry); if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->i.inode, NULL, 1)) { spin_unlock(&old_entry->lock); - free_chunk(chunk); + fsnotify_put_mark(chunk_entry); fsnotify_put_mark(old_entry); return -ENOSPC; } @@ -444,8 +444,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) spin_unlock(&chunk_entry->lock); spin_unlock(&old_entry->lock); fsnotify_destroy_mark(old_entry); + fsnotify_put_mark(chunk_entry); /* drop initial reference */ fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */ - fsnotify_put_mark(old_entry); /* and kill it */ return 0; } @@ -595,7 +595,7 @@ void audit_trim_trees(void) root_mnt = collect_mounts(&path); path_put(&path); - if (!root_mnt) + if (IS_ERR(root_mnt)) goto skip_it; spin_lock(&hash_lock); @@ -669,8 +669,8 @@ int audit_add_tree_rule(struct audit_krule *rule) goto Err; mnt = collect_mounts(&path); path_put(&path); - if (!mnt) { - err = -ENOMEM; + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); goto Err; } @@ -719,8 +719,8 @@ int audit_tag_tree(char *old, char *new) return err; tagged = collect_mounts(&path2); path_put(&path2); - if (!tagged) - return -ENOMEM; + if (IS_ERR(tagged)) + return PTR_ERR(tagged); err = kern_path(old, 0, &path1); if (err) { @@ -916,7 +916,12 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify struct audit_chunk *chunk = container_of(entry, struct audit_chunk, mark); evict_chunk(chunk); - fsnotify_put_mark(entry); + + /* + * We are guaranteed to have at least one reference to the mark from + * either the inode or the caller of fsnotify_destroy_mark(). + */ + BUG_ON(atomic_read(&entry->refcnt) < 1); } static bool audit_tree_send_event(struct fsnotify_group *group, struct inode *inode, diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index e683869365d..3823281401b 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -355,34 +355,15 @@ static void audit_remove_parent_watches(struct audit_parent *parent) /* Get path information necessary for adding watches. */ static int audit_get_nd(struct audit_watch *watch, struct path *parent) { - struct nameidata nd; - struct dentry *d; - int err; - - err = kern_path_parent(watch->path, &nd); - if (err) - return err; - - if (nd.last_type != LAST_NORM) { - path_put(&nd.path); - return -EINVAL; - } - - mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); - d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); - if (IS_ERR(d)) { - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - path_put(&nd.path); + struct dentry *d = kern_path_locked(watch->path, parent); + if (IS_ERR(d)) return PTR_ERR(d); - } + mutex_unlock(&parent->dentry->d_inode->i_mutex); if (d->d_inode) { /* update watch filter fields */ watch->dev = d->d_inode->i_sb->s_dev; watch->ino = d->d_inode->i_ino; } - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - - *parent = nd.path; dput(d); return 0; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b303dfc7dce..79818507e44 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -822,7 +822,7 @@ EXPORT_SYMBOL_GPL(cgroup_unlock); */ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); -static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); static const struct inode_operations cgroup_dir_inode_operations; @@ -954,7 +954,7 @@ static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) dget(d); d_delete(d); - simple_unlink(d->d_inode, d); + simple_unlink(cgrp->dentry->d_inode, d); list_del_init(&cfe->node); dput(d); @@ -1068,28 +1068,24 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]); BUG_ON(!dummytop->subsys[i]); BUG_ON(dummytop->subsys[i]->cgroup != dummytop); - mutex_lock(&ss->hierarchy_mutex); cgrp->subsys[i] = dummytop->subsys[i]; cgrp->subsys[i]->cgroup = cgrp; list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) ss->bind(cgrp); - mutex_unlock(&ss->hierarchy_mutex); /* refcount was already taken, and we're keeping it */ } else if (bit & removed_bits) { /* We're removing this subsystem */ BUG_ON(ss == NULL); BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]); BUG_ON(cgrp->subsys[i]->cgroup != cgrp); - mutex_lock(&ss->hierarchy_mutex); if (ss->bind) ss->bind(dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; subsys[i]->root = &rootnode; list_move(&ss->sibling, &rootnode.subsys_list); - mutex_unlock(&ss->hierarchy_mutex); /* subsystem is now free - drop reference on module */ module_put(ss->module); } else if (bit & final_bits) { @@ -1587,7 +1583,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, opts.new_root = new_root; /* Locate an existing or new sb for this hierarchy */ - sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts); + sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts); if (IS_ERR(sb)) { ret = PTR_ERR(sb); cgroup_drop_root(opts.new_root); @@ -2570,7 +2566,7 @@ static const struct inode_operations cgroup_dir_inode_operations = { .rename = cgroup_rename, }; -static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); @@ -3915,37 +3911,6 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, set_bit(CSS_CLEAR_CSS_REFS, &css->flags); } -static void cgroup_lock_hierarchy(struct cgroupfs_root *root) -{ - /* We need to take each hierarchy_mutex in a consistent order */ - int i; - - /* - * No worry about a race with rebind_subsystems that might mess up the - * locking order, since both parties are under cgroup_mutex. - */ - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup_subsys *ss = subsys[i]; - if (ss == NULL) - continue; - if (ss->root == root) - mutex_lock(&ss->hierarchy_mutex); - } -} - -static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) -{ - int i; - - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup_subsys *ss = subsys[i]; - if (ss == NULL) - continue; - if (ss->root == root) - mutex_unlock(&ss->hierarchy_mutex); - } -} - /* * cgroup_create - create a cgroup * @parent: cgroup that will be parent of the new cgroup @@ -4006,9 +3971,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, ss->post_clone(cgrp); } - cgroup_lock_hierarchy(root); list_add(&cgrp->sibling, &cgrp->parent->children); - cgroup_unlock_hierarchy(root); root->number_of_cgroups++; err = cgroup_create_dir(cgrp, dentry, mode); @@ -4035,9 +3998,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, err_remove: - cgroup_lock_hierarchy(root); list_del(&cgrp->sibling); - cgroup_unlock_hierarchy(root); root->number_of_cgroups--; err_destroy: @@ -4245,10 +4206,8 @@ again: list_del_init(&cgrp->release_list); raw_spin_unlock(&release_list_lock); - cgroup_lock_hierarchy(cgrp->root); /* delete this cgroup from parent->children */ list_del_init(&cgrp->sibling); - cgroup_unlock_hierarchy(cgrp->root); list_del_init(&cgrp->allcg_node); @@ -4322,8 +4281,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); - mutex_init(&ss->hierarchy_mutex); - lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; /* this function shouldn't be used with modular subsystems, since they @@ -4450,8 +4407,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) } write_unlock(&css_set_lock); - mutex_init(&ss->hierarchy_mutex); - lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; /* success! */ diff --git a/kernel/cpu.c b/kernel/cpu.c index a4eb5227a19..e615dfbcf79 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -280,12 +280,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) __func__, cpu); goto out_release; } + smpboot_park_threads(cpu); err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ + smpboot_unpark_threads(cpu); cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); - goto out_release; } BUG_ON(cpu_online(cpu)); @@ -354,6 +355,10 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out; } + ret = smpboot_create_threads(cpu); + if (ret) + goto out; + ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); if (ret) { nr_calls--; @@ -368,6 +373,9 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); + /* Wake the per cpu threads */ + smpboot_unpark_threads(cpu); + /* Now call notifier in preparation. */ cpu_notify(CPU_ONLINE | mod, hcpu); @@ -416,7 +424,7 @@ int __cpuinit cpu_up(unsigned int cpu) if (pgdat->node_zonelists->_zonerefs->zone == NULL) { mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL); + build_all_zonelists(NULL, NULL); mutex_unlock(&zonelists_mutex); } #endif diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 8c8bd652dd1..f33c7153b6d 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -147,6 +147,12 @@ typedef enum { CS_SPREAD_SLAB, } cpuset_flagbits_t; +/* the type of hotplug event */ +enum hotplug_event { + CPUSET_CPU_OFFLINE, + CPUSET_MEM_OFFLINE, +}; + /* convenient tests for these bits */ static inline int is_cpu_exclusive(const struct cpuset *cs) { @@ -1990,8 +1996,36 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) } /* - * Walk the specified cpuset subtree and look for empty cpusets. - * The tasks of such cpuset must be moved to a parent cpuset. + * Helper function to traverse cpusets. + * It can be used to walk the cpuset tree from top to bottom, completing + * one layer before dropping down to the next (thus always processing a + * node before any of its children). + */ +static struct cpuset *cpuset_next(struct list_head *queue) +{ + struct cpuset *cp; + struct cpuset *child; /* scans child cpusets of cp */ + struct cgroup *cont; + + if (list_empty(queue)) + return NULL; + + cp = list_first_entry(queue, struct cpuset, stack_list); + list_del(queue->next); + list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { + child = cgroup_cs(cont); + list_add_tail(&child->stack_list, queue); + } + + return cp; +} + + +/* + * Walk the specified cpuset subtree upon a hotplug operation (CPU/Memory + * online/offline) and update the cpusets accordingly. + * For regular CPU/Mem hotplug, look for empty cpusets; the tasks of such + * cpuset must be moved to a parent cpuset. * * Called with cgroup_mutex held. We take callback_mutex to modify * cpus_allowed and mems_allowed. @@ -2000,50 +2034,61 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) * before dropping down to the next. It always processes a node before * any of its children. * - * For now, since we lack memory hot unplug, we'll never see a cpuset - * that has tasks along with an empty 'mems'. But if we did see such - * a cpuset, we'd handle it just like we do if its 'cpus' was empty. + * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY + * if all present pages from a node are offlined. */ -static void scan_for_empty_cpusets(struct cpuset *root) +static void +scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event) { LIST_HEAD(queue); - struct cpuset *cp; /* scans cpusets being updated */ - struct cpuset *child; /* scans child cpusets of cp */ - struct cgroup *cont; + struct cpuset *cp; /* scans cpusets being updated */ static nodemask_t oldmems; /* protected by cgroup_mutex */ list_add_tail((struct list_head *)&root->stack_list, &queue); - while (!list_empty(&queue)) { - cp = list_first_entry(&queue, struct cpuset, stack_list); - list_del(queue.next); - list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { - child = cgroup_cs(cont); - list_add_tail(&child->stack_list, &queue); + switch (event) { + case CPUSET_CPU_OFFLINE: + while ((cp = cpuset_next(&queue)) != NULL) { + + /* Continue past cpusets with all cpus online */ + if (cpumask_subset(cp->cpus_allowed, cpu_active_mask)) + continue; + + /* Remove offline cpus from this cpuset. */ + mutex_lock(&callback_mutex); + cpumask_and(cp->cpus_allowed, cp->cpus_allowed, + cpu_active_mask); + mutex_unlock(&callback_mutex); + + /* Move tasks from the empty cpuset to a parent */ + if (cpumask_empty(cp->cpus_allowed)) + remove_tasks_in_empty_cpuset(cp); + else + update_tasks_cpumask(cp, NULL); } + break; - /* Continue past cpusets with all cpus, mems online */ - if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) && - nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) - continue; + case CPUSET_MEM_OFFLINE: + while ((cp = cpuset_next(&queue)) != NULL) { - oldmems = cp->mems_allowed; + /* Continue past cpusets with all mems online */ + if (nodes_subset(cp->mems_allowed, + node_states[N_HIGH_MEMORY])) + continue; - /* Remove offline cpus and mems from this cpuset. */ - mutex_lock(&callback_mutex); - cpumask_and(cp->cpus_allowed, cp->cpus_allowed, - cpu_active_mask); - nodes_and(cp->mems_allowed, cp->mems_allowed, + oldmems = cp->mems_allowed; + + /* Remove offline mems from this cpuset. */ + mutex_lock(&callback_mutex); + nodes_and(cp->mems_allowed, cp->mems_allowed, node_states[N_HIGH_MEMORY]); - mutex_unlock(&callback_mutex); + mutex_unlock(&callback_mutex); - /* Move tasks from the empty cpuset to a parent */ - if (cpumask_empty(cp->cpus_allowed) || - nodes_empty(cp->mems_allowed)) - remove_tasks_in_empty_cpuset(cp); - else { - update_tasks_cpumask(cp, NULL); - update_tasks_nodemask(cp, &oldmems, NULL); + /* Move tasks from the empty cpuset to a parent */ + if (nodes_empty(cp->mems_allowed)) + remove_tasks_in_empty_cpuset(cp); + else + update_tasks_nodemask(cp, &oldmems, NULL); } } } @@ -2054,13 +2099,19 @@ static void scan_for_empty_cpusets(struct cpuset *root) * (of no affect) on systems that are actively using CPU hotplug * but making no active use of cpusets. * + * The only exception to this is suspend/resume, where we don't + * modify cpusets at all. + * * This routine ensures that top_cpuset.cpus_allowed tracks * cpu_active_mask on each CPU hotplug (cpuhp) event. * * Called within get_online_cpus(). Needs to call cgroup_lock() * before calling generate_sched_domains(). + * + * @cpu_online: Indicates whether this is a CPU online event (true) or + * a CPU offline event (false). */ -void cpuset_update_active_cpus(void) +void cpuset_update_active_cpus(bool cpu_online) { struct sched_domain_attr *attr; cpumask_var_t *doms; @@ -2070,7 +2121,10 @@ void cpuset_update_active_cpus(void) mutex_lock(&callback_mutex); cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); mutex_unlock(&callback_mutex); - scan_for_empty_cpusets(&top_cpuset); + + if (!cpu_online) + scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_CPU_OFFLINE); + ndoms = generate_sched_domains(&doms, &attr); cgroup_unlock(); @@ -2082,7 +2136,7 @@ void cpuset_update_active_cpus(void) /* * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY]. * Call this routine anytime after node_states[N_HIGH_MEMORY] changes. - * See also the previous routine cpuset_track_online_cpus(). + * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) @@ -2101,9 +2155,9 @@ static int cpuset_track_online_nodes(struct notifier_block *self, case MEM_OFFLINE: /* * needn't update top_cpuset.mems_allowed explicitly because - * scan_for_empty_cpusets() will update it. + * scan_cpusets_upon_hotplug() will update it. */ - scan_for_empty_cpusets(&top_cpuset); + scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_MEM_OFFLINE); break; default: break; diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c index 8b68ce78ff1..be7b33b73d3 100644 --- a/kernel/debug/kdb/kdb_debugger.c +++ b/kernel/debug/kdb/kdb_debugger.c @@ -12,6 +12,7 @@ #include <linux/kdb.h> #include <linux/kdebug.h> #include <linux/export.h> +#include <linux/hardirq.h> #include "kdb_private.h" #include "../debug_core.h" @@ -52,6 +53,9 @@ int kdb_stub(struct kgdb_state *ks) if (atomic_read(&kgdb_setting_breakpoint)) reason = KDB_REASON_KEYBOARD; + if (in_nmi()) + reason = KDB_REASON_NMI; + for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) { if ((bp->bp_enabled) && (bp->bp_addr == addr)) { reason = KDB_REASON_BREAK; diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index bb9520f0f6f..0a69d2adc4f 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -715,9 +715,6 @@ kdb_printit: /* check for having reached the LINES number of printed lines */ if (kdb_nextline == linecount) { char buf1[16] = ""; -#if defined(CONFIG_SMP) - char buf2[32]; -#endif /* Watch out for recursion here. Any routine that calls * kdb_printf will come back through here. And kdb_read @@ -732,14 +729,6 @@ kdb_printit: if (moreprompt == NULL) moreprompt = "more> "; -#if defined(CONFIG_SMP) - if (strchr(moreprompt, '%')) { - sprintf(buf2, moreprompt, get_cpu()); - put_cpu(); - moreprompt = buf2; - } -#endif - kdb_input_flush(); c = console_drivers; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 67b847dfa2b..31df1706b9a 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/kmsg_dump.h> #include <linux/reboot.h> #include <linux/sched.h> #include <linux/sysrq.h> @@ -138,11 +139,10 @@ static const int __nkdb_err = sizeof(kdbmsgs) / sizeof(kdbmsg_t); static char *__env[] = { #if defined(CONFIG_SMP) "PROMPT=[%d]kdb> ", - "MOREPROMPT=[%d]more> ", #else "PROMPT=kdb> ", - "MOREPROMPT=more> ", #endif + "MOREPROMPT=more> ", "RADIX=16", "MDCOUNT=8", /* lines of md output */ KDB_PLATFORM_ENV, @@ -1235,18 +1235,6 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, *cmdbuf = '\0'; *(cmd_hist[cmd_head]) = '\0'; - if (KDB_FLAG(ONLY_DO_DUMP)) { - /* kdb is off but a catastrophic error requires a dump. - * Take the dump and reboot. - * Turn on logging so the kdb output appears in the log - * buffer in the dump. - */ - const char *setargs[] = { "set", "LOGGING", "1" }; - kdb_set(2, setargs); - kdb_reboot(0, NULL); - /*NOTREACHED*/ - } - do_full_getstr: #if defined(CONFIG_SMP) snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"), @@ -2040,8 +2028,15 @@ static int kdb_env(int argc, const char **argv) */ static int kdb_dmesg(int argc, const char **argv) { - char *syslog_data[4], *start, *end, c = '\0', *p; - int diag, logging, logsize, lines = 0, adjust = 0, n; + int diag; + int logging; + int lines = 0; + int adjust = 0; + int n = 0; + int skip = 0; + struct kmsg_dumper dumper = { .active = 1 }; + size_t len; + char buf[201]; if (argc > 2) return KDB_ARGCOUNT; @@ -2064,22 +2059,10 @@ static int kdb_dmesg(int argc, const char **argv) kdb_set(2, setargs); } - /* syslog_data[0,1] physical start, end+1. syslog_data[2,3] - * logical start, end+1. */ - kdb_syslog_data(syslog_data); - if (syslog_data[2] == syslog_data[3]) - return 0; - logsize = syslog_data[1] - syslog_data[0]; - start = syslog_data[2]; - end = syslog_data[3]; -#define KDB_WRAP(p) (((p - syslog_data[0]) % logsize) + syslog_data[0]) - for (n = 0, p = start; p < end; ++p) { - c = *KDB_WRAP(p); - if (c == '\n') - ++n; - } - if (c != '\n') - ++n; + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, NULL, 0, NULL)) + n++; + if (lines < 0) { if (adjust >= n) kdb_printf("buffer only contains %d lines, nothing " @@ -2087,21 +2070,11 @@ static int kdb_dmesg(int argc, const char **argv) else if (adjust - lines >= n) kdb_printf("buffer only contains %d lines, last %d " "lines printed\n", n, n - adjust); - if (adjust) { - for (; start < end && adjust; ++start) { - if (*KDB_WRAP(start) == '\n') - --adjust; - } - if (start < end) - ++start; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - ++lines; - } - end = p; + skip = adjust; + lines = abs(lines); } else if (lines > 0) { - int skip = n - (adjust + lines); + skip = n - lines - adjust; + lines = abs(lines); if (adjust >= n) { kdb_printf("buffer only contains %d lines, " "nothing printed\n", n); @@ -2112,35 +2085,24 @@ static int kdb_dmesg(int argc, const char **argv) kdb_printf("buffer only contains %d lines, first " "%d lines printed\n", n, lines); } - for (; start < end && skip; ++start) { - if (*KDB_WRAP(start) == '\n') - --skip; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - --lines; - } - end = p; + } else { + lines = n; } - /* Do a line at a time (max 200 chars) to reduce protocol overhead */ - c = '\n'; - while (start != end) { - char buf[201]; - p = buf; - if (KDB_FLAG(CMD_INTERRUPT)) - return 0; - while (start < end && (c = *KDB_WRAP(start)) && - (p - buf) < sizeof(buf)-1) { - ++start; - *p++ = c; - if (c == '\n') - break; + + if (skip >= n || skip < 0) + return 0; + + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, buf, sizeof(buf), &len)) { + if (skip) { + skip--; + continue; } - *p = '\0'; - kdb_printf("%s", buf); + if (!lines--) + break; + + kdb_printf("%.*s\n", (int)len - 1, buf); } - if (c != '\n') - kdb_printf("\n"); return 0; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 47c4e56e513..392ec6a2584 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -205,7 +205,6 @@ extern char kdb_grep_string[]; extern int kdb_grep_leading; extern int kdb_grep_trailing; extern char *kdb_cmds[]; -extern void kdb_syslog_data(char *syslog_data[]); extern unsigned long kdb_task_state_string(const char *); extern char kdb_task_state_char (const struct task_struct *); extern unsigned long kdb_task_state(const struct task_struct *p, diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 6581a040f39..c77206184b8 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -153,11 +153,17 @@ put_callchain_entry(int rctx) put_recursion_context(__get_cpu_var(callchain_recursion), rctx); } -struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) +struct perf_callchain_entry * +perf_callchain(struct perf_event *event, struct pt_regs *regs) { int rctx; struct perf_callchain_entry *entry; + int kernel = !event->attr.exclude_callchain_kernel; + int user = !event->attr.exclude_callchain_user; + + if (!kernel && !user) + return NULL; entry = get_callchain_entry(&rctx); if (rctx == -1) @@ -168,18 +174,29 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) entry->nr = 0; - if (!user_mode(regs)) { + if (kernel && !user_mode(regs)) { perf_callchain_store(entry, PERF_CONTEXT_KERNEL); perf_callchain_kernel(entry, regs); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; } - if (regs) { - perf_callchain_store(entry, PERF_CONTEXT_USER); - perf_callchain_user(entry, regs); + if (user) { + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + /* + * Disallow cross-task user callchains. + */ + if (event->ctx->task && event->ctx->task != current) + goto exit_put; + + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_user(entry, regs); + } } exit_put: diff --git a/kernel/events/core.c b/kernel/events/core.c index d7d71d6ec97..7b9df353ba1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -36,6 +36,7 @@ #include <linux/perf_event.h> #include <linux/ftrace_event.h> #include <linux/hw_breakpoint.h> +#include <linux/mm_types.h> #include "internal.h" @@ -1253,7 +1254,7 @@ retry: /* * Cross CPU call to disable a performance event */ -static int __perf_event_disable(void *info) +int __perf_event_disable(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; @@ -1645,6 +1646,8 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); event->ctx = ctx; + if (event->cpu != -1) + event->cpu = cpu; if (!task) { /* @@ -2933,12 +2936,12 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel); /* * Called when the last reference to the file is gone. */ -static int perf_release(struct inode *inode, struct file *file) +static void put_event(struct perf_event *event) { - struct perf_event *event = file->private_data; struct task_struct *owner; - file->private_data = NULL; + if (!atomic_long_dec_and_test(&event->refcount)) + return; rcu_read_lock(); owner = ACCESS_ONCE(event->owner); @@ -2973,7 +2976,13 @@ static int perf_release(struct inode *inode, struct file *file) put_task_struct(owner); } - return perf_event_release_kernel(event); + perf_event_release_kernel(event); +} + +static int perf_release(struct inode *inode, struct file *file) +{ + put_event(file->private_data); + return 0; } u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) @@ -3225,7 +3234,7 @@ unlock: static const struct file_operations perf_fops; -static struct perf_event *perf_fget_light(int fd, int *fput_needed) +static struct file *perf_fget_light(int fd, int *fput_needed) { struct file *file; @@ -3239,7 +3248,7 @@ static struct perf_event *perf_fget_light(int fd, int *fput_needed) return ERR_PTR(-EBADF); } - return file->private_data; + return file; } static int perf_event_set_output(struct perf_event *event, @@ -3271,19 +3280,21 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case PERF_EVENT_IOC_SET_OUTPUT: { + struct file *output_file = NULL; struct perf_event *output_event = NULL; int fput_needed = 0; int ret; if (arg != -1) { - output_event = perf_fget_light(arg, &fput_needed); - if (IS_ERR(output_event)) - return PTR_ERR(output_event); + output_file = perf_fget_light(arg, &fput_needed); + if (IS_ERR(output_file)) + return PTR_ERR(output_file); + output_event = output_file->private_data; } ret = perf_event_set_output(event, output_event); if (output_event) - fput_light(output_event->filp, fput_needed); + fput_light(output_file, fput_needed); return ret; } @@ -3754,6 +3765,132 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); +static void +perf_output_sample_regs(struct perf_output_handle *handle, + struct pt_regs *regs, u64 mask) +{ + int bit; + + for_each_set_bit(bit, (const unsigned long *) &mask, + sizeof(mask) * BITS_PER_BYTE) { + u64 val; + + val = perf_reg_value(regs, bit); + perf_output_put(handle, val); + } +} + +static void perf_sample_regs_user(struct perf_regs_user *regs_user, + struct pt_regs *regs) +{ + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + regs_user->regs = regs; + regs_user->abi = perf_reg_abi(current); + } +} + +/* + * Get remaining task size from user stack pointer. + * + * It'd be better to take stack vma map and limit this more + * precisly, but there's no way to get it safely under interrupt, + * so using TASK_SIZE as limit. + */ +static u64 perf_ustack_task_size(struct pt_regs *regs) +{ + unsigned long addr = perf_user_stack_pointer(regs); + + if (!addr || addr >= TASK_SIZE) + return 0; + + return TASK_SIZE - addr; +} + +static u16 +perf_sample_ustack_size(u16 stack_size, u16 header_size, + struct pt_regs *regs) +{ + u64 task_size; + + /* No regs, no stack pointer, no dump. */ + if (!regs) + return 0; + + /* + * Check if we fit in with the requested stack size into the: + * - TASK_SIZE + * If we don't, we limit the size to the TASK_SIZE. + * + * - remaining sample size + * If we don't, we customize the stack size to + * fit in to the remaining sample size. + */ + + task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs)); + stack_size = min(stack_size, (u16) task_size); + + /* Current header size plus static size and dynamic size. */ + header_size += 2 * sizeof(u64); + + /* Do we fit in with the current stack dump size? */ + if ((u16) (header_size + stack_size) < header_size) { + /* + * If we overflow the maximum size for the sample, + * we customize the stack dump size to fit in. + */ + stack_size = USHRT_MAX - header_size - sizeof(u64); + stack_size = round_up(stack_size, sizeof(u64)); + } + + return stack_size; +} + +static void +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, + struct pt_regs *regs) +{ + /* Case of a kernel thread, nothing to dump */ + if (!regs) { + u64 size = 0; + perf_output_put(handle, size); + } else { + unsigned long sp; + unsigned int rem; + u64 dyn_size; + + /* + * We dump: + * static size + * - the size requested by user or the best one we can fit + * in to the sample max size + * data + * - user stack dump data + * dynamic size + * - the actual dumped size + */ + + /* Static size. */ + perf_output_put(handle, dump_size); + + /* Data. */ + sp = perf_user_stack_pointer(regs); + rem = __output_copy_user(handle, (void *) sp, dump_size); + dyn_size = dump_size - rem; + + perf_output_skip(handle, rem); + + /* Dynamic size. */ + perf_output_put(handle, dyn_size); + } +} + static void __perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event) @@ -4014,6 +4151,28 @@ void perf_output_sample(struct perf_output_handle *handle, perf_output_put(handle, nr); } } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + u64 abi = data->regs_user.abi; + + /* + * If there are no regs to dump, notice it through + * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE). + */ + perf_output_put(handle, abi); + + if (abi) { + u64 mask = event->attr.sample_regs_user; + perf_output_sample_regs(handle, + data->regs_user.regs, + mask); + } + } + + if (sample_type & PERF_SAMPLE_STACK_USER) + perf_output_sample_ustack(handle, + data->stack_user_size, + data->regs_user.regs); } void perf_prepare_sample(struct perf_event_header *header, @@ -4037,7 +4196,7 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; - data->callchain = perf_callchain(regs); + data->callchain = perf_callchain(event, regs); if (data->callchain) size += data->callchain->nr; @@ -4065,6 +4224,49 @@ void perf_prepare_sample(struct perf_event_header *header, } header->size += size; } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + /* regs dump ABI info */ + int size = sizeof(u64); + + perf_sample_regs_user(&data->regs_user, regs); + + if (data->regs_user.regs) { + u64 mask = event->attr.sample_regs_user; + size += hweight64(mask) * sizeof(u64); + } + + header->size += size; + } + + if (sample_type & PERF_SAMPLE_STACK_USER) { + /* + * Either we need PERF_SAMPLE_STACK_USER bit to be allways + * processed as the last one or have additional check added + * in case new sample type is added, because we could eat + * up the rest of the sample size. + */ + struct perf_regs_user *uregs = &data->regs_user; + u16 stack_size = event->attr.sample_stack_user; + u16 size = sizeof(u64); + + if (!uregs->abi) + perf_sample_regs_user(uregs, regs); + + stack_size = perf_sample_ustack_size(stack_size, header->size, + uregs->regs); + + /* + * If there is something to dump, add space for the dump + * itself and for the field that tells the dynamic size, + * which is how many have been actually dumped. + */ + if (stack_size) + size += sizeof(u64) + stack_size; + + data->stack_user_size = stack_size; + header->size += size; + } } static void perf_event_output(struct perf_event *event, @@ -5207,7 +5409,8 @@ static int perf_tp_event_match(struct perf_event *event, } void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, - struct pt_regs *regs, struct hlist_head *head, int rctx) + struct pt_regs *regs, struct hlist_head *head, int rctx, + struct task_struct *task) { struct perf_sample_data data; struct perf_event *event; @@ -5226,6 +5429,31 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, perf_swevent_event(event, count, &data, regs); } + /* + * If we got specified a target task, also iterate its context and + * deliver this event there too. + */ + if (task && task != current) { + struct perf_event_context *ctx; + struct trace_entry *entry = record; + + rcu_read_lock(); + ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]); + if (!ctx) + goto unlock; + + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->attr.type != PERF_TYPE_TRACEPOINT) + continue; + if (event->attr.config != entry->type) + continue; + if (perf_tp_event_match(event, &data, regs)) + perf_swevent_event(event, count, &data, regs); + } +unlock: + rcu_read_unlock(); + } + perf_swevent_put_recursion_context(rctx); } EXPORT_SYMBOL_GPL(perf_tp_event); @@ -5922,6 +6150,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, mutex_init(&event->mmap_mutex); + atomic_long_set(&event->refcount, 1); event->cpu = cpu; event->attr = *attr; event->group_leader = group_leader; @@ -6114,6 +6343,28 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->branch_sample_type = mask; } } + + if (attr->sample_type & PERF_SAMPLE_REGS_USER) { + ret = perf_reg_validate(attr->sample_regs_user); + if (ret) + return ret; + } + + if (attr->sample_type & PERF_SAMPLE_STACK_USER) { + if (!arch_perf_have_user_stack_dump()) + return -ENOSYS; + + /* + * We have __u32 type for the size, but so far + * we can only use __u16 as maximum due to the + * __u16 sample size limit. + */ + if (attr->sample_stack_user >= USHRT_MAX) + ret = -EINVAL; + else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64))) + ret = -EINVAL; + } + out: return ret; @@ -6232,12 +6483,12 @@ SYSCALL_DEFINE5(perf_event_open, return event_fd; if (group_fd != -1) { - group_leader = perf_fget_light(group_fd, &fput_needed); - if (IS_ERR(group_leader)) { - err = PTR_ERR(group_leader); + group_file = perf_fget_light(group_fd, &fput_needed); + if (IS_ERR(group_file)) { + err = PTR_ERR(group_file); goto err_fd; } - group_file = group_leader->filp; + group_leader = group_file->private_data; if (flags & PERF_FLAG_FD_OUTPUT) output_event = group_leader; if (flags & PERF_FLAG_FD_NO_GROUP) @@ -6252,6 +6503,8 @@ SYSCALL_DEFINE5(perf_event_open, } } + get_online_cpus(); + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL, NULL); if (IS_ERR(event)) { @@ -6304,7 +6557,7 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, cpu); + ctx = find_get_context(pmu, task, event->cpu); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; @@ -6372,25 +6625,27 @@ SYSCALL_DEFINE5(perf_event_open, put_ctx(gctx); } - event->filp = event_file; WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); if (move_group) { - perf_install_in_context(ctx, group_leader, cpu); + synchronize_rcu(); + perf_install_in_context(ctx, group_leader, event->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_install_in_context(ctx, sibling, cpu); + perf_install_in_context(ctx, sibling, event->cpu); get_ctx(ctx); } } - perf_install_in_context(ctx, event, cpu); + perf_install_in_context(ctx, event, event->cpu); ++ctx->generation; perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); + put_online_cpus(); + event->owner = current; mutex_lock(¤t->perf_event_mutex); @@ -6419,6 +6674,7 @@ err_context: err_alloc: free_event(event); err_task: + put_online_cpus(); if (task) put_task_struct(task); err_group_fd: @@ -6462,7 +6718,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, goto err_free; } - event->filp = NULL; WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); perf_install_in_context(ctx, event, cpu); @@ -6479,6 +6734,39 @@ err: } EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) +{ + struct perf_event_context *src_ctx; + struct perf_event_context *dst_ctx; + struct perf_event *event, *tmp; + LIST_HEAD(events); + + src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx; + dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx; + + mutex_lock(&src_ctx->mutex); + list_for_each_entry_safe(event, tmp, &src_ctx->event_list, + event_entry) { + perf_remove_from_context(event); + put_ctx(src_ctx); + list_add(&event->event_entry, &events); + } + mutex_unlock(&src_ctx->mutex); + + synchronize_rcu(); + + mutex_lock(&dst_ctx->mutex); + list_for_each_entry_safe(event, tmp, &events, event_entry) { + list_del(&event->event_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + mutex_unlock(&dst_ctx->mutex); +} +EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); + static void sync_child_event(struct perf_event *child_event, struct task_struct *child) { @@ -6511,7 +6799,7 @@ static void sync_child_event(struct perf_event *child_event, * Release the parent event, if this was the last * reference to it. */ - fput(parent_event->filp); + put_event(parent_event); } static void @@ -6587,9 +6875,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) * * __perf_event_exit_task() * sync_child_event() - * fput(parent_event->filp) - * perf_release() - * mutex_lock(&ctx->mutex) + * put_event() + * mutex_lock(&ctx->mutex) * * But since its the parent context it won't be the same instance. */ @@ -6657,7 +6944,7 @@ static void perf_free_event(struct perf_event *event, list_del_init(&event->child_list); mutex_unlock(&parent->child_mutex); - fput(parent->filp); + put_event(parent); perf_group_detach(event); list_del_event(event, ctx); @@ -6737,6 +7024,12 @@ inherit_event(struct perf_event *parent_event, NULL, NULL); if (IS_ERR(child_event)) return child_event; + + if (!atomic_long_inc_not_zero(&parent_event->refcount)) { + free_event(child_event); + return NULL; + } + get_ctx(child_ctx); /* @@ -6778,14 +7071,6 @@ inherit_event(struct perf_event *parent_event, raw_spin_unlock_irqrestore(&child_ctx->lock, flags); /* - * Get a reference to the parent filp - we will fput it - * when the child event exits. This is safe to do because - * we are in the parent and we know that the filp still - * exists and has a nonzero count: - */ - atomic_long_inc(&parent_event->filp->f_count); - - /* * Link this into the parent event's child list */ WARN_ON_ONCE(parent_event->ctx->parent_ctx); diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index bb38c4d3ee1..9a7b487c6fe 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -453,7 +453,16 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att int old_type = bp->attr.bp_type; int err = 0; - perf_event_disable(bp); + /* + * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it + * will not be possible to raise IPIs that invoke __perf_event_disable. + * So call the function directly after making sure we are targeting the + * current task. + */ + if (irqs_disabled() && bp->ctx && bp->ctx->task == current) + __perf_event_disable(bp); + else + perf_event_disable(bp); bp->attr.bp_addr = attr->bp_addr; bp->attr.bp_type = attr->bp_type; diff --git a/kernel/events/internal.h b/kernel/events/internal.h index b0b107f90af..d56a64c99a8 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -2,6 +2,7 @@ #define _KERNEL_EVENTS_INTERNAL_H #include <linux/hardirq.h> +#include <linux/uaccess.h> /* Buffer handling */ @@ -76,32 +77,56 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb) return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); } -static inline void -__output_copy(struct perf_output_handle *handle, - const void *buf, unsigned int len) +#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ +static inline unsigned int \ +func_name(struct perf_output_handle *handle, \ + const void *buf, unsigned int len) \ +{ \ + unsigned long size, written; \ + \ + do { \ + size = min_t(unsigned long, handle->size, len); \ + \ + written = memcpy_func(handle->addr, buf, size); \ + \ + len -= written; \ + handle->addr += written; \ + buf += written; \ + handle->size -= written; \ + if (!handle->size) { \ + struct ring_buffer *rb = handle->rb; \ + \ + handle->page++; \ + handle->page &= rb->nr_pages - 1; \ + handle->addr = rb->data_pages[handle->page]; \ + handle->size = PAGE_SIZE << page_order(rb); \ + } \ + } while (len && written == size); \ + \ + return len; \ +} + +static inline int memcpy_common(void *dst, const void *src, size_t n) { - do { - unsigned long size = min_t(unsigned long, handle->size, len); - - memcpy(handle->addr, buf, size); - - len -= size; - handle->addr += size; - buf += size; - handle->size -= size; - if (!handle->size) { - struct ring_buffer *rb = handle->rb; - - handle->page++; - handle->page &= rb->nr_pages - 1; - handle->addr = rb->data_pages[handle->page]; - handle->size = PAGE_SIZE << page_order(rb); - } - } while (len); + memcpy(dst, src, n); + return n; } +DEFINE_OUTPUT_COPY(__output_copy, memcpy_common) + +#define MEMCPY_SKIP(dst, src, n) (n) + +DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP) + +#ifndef arch_perf_out_copy_user +#define arch_perf_out_copy_user __copy_from_user_inatomic +#endif + +DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) + /* Callchain handling */ -extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs); +extern struct perf_callchain_entry * +perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(void); extern void put_callchain_buffers(void); @@ -133,4 +158,20 @@ static inline void put_recursion_context(int *recursion, int rctx) recursion[rctx]--; } +#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP +static inline bool arch_perf_have_user_stack_dump(void) +{ + return true; +} + +#define perf_user_stack_pointer(regs) user_stack_pointer(regs) +#else +static inline bool arch_perf_have_user_stack_dump(void) +{ + return false; +} + +#define perf_user_stack_pointer(regs) 0 +#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */ + #endif /* _KERNEL_EVENTS_INTERNAL_H */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 6ddaba43fb7..23cb34ff397 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -182,10 +182,16 @@ out: return -ENOSPC; } -void perf_output_copy(struct perf_output_handle *handle, +unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { - __output_copy(handle, buf, len); + return __output_copy(handle, buf, len); +} + +unsigned int perf_output_skip(struct perf_output_handle *handle, + unsigned int len) +{ + return __output_skip(handle, NULL, len); } void perf_output_end(struct perf_output_handle *handle) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 985be4d80fe..912ef48d28a 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -32,19 +32,36 @@ #include <linux/swap.h> /* try_to_free_swap */ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ +#include "../../mm/internal.h" /* munlock_vma_page */ #include <linux/uprobes.h> #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE -static struct srcu_struct uprobes_srcu; static struct rb_root uprobes_tree = RB_ROOT; static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 +/* + * We need separate register/unregister and mmap/munmap lock hashes because + * of mmap_sem nesting. + * + * uprobe_register() needs to install probes on (potentially) all processes + * and thus needs to acquire multiple mmap_sems (consequtively, not + * concurrently), whereas uprobe_mmap() is called while holding mmap_sem + * for the particular process doing the mmap. + * + * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem + * because of lock order against i_mmap_mutex. This means there's a hole in + * the register vma iteration where a mmap() can happen. + * + * Thus uprobe_register() can race with uprobe_mmap() and we can try and + * install a probe where one is already installed. + */ + /* serialize (un)register */ static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; @@ -61,17 +78,6 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; */ static atomic_t uprobe_events = ATOMIC_INIT(0); -/* - * Maintain a temporary per vma info that can be used to search if a vma - * has already been handled. This structure is introduced since extending - * vm_area_struct wasnt recommended. - */ -struct vma_info { - struct list_head probe_list; - struct mm_struct *mm; - loff_t vaddr; -}; - struct uprobe { struct rb_node rb_node; /* node in the rb tree */ atomic_t ref; @@ -100,20 +106,21 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register) if (!is_register) return true; - if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) + if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) + == (VM_READ|VM_EXEC)) return true; return false; } -static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) +static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset) { - loff_t vaddr; - - vaddr = vma->vm_start + offset; - vaddr -= vma->vm_pgoff << PAGE_SHIFT; + return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT); +} - return vaddr; +static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr) +{ + return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start); } /** @@ -121,41 +128,27 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) * based on replace_page in mm/ksm.c * * @vma: vma that holds the pte pointing to page + * @addr: address the old @page is mapped at * @page: the cowed page we are replacing by kpage * @kpage: the modified page we replace page by * * Returns 0 on success, -EFAULT on failure. */ -static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) +static int __replace_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, struct page *kpage) { struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; spinlock_t *ptl; - unsigned long addr; - int err = -EFAULT; - - addr = page_address_in_vma(page, vma); - if (addr == -EFAULT) - goto out; - - pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) - goto out; - - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) - goto out; + pte_t *ptep; + int err; - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - goto out; + /* For try_to_free_swap() and munlock_vma_page() below */ + lock_page(page); - ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); + err = -EAGAIN; + ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) - goto out; + goto unlock; get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr); @@ -172,11 +165,15 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page_remove_rmap(page); if (!page_mapped(page)) try_to_free_swap(page); - put_page(page); pte_unmap_unlock(ptep, ptl); - err = 0; -out: + if (vma->vm_flags & VM_LOCKED) + munlock_vma_page(page); + put_page(page); + + err = 0; + unlock: + unlock_page(page); return err; } @@ -218,79 +215,46 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { struct page *old_page, *new_page; - struct address_space *mapping; void *vaddr_old, *vaddr_new; struct vm_area_struct *vma; - struct uprobe *uprobe; - loff_t addr; int ret; +retry: /* Read the page with vaddr into memory */ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); if (ret <= 0) return ret; - ret = -EINVAL; - - /* - * We are interested in text pages only. Our pages of interest - * should be mapped for read and execute only. We desist from - * adding probes in write mapped pages since the breakpoints - * might end up in the file copy. - */ - if (!valid_vma(vma, is_swbp_insn(&opcode))) - goto put_out; - - uprobe = container_of(auprobe, struct uprobe, arch); - mapping = uprobe->inode->i_mapping; - if (mapping != vma->vm_file->f_mapping) - goto put_out; - - addr = vma_address(vma, uprobe->offset); - if (vaddr != (unsigned long)addr) - goto put_out; - ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) - goto put_out; + goto put_old; __SetPageUptodate(new_page); - /* - * lock page will serialize against do_wp_page()'s - * PageAnon() handling - */ - lock_page(old_page); /* copy the page now that we've got it stable */ vaddr_old = kmap_atomic(old_page); vaddr_new = kmap_atomic(new_page); memcpy(vaddr_new, vaddr_old, PAGE_SIZE); - - /* poke the new insn in, ASSUMES we don't cross page boundary */ - vaddr &= ~PAGE_MASK; - BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); kunmap_atomic(vaddr_old); ret = anon_vma_prepare(vma); if (ret) - goto unlock_out; + goto put_new; - lock_page(new_page); - ret = __replace_page(vma, old_page, new_page); - unlock_page(new_page); + ret = __replace_page(vma, vaddr, old_page, new_page); -unlock_out: - unlock_page(old_page); +put_new: page_cache_release(new_page); - -put_out: +put_old: put_page(old_page); + if (unlikely(ret == -EAGAIN)) + goto retry; return ret; } @@ -312,16 +276,14 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_ void *vaddr_new; int ret; - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL); + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (ret <= 0) return ret; - lock_page(page); vaddr_new = kmap_atomic(page); vaddr &= ~PAGE_MASK; memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); - unlock_page(page); put_page(page); @@ -333,10 +295,20 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) uprobe_opcode_t opcode; int result; + if (current->mm == mm) { + pagefault_disable(); + result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, + sizeof(opcode)); + pagefault_enable(); + + if (likely(result == 0)) + goto out; + } + result = read_opcode(mm, vaddr, &opcode); if (result) return result; - +out: if (is_swbp_insn(&opcode)) return 1; @@ -355,10 +327,12 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { int result; - + /* + * See the comment near uprobes_hash(). + */ result = is_swbp_at_addr(mm, vaddr); if (result == 1) - return -EEXIST; + return 0; if (result) return result; @@ -371,24 +345,22 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned * @mm: the probed process address space. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. - * @verify: if true, verify existance of breakpoint instruction. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ int __weak -set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, bool verify) +set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { - if (verify) { - int result; + int result; - result = is_swbp_at_addr(mm, vaddr); - if (!result) - return -EINVAL; + result = is_swbp_at_addr(mm, vaddr); + if (!result) + return -EINVAL; + + if (result != 1) + return result; - if (result != 1) - return result; - } return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn); } @@ -439,11 +411,10 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; - unsigned long flags; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); return uprobe; } @@ -490,12 +461,11 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe) */ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { - unsigned long flags; struct uprobe *u; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); /* For now assume that the instruction need not be single-stepped */ uprobe->flags |= UPROBE_SKIP_SSTEP; @@ -520,7 +490,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = igrab(inode); uprobe->offset = offset; init_rwsem(&uprobe->consumer_rwsem); - INIT_LIST_HEAD(&uprobe->pending_list); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); @@ -588,20 +557,22 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) } static int -__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn, - unsigned long nbytes, unsigned long offset) +__copy_insn(struct address_space *mapping, struct file *filp, char *insn, + unsigned long nbytes, loff_t offset) { - struct file *filp = vma->vm_file; struct page *page; void *vaddr; - unsigned long off1; - unsigned long idx; + unsigned long off; + pgoff_t idx; if (!filp) return -EINVAL; - idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); - off1 = offset &= ~PAGE_MASK; + if (!mapping->a_ops->readpage) + return -EIO; + + idx = offset >> PAGE_CACHE_SHIFT; + off = offset & ~PAGE_MASK; /* * Ensure that the page that has the original instruction is @@ -612,22 +583,20 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins return PTR_ERR(page); vaddr = kmap_atomic(page); - memcpy(insn, vaddr + off1, nbytes); + memcpy(insn, vaddr + off, nbytes); kunmap_atomic(vaddr); page_cache_release(page); return 0; } -static int -copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) +static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping; unsigned long nbytes; int bytes; - addr &= ~PAGE_MASK; - nbytes = PAGE_SIZE - addr; + nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK); mapping = uprobe->inode->i_mapping; /* Instruction at end of binary; copy only available bytes */ @@ -638,13 +607,13 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) /* Instruction at the page-boundary; copy bytes in second page */ if (nbytes < bytes) { - if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes, - bytes - nbytes, uprobe->offset + nbytes)) - return -ENOMEM; - + int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes, + bytes - nbytes, uprobe->offset + nbytes); + if (err) + return err; bytes = nbytes; } - return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset); + return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset); } /* @@ -672,9 +641,9 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) */ static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, - struct vm_area_struct *vma, loff_t vaddr) + struct vm_area_struct *vma, unsigned long vaddr) { - unsigned long addr; + bool first_uprobe; int ret; /* @@ -685,204 +654,194 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, * Hence behave as if probe already existed. */ if (!uprobe->consumers) - return -EEXIST; - - addr = (unsigned long)vaddr; + return 0; if (!(uprobe->flags & UPROBE_COPY_INSN)) { - ret = copy_insn(uprobe, vma, addr); + ret = copy_insn(uprobe, vma->vm_file); if (ret) return ret; if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) - return -EEXIST; + return -ENOTSUPP; - ret = arch_uprobe_analyze_insn(&uprobe->arch, mm); + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) return ret; + /* write_opcode() assumes we don't cross page boundary */ + BUG_ON((uprobe->offset & ~PAGE_MASK) + + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + uprobe->flags |= UPROBE_COPY_INSN; } /* - * Ideally, should be updating the probe count after the breakpoint - * has been successfully inserted. However a thread could hit the - * breakpoint we just inserted even before the probe count is - * incremented. If this is the first breakpoint placed, breakpoint - * notifier might ignore uprobes and pass the trap to the thread. - * Hence increment before and decrement on failure. + * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), + * the task can hit this breakpoint right after __replace_page(). */ - atomic_inc(&mm->uprobes_state.count); - ret = set_swbp(&uprobe->arch, mm, addr); - if (ret) - atomic_dec(&mm->uprobes_state.count); + first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); + if (first_uprobe) + set_bit(MMF_HAS_UPROBES, &mm->flags); + + ret = set_swbp(&uprobe->arch, mm, vaddr); + if (!ret) + clear_bit(MMF_RECALC_UPROBES, &mm->flags); + else if (first_uprobe) + clear_bit(MMF_HAS_UPROBES, &mm->flags); return ret; } static void -remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr) +remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true)) - atomic_dec(&mm->uprobes_state.count); + /* can happen if uprobe_register() fails */ + if (!test_bit(MMF_HAS_UPROBES, &mm->flags)) + return; + + set_bit(MMF_RECALC_UPROBES, &mm->flags); + set_orig_insn(&uprobe->arch, mm, vaddr); } /* - * There could be threads that have hit the breakpoint and are entering the - * notifier code and trying to acquire the uprobes_treelock. The thread - * calling delete_uprobe() that is removing the uprobe from the rb_tree can - * race with these threads and might acquire the uprobes_treelock compared - * to some of the breakpoint hit threads. In such a case, the breakpoint - * hit threads will not find the uprobe. The current unregistering thread - * waits till all other threads have hit a breakpoint, to acquire the - * uprobes_treelock before the uprobe is removed from the rbtree. + * There could be threads that have already hit the breakpoint. They + * will recheck the current insn and restart if find_uprobe() fails. + * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { - unsigned long flags; - - synchronize_srcu(&uprobes_srcu); - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); iput(uprobe->inode); put_uprobe(uprobe); atomic_dec(&uprobe_events); } -static struct vma_info * -__find_next_vma_info(struct address_space *mapping, struct list_head *head, - struct vma_info *vi, loff_t offset, bool is_register) +struct map_info { + struct map_info *next; + struct mm_struct *mm; + unsigned long vaddr; +}; + +static inline struct map_info *free_map_info(struct map_info *info) +{ + struct map_info *next = info->next; + kfree(info); + return next; +} + +static struct map_info * +build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { + unsigned long pgoff = offset >> PAGE_SHIFT; struct prio_tree_iter iter; struct vm_area_struct *vma; - struct vma_info *tmpvi; - unsigned long pgoff; - int existing_vma; - loff_t vaddr; - - pgoff = offset >> PAGE_SHIFT; + struct map_info *curr = NULL; + struct map_info *prev = NULL; + struct map_info *info; + int more = 0; + again: + mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; - existing_vma = 0; - vaddr = vma_address(vma, offset); - - list_for_each_entry(tmpvi, head, probe_list) { - if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { - existing_vma = 1; - break; - } + if (!prev && !more) { + /* + * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through + * reclaim. This is optimistic, no harm done if it fails. + */ + prev = kmalloc(sizeof(struct map_info), + GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (prev) + prev->next = NULL; } - - /* - * Another vma needs a probe to be installed. However skip - * installing the probe if the vma is about to be unlinked. - */ - if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { - vi->mm = vma->vm_mm; - vi->vaddr = vaddr; - list_add(&vi->probe_list, head); - - return vi; + if (!prev) { + more++; + continue; } - } - - return NULL; -} -/* - * Iterate in the rmap prio tree and find a vma where a probe has not - * yet been inserted. - */ -static struct vma_info * -find_next_vma_info(struct address_space *mapping, struct list_head *head, - loff_t offset, bool is_register) -{ - struct vma_info *vi, *retvi; + if (!atomic_inc_not_zero(&vma->vm_mm->mm_users)) + continue; - vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); - if (!vi) - return ERR_PTR(-ENOMEM); + info = prev; + prev = prev->next; + info->next = curr; + curr = info; - mutex_lock(&mapping->i_mmap_mutex); - retvi = __find_next_vma_info(mapping, head, vi, offset, is_register); + info->mm = vma->vm_mm; + info->vaddr = offset_to_vaddr(vma, offset); + } mutex_unlock(&mapping->i_mmap_mutex); - if (!retvi) - kfree(vi); + if (!more) + goto out; + + prev = curr; + while (curr) { + mmput(curr->mm); + curr = curr->next; + } - return retvi; + do { + info = kmalloc(sizeof(struct map_info), GFP_KERNEL); + if (!info) { + curr = ERR_PTR(-ENOMEM); + goto out; + } + info->next = prev; + prev = info; + } while (--more); + + goto again; + out: + while (prev) + prev = free_map_info(prev); + return curr; } static int register_for_each_vma(struct uprobe *uprobe, bool is_register) { - struct list_head try_list; - struct vm_area_struct *vma; - struct address_space *mapping; - struct vma_info *vi, *tmpvi; - struct mm_struct *mm; - loff_t vaddr; - int ret; + struct map_info *info; + int err = 0; - mapping = uprobe->inode->i_mapping; - INIT_LIST_HEAD(&try_list); + info = build_map_info(uprobe->inode->i_mapping, + uprobe->offset, is_register); + if (IS_ERR(info)) + return PTR_ERR(info); - ret = 0; + while (info) { + struct mm_struct *mm = info->mm; + struct vm_area_struct *vma; - for (;;) { - vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register); - if (!vi) - break; + if (err) + goto free; - if (IS_ERR(vi)) { - ret = PTR_ERR(vi); - break; - } + down_write(&mm->mmap_sem); + vma = find_vma(mm, info->vaddr); + if (!vma || !valid_vma(vma, is_register) || + vma->vm_file->f_mapping->host != uprobe->inode) + goto unlock; - mm = vi->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, (unsigned long)vi->vaddr); - if (!vma || !valid_vma(vma, is_register)) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - vaddr = vma_address(vma, uprobe->offset); - if (vma->vm_file->f_mapping->host != uprobe->inode || - vaddr != vi->vaddr) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } + if (vma->vm_start > info->vaddr || + vaddr_to_offset(vma, info->vaddr) != uprobe->offset) + goto unlock; if (is_register) - ret = install_breakpoint(uprobe, mm, vma, vi->vaddr); + err = install_breakpoint(uprobe, mm, vma, info->vaddr); else - remove_breakpoint(uprobe, mm, vi->vaddr); + remove_breakpoint(uprobe, mm, info->vaddr); - up_read(&mm->mmap_sem); + unlock: + up_write(&mm->mmap_sem); + free: mmput(mm); - if (is_register) { - if (ret && ret == -EEXIST) - ret = 0; - if (ret) - break; - } - } - - list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { - list_del(&vi->probe_list); - kfree(vi); + info = free_map_info(info); } - return ret; + return err; } static int __uprobe_register(struct uprobe *uprobe) @@ -941,7 +900,8 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * } mutex_unlock(uprobes_hash(inode)); - put_uprobe(uprobe); + if (uprobe) + put_uprobe(uprobe); return ret; } @@ -977,80 +937,79 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume put_uprobe(uprobe); } -/* - * Of all the nodes that correspond to the given inode, return the node - * with the least offset. - */ -static struct rb_node *find_least_offset_node(struct inode *inode) +static struct rb_node * +find_node_in_range(struct inode *inode, loff_t min, loff_t max) { - struct uprobe u = { .inode = inode, .offset = 0}; struct rb_node *n = uprobes_tree.rb_node; - struct rb_node *close_node = NULL; - struct uprobe *uprobe; - int match; while (n) { - uprobe = rb_entry(n, struct uprobe, rb_node); - match = match_uprobe(&u, uprobe); - - if (uprobe->inode == inode) - close_node = n; - - if (!match) - return close_node; + struct uprobe *u = rb_entry(n, struct uprobe, rb_node); - if (match < 0) + if (inode < u->inode) { n = n->rb_left; - else + } else if (inode > u->inode) { n = n->rb_right; + } else { + if (max < u->offset) + n = n->rb_left; + else if (min > u->offset) + n = n->rb_right; + else + break; + } } - return close_node; + return n; } /* - * For a given inode, build a list of probes that need to be inserted. + * For a given range in vma, build a list of probes that need to be inserted. */ -static void build_probe_list(struct inode *inode, struct list_head *head) +static void build_probe_list(struct inode *inode, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *head) { - struct uprobe *uprobe; - unsigned long flags; - struct rb_node *n; - - spin_lock_irqsave(&uprobes_treelock, flags); - - n = find_least_offset_node(inode); + loff_t min, max; + struct rb_node *n, *t; + struct uprobe *u; - for (; n; n = rb_next(n)) { - uprobe = rb_entry(n, struct uprobe, rb_node); - if (uprobe->inode != inode) - break; + INIT_LIST_HEAD(head); + min = vaddr_to_offset(vma, start); + max = min + (end - start) - 1; - list_add(&uprobe->pending_list, head); - atomic_inc(&uprobe->ref); + spin_lock(&uprobes_treelock); + n = find_node_in_range(inode, min, max); + if (n) { + for (t = n; t; t = rb_prev(t)) { + u = rb_entry(t, struct uprobe, rb_node); + if (u->inode != inode || u->offset < min) + break; + list_add(&u->pending_list, head); + atomic_inc(&u->ref); + } + for (t = n; (t = rb_next(t)); ) { + u = rb_entry(t, struct uprobe, rb_node); + if (u->inode != inode || u->offset > max) + break; + list_add(&u->pending_list, head); + atomic_inc(&u->ref); + } } - - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); } /* - * Called from mmap_region. - * called with mm->mmap_sem acquired. - * - * Return -ve no if we fail to insert probes and we cannot - * bail-out. - * Return 0 otherwise. i.e: + * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. * - * - successful insertion of probes - * - (or) no possible probes to be inserted. - * - (or) insertion of probes failed but we can bail-out. + * Currently we ignore all errors and always return 0, the callers + * can't handle the failure anyway. */ int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; - int ret, count; if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) return 0; @@ -1059,54 +1018,38 @@ int uprobe_mmap(struct vm_area_struct *vma) if (!inode) return 0; - INIT_LIST_HEAD(&tmp_list); mutex_lock(uprobes_mmap_hash(inode)); - build_probe_list(inode, &tmp_list); - - ret = 0; - count = 0; + build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); - if (!ret) { - vaddr = vma_address(vma, uprobe->offset); - - if (vaddr < vma->vm_start || vaddr >= vma->vm_end) { - put_uprobe(uprobe); - continue; - } - - ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); - - /* Ignore double add: */ - if (ret == -EEXIST) { - ret = 0; - - if (!is_swbp_at_addr(vma->vm_mm, vaddr)) - continue; - - /* - * Unable to insert a breakpoint, but - * breakpoint lies underneath. Increment the - * probe count. - */ - atomic_inc(&vma->vm_mm->uprobes_state.count); - } - - if (!ret) - count++; + if (!fatal_signal_pending(current)) { + unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); + install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } put_uprobe(uprobe); } - mutex_unlock(uprobes_mmap_hash(inode)); - if (ret) - atomic_sub(count, &vma->vm_mm->uprobes_state.count); + return 0; +} - return ret; +static bool +vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + loff_t min, max; + struct inode *inode; + struct rb_node *n; + + inode = vma->vm_file->f_mapping->host; + + min = vaddr_to_offset(vma, start); + max = min + (end - start) - 1; + + spin_lock(&uprobes_treelock); + n = find_node_in_range(inode, min, max); + spin_unlock(&uprobes_treelock); + + return !!n; } /* @@ -1114,41 +1057,18 @@ int uprobe_mmap(struct vm_area_struct *vma) */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct list_head tmp_list; - struct uprobe *uprobe, *u; - struct inode *inode; - if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) return; - if (!atomic_read(&vma->vm_mm->uprobes_state.count)) + if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ return; - inode = vma->vm_file->f_mapping->host; - if (!inode) + if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || + test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) return; - INIT_LIST_HEAD(&tmp_list); - mutex_lock(uprobes_mmap_hash(inode)); - build_probe_list(inode, &tmp_list); - - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); - vaddr = vma_address(vma, uprobe->offset); - - if (vaddr >= start && vaddr < end) { - /* - * An unregister could have removed the probe before - * unmap. So check before we decrement the count. - */ - if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1) - atomic_dec(&vma->vm_mm->uprobes_state.count); - } - put_uprobe(uprobe); - } - mutex_unlock(uprobes_mmap_hash(inode)); + if (vma_has_uprobes(vma, start, end)) + set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); } /* Slot allocation for XOL */ @@ -1250,13 +1170,15 @@ void uprobe_clear_state(struct mm_struct *mm) kfree(area); } -/* - * uprobe_reset_state - Free the area allocated for slots. - */ -void uprobe_reset_state(struct mm_struct *mm) +void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { - mm->uprobes_state.xol_area = NULL; - atomic_set(&mm->uprobes_state.count, 0); + newmm->uprobes_state.xol_area = NULL; + + if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { + set_bit(MMF_HAS_UPROBES, &newmm->flags); + /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ + set_bit(MMF_RECALC_UPROBES, &newmm->flags); + } } /* @@ -1378,9 +1300,6 @@ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; - if (t->uprobe_srcu_id != -1) - srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id); - if (!utask) return; @@ -1398,7 +1317,6 @@ void uprobe_free_utask(struct task_struct *t) void uprobe_copy_process(struct task_struct *t) { t->utask = NULL; - t->uprobe_srcu_id = -1; } /* @@ -1417,7 +1335,6 @@ static struct uprobe_task *add_utask(void) if (unlikely(!utask)) return NULL; - utask->active_uprobe = NULL; current->utask = utask; return utask; } @@ -1479,41 +1396,93 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) return false; } +static void mmf_recalc_uprobes(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!valid_vma(vma, false)) + continue; + /* + * This is not strictly accurate, we can race with + * uprobe_unregister() and see the already removed + * uprobe if delete_uprobe() was not yet called. + */ + if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) + return; + } + + clear_bit(MMF_HAS_UPROBES, &mm->flags); +} + +static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) +{ + struct mm_struct *mm = current->mm; + struct uprobe *uprobe = NULL; + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, bp_vaddr); + if (vma && vma->vm_start <= bp_vaddr) { + if (valid_vma(vma, false)) { + struct inode *inode = vma->vm_file->f_mapping->host; + loff_t offset = vaddr_to_offset(vma, bp_vaddr); + + uprobe = find_uprobe(inode, offset); + } + + if (!uprobe) + *is_swbp = is_swbp_at_addr(mm, bp_vaddr); + } else { + *is_swbp = -EFAULT; + } + + if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) + mmf_recalc_uprobes(mm); + up_read(&mm->mmap_sem); + + return uprobe; +} + +void __weak arch_uprobe_enable_step(struct arch_uprobe *arch) +{ + user_enable_single_step(current); +} + +void __weak arch_uprobe_disable_step(struct arch_uprobe *arch) +{ + user_disable_single_step(current); +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { - struct vm_area_struct *vma; struct uprobe_task *utask; struct uprobe *uprobe; - struct mm_struct *mm; unsigned long bp_vaddr; + int uninitialized_var(is_swbp); - uprobe = NULL; bp_vaddr = uprobe_get_swbp_addr(regs); - mm = current->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, bp_vaddr); - - if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) { - struct inode *inode; - loff_t offset; - - inode = vma->vm_file->f_mapping->host; - offset = bp_vaddr - vma->vm_start; - offset += (vma->vm_pgoff << PAGE_SHIFT); - uprobe = find_uprobe(inode, offset); - } - - srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id); - current->uprobe_srcu_id = -1; - up_read(&mm->mmap_sem); + uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { - /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + if (is_swbp > 0) { + /* No matching uprobe; signal SIGTRAP. */ + send_sig(SIGTRAP, current, 0); + } else { + /* + * Either we raced with uprobe_unregister() or we can't + * access this memory. The latter is only possible if + * another thread plays with our ->mm. In both cases + * we can simply restart. If this vma was unmapped we + * can pretend this insn was not executed yet and get + * the (correct) SIGSEGV after restart. + */ + instruction_pointer_set(regs, bp_vaddr); + } return; } @@ -1531,7 +1500,7 @@ static void handle_swbp(struct pt_regs *regs) utask->state = UTASK_SSTEP; if (!pre_ssout(uprobe, regs, bp_vaddr)) { - user_enable_single_step(current); + arch_uprobe_enable_step(&uprobe->arch); return; } @@ -1540,17 +1509,15 @@ cleanup_ret: utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; } - if (uprobe) { - if (!(uprobe->flags & UPROBE_SKIP_SSTEP)) + if (!(uprobe->flags & UPROBE_SKIP_SSTEP)) - /* - * cannot singlestep; cannot skip instruction; - * re-execute the instruction. - */ - instruction_pointer_set(regs, bp_vaddr); + /* + * cannot singlestep; cannot skip instruction; + * re-execute the instruction. + */ + instruction_pointer_set(regs, bp_vaddr); - put_uprobe(uprobe); - } + put_uprobe(uprobe); } /* @@ -1569,10 +1536,10 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) else WARN_ON_ONCE(1); + arch_uprobe_disable_step(&uprobe->arch); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; - user_disable_single_step(current); xol_free_insn_slot(current); spin_lock_irq(¤t->sighand->siglock); @@ -1611,8 +1578,7 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { struct uprobe_task *utask; - if (!current->mm || !atomic_read(¤t->mm->uprobes_state.count)) - /* task is currently not uprobed */ + if (!current->mm || !test_bit(MMF_HAS_UPROBES, ¤t->mm->flags)) return 0; utask = current->utask; @@ -1620,7 +1586,6 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs) utask->state = UTASK_BP_HIT; set_thread_flag(TIF_UPROBE); - current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu); return 1; } @@ -1655,7 +1620,6 @@ static int __init init_uprobes(void) mutex_init(&uprobes_mutex[i]); mutex_init(&uprobes_mmap_mutex[i]); } - init_srcu_struct(&uprobes_srcu); return register_die_notifier(&uprobe_exception_nb); } diff --git a/kernel/exit.c b/kernel/exit.c index 2f59cc33451..f65345f9e5b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -483,7 +483,7 @@ static void close_files(struct files_struct * files) rcu_read_unlock(); for (;;) { unsigned long set; - i = j * __NFDBITS; + i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; @@ -953,14 +953,11 @@ void do_exit(long code) exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against - * an exiting task cleaning up the robust pi futexes, and in - * task_work_add() to avoid the race with exit_task_work(). + * an exiting task cleaning up the robust pi futexes. */ smp_mb(); raw_spin_unlock_wait(&tsk->pi_lock); - exit_task_work(tsk); - if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), @@ -995,6 +992,7 @@ void do_exit(long code) exit_shm(tsk); exit_files(tsk); exit_fs(tsk); + exit_task_work(tsk); check_stack_usage(); exit_thread(); diff --git a/kernel/fork.c b/kernel/fork.c index f00e319d837..5a0e74d89a5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -114,6 +114,10 @@ int nr_processes(void) return total; } +void __weak arch_release_task_struct(struct task_struct *tsk) +{ +} + #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static struct kmem_cache *task_struct_cachep; @@ -122,17 +126,17 @@ static inline struct task_struct *alloc_task_struct_node(int node) return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } -void __weak arch_release_task_struct(struct task_struct *tsk) { } - static inline void free_task_struct(struct task_struct *tsk) { - arch_release_task_struct(tsk); kmem_cache_free(task_struct_cachep, tsk); } #endif +void __weak arch_release_thread_info(struct thread_info *ti) +{ +} + #ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR -void __weak arch_release_thread_info(struct thread_info *ti) { } /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a @@ -150,7 +154,6 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, static inline void free_thread_info(struct thread_info *ti) { - arch_release_thread_info(ti); free_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else @@ -164,7 +167,6 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, static void free_thread_info(struct thread_info *ti) { - arch_release_thread_info(ti); kmem_cache_free(thread_info_cache, ti); } @@ -205,10 +207,12 @@ static void account_kernel_stack(struct thread_info *ti, int account) void free_task(struct task_struct *tsk) { account_kernel_stack(tsk->stack, -1); + arch_release_thread_info(tsk->stack); free_thread_info(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); put_seccomp_filter(tsk); + arch_release_task_struct(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -298,23 +302,16 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return NULL; ti = alloc_thread_info_node(tsk, node); - if (!ti) { - free_task_struct(tsk); - return NULL; - } + if (!ti) + goto free_tsk; err = arch_dup_task_struct(tsk, orig); + if (err) + goto free_ti; - /* - * We defer looking at err, because we will need this setup - * for the clean up path to work correctly. - */ tsk->stack = ti; - setup_thread_stack(tsk, orig); - - if (err) - goto out; + setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); stackend = end_of_stack(tsk); @@ -338,8 +335,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return tsk; -out: +free_ti: free_thread_info(ti); +free_tsk: free_task_struct(tsk); return NULL; } @@ -355,6 +353,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) down_write(&oldmm->mmap_sem); flush_cache_dup_mm(oldmm); + uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ @@ -383,16 +382,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { - long pages = vma_pages(mpnt); - mm->total_vm -= pages; vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, - -pages); + -vma_pages(mpnt)); continue; } charge = 0; if (mpnt->vm_flags & VM_ACCOUNT) { - unsigned long len; - len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT; + unsigned long len = vma_pages(mpnt); + if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; @@ -458,9 +455,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; - - if (file && uprobe_mmap(tmp)) - goto out; } /* a new mm has just been created */ arch_dup_mmap(oldmm, mm); @@ -843,8 +837,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) #ifdef CONFIG_TRANSPARENT_HUGEPAGE mm->pmd_huge_pte = NULL; #endif - uprobe_reset_state(mm); - if (!mm_init(mm, tsk)) goto fail_nomem; @@ -1284,11 +1276,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - p->hardirqs_enabled = 1; -#else p->hardirqs_enabled = 0; -#endif p->hardirq_enable_ip = 0; p->hardirq_enable_event = 0; p->hardirq_disable_ip = _THIS_IP_; @@ -1310,7 +1298,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG p->memcg_batch.do_batch = 0; p->memcg_batch.memcg = NULL; #endif @@ -1420,7 +1408,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); - INIT_HLIST_HEAD(&p->task_works); + p->task_works = NULL; /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible diff --git a/kernel/futex.c b/kernel/futex.c index e2b0fb9a0b3..3717e7b306e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2231,11 +2231,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * @uaddr2: the pi futex we will take prior to returning to user-space * * The caller will wait on uaddr and will be requeued by futex_requeue() to - * uaddr2 which must be PI aware. Normal wakeup will wake on uaddr2 and - * complete the acquisition of the rt_mutex prior to returning to userspace. - * This ensures the rt_mutex maintains an owner when it has waiters; without - * one, the pi logic wouldn't know which task to boost/deboost, if there was a - * need to. + * uaddr2 which must be PI aware and unique from uaddr. Normal wakeup will wake + * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to + * userspace. This ensures the rt_mutex maintains an owner when it has waiters; + * without one, the pi logic would not know which task to boost/deboost, if + * there was a need to. * * We call schedule in futex_wait_queue_me() when we enqueue and return there * via the following: @@ -2272,6 +2272,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, struct futex_q q = futex_q_init; int res, ret; + if (uaddr == uaddr2) + return -EINVAL; + if (!bitset) return -EINVAL; @@ -2343,7 +2346,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * signal. futex_unlock_pi() will not destroy the lock_ptr nor * the pi_state. */ - WARN_ON(!&q.pi_state); + WARN_ON(!q.pi_state); pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1); debug_rt_mutex_free_waiter(&rt_waiter); @@ -2370,7 +2373,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * fault, unlock the rt_mutex and return the fault to userspace. */ if (ret == -EFAULT) { - if (rt_mutex_owner(pi_mutex) == current) + if (pi_mutex && rt_mutex_owner(pi_mutex) == current) rt_mutex_unlock(pi_mutex); } else if (ret == -EINTR) { /* diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index eebd6d5cfb4..57d86d07221 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -671,6 +671,7 @@ irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, irq_set_chip(irq, chip); __irq_set_handler(irq, handle, 0, name); } +EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) { diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c index b5fcd96c710..988dc58e884 100644 --- a/kernel/irq/dummychip.c +++ b/kernel/irq/dummychip.c @@ -6,6 +6,7 @@ */ #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/export.h> #include "internals.h" @@ -57,3 +58,4 @@ struct irq_chip dummy_irq_chip = { .irq_mask = noop, .irq_unmask = noop, }; +EXPORT_SYMBOL_GPL(dummy_irq_chip); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index bdb18032555..131ca176b49 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -133,7 +133,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) { irqreturn_t retval = IRQ_NONE; - unsigned int random = 0, irq = desc->irq_data.irq; + unsigned int flags = 0, irq = desc->irq_data.irq; do { irqreturn_t res; @@ -161,7 +161,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) /* Fall through to add to randomness */ case IRQ_HANDLED: - random |= action->flags; + flags |= action->flags; break; default: @@ -172,8 +172,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) action = action->next; } while (action); - if (random & IRQF_SAMPLE_RANDOM) - add_interrupt_randomness(irq); + add_interrupt_randomness(irq, flags); if (!noirqdebug) note_interrupt(irq, desc, retval); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 41c1564103f..49a77727db4 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -10,6 +10,7 @@ #include <linux/mutex.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/topology.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/smp.h> @@ -45,7 +46,8 @@ static struct irq_domain *irq_domain_alloc(struct device_node *of_node, { struct irq_domain *domain; - domain = kzalloc(sizeof(*domain), GFP_KERNEL); + domain = kzalloc_node(sizeof(*domain), GFP_KERNEL, + of_node_to_nid(of_node)); if (WARN_ON(!domain)) return NULL; @@ -138,6 +140,36 @@ static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain, } /** + * irq_domain_add_simple() - Allocate and register a simple irq_domain. + * @of_node: pointer to interrupt controller's device tree node. + * @size: total number of irqs in mapping + * @first_irq: first number of irq block assigned to the domain + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + * + * Allocates a legacy irq_domain if irq_base is positive or a linear + * domain otherwise. + * + * This is intended to implement the expected behaviour for most + * interrupt controllers which is that a linear mapping should + * normally be used unless the system requires a legacy mapping in + * order to support supplying interrupt numbers during non-DT + * registration of devices. + */ +struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) +{ + if (first_irq > 0) + return irq_domain_add_legacy(of_node, size, first_irq, 0, + ops, host_data); + else + return irq_domain_add_linear(of_node, size, ops, host_data); +} + +/** * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. * @size: total number of irqs in legacy mapping @@ -203,7 +235,8 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, * one can then use irq_create_mapping() to * explicitly change them */ - ops->map(domain, irq, hwirq); + if (ops->map) + ops->map(domain, irq, hwirq); /* Clear norequest flags */ irq_clear_status_flags(irq, IRQ_NOREQUEST); @@ -215,7 +248,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, EXPORT_SYMBOL_GPL(irq_domain_add_legacy); /** - * irq_domain_add_linear() - Allocate and register a legacy revmap irq_domain. + * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. * @size: Number of interrupts in the domain. * @ops: map/unmap domain callbacks @@ -229,7 +262,8 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node, struct irq_domain *domain; unsigned int *revmap; - revmap = kzalloc(sizeof(*revmap) * size, GFP_KERNEL); + revmap = kzalloc_node(sizeof(*revmap) * size, GFP_KERNEL, + of_node_to_nid(of_node)); if (WARN_ON(!revmap)) return NULL; @@ -330,24 +364,112 @@ void irq_set_default_host(struct irq_domain *domain) } EXPORT_SYMBOL_GPL(irq_set_default_host); -static int irq_setup_virq(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +static void irq_domain_disassociate_many(struct irq_domain *domain, + unsigned int irq_base, int count) { - struct irq_data *irq_data = irq_get_irq_data(virq); + /* + * disassociate in reverse order; + * not strictly necessary, but nice for unwinding + */ + while (count--) { + int irq = irq_base + count; + struct irq_data *irq_data = irq_get_irq_data(irq); + irq_hw_number_t hwirq = irq_data->hwirq; + + if (WARN_ON(!irq_data || irq_data->domain != domain)) + continue; + + irq_set_status_flags(irq, IRQ_NOREQUEST); + + /* remove chip and handler */ + irq_set_chip_and_handler(irq, NULL, NULL); + + /* Make sure it's completed */ + synchronize_irq(irq); + + /* Tell the PIC about it */ + if (domain->ops->unmap) + domain->ops->unmap(domain, irq); + smp_mb(); - irq_data->hwirq = hwirq; - irq_data->domain = domain; - if (domain->ops->map(domain, virq, hwirq)) { - pr_debug("irq-%i==>hwirq-0x%lx mapping failed\n", virq, hwirq); irq_data->domain = NULL; irq_data->hwirq = 0; - return -1; + + /* Clear reverse map */ + switch(domain->revmap_type) { + case IRQ_DOMAIN_MAP_LINEAR: + if (hwirq < domain->revmap_data.linear.size) + domain->revmap_data.linear.revmap[hwirq] = 0; + break; + case IRQ_DOMAIN_MAP_TREE: + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_data.tree, hwirq); + mutex_unlock(&revmap_trees_mutex); + break; + } } +} + +int irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, + irq_hw_number_t hwirq_base, int count) +{ + unsigned int virq = irq_base; + irq_hw_number_t hwirq = hwirq_base; + int i, ret; + + pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, + of_node_full_name(domain->of_node), irq_base, (int)hwirq_base, count); + + for (i = 0; i < count; i++) { + struct irq_data *irq_data = irq_get_irq_data(virq + i); + + if (WARN(!irq_data, "error: irq_desc not allocated; " + "irq=%i hwirq=0x%x\n", virq + i, (int)hwirq + i)) + return -EINVAL; + if (WARN(irq_data->domain, "error: irq_desc already associated; " + "irq=%i hwirq=0x%x\n", virq + i, (int)hwirq + i)) + return -EINVAL; + }; + + for (i = 0; i < count; i++, virq++, hwirq++) { + struct irq_data *irq_data = irq_get_irq_data(virq); + + irq_data->hwirq = hwirq; + irq_data->domain = domain; + if (domain->ops->map) { + ret = domain->ops->map(domain, virq, hwirq); + if (ret != 0) { + pr_err("irq-%i==>hwirq-0x%lx mapping failed: %d\n", + virq, hwirq, ret); + WARN_ON(1); + irq_data->domain = NULL; + irq_data->hwirq = 0; + goto err_unmap; + } + } - irq_clear_status_flags(virq, IRQ_NOREQUEST); + switch (domain->revmap_type) { + case IRQ_DOMAIN_MAP_LINEAR: + if (hwirq < domain->revmap_data.linear.size) + domain->revmap_data.linear.revmap[hwirq] = virq; + break; + case IRQ_DOMAIN_MAP_TREE: + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data); + mutex_unlock(&revmap_trees_mutex); + break; + } + + irq_clear_status_flags(virq, IRQ_NOREQUEST); + } return 0; + + err_unmap: + irq_domain_disassociate_many(domain, irq_base, i); + return -EINVAL; } +EXPORT_SYMBOL_GPL(irq_domain_associate_many); /** * irq_create_direct_mapping() - Allocate an irq for direct mapping @@ -364,10 +486,10 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) if (domain == NULL) domain = irq_default_domain; - BUG_ON(domain == NULL); - WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP); + if (WARN_ON(!domain || domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP)) + return 0; - virq = irq_alloc_desc_from(1, 0); + virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); if (!virq) { pr_debug("create_direct virq allocation failed\n"); return 0; @@ -380,7 +502,7 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) } pr_debug("create_direct obtained virq %d\n", virq); - if (irq_setup_virq(domain, virq, virq)) { + if (irq_domain_associate(domain, virq, virq)) { irq_free_desc(virq); return 0; } @@ -433,27 +555,64 @@ unsigned int irq_create_mapping(struct irq_domain *domain, hint = hwirq % nr_irqs; if (hint == 0) hint++; - virq = irq_alloc_desc_from(hint, 0); + virq = irq_alloc_desc_from(hint, of_node_to_nid(domain->of_node)); if (virq <= 0) - virq = irq_alloc_desc_from(1, 0); + virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; } - if (irq_setup_virq(domain, virq, hwirq)) { - if (domain->revmap_type != IRQ_DOMAIN_MAP_LEGACY) - irq_free_desc(virq); + if (irq_domain_associate(domain, virq, hwirq)) { + irq_free_desc(virq); return 0; } pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", - hwirq, domain->of_node ? domain->of_node->full_name : "null", virq); + hwirq, of_node_full_name(domain->of_node), virq); return virq; } EXPORT_SYMBOL_GPL(irq_create_mapping); +/** + * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs + * @domain: domain owning the interrupt range + * @irq_base: beginning of linux IRQ range + * @hwirq_base: beginning of hardware IRQ range + * @count: Number of interrupts to map + * + * This routine is used for allocating and mapping a range of hardware + * irqs to linux irqs where the linux irq numbers are at pre-defined + * locations. For use by controllers that already have static mappings + * to insert in to the domain. + * + * Non-linear users can use irq_create_identity_mapping() for IRQ-at-a-time + * domain insertion. + * + * 0 is returned upon success, while any failure to establish a static + * mapping is treated as an error. + */ +int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, + irq_hw_number_t hwirq_base, int count) +{ + int ret; + + ret = irq_alloc_descs(irq_base, irq_base, count, + of_node_to_nid(domain->of_node)); + if (unlikely(ret < 0)) + return ret; + + ret = irq_domain_associate_many(domain, irq_base, hwirq_base, count); + if (unlikely(ret < 0)) { + irq_free_descs(irq_base, count); + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(irq_create_strict_mappings); + unsigned int irq_create_of_mapping(struct device_node *controller, const u32 *intspec, unsigned int intsize) { @@ -477,7 +636,7 @@ unsigned int irq_create_of_mapping(struct device_node *controller, return intspec[0]; #endif pr_warning("no irq domain found for %s !\n", - controller->full_name); + of_node_full_name(controller)); return 0; } @@ -511,7 +670,6 @@ void irq_dispose_mapping(unsigned int virq) { struct irq_data *irq_data = irq_get_irq_data(virq); struct irq_domain *domain; - irq_hw_number_t hwirq; if (!virq || !irq_data) return; @@ -524,33 +682,7 @@ void irq_dispose_mapping(unsigned int virq) if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) return; - irq_set_status_flags(virq, IRQ_NOREQUEST); - - /* remove chip and handler */ - irq_set_chip_and_handler(virq, NULL, NULL); - - /* Make sure it's completed */ - synchronize_irq(virq); - - /* Tell the PIC about it */ - if (domain->ops->unmap) - domain->ops->unmap(domain, virq); - smp_mb(); - - /* Clear reverse map */ - hwirq = irq_data->hwirq; - switch(domain->revmap_type) { - case IRQ_DOMAIN_MAP_LINEAR: - if (hwirq < domain->revmap_data.linear.size) - domain->revmap_data.linear.revmap[hwirq] = 0; - break; - case IRQ_DOMAIN_MAP_TREE: - mutex_lock(&revmap_trees_mutex); - radix_tree_delete(&domain->revmap_data.tree, hwirq); - mutex_unlock(&revmap_trees_mutex); - break; - } - + irq_domain_disassociate_many(domain, virq, 1); irq_free_desc(virq); } EXPORT_SYMBOL_GPL(irq_dispose_mapping); @@ -559,16 +691,11 @@ EXPORT_SYMBOL_GPL(irq_dispose_mapping); * irq_find_mapping() - Find a linux irq from an hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space - * - * This is a slow path, for use by generic code. It's expected that an - * irq controller implementation directly calls the appropriate low level - * mapping function. */ unsigned int irq_find_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { - unsigned int i; - unsigned int hint = hwirq % nr_irqs; + struct irq_data *data; /* Look for default domain if nececssary */ if (domain == NULL) @@ -576,115 +703,47 @@ unsigned int irq_find_mapping(struct irq_domain *domain, if (domain == NULL) return 0; - /* legacy -> bail early */ - if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) + switch (domain->revmap_type) { + case IRQ_DOMAIN_MAP_LEGACY: return irq_domain_legacy_revmap(domain, hwirq); - - /* Slow path does a linear search of the map */ - if (hint == 0) - hint = 1; - i = hint; - do { - struct irq_data *data = irq_get_irq_data(i); + case IRQ_DOMAIN_MAP_LINEAR: + return irq_linear_revmap(domain, hwirq); + case IRQ_DOMAIN_MAP_TREE: + rcu_read_lock(); + data = radix_tree_lookup(&domain->revmap_data.tree, hwirq); + rcu_read_unlock(); + if (data) + return data->irq; + break; + case IRQ_DOMAIN_MAP_NOMAP: + data = irq_get_irq_data(hwirq); if (data && (data->domain == domain) && (data->hwirq == hwirq)) - return i; - i++; - if (i >= nr_irqs) - i = 1; - } while(i != hint); + return hwirq; + break; + } + return 0; } EXPORT_SYMBOL_GPL(irq_find_mapping); /** - * irq_radix_revmap_lookup() - Find a linux irq from a hw irq number. - * @domain: domain owning this hardware interrupt - * @hwirq: hardware irq number in that domain space - * - * This is a fast path, for use by irq controller code that uses radix tree - * revmaps - */ -unsigned int irq_radix_revmap_lookup(struct irq_domain *domain, - irq_hw_number_t hwirq) -{ - struct irq_data *irq_data; - - if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_TREE)) - return irq_find_mapping(domain, hwirq); - - /* - * Freeing an irq can delete nodes along the path to - * do the lookup via call_rcu. - */ - rcu_read_lock(); - irq_data = radix_tree_lookup(&domain->revmap_data.tree, hwirq); - rcu_read_unlock(); - - /* - * If found in radix tree, then fine. - * Else fallback to linear lookup - this should not happen in practice - * as it means that we failed to insert the node in the radix tree. - */ - return irq_data ? irq_data->irq : irq_find_mapping(domain, hwirq); -} -EXPORT_SYMBOL_GPL(irq_radix_revmap_lookup); - -/** - * irq_radix_revmap_insert() - Insert a hw irq to linux irq number mapping. - * @domain: domain owning this hardware interrupt - * @virq: linux irq number - * @hwirq: hardware irq number in that domain space - * - * This is for use by irq controllers that use a radix tree reverse - * mapping for fast lookup. - */ -void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) -{ - struct irq_data *irq_data = irq_get_irq_data(virq); - - if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_TREE)) - return; - - if (virq) { - mutex_lock(&revmap_trees_mutex); - radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data); - mutex_unlock(&revmap_trees_mutex); - } -} -EXPORT_SYMBOL_GPL(irq_radix_revmap_insert); - -/** * irq_linear_revmap() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space * - * This is a fast path, for use by irq controller code that uses linear - * revmaps. It does fallback to the slow path if the revmap doesn't exist - * yet and will create the revmap entry with appropriate locking + * This is a fast path that can be called directly by irq controller code to + * save a handful of instructions. */ unsigned int irq_linear_revmap(struct irq_domain *domain, irq_hw_number_t hwirq) { - unsigned int *revmap; - - if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR)) - return irq_find_mapping(domain, hwirq); + BUG_ON(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR); - /* Check revmap bounds */ - if (unlikely(hwirq >= domain->revmap_data.linear.size)) - return irq_find_mapping(domain, hwirq); - - /* Check if revmap was allocated */ - revmap = domain->revmap_data.linear.revmap; - if (unlikely(revmap == NULL)) - return irq_find_mapping(domain, hwirq); - - /* Fill up revmap with slow path if no mapping found */ - if (unlikely(!revmap[hwirq])) - revmap[hwirq] = irq_find_mapping(domain, hwirq); + /* Check revmap bounds; complain if exceeded */ + if (WARN_ON(hwirq >= domain->revmap_data.linear.size)) + return 0; - return revmap[hwirq]; + return domain->revmap_data.linear.revmap[hwirq]; } EXPORT_SYMBOL_GPL(irq_linear_revmap); @@ -725,8 +784,8 @@ static int virq_debug_show(struct seq_file *m, void *private) data = irq_desc_get_chip_data(desc); seq_printf(m, data ? "0x%p " : " %p ", data); - if (desc->irq_data.domain && desc->irq_data.domain->of_node) - p = desc->irq_data.domain->of_node->full_name; + if (desc->irq_data.domain) + p = of_node_full_name(desc->irq_data.domain->of_node); else p = none; seq_printf(m, "%s\n", p); @@ -761,12 +820,6 @@ static int __init irq_debugfs_init(void) __initcall(irq_debugfs_init); #endif /* CONFIG_IRQ_DOMAIN_DEBUG */ -static int irq_domain_simple_map(struct irq_domain *d, unsigned int irq, - irq_hw_number_t hwirq) -{ - return 0; -} - /** * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings * @@ -829,7 +882,6 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell); const struct irq_domain_ops irq_domain_simple_ops = { - .map = irq_domain_simple_map, .xlate = irq_domain_xlate_onetwocell, }; EXPORT_SYMBOL_GPL(irq_domain_simple_ops); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 8c548232ba3..4c69326aa77 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -781,7 +781,7 @@ static void wake_threads_waitq(struct irq_desc *desc) wake_up(&desc->wait_for_threads); } -static void irq_thread_dtor(struct task_work *unused) +static void irq_thread_dtor(struct callback_head *unused) { struct task_struct *tsk = current; struct irq_desc *desc; @@ -813,7 +813,7 @@ static void irq_thread_dtor(struct task_work *unused) */ static int irq_thread(void *data) { - struct task_work on_exit_work; + struct callback_head on_exit_work; static const struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, }; @@ -830,7 +830,7 @@ static int irq_thread(void *data) sched_setscheduler(current, SCHED_FIFO, ¶m); - init_task_work(&on_exit_work, irq_thread_dtor, NULL); + init_task_work(&on_exit_work, irq_thread_dtor); task_work_add(current, &on_exit_work, false); while (!irq_wait_for_interrupt(action)) { @@ -893,22 +893,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) return -ENOSYS; if (!try_module_get(desc->owner)) return -ENODEV; - /* - * Some drivers like serial.c use request_irq() heavily, - * so we have to be careful not to interfere with a - * running system. - */ - if (new->flags & IRQF_SAMPLE_RANDOM) { - /* - * This function might sleep, we want to call it first, - * outside of the atomic block. - * Yes, this might clear the entropy pool if the wrong - * driver is attempted to be loaded, without actually - * installing a new handler, but is this really a problem, - * only the sysadmin is able to do this. - */ - rand_initialize_irq(irq); - } /* * Check whether the interrupt nests into another interrupt @@ -960,6 +944,18 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } /* + * Drivers are often written to work w/o knowledge about the + * underlying irq chip implementation, so a request for a + * threaded irq without a primary hard irq context handler + * requires the ONESHOT flag to be set. Some irq chips like + * MSI based interrupts are per se one shot safe. Check the + * chip flags, so we can avoid the unmask dance at the end of + * the threaded handler for those. + */ + if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) + new->flags &= ~IRQF_ONESHOT; + + /* * The following block of code has to be executed atomically */ raw_spin_lock_irqsave(&desc->lock, flags); @@ -1033,7 +1029,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ new->thread_mask = 1 << ffz(thread_mask); - } else if (new->handler == irq_default_primary_handler) { + } else if (new->handler == irq_default_primary_handler && + !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) { /* * The interrupt was requested with handler = NULL, so * we use the default primary handler for it. But it @@ -1354,7 +1351,6 @@ EXPORT_SYMBOL(free_irq); * Flags: * * IRQF_SHARED Interrupt is shared - * IRQF_SAMPLE_RANDOM The interrupt can be used for entropy * IRQF_TRIGGER_* Specify active edge(s) or level * */ diff --git a/kernel/kexec.c b/kernel/kexec.c index 4e2e472f6ae..0668d58d641 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1424,7 +1424,7 @@ static void update_vmcoreinfo_note(void) void crash_save_vmcoreinfo(void) { - vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds()); + vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); update_vmcoreinfo_note(); } diff --git a/kernel/kmod.c b/kernel/kmod.c index ff2c7cb86d7..6f99aead66c 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -45,6 +45,13 @@ extern int max_threads; static struct workqueue_struct *khelper_wq; +/* + * kmod_thread_locker is used for deadlock avoidance. There is no explicit + * locking to protect this global - it is private to the singleton khelper + * thread and should only ever be modified by that thread. + */ +static const struct task_struct *kmod_thread_locker; + #define CAP_BSET (void *)1 #define CAP_PI (void *)2 @@ -221,6 +228,13 @@ fail: return 0; } +static int call_helper(void *data) +{ + /* Worker thread started blocking khelper thread. */ + kmod_thread_locker = current; + return ____call_usermodehelper(data); +} + static void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) @@ -295,9 +309,12 @@ static void __call_usermodehelper(struct work_struct *work) if (wait == UMH_WAIT_PROC) pid = kernel_thread(wait_for_helper, sub_info, CLONE_FS | CLONE_FILES | SIGCHLD); - else - pid = kernel_thread(____call_usermodehelper, sub_info, + else { + pid = kernel_thread(call_helper, sub_info, CLONE_VFORK | SIGCHLD); + /* Worker thread stopped blocking khelper thread. */ + kmod_thread_locker = NULL; + } switch (wait) { case UMH_NO_WAIT: @@ -548,6 +565,16 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) retval = -EBUSY; goto out; } + /* + * Worker thread must not wait for khelper thread at below + * wait_for_completion() if the thread was created with CLONE_VFORK + * flag, for khelper thread is already waiting for the thread at + * wait_for_completion() in do_fork(). + */ + if (wait != UMH_NO_WAIT && current == kmod_thread_locker) { + retval = -EBUSY; + goto out; + } sub_info->complete = &done; sub_info->wait = wait; @@ -577,6 +604,12 @@ unlock: return retval; } +/* + * call_usermodehelper_fns() will not run the caller-provided cleanup function + * if a memory allocation failure is experienced. So the caller might need to + * check the call_usermodehelper_fns() return value: if it is -ENOMEM, perform + * the necessaary cleanup within the caller. + */ int call_usermodehelper_fns( char *path, char **argv, char **envp, int wait, int (*init)(struct subprocess_info *info, struct cred *new), diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c62b8546cc9..098f396aa40 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -561,9 +561,9 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) { LIST_HEAD(free_list); + mutex_lock(&kprobe_mutex); /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); - mutex_lock(&kprobe_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) @@ -586,8 +586,8 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(&free_list); - mutex_unlock(&kprobe_mutex); mutex_unlock(&module_mutex); + mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) @@ -759,20 +759,32 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p) struct kprobe *ap; struct optimized_kprobe *op; + /* Impossible to optimize ftrace-based kprobe */ + if (kprobe_ftrace(p)) + return; + + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + mutex_lock(&text_mutex); + ap = alloc_aggr_kprobe(p); if (!ap) - return; + goto out; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe */ arch_remove_optimized_kprobe(op); kfree(op); - return; + goto out; } init_aggr_kprobe(ap, p); - optimize_kprobe(ap); + optimize_kprobe(ap); /* This just kicks optimizer thread */ + +out: + mutex_unlock(&text_mutex); + jump_label_unlock(); } #ifdef CONFIG_SYSCTL @@ -907,9 +919,64 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) } #endif /* CONFIG_OPTPROBES */ +#ifdef KPROBES_CAN_USE_FTRACE +static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { + .func = kprobe_ftrace_handler, + .flags = FTRACE_OPS_FL_SAVE_REGS, +}; +static int kprobe_ftrace_enabled; + +/* Must ensure p->addr is really on ftrace */ +static int __kprobes prepare_kprobe(struct kprobe *p) +{ + if (!kprobe_ftrace(p)) + return arch_prepare_kprobe(p); + + return arch_prepare_kprobe_ftrace(p); +} + +/* Caller must lock kprobe_mutex */ +static void __kprobes arm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 0, 0); + WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + kprobe_ftrace_enabled++; + if (kprobe_ftrace_enabled == 1) { + ret = register_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } +} + +/* Caller must lock kprobe_mutex */ +static void __kprobes disarm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + kprobe_ftrace_enabled--; + if (kprobe_ftrace_enabled == 0) { + ret = unregister_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 1, 0); + WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); +} +#else /* !KPROBES_CAN_USE_FTRACE */ +#define prepare_kprobe(p) arch_prepare_kprobe(p) +#define arm_kprobe_ftrace(p) do {} while (0) +#define disarm_kprobe_ftrace(p) do {} while (0) +#endif + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { + if (unlikely(kprobe_ftrace(kp))) { + arm_kprobe_ftrace(kp); + return; + } /* * Here, since __arm_kprobe() doesn't use stop_machine(), * this doesn't cause deadlock on text_mutex. So, we don't @@ -921,11 +988,15 @@ static void __kprobes arm_kprobe(struct kprobe *kp) } /* Disarm a kprobe with text_mutex */ -static void __kprobes disarm_kprobe(struct kprobe *kp) +static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt) { + if (unlikely(kprobe_ftrace(kp))) { + disarm_kprobe_ftrace(kp); + return; + } /* Ditto */ mutex_lock(&text_mutex); - __disarm_kprobe(kp, true); + __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); } @@ -1144,12 +1215,6 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; - if (kprobe_disabled(ap) && !kprobe_disabled(p)) { - ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) - /* Arm the breakpoint again. */ - __arm_kprobe(ap); - } return 0; } @@ -1189,11 +1254,22 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, int ret = 0; struct kprobe *ap = orig_p; + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + /* + * Get online CPUs to avoid text_mutex deadlock.with stop machine, + * which is invoked by unoptimize_kprobe() in add_new_kprobe() + */ + get_online_cpus(); + mutex_lock(&text_mutex); + if (!kprobe_aggrprobe(orig_p)) { /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ ap = alloc_aggr_kprobe(orig_p); - if (!ap) - return -ENOMEM; + if (!ap) { + ret = -ENOMEM; + goto out; + } init_aggr_kprobe(ap, orig_p); } else if (kprobe_unused(ap)) /* This probe is going to die. Rescue it */ @@ -1213,7 +1289,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, * free aggr_probe. It will be used next time, or * freed by unregister_kprobe. */ - return ret; + goto out; /* Prepare optimized instructions if possible. */ prepare_optimized_kprobe(ap); @@ -1228,7 +1304,20 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, /* Copy ap's insn slot to p */ copy_kprobe(ap, p); - return add_new_kprobe(ap, p); + ret = add_new_kprobe(ap, p); + +out: + mutex_unlock(&text_mutex); + put_online_cpus(); + jump_label_unlock(); + + if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { + ap->flags &= ~KPROBE_FLAG_DISABLED; + if (!kprobes_all_disarmed) + /* Arm the breakpoint again. */ + arm_kprobe(ap); + } + return ret; } static int __kprobes in_kprobes_functions(unsigned long addr) @@ -1313,71 +1402,96 @@ static inline int check_kprobe_rereg(struct kprobe *p) return ret; } -int __kprobes register_kprobe(struct kprobe *p) +static __kprobes int check_kprobe_address_safe(struct kprobe *p, + struct module **probed_mod) { int ret = 0; - struct kprobe *old_p; - struct module *probed_mod; - kprobe_opcode_t *addr; - - addr = kprobe_addr(p); - if (IS_ERR(addr)) - return PTR_ERR(addr); - p->addr = addr; + unsigned long ftrace_addr; - ret = check_kprobe_rereg(p); - if (ret) - return ret; + /* + * If the address is located on a ftrace nop, set the + * breakpoint to the following instruction. + */ + ftrace_addr = ftrace_location((unsigned long)p->addr); + if (ftrace_addr) { +#ifdef KPROBES_CAN_USE_FTRACE + /* Given address is not on the instruction boundary */ + if ((unsigned long)p->addr != ftrace_addr) + return -EILSEQ; + p->flags |= KPROBE_FLAG_FTRACE; +#else /* !KPROBES_CAN_USE_FTRACE */ + return -EINVAL; +#endif + } jump_label_lock(); preempt_disable(); + + /* Ensure it is not in reserved area nor out of text */ if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || - ftrace_text_reserved(p->addr, p->addr) || jump_label_text_reserved(p->addr, p->addr)) { ret = -EINVAL; - goto cannot_probe; + goto out; } - /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ - p->flags &= KPROBE_FLAG_DISABLED; - - /* - * Check if are we probing a module. - */ - probed_mod = __module_text_address((unsigned long) p->addr); - if (probed_mod) { - /* Return -ENOENT if fail. */ - ret = -ENOENT; + /* Check if are we probing a module */ + *probed_mod = __module_text_address((unsigned long) p->addr); + if (*probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ - if (unlikely(!try_module_get(probed_mod))) - goto cannot_probe; + if (unlikely(!try_module_get(*probed_mod))) { + ret = -ENOENT; + goto out; + } /* * If the module freed .init.text, we couldn't insert * kprobes in there. */ - if (within_module_init((unsigned long)p->addr, probed_mod) && - probed_mod->state != MODULE_STATE_COMING) { - module_put(probed_mod); - goto cannot_probe; + if (within_module_init((unsigned long)p->addr, *probed_mod) && + (*probed_mod)->state != MODULE_STATE_COMING) { + module_put(*probed_mod); + *probed_mod = NULL; + ret = -ENOENT; } - /* ret will be updated by following code */ } +out: preempt_enable(); jump_label_unlock(); + return ret; +} + +int __kprobes register_kprobe(struct kprobe *p) +{ + int ret; + struct kprobe *old_p; + struct module *probed_mod; + kprobe_opcode_t *addr; + + /* Adjust probe address from symbol */ + addr = kprobe_addr(p); + if (IS_ERR(addr)) + return PTR_ERR(addr); + p->addr = addr; + + ret = check_kprobe_rereg(p); + if (ret) + return ret; + + /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ + p->flags &= KPROBE_FLAG_DISABLED; p->nmissed = 0; INIT_LIST_HEAD(&p->list); - mutex_lock(&kprobe_mutex); - jump_label_lock(); /* needed to call jump_label_text_reserved() */ + ret = check_kprobe_address_safe(p, &probed_mod); + if (ret) + return ret; - get_online_cpus(); /* For avoiding text_mutex deadlock. */ - mutex_lock(&text_mutex); + mutex_lock(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { @@ -1386,7 +1500,9 @@ int __kprobes register_kprobe(struct kprobe *p) goto out; } - ret = arch_prepare_kprobe(p); + mutex_lock(&text_mutex); /* Avoiding text modification */ + ret = prepare_kprobe(p); + mutex_unlock(&text_mutex); if (ret) goto out; @@ -1395,26 +1511,18 @@ int __kprobes register_kprobe(struct kprobe *p) &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) - __arm_kprobe(p); + arm_kprobe(p); /* Try to optimize kprobe */ try_to_optimize_kprobe(p); out: - mutex_unlock(&text_mutex); - put_online_cpus(); - jump_label_unlock(); mutex_unlock(&kprobe_mutex); if (probed_mod) module_put(probed_mod); return ret; - -cannot_probe: - preempt_enable(); - jump_label_unlock(); - return ret; } EXPORT_SYMBOL_GPL(register_kprobe); @@ -1451,7 +1559,7 @@ static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { - disarm_kprobe(orig_p); + disarm_kprobe(orig_p, true); orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -2049,10 +2157,11 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, if (!pp) pp = p; - seq_printf(pi, "%s%s%s\n", + seq_printf(pi, "%s%s%s%s\n", (kprobe_gone(p) ? "[GONE]" : ""), ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), - (kprobe_optimized(pp) ? "[OPTIMIZED]" : "")); + (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), + (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -2131,14 +2240,12 @@ static void __kprobes arm_all_kprobes(void) goto already_enabled; /* Arming kprobes doesn't optimize kprobe itself */ - mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_disabled(p)) - __arm_kprobe(p); + arm_kprobe(p); } - mutex_unlock(&text_mutex); kprobes_all_disarmed = false; printk(KERN_INFO "Kprobes globally enabled\n"); @@ -2166,15 +2273,13 @@ static void __kprobes disarm_all_kprobes(void) kprobes_all_disarmed = true; printk(KERN_INFO "Kprobes globally disabled\n"); - mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - __disarm_kprobe(p, false); + disarm_kprobe(p, false); } } - mutex_unlock(&text_mutex); mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ diff --git a/kernel/kthread.c b/kernel/kthread.c index 3d3de633702..146a6fa9682 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -37,11 +37,20 @@ struct kthread_create_info }; struct kthread { - int should_stop; + unsigned long flags; + unsigned int cpu; void *data; + struct completion parked; struct completion exited; }; +enum KTHREAD_BITS { + KTHREAD_IS_PER_CPU = 0, + KTHREAD_SHOULD_STOP, + KTHREAD_SHOULD_PARK, + KTHREAD_IS_PARKED, +}; + #define to_kthread(tsk) \ container_of((tsk)->vfork_done, struct kthread, exited) @@ -52,13 +61,29 @@ struct kthread { * and this will return true. You should then return, and your return * value will be passed through to kthread_stop(). */ -int kthread_should_stop(void) +bool kthread_should_stop(void) { - return to_kthread(current)->should_stop; + return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); } EXPORT_SYMBOL(kthread_should_stop); /** + * kthread_should_park - should this kthread park now? + * + * When someone calls kthread_park() on your kthread, it will be woken + * and this will return true. You should then do the necessary + * cleanup and call kthread_parkme() + * + * Similar to kthread_should_stop(), but this keeps the thread alive + * and in a park position. kthread_unpark() "restarts" the thread and + * calls the thread function again. + */ +bool kthread_should_park(void) +{ + return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags); +} + +/** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen * @@ -96,6 +121,24 @@ void *kthread_data(struct task_struct *task) return to_kthread(task)->data; } +static void __kthread_parkme(struct kthread *self) +{ + __set_current_state(TASK_INTERRUPTIBLE); + while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) { + if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags)) + complete(&self->parked); + schedule(); + __set_current_state(TASK_INTERRUPTIBLE); + } + clear_bit(KTHREAD_IS_PARKED, &self->flags); + __set_current_state(TASK_RUNNING); +} + +void kthread_parkme(void) +{ + __kthread_parkme(to_kthread(current)); +} + static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ @@ -105,9 +148,10 @@ static int kthread(void *_create) struct kthread self; int ret; - self.should_stop = 0; + self.flags = 0; self.data = data; init_completion(&self.exited); + init_completion(&self.parked); current->vfork_done = &self.exited; /* OK, tell user we're spawned, wait for stop or wakeup */ @@ -117,9 +161,11 @@ static int kthread(void *_create) schedule(); ret = -EINTR; - if (!self.should_stop) - ret = threadfn(data); + if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) { + __kthread_parkme(&self); + ret = threadfn(data); + } /* we can't just return, we must preserve "self" on stack */ do_exit(ret); } @@ -172,8 +218,7 @@ static void create_kthread(struct kthread_create_info *create) * Returns a task_struct or ERR_PTR(-ENOMEM). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), - void *data, - int node, + void *data, int node, const char namefmt[], ...) { @@ -210,6 +255,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), } EXPORT_SYMBOL(kthread_create_on_node); +static void __kthread_bind(struct task_struct *p, unsigned int cpu) +{ + /* It's safe because the task is inactive. */ + do_set_cpus_allowed(p, cpumask_of(cpu)); + p->flags |= PF_THREAD_BOUND; +} + /** * kthread_bind - bind a just-created kthread to a cpu. * @p: thread created by kthread_create(). @@ -226,14 +278,112 @@ void kthread_bind(struct task_struct *p, unsigned int cpu) WARN_ON(1); return; } - - /* It's safe because the task is inactive. */ - do_set_cpus_allowed(p, cpumask_of(cpu)); - p->flags |= PF_THREAD_BOUND; + __kthread_bind(p, cpu); } EXPORT_SYMBOL(kthread_bind); /** + * kthread_create_on_cpu - Create a cpu bound kthread + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: This helper function creates and names a kernel thread + * The thread will be woken and put into park mode. + */ +struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), + void *data, unsigned int cpu, + const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, + cpu); + if (IS_ERR(p)) + return p; + set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); + to_kthread(p)->cpu = cpu; + /* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */ + kthread_park(p); + return p; +} + +static struct kthread *task_get_live_kthread(struct task_struct *k) +{ + struct kthread *kthread; + + get_task_struct(k); + kthread = to_kthread(k); + /* It might have exited */ + barrier(); + if (k->vfork_done != NULL) + return kthread; + return NULL; +} + +/** + * kthread_unpark - unpark a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_park() for @k to return false, wakes it, and + * waits for it to return. If the thread is marked percpu then its + * bound to the cpu again. + */ +void kthread_unpark(struct task_struct *k) +{ + struct kthread *kthread = task_get_live_kthread(k); + + if (kthread) { + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * We clear the IS_PARKED bit here as we don't wait + * until the task has left the park code. So if we'd + * park before that happens we'd see the IS_PARKED bit + * which might be about to be cleared. + */ + if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) + __kthread_bind(k, kthread->cpu); + wake_up_process(k); + } + } + put_task_struct(k); +} + +/** + * kthread_park - park a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_park() for @k to return true, wakes it, and + * waits for it to return. This can also be called after kthread_create() + * instead of calling wake_up_process(): the thread will park without + * calling threadfn(). + * + * Returns 0 if the thread is parked, -ENOSYS if the thread exited. + * If called by the kthread itself just the park bit is set. + */ +int kthread_park(struct task_struct *k) +{ + struct kthread *kthread = task_get_live_kthread(k); + int ret = -ENOSYS; + + if (kthread) { + if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + if (k != current) { + wake_up_process(k); + wait_for_completion(&kthread->parked); + } + } + ret = 0; + } + put_task_struct(k); + return ret; +} + +/** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * @@ -250,16 +400,13 @@ EXPORT_SYMBOL(kthread_bind); */ int kthread_stop(struct task_struct *k) { - struct kthread *kthread; + struct kthread *kthread = task_get_live_kthread(k); int ret; trace_sched_kthread_stop(k); - get_task_struct(k); - - kthread = to_kthread(k); - barrier(); /* it might have exited */ - if (k->vfork_done != NULL) { - kthread->should_stop = 1; + if (kthread) { + set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); wake_up_process(k); wait_for_completion(&kthread->exited); } @@ -360,16 +507,12 @@ repeat: struct kthread_work, node); list_del_init(&work->node); } + worker->current_work = work; spin_unlock_irq(&worker->lock); if (work) { __set_current_state(TASK_RUNNING); work->func(work); - smp_wmb(); /* wmb worker-b0 paired with flush-b1 */ - work->done_seq = work->queue_seq; - smp_mb(); /* mb worker-b1 paired with flush-b0 */ - if (atomic_read(&work->flushing)) - wake_up_all(&work->done); } else if (!freezing(current)) schedule(); @@ -378,6 +521,19 @@ repeat: } EXPORT_SYMBOL_GPL(kthread_worker_fn); +/* insert @work before @pos in @worker */ +static void insert_kthread_work(struct kthread_worker *worker, + struct kthread_work *work, + struct list_head *pos) +{ + lockdep_assert_held(&worker->lock); + + list_add_tail(&work->node, pos); + work->worker = worker; + if (likely(worker->task)) + wake_up_process(worker->task); +} + /** * queue_kthread_work - queue a kthread_work * @worker: target kthread_worker @@ -395,10 +551,7 @@ bool queue_kthread_work(struct kthread_worker *worker, spin_lock_irqsave(&worker->lock, flags); if (list_empty(&work->node)) { - list_add_tail(&work->node, &worker->work_list); - work->queue_seq++; - if (likely(worker->task)) - wake_up_process(worker->task); + insert_kthread_work(worker, work, &worker->work_list); ret = true; } spin_unlock_irqrestore(&worker->lock, flags); @@ -406,6 +559,18 @@ bool queue_kthread_work(struct kthread_worker *worker, } EXPORT_SYMBOL_GPL(queue_kthread_work); +struct kthread_flush_work { + struct kthread_work work; + struct completion done; +}; + +static void kthread_flush_work_fn(struct kthread_work *work) +{ + struct kthread_flush_work *fwork = + container_of(work, struct kthread_flush_work, work); + complete(&fwork->done); +} + /** * flush_kthread_work - flush a kthread_work * @work: work to flush @@ -414,39 +579,37 @@ EXPORT_SYMBOL_GPL(queue_kthread_work); */ void flush_kthread_work(struct kthread_work *work) { - int seq = work->queue_seq; - - atomic_inc(&work->flushing); + struct kthread_flush_work fwork = { + KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), + COMPLETION_INITIALIZER_ONSTACK(fwork.done), + }; + struct kthread_worker *worker; + bool noop = false; - /* - * mb flush-b0 paired with worker-b1, to make sure either - * worker sees the above increment or we see done_seq update. - */ - smp_mb__after_atomic_inc(); +retry: + worker = work->worker; + if (!worker) + return; - /* A - B <= 0 tests whether B is in front of A regardless of overflow */ - wait_event(work->done, seq - work->done_seq <= 0); - atomic_dec(&work->flushing); + spin_lock_irq(&worker->lock); + if (work->worker != worker) { + spin_unlock_irq(&worker->lock); + goto retry; + } - /* - * rmb flush-b1 paired with worker-b0, to make sure our caller - * sees every change made by work->func(). - */ - smp_mb__after_atomic_dec(); -} -EXPORT_SYMBOL_GPL(flush_kthread_work); + if (!list_empty(&work->node)) + insert_kthread_work(worker, &fwork.work, work->node.next); + else if (worker->current_work == work) + insert_kthread_work(worker, &fwork.work, worker->work_list.next); + else + noop = true; -struct kthread_flush_work { - struct kthread_work work; - struct completion done; -}; + spin_unlock_irq(&worker->lock); -static void kthread_flush_work_fn(struct kthread_work *work) -{ - struct kthread_flush_work *fwork = - container_of(work, struct kthread_flush_work, work); - complete(&fwork->done); + if (!noop) + wait_for_completion(&fwork.done); } +EXPORT_SYMBOL_GPL(flush_kthread_work); /** * flush_kthread_worker - flush all current works on a kthread_worker diff --git a/kernel/lockdep.c b/kernel/lockdep.c index ea9ee4518c3..7981e5b2350 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2998,6 +2998,42 @@ EXPORT_SYMBOL_GPL(lockdep_init_map); struct lock_class_key __lockdep_no_validate__; +static int +print_lock_nested_lock_not_held(struct task_struct *curr, + struct held_lock *hlock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n"); + printk("==================================\n"); + printk("[ BUG: Nested lock was not taken ]\n"); + print_kernel_ident(); + printk("----------------------------------\n"); + + printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); + print_lock(hlock); + + printk("\nbut this task is not holding:\n"); + printk("%s\n", hlock->nest_lock->name); + + printk("\nstack backtrace:\n"); + dump_stack(); + + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static int __lock_is_held(struct lockdep_map *lock); + /* * This gets called for every mutex_lock*()/spin_lock*() operation. * We maintain the dependency maps and validate the locking attempt: @@ -3139,6 +3175,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, } chain_key = iterate_chain_key(chain_key, id); + if (nest_lock && !__lock_is_held(nest_lock)) + return print_lock_nested_lock_not_held(curr, hlock, ip); + if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) return 0; diff --git a/kernel/panic.c b/kernel/panic.c index d2a5f4ecc6d..e1b2822fff9 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -75,6 +75,14 @@ void panic(const char *fmt, ...) int state = 0; /* + * Disable local interrupts. This will prevent panic_smp_self_stop + * from deadlocking the first cpu that invokes the panic, since + * there is nothing to prevent an interrupt handler (that runs + * after the panic_lock is acquired) from invoking panic again. + */ + local_irq_disable(); + + /* * 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... diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index b3c7fd55425..6144bab8fd8 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -232,15 +232,19 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, */ tmp.data = ¤t->nsproxy->pid_ns->last_pid; - return proc_dointvec(&tmp, write, buffer, lenp, ppos); + return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); } +extern int pid_max; +static int zero = 0; static struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, + .extra1 = &zero, + .extra2 = &pid_max, }, { } }; diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 8f9b4eb974e..a70518c9d82 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -175,7 +175,7 @@ config PM_TEST_SUSPEND You probably want to have your system's RTC driver statically linked, ensuring that it's available when this test runs. -config CAN_PM_TRACE +config PM_SLEEP_DEBUG def_bool y depends on PM_DEBUG && PM_SLEEP @@ -196,7 +196,7 @@ config PM_TRACE config PM_TRACE_RTC bool "Suspend/resume event tracing" - depends on CAN_PM_TRACE + depends on PM_SLEEP_DEBUG depends on X86 select PM_TRACE ---help--- diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 8b53db38a27..b26f5f1e773 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -5,6 +5,7 @@ * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc. + * Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com> * * This file is released under the GPLv2. */ @@ -27,7 +28,6 @@ #include <linux/syscore_ops.h> #include <linux/ctype.h> #include <linux/genhd.h> -#include <scsi/scsi_scan.h> #include "power.h" @@ -46,6 +46,9 @@ enum { HIBERNATION_PLATFORM, HIBERNATION_SHUTDOWN, HIBERNATION_REBOOT, +#ifdef CONFIG_SUSPEND + HIBERNATION_SUSPEND, +#endif /* keep last */ __HIBERNATION_AFTER_LAST }; @@ -354,6 +357,7 @@ int hibernation_snapshot(int platform_mode) } suspend_console(); + ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); @@ -379,6 +383,7 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) pm_restore_gfp_mask(); + ftrace_start(); resume_console(); dpm_complete(msg); @@ -481,6 +486,7 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); + ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { @@ -488,6 +494,7 @@ int hibernation_restore(int platform_mode) dpm_resume_end(PMSG_RECOVER); } pm_restore_gfp_mask(); + ftrace_start(); resume_console(); pm_restore_console(); return error; @@ -514,6 +521,7 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); + ftrace_stop(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -557,6 +565,7 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); + ftrace_start(); resume_console(); Close: @@ -574,6 +583,10 @@ int hibernation_platform_enter(void) */ static void power_down(void) { +#ifdef CONFIG_SUSPEND + int error; +#endif + switch (hibernation_mode) { case HIBERNATION_REBOOT: kernel_restart(NULL); @@ -583,6 +596,25 @@ static void power_down(void) case HIBERNATION_SHUTDOWN: kernel_power_off(); break; +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: + error = suspend_devices_and_enter(PM_SUSPEND_MEM); + if (error) { + if (hibernation_ops) + hibernation_mode = HIBERNATION_PLATFORM; + else + hibernation_mode = HIBERNATION_SHUTDOWN; + power_down(); + } + /* + * Restore swap signature. + */ + error = swsusp_unmark(); + if (error) + printk(KERN_ERR "PM: Swap will be unusable! " + "Try swapon -a.\n"); + return; +#endif } kernel_halt(); /* @@ -748,13 +780,6 @@ static int software_resume(void) async_synchronize_full(); } - /* - * We can't depend on SCSI devices being available after loading - * one of their modules until scsi_complete_async_scans() is - * called and the resume device usually is a SCSI one. - */ - scsi_complete_async_scans(); - swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { error = -ENODEV; @@ -827,6 +852,9 @@ static const char * const hibernation_modes[] = { [HIBERNATION_PLATFORM] = "platform", [HIBERNATION_SHUTDOWN] = "shutdown", [HIBERNATION_REBOOT] = "reboot", +#ifdef CONFIG_SUSPEND + [HIBERNATION_SUSPEND] = "suspend", +#endif }; /* @@ -867,6 +895,9 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, switch (i) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: +#endif break; case HIBERNATION_PLATFORM: if (hibernation_ops) @@ -907,6 +938,9 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, switch (mode) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: +#endif hibernation_mode = mode; break; case HIBERNATION_PLATFORM: diff --git a/kernel/power/main.c b/kernel/power/main.c index 428f8a034e9..f458238109c 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -235,6 +235,47 @@ late_initcall(pm_debugfs_init); #endif /* CONFIG_PM_SLEEP */ +#ifdef CONFIG_PM_SLEEP_DEBUG +/* + * pm_print_times: print time taken by devices to suspend and resume. + * + * show() returns whether printing of suspend and resume times is enabled. + * store() accepts 0 or 1. 0 disables printing and 1 enables it. + */ +bool pm_print_times_enabled; + +static ssize_t pm_print_times_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", pm_print_times_enabled); +} + +static ssize_t pm_print_times_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + pm_print_times_enabled = !!val; + return n; +} + +power_attr(pm_print_times); + +static inline void pm_print_times_init(void) +{ + pm_print_times_enabled = !!initcall_debug; +} +#else /* !CONFIG_PP_SLEEP_DEBUG */ +static inline void pm_print_times_init(void) {} +#endif /* CONFIG_PM_SLEEP_DEBUG */ + struct kobject *power_kobj; /** @@ -531,6 +572,9 @@ static struct attribute * g[] = { #ifdef CONFIG_PM_DEBUG &pm_test_attr.attr, #endif +#ifdef CONFIG_PM_SLEEP_DEBUG + &pm_print_times_attr.attr, +#endif #endif NULL, }; @@ -566,6 +610,7 @@ static int __init pm_init(void) error = sysfs_create_group(power_kobj, &attr_group); if (error) return error; + pm_print_times_init(); return pm_autosleep_init(); } diff --git a/kernel/power/power.h b/kernel/power/power.h index b0bd4beaebf..7d4b7ffb3c1 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -156,6 +156,9 @@ extern void swsusp_free(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); extern void swsusp_close(fmode_t); +#ifdef CONFIG_SUSPEND +extern int swsusp_unmark(void); +#endif /* kernel/power/block_io.c */ extern struct block_device *hib_resume_bdev; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 396d262b8fd..c8b7446b27d 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> +#include <linux/ftrace.h> #include <trace/events/power.h> #include "power.h" @@ -212,6 +213,7 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); + ftrace_stop(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -231,6 +233,7 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); + ftrace_start(); resume_console(); Close: if (suspend_ops->end) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 11e22c068e8..3c9d764eb0d 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -448,9 +448,9 @@ static int save_image(struct swap_map_handle *handle, struct timeval start; struct timeval stop; - printk(KERN_INFO "PM: Saving image data pages (%u pages) ... ", + printk(KERN_INFO "PM: Saving image data pages (%u pages)...\n", nr_to_write); - m = nr_to_write / 100; + m = nr_to_write / 10; if (!m) m = 1; nr_pages = 0; @@ -464,7 +464,8 @@ static int save_image(struct swap_map_handle *handle, if (ret) break; if (!(nr_pages % m)) - printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_INFO "PM: Image saving progress: %3d%%\n", + nr_pages / m * 10); nr_pages++; } err2 = hib_wait_on_bio_chain(&bio); @@ -472,9 +473,7 @@ static int save_image(struct swap_map_handle *handle, if (!ret) ret = err2; if (!ret) - printk(KERN_CONT "\b\b\b\bdone\n"); - else - printk(KERN_CONT "\n"); + printk(KERN_INFO "PM: Image saving done.\n"); swsusp_show_speed(&start, &stop, nr_to_write, "Wrote"); return ret; } @@ -668,9 +667,9 @@ static int save_image_lzo(struct swap_map_handle *handle, printk(KERN_INFO "PM: Using %u thread(s) for compression.\n" - "PM: Compressing and saving image data (%u pages) ... ", + "PM: Compressing and saving image data (%u pages)...\n", nr_threads, nr_to_write); - m = nr_to_write / 100; + m = nr_to_write / 10; if (!m) m = 1; nr_pages = 0; @@ -690,8 +689,10 @@ static int save_image_lzo(struct swap_map_handle *handle, data_of(*snapshot), PAGE_SIZE); if (!(nr_pages % m)) - printk(KERN_CONT "\b\b\b\b%3d%%", - nr_pages / m); + printk(KERN_INFO + "PM: Image saving progress: " + "%3d%%\n", + nr_pages / m * 10); nr_pages++; } if (!off) @@ -761,11 +762,8 @@ out_finish: do_gettimeofday(&stop); if (!ret) ret = err2; - if (!ret) { - printk(KERN_CONT "\b\b\b\bdone\n"); - } else { - printk(KERN_CONT "\n"); - } + if (!ret) + printk(KERN_INFO "PM: Image saving done.\n"); swsusp_show_speed(&start, &stop, nr_to_write, "Wrote"); out_clean: if (crc) { @@ -973,9 +971,9 @@ static int load_image(struct swap_map_handle *handle, int err2; unsigned nr_pages; - printk(KERN_INFO "PM: Loading image data pages (%u pages) ... ", + printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n", nr_to_read); - m = nr_to_read / 100; + m = nr_to_read / 10; if (!m) m = 1; nr_pages = 0; @@ -993,7 +991,8 @@ static int load_image(struct swap_map_handle *handle, if (ret) break; if (!(nr_pages % m)) - printk("\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_INFO "PM: Image loading progress: %3d%%\n", + nr_pages / m * 10); nr_pages++; } err2 = hib_wait_on_bio_chain(&bio); @@ -1001,12 +1000,11 @@ static int load_image(struct swap_map_handle *handle, if (!ret) ret = err2; if (!ret) { - printk("\b\b\b\bdone\n"); + printk(KERN_INFO "PM: Image loading done.\n"); snapshot_write_finalize(snapshot); if (!snapshot_image_loaded(snapshot)) ret = -ENODATA; - } else - printk("\n"); + } swsusp_show_speed(&start, &stop, nr_to_read, "Read"); return ret; } @@ -1185,9 +1183,9 @@ static int load_image_lzo(struct swap_map_handle *handle, printk(KERN_INFO "PM: Using %u thread(s) for decompression.\n" - "PM: Loading and decompressing image data (%u pages) ... ", + "PM: Loading and decompressing image data (%u pages)...\n", nr_threads, nr_to_read); - m = nr_to_read / 100; + m = nr_to_read / 10; if (!m) m = 1; nr_pages = 0; @@ -1319,7 +1317,10 @@ static int load_image_lzo(struct swap_map_handle *handle, data[thr].unc + off, PAGE_SIZE); if (!(nr_pages % m)) - printk("\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_INFO + "PM: Image loading progress: " + "%3d%%\n", + nr_pages / m * 10); nr_pages++; ret = snapshot_write_next(snapshot); @@ -1344,7 +1345,7 @@ out_finish: } do_gettimeofday(&stop); if (!ret) { - printk("\b\b\b\bdone\n"); + printk(KERN_INFO "PM: Image loading done.\n"); snapshot_write_finalize(snapshot); if (!snapshot_image_loaded(snapshot)) ret = -ENODATA; @@ -1357,8 +1358,7 @@ out_finish: } } } - } else - printk("\n"); + } swsusp_show_speed(&start, &stop, nr_to_read, "Read"); out_clean: for (i = 0; i < ring_size; i++) @@ -1472,6 +1472,34 @@ void swsusp_close(fmode_t mode) blkdev_put(hib_resume_bdev, mode); } +/** + * swsusp_unmark - Unmark swsusp signature in the resume device + */ + +#ifdef CONFIG_SUSPEND +int swsusp_unmark(void) +{ + int error; + + hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL); + if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) { + memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10); + error = hib_bio_write_page(swsusp_resume_block, + swsusp_header, NULL); + } else { + printk(KERN_ERR "PM: Cannot find swsusp signature!\n"); + error = -ENODEV; + } + + /* + * We just returned from suspend, we don't need the image any more. + */ + free_all_swap_pages(root_swap); + + return error; +} +#endif + static int swsusp_header_init(void) { swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL); diff --git a/kernel/power/user.c b/kernel/power/user.c index 91b0fd021a9..4ed81e74f86 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -24,7 +24,6 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> -#include <scsi/scsi_scan.h> #include <asm/uaccess.h> @@ -84,7 +83,6 @@ static int snapshot_open(struct inode *inode, struct file *filp) * appear. */ wait_for_device_probe(); - scsi_complete_async_scans(); data->swap = -1; data->mode = O_WRONLY; diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index c8fba338007..8f50de394d2 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -9,6 +9,7 @@ * manipulate wakelocks on Android. */ +#include <linux/capability.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/err.h> @@ -188,6 +189,9 @@ int pm_wake_lock(const char *buf) size_t len; int ret = 0; + if (!capable(CAP_BLOCK_SUSPEND)) + return -EPERM; + while (*str && !isspace(*str)) str++; @@ -231,6 +235,9 @@ int pm_wake_unlock(const char *buf) size_t len; int ret = 0; + if (!capable(CAP_BLOCK_SUSPEND)) + return -EPERM; + len = strlen(buf); if (!len) return -EINVAL; diff --git a/kernel/printk.c b/kernel/printk.c index 177fa49357a..66a2ea37b57 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -216,6 +216,7 @@ struct log { */ static DEFINE_RAW_SPINLOCK(logbuf_lock); +#ifdef CONFIG_PRINTK /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static u32 syslog_idx; @@ -228,14 +229,19 @@ static u32 log_first_idx; /* index and sequence number of the next record to store in the buffer */ static u64 log_next_seq; -#ifdef CONFIG_PRINTK static u32 log_next_idx; +/* the next printk record to write to the console */ +static u64 console_seq; +static u32 console_idx; +static enum log_flags console_prev; + /* the next printk record to read after the last 'clear' command */ static u64 clear_seq; static u32 clear_idx; -#define LOG_LINE_MAX 1024 +#define PREFIX_MAX 32 +#define LOG_LINE_MAX 1024 - PREFIX_MAX /* record buffer */ #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) @@ -360,6 +366,7 @@ static void log_store(int facility, int level, struct devkmsg_user { u64 seq; u32 idx; + enum log_flags prev; struct mutex lock; char buf[8192]; }; @@ -382,8 +389,10 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv, line = buf; for (i = 0; i < count; i++) { - if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) + if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) { + ret = -EFAULT; goto out; + } line += iv[i].iov_len; } @@ -425,6 +434,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, struct log *msg; u64 ts_usec; size_t i; + char cont = '-'; size_t len; ssize_t ret; @@ -462,8 +472,25 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, msg = log_from_idx(user->idx); ts_usec = msg->ts_nsec; do_div(ts_usec, 1000); - len = sprintf(user->buf, "%u,%llu,%llu;", - (msg->facility << 3) | msg->level, user->seq, ts_usec); + + /* + * If we couldn't merge continuation line fragments during the print, + * export the stored flags to allow an optional external merge of the + * records. Merging the records isn't always neccessarily correct, like + * when we hit a race during printing. In most cases though, it produces + * better readable output. 'c' in the record flags mark the first + * fragment of a line, '+' the following. + */ + if (msg->flags & LOG_CONT && !(user->prev & LOG_CONT)) + cont = 'c'; + else if ((msg->flags & LOG_CONT) || + ((user->prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))) + cont = '+'; + + len = sprintf(user->buf, "%u,%llu,%llu,%c;", + (msg->facility << 3) | msg->level, + user->seq, ts_usec, cont); + user->prev = msg->flags; /* escape non-printable characters */ for (i = 0; i < msg->text_len; i++) { @@ -646,6 +673,15 @@ void log_buf_kexec_setup(void) VMCOREINFO_SYMBOL(log_buf_len); VMCOREINFO_SYMBOL(log_first_idx); VMCOREINFO_SYMBOL(log_next_idx); + /* + * Export struct log size and field offsets. User space tools can + * parse it and detect any changes to structure down the line. + */ + VMCOREINFO_STRUCT_SIZE(log); + VMCOREINFO_OFFSET(log, ts_nsec); + VMCOREINFO_OFFSET(log, len); + VMCOREINFO_OFFSET(log, text_len); + VMCOREINFO_OFFSET(log, dict_len); } #endif @@ -876,7 +912,7 @@ static size_t msg_print_text(const struct log *msg, enum log_flags prev, if (buf) { if (print_prefix(msg, syslog, NULL) + - text_len + 1>= size - len) + text_len + 1 >= size - len) break; if (prefix) @@ -907,7 +943,7 @@ static int syslog_print(char __user *buf, int size) struct log *msg; int len = 0; - text = kmalloc(LOG_LINE_MAX, GFP_KERNEL); + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; @@ -930,7 +966,8 @@ static int syslog_print(char __user *buf, int size) skip = syslog_partial; msg = log_from_idx(syslog_idx); - n = msg_print_text(msg, syslog_prev, true, text, LOG_LINE_MAX); + n = msg_print_text(msg, syslog_prev, true, text, + LOG_LINE_MAX + PREFIX_MAX); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_idx = log_next(syslog_idx); @@ -969,7 +1006,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) char *text; int len = 0; - text = kmalloc(LOG_LINE_MAX, GFP_KERNEL); + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; @@ -997,6 +1034,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) struct log *msg = log_from_idx(idx); len += msg_print_text(msg, prev, true, NULL, 0); + prev = msg->flags; idx = log_next(idx); seq++; } @@ -1009,6 +1047,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) struct log *msg = log_from_idx(idx); len -= msg_print_text(msg, prev, true, NULL, 0); + prev = msg->flags; idx = log_next(idx); seq++; } @@ -1022,7 +1061,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear) struct log *msg = log_from_idx(idx); int textlen; - textlen = msg_print_text(msg, prev, true, text, LOG_LINE_MAX); + textlen = msg_print_text(msg, prev, true, text, + LOG_LINE_MAX + PREFIX_MAX); if (textlen < 0) { len = textlen; break; @@ -1192,21 +1232,6 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } -#ifdef CONFIG_KGDB_KDB -/* kdb dmesg command needs access to the syslog buffer. do_syslog() - * uses locks so it cannot be used during debugging. Just tell kdb - * where the start and end of the physical and logical logs are. This - * is equivalent to do_syslog(3). - */ -void kdb_syslog_data(char *syslog_data[4]) -{ - syslog_data[0] = log_buf; - syslog_data[1] = log_buf + log_buf_len; - syslog_data[2] = log_buf + log_first_idx; - syslog_data[3] = log_buf + log_next_idx; -} -#endif /* CONFIG_KGDB_KDB */ - static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) @@ -1364,20 +1389,36 @@ static struct cont { u64 ts_nsec; /* time of first print */ u8 level; /* log level of first message */ u8 facility; /* log level of first message */ + enum log_flags flags; /* prefix, newline flags */ bool flushed:1; /* buffer sealed and committed */ } cont; -static void cont_flush(void) +static void cont_flush(enum log_flags flags) { if (cont.flushed) return; if (cont.len == 0) return; - log_store(cont.facility, cont.level, LOG_NOCONS, cont.ts_nsec, - NULL, 0, cont.buf, cont.len); - - cont.flushed = true; + if (cont.cons) { + /* + * If a fragment of this line was directly flushed to the + * console; wait for the console to pick up the rest of the + * line. LOG_NOCONS suppresses a duplicated output. + */ + log_store(cont.facility, cont.level, flags | LOG_NOCONS, + cont.ts_nsec, NULL, 0, cont.buf, cont.len); + cont.flags = flags; + cont.flushed = true; + } else { + /* + * If no fragment of this line ever reached the console, + * just submit it to the store and free the buffer. + */ + log_store(cont.facility, cont.level, flags, 0, + NULL, 0, cont.buf, cont.len); + cont.len = 0; + } } static bool cont_add(int facility, int level, const char *text, size_t len) @@ -1386,7 +1427,8 @@ static bool cont_add(int facility, int level, const char *text, size_t len) return false; if (cont.len + len > sizeof(cont.buf)) { - cont_flush(); + /* the line gets too long, split it up in separate records */ + cont_flush(LOG_CONT); return false; } @@ -1395,12 +1437,17 @@ static bool cont_add(int facility, int level, const char *text, size_t len) cont.level = level; cont.owner = current; cont.ts_nsec = local_clock(); + cont.flags = 0; cont.cons = 0; cont.flushed = false; } memcpy(cont.buf + cont.len, text, len); cont.len += len; + + if (cont.len > (sizeof(cont.buf) * 80) / 100) + cont_flush(LOG_CONT); + return true; } @@ -1409,7 +1456,7 @@ static size_t cont_print_text(char *text, size_t size) size_t textlen = 0; size_t len; - if (cont.cons == 0) { + if (cont.cons == 0 && (console_prev & LOG_NEWLINE)) { textlen += print_time(cont.ts_nsec, text); size -= textlen; } @@ -1424,7 +1471,8 @@ static size_t cont_print_text(char *text, size_t size) } if (cont.flushed) { - text[textlen++] = '\n'; + if (cont.flags & LOG_NEWLINE) + text[textlen++] = '\n'; /* got everything, release buffer */ cont.len = 0; } @@ -1496,17 +1544,23 @@ asmlinkage int vprintk_emit(int facility, int level, lflags |= LOG_NEWLINE; } - /* strip syslog prefix and extract log level or control flags */ - if (text[0] == '<' && text[1] && text[2] == '>') { - switch (text[1]) { - case '0' ... '7': - if (level == -1) - level = text[1] - '0'; - case 'd': /* KERN_DEFAULT */ - lflags |= LOG_PREFIX; - case 'c': /* KERN_CONT */ - text += 3; - text_len -= 3; + /* strip kernel syslog prefix and extract log level or control flags */ + if (facility == 0) { + int kern_level = printk_get_level(text); + + if (kern_level) { + const char *end_of_header = printk_skip_level(text); + switch (kern_level) { + case '0' ... '7': + if (level == -1) + level = kern_level - '0'; + case 'd': /* KERN_DEFAULT */ + lflags |= LOG_PREFIX; + case 'c': /* KERN_CONT */ + break; + } + text_len -= end_of_header - text; + text = (char *)end_of_header; } } @@ -1522,7 +1576,7 @@ asmlinkage int vprintk_emit(int facility, int level, * or another task also prints continuation lines. */ if (cont.len && (lflags & LOG_PREFIX || cont.owner != current)) - cont_flush(); + cont_flush(LOG_NEWLINE); /* buffer line if possible, otherwise store it right away */ if (!cont_add(facility, level, text, text_len)) @@ -1540,7 +1594,7 @@ asmlinkage int vprintk_emit(int facility, int level, if (cont.len && cont.owner == current) { if (!(lflags & LOG_PREFIX)) stored = cont_add(facility, level, text, text_len); - cont_flush(); + cont_flush(LOG_NEWLINE); } if (!stored) @@ -1631,9 +1685,20 @@ asmlinkage int printk(const char *fmt, ...) } EXPORT_SYMBOL(printk); -#else +#else /* CONFIG_PRINTK */ +#define LOG_LINE_MAX 0 +#define PREFIX_MAX 0 #define LOG_LINE_MAX 0 +static u64 syslog_seq; +static u32 syslog_idx; +static u64 console_seq; +static u32 console_idx; +static enum log_flags syslog_prev; +static u64 log_first_seq; +static u32 log_first_idx; +static u64 log_next_seq; +static enum log_flags console_prev; static struct cont { size_t len; size_t cons; @@ -1917,10 +1982,34 @@ void wake_up_klogd(void) this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); } -/* the next printk record to write to the console */ -static u64 console_seq; -static u32 console_idx; -static enum log_flags console_prev; +static void console_cont_flush(char *text, size_t size) +{ + unsigned long flags; + size_t len; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + + if (!cont.len) + goto out; + + /* + * We still queue earlier records, likely because the console was + * busy. The earlier ones need to be printed before this one, we + * did not flush any fragment so far, so just let it queue up. + */ + if (console_seq < log_next_seq && !cont.cons) + goto out; + + len = cont_print_text(text, size); + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, text, len); + start_critical_timings(); + local_irq_restore(flags); + return; +out: + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +} /** * console_unlock - unlock the console system @@ -1938,7 +2027,7 @@ static enum log_flags console_prev; */ void console_unlock(void) { - static char text[LOG_LINE_MAX]; + static char text[LOG_LINE_MAX + PREFIX_MAX]; static u64 seen_seq; unsigned long flags; bool wake_klogd = false; @@ -1952,19 +2041,7 @@ void console_unlock(void) console_may_schedule = 0; /* flush buffered message fragment immediately to console */ - raw_spin_lock_irqsave(&logbuf_lock, flags); - if (cont.len && (cont.cons < cont.len || cont.flushed)) { - size_t len; - - len = cont_print_text(text, sizeof(text)); - raw_spin_unlock(&logbuf_lock); - stop_critical_timings(); - call_console_drivers(cont.level, text, len); - start_critical_timings(); - local_irq_restore(flags); - } else - raw_spin_unlock_irqrestore(&logbuf_lock, flags); - + console_cont_flush(text, sizeof(text)); again: for (;;) { struct log *msg; @@ -2001,6 +2078,7 @@ skip: * will properly dump everything later. */ msg->flags &= ~LOG_NOCONS; + console_prev = msg->flags; goto skip; } @@ -2525,7 +2603,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) } /** - * kmsg_dump_get_line - retrieve one kmsg log line + * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to @@ -2540,11 +2618,12 @@ void kmsg_dump(enum kmsg_dump_reason reason) * * A return value of FALSE indicates that there are no more records to * read. + * + * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ -bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len) +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) { - unsigned long flags; struct log *msg; size_t l = 0; bool ret = false; @@ -2552,7 +2631,6 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, if (!dumper->active) goto out; - raw_spin_lock_irqsave(&logbuf_lock, flags); if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; @@ -2560,10 +2638,8 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, } /* last entry */ - if (dumper->cur_seq >= log_next_seq) { - raw_spin_unlock_irqrestore(&logbuf_lock, flags); + if (dumper->cur_seq >= log_next_seq) goto out; - } msg = log_from_idx(dumper->cur_idx); l = msg_print_text(msg, 0, syslog, line, size); @@ -2571,12 +2647,41 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, dumper->cur_idx = log_next(dumper->cur_idx); dumper->cur_seq++; ret = true; - raw_spin_unlock_irqrestore(&logbuf_lock, flags); out: if (len) *len = l; return ret; } + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + return ret; +} EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** @@ -2679,6 +2784,24 @@ out: EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** + * kmsg_dump_rewind_nolock - reset the interator (unlocked version) + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + * + * The function is similar to kmsg_dump_rewind(), but grabs no locks. + */ +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; +} + +/** * kmsg_dump_rewind - reset the interator * @dumper: registered kmsg dumper * @@ -2691,10 +2814,7 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper) unsigned long flags; raw_spin_lock_irqsave(&logbuf_lock, flags); - dumper->cur_seq = clear_seq; - dumper->cur_idx = clear_idx; - dumper->next_seq = log_next_seq; - dumper->next_idx = log_next_idx; + kmsg_dump_rewind_nolock(dumper); raw_spin_unlock_irqrestore(&logbuf_lock, flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 95cba41ce1e..29ca1c6da59 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -45,6 +45,7 @@ #include <linux/mutex.h> #include <linux/export.h> #include <linux/hardirq.h> +#include <linux/delay.h> #define CREATE_TRACE_POINTS #include <trace/events/rcu.h> @@ -54,6 +55,53 @@ #ifdef CONFIG_PREEMPT_RCU /* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + barrier(); /* critical section before exit code. */ + t->rcu_read_lock_nesting = INT_MIN; +#ifdef CONFIG_PROVE_RCU_DELAY + udelay(10); /* Make preemption more probable. */ +#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + +/* * Check for a task exiting while in a preemptible-RCU read-side * critical section, clean up if so. No need to issue warnings, * as debug_check_no_locks_held() already does this if lockdep diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 37a5444204d..e4c6a598d6f 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -56,25 +56,28 @@ static void __call_rcu(struct rcu_head *head, static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ -static void rcu_idle_enter_common(long long oldval) +static void rcu_idle_enter_common(long long newval) { - if (rcu_dynticks_nesting) { + if (newval) { RCU_TRACE(trace_rcu_dyntick("--=", - oldval, rcu_dynticks_nesting)); + rcu_dynticks_nesting, newval)); + rcu_dynticks_nesting = newval; return; } - RCU_TRACE(trace_rcu_dyntick("Start", oldval, rcu_dynticks_nesting)); + RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval)); if (!is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task", - oldval, rcu_dynticks_nesting)); + rcu_dynticks_nesting, newval)); ftrace_dump(DUMP_ALL); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ } rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ + barrier(); + rcu_dynticks_nesting = newval; } /* @@ -84,17 +87,16 @@ static void rcu_idle_enter_common(long long oldval) void rcu_idle_enter(void) { unsigned long flags; - long long oldval; + long long newval; local_irq_save(flags); - oldval = rcu_dynticks_nesting; WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0); if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) - rcu_dynticks_nesting = 0; + newval = 0; else - rcu_dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; - rcu_idle_enter_common(oldval); + newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE; + rcu_idle_enter_common(newval); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_enter); @@ -105,15 +107,15 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter); void rcu_irq_exit(void) { unsigned long flags; - long long oldval; + long long newval; local_irq_save(flags); - oldval = rcu_dynticks_nesting; - rcu_dynticks_nesting--; - WARN_ON_ONCE(rcu_dynticks_nesting < 0); - rcu_idle_enter_common(oldval); + newval = rcu_dynticks_nesting - 1; + WARN_ON_ONCE(newval < 0); + rcu_idle_enter_common(newval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_irq_exit); /* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */ static void rcu_idle_exit_common(long long oldval) @@ -171,8 +173,9 @@ void rcu_irq_enter(void) rcu_idle_exit_common(oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_irq_enter); -#ifdef CONFIG_PROVE_RCU +#ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Test whether RCU thinks that the current CPU is idle. @@ -183,7 +186,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* * Test whether the current CPU was interrupted from idle. Nested diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index fc31a2d6510..3d019028220 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,7 +132,6 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -279,7 +278,7 @@ static int rcu_boost(void) rcu_preempt_ctrlblk.exp_tasks == NULL) return 0; /* Nothing to boost. */ - raw_local_irq_save(flags); + local_irq_save(flags); /* * Recheck with irqs disabled: all tasks in need of boosting @@ -288,7 +287,7 @@ static int rcu_boost(void) */ if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) { - raw_local_irq_restore(flags); + local_irq_restore(flags); return 0; } @@ -318,7 +317,7 @@ static int rcu_boost(void) t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; - raw_local_irq_restore(flags); + local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ @@ -351,8 +350,9 @@ static int rcu_initiate_boost(void) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); - } else + } else { RCU_TRACE(rcu_initiate_boost_trace()); + } return 1; } @@ -527,23 +527,11 @@ void rcu_preempt_note_context_switch(void) } /* - * Tiny-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutiny.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -627,38 +615,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } /* - * Tiny-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the rcu_preempt_ctrlblk structure, which is * checked elsewhere. This is called from the scheduling-clock interrupt. @@ -823,9 +779,9 @@ void synchronize_rcu_expedited(void) rpcp->exp_tasks = NULL; /* Wait for tail of ->blkd_tasks list to drain. */ - if (!rcu_preempted_readers_exp()) + if (!rcu_preempted_readers_exp()) { local_irq_restore(flags); - else { + } else { rcu_initiate_boost(); local_irq_restore(flags); wait_event(sync_rcu_preempt_exp_wq, @@ -846,8 +802,6 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); */ int rcu_preempt_needs_cpu(void) { - if (!rcu_preempt_running_reader()) - rcu_preempt_cpu_qs(); return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } @@ -1037,9 +991,9 @@ static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n) { unsigned long flags; - raw_local_irq_save(flags); + local_irq_save(flags); rcp->qlen -= n; - raw_local_irq_restore(flags); + local_irq_restore(flags); } /* diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index e66b34ab755..aaa7b9f3532 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -49,15 +49,15 @@ #include <asm/byteorder.h> MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and " - "Josh Triplett <josh@freedesktop.org>"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>"); static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ -static int stat_interval; /* Interval between stats, in seconds. */ - /* Defaults to "only at end of test". */ +static int stat_interval = 60; /* Interval between stats, in seconds. */ + /* Zero means "only at end of test". */ static bool verbose; /* Print more debug info. */ -static bool test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ +static bool test_no_idle_hz = true; + /* Test RCU support for tickless idle CPUs. */ static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/ static int stutter = 5; /* Start/stop testing interval (in sec) */ static int irqreader = 1; /* RCU readers from irq (timers). */ @@ -120,11 +120,11 @@ MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)"); #define TORTURE_FLAG "-torture:" #define PRINTK_STRING(s) \ - do { printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0) + do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0) #define VERBOSE_PRINTK_STRING(s) \ - do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0) + do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0) #define VERBOSE_PRINTK_ERRSTRING(s) \ - do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0) + do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0) static char printk_buf[4096]; @@ -177,8 +177,14 @@ static long n_rcu_torture_boosts; static long n_rcu_torture_timers; static long n_offline_attempts; static long n_offline_successes; +static unsigned long sum_offline; +static int min_offline = -1; +static int max_offline; static long n_online_attempts; static long n_online_successes; +static unsigned long sum_online; +static int min_online = -1; +static int max_online; static long n_barrier_attempts; static long n_barrier_successes; static struct list_head rcu_torture_removed; @@ -206,6 +212,7 @@ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ +static bool barrier_phase; /* Test phase. */ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); @@ -235,7 +242,7 @@ rcutorture_shutdown_notify(struct notifier_block *unused1, if (fullstop == FULLSTOP_DONTSTOP) fullstop = FULLSTOP_SHUTDOWN; else - printk(KERN_WARNING /* but going down anyway, so... */ + pr_warn(/* but going down anyway, so... */ "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); mutex_unlock(&fullstop_mutex); return NOTIFY_DONE; @@ -248,7 +255,7 @@ rcutorture_shutdown_notify(struct notifier_block *unused1, static void rcutorture_shutdown_absorb(char *title) { if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { - printk(KERN_NOTICE + pr_notice( "rcutorture thread %s parking due to system shutdown\n", title); schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT); @@ -407,8 +414,9 @@ rcu_torture_cb(struct rcu_head *p) if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { rp->rtort_mbtest = 0; rcu_torture_free(rp); - } else + } else { cur_ops->deferred_free(rp); + } } static int rcu_no_completed(void) @@ -635,6 +643,17 @@ static void srcu_torture_synchronize(void) synchronize_srcu(&srcu_ctl); } +static void srcu_torture_call(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + call_srcu(&srcu_ctl, head, func); +} + +static void srcu_torture_barrier(void) +{ + srcu_barrier(&srcu_ctl); +} + static int srcu_torture_stats(char *page) { int cnt = 0; @@ -661,8 +680,8 @@ static struct rcu_torture_ops srcu_ops = { .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, - .call = NULL, - .cb_barrier = NULL, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, .name = "srcu" }; @@ -1013,7 +1032,11 @@ rcu_torture_fakewriter(void *arg) do { schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); udelay(rcu_random(&rand) & 0x3ff); - cur_ops->sync(); + if (cur_ops->cb_barrier != NULL && + rcu_random(&rand) % (nfakewriters * 8) == 0) + cur_ops->cb_barrier(); + else + cur_ops->sync(); rcu_stutter_wait("rcu_torture_fakewriter"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); @@ -1183,27 +1206,29 @@ rcu_torture_printk(char *page) } cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " - "rtmbe: %d rtbke: %ld rtbre: %ld " - "rtbf: %ld rtb: %ld nt: %ld " - "onoff: %ld/%ld:%ld/%ld " - "barrier: %ld/%ld:%ld", + "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), atomic_read(&n_rcu_torture_alloc), atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free), + atomic_read(&n_rcu_torture_free)); + cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ", atomic_read(&n_rcu_torture_mberror), n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror, + n_rcu_torture_boost_rterror); + cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers, - n_online_successes, - n_online_attempts, - n_offline_successes, - n_offline_attempts, + n_rcu_torture_timers); + cnt += sprintf(&page[cnt], + "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", + n_online_successes, n_online_attempts, + n_offline_successes, n_offline_attempts, + min_online, max_online, + min_offline, max_offline, + sum_online, sum_offline, HZ); + cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld", n_barrier_successes, n_barrier_attempts, n_rcu_torture_barrier_error); @@ -1251,7 +1276,7 @@ rcu_torture_stats_print(void) int cnt; cnt = rcu_torture_printk(printk_buf); - printk(KERN_ALERT "%s", printk_buf); + pr_alert("%s", printk_buf); } /* @@ -1364,20 +1389,20 @@ rcu_torture_stutter(void *arg) static inline void rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag) { - printk(KERN_ALERT "%s" TORTURE_FLAG - "--- %s: nreaders=%d nfakewriters=%d " - "stat_interval=%d verbose=%d test_no_idle_hz=%d " - "shuffle_interval=%d stutter=%d irqreader=%d " - "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " - "test_boost=%d/%d test_boost_interval=%d " - "test_boost_duration=%d shutdown_secs=%d " - "onoff_interval=%d onoff_holdoff=%d\n", - torture_type, tag, nrealreaders, nfakewriters, - stat_interval, verbose, test_no_idle_hz, shuffle_interval, - stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, - test_boost, cur_ops->can_boost, - test_boost_interval, test_boost_duration, shutdown_secs, - onoff_interval, onoff_holdoff); + pr_alert("%s" TORTURE_FLAG + "--- %s: nreaders=%d nfakewriters=%d " + "stat_interval=%d verbose=%d test_no_idle_hz=%d " + "shuffle_interval=%d stutter=%d irqreader=%d " + "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " + "test_boost=%d/%d test_boost_interval=%d " + "test_boost_duration=%d shutdown_secs=%d " + "onoff_interval=%d onoff_holdoff=%d\n", + torture_type, tag, nrealreaders, nfakewriters, + stat_interval, verbose, test_no_idle_hz, shuffle_interval, + stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, + test_boost, cur_ops->can_boost, + test_boost_interval, test_boost_duration, shutdown_secs, + onoff_interval, onoff_holdoff); } static struct notifier_block rcutorture_shutdown_nb = { @@ -1444,10 +1469,9 @@ rcu_torture_shutdown(void *arg) !kthread_should_stop()) { delta = shutdown_time - jiffies_snap; if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_shutdown task: %lu " - "jiffies remaining\n", - torture_type, delta); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_shutdown task: %lu jiffies remaining\n", + torture_type, delta); schedule_timeout_interruptible(delta); jiffies_snap = ACCESS_ONCE(jiffies); } @@ -1475,8 +1499,10 @@ static int __cpuinit rcu_torture_onoff(void *arg) { int cpu; + unsigned long delta; int maxcpu = -1; DEFINE_RCU_RANDOM(rand); + unsigned long starttime; VERBOSE_PRINTK_STRING("rcu_torture_onoff task started"); for_each_online_cpu(cpu) @@ -1491,31 +1517,51 @@ rcu_torture_onoff(void *arg) cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1); if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: offlining %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: offlining %d\n", + torture_type, cpu); + starttime = jiffies; n_offline_attempts++; if (cpu_down(cpu) == 0) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "offlined %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: offlined %d\n", + torture_type, cpu); n_offline_successes++; + delta = jiffies - starttime; + sum_offline += delta; + if (min_offline < 0) { + min_offline = delta; + max_offline = delta; + } + if (min_offline > delta) + min_offline = delta; + if (max_offline < delta) + max_offline = delta; } } else if (cpu_is_hotpluggable(cpu)) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: onlining %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: onlining %d\n", + torture_type, cpu); + starttime = jiffies; n_online_attempts++; if (cpu_up(cpu) == 0) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "onlined %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: onlined %d\n", + torture_type, cpu); n_online_successes++; + delta = jiffies - starttime; + sum_online += delta; + if (min_online < 0) { + min_online = delta; + max_online = delta; + } + if (min_online > delta) + min_online = delta; + if (max_online < delta) + max_online = delta; } } schedule_timeout_interruptible(onoff_interval * HZ); @@ -1580,14 +1626,14 @@ static int __cpuinit rcu_torture_stall(void *args) if (!kthread_should_stop()) { stop_at = get_seconds() + stall_cpu; /* RCU CPU stall is expected behavior in following code. */ - printk(KERN_ALERT "rcu_torture_stall start.\n"); + pr_alert("rcu_torture_stall start.\n"); rcu_read_lock(); preempt_disable(); while (ULONG_CMP_LT(get_seconds(), stop_at)) continue; /* Induce RCU CPU stall warning. */ preempt_enable(); rcu_read_unlock(); - printk(KERN_ALERT "rcu_torture_stall end.\n"); + pr_alert("rcu_torture_stall end.\n"); } rcutorture_shutdown_absorb("rcu_torture_stall"); while (!kthread_should_stop()) @@ -1631,6 +1677,7 @@ void rcu_torture_barrier_cbf(struct rcu_head *rcu) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; + bool lastphase = 0; struct rcu_head rcu; init_rcu_head_on_stack(&rcu); @@ -1638,9 +1685,11 @@ static int rcu_torture_barrier_cbs(void *arg) set_user_nice(current, 19); do { wait_event(barrier_cbs_wq[myid], - atomic_read(&barrier_cbs_count) == n_barrier_cbs || + barrier_phase != lastphase || kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP); + lastphase = barrier_phase; + smp_mb(); /* ensure barrier_phase load before ->call(). */ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) break; cur_ops->call(&rcu, rcu_torture_barrier_cbf); @@ -1665,7 +1714,8 @@ static int rcu_torture_barrier(void *arg) do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); - /* wake_up() path contains the required barriers. */ + smp_mb(); /* Ensure barrier_phase after prior assignments. */ + barrier_phase = !barrier_phase; for (i = 0; i < n_barrier_cbs; i++) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, @@ -1684,7 +1734,7 @@ static int rcu_torture_barrier(void *arg) schedule_timeout_interruptible(HZ / 10); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping"); - rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); + rcutorture_shutdown_absorb("rcu_torture_barrier"); while (!kthread_should_stop()) schedule_timeout_interruptible(1); return 0; @@ -1699,12 +1749,12 @@ static int rcu_torture_barrier_init(void) if (n_barrier_cbs == 0) return 0; if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) { - printk(KERN_ALERT "%s" TORTURE_FLAG - " Call or barrier ops missing for %s,\n", - torture_type, cur_ops->name); - printk(KERN_ALERT "%s" TORTURE_FLAG - " RCU barrier testing omitted from run.\n", - torture_type); + pr_alert("%s" TORTURE_FLAG + " Call or barrier ops missing for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " RCU barrier testing omitted from run.\n", + torture_type); return 0; } atomic_set(&barrier_cbs_count, 0); @@ -1797,7 +1847,7 @@ rcu_torture_cleanup(void) mutex_lock(&fullstop_mutex); rcutorture_record_test_transition(); if (fullstop == FULLSTOP_SHUTDOWN) { - printk(KERN_WARNING /* but going down anyway, so... */ + pr_warn(/* but going down anyway, so... */ "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); mutex_unlock(&fullstop_mutex); schedule_timeout_uninterruptible(10); @@ -1908,8 +1958,8 @@ rcu_torture_init(void) static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, - &srcu_ops, &srcu_sync_ops, &srcu_raw_ops, - &srcu_raw_sync_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops, + &srcu_raw_ops, &srcu_raw_sync_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); @@ -1921,18 +1971,17 @@ rcu_torture_init(void) break; } if (i == ARRAY_SIZE(torture_ops)) { - printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n", - torture_type); - printk(KERN_ALERT "rcu-torture types:"); + pr_alert("rcu-torture: invalid torture type: \"%s\"\n", + torture_type); + pr_alert("rcu-torture types:"); for (i = 0; i < ARRAY_SIZE(torture_ops); i++) - printk(KERN_ALERT " %s", torture_ops[i]->name); - printk(KERN_ALERT "\n"); + pr_alert(" %s", torture_ops[i]->name); + pr_alert("\n"); mutex_unlock(&fullstop_mutex); return -EINVAL; } if (cur_ops->fqs == NULL && fqs_duration != 0) { - printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero " - "fqs_duration, fqs disabled.\n"); + pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); fqs_duration = 0; } if (cur_ops->init) @@ -1980,14 +2029,15 @@ rcu_torture_init(void) /* Start up the kthreads. */ VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task"); - writer_task = kthread_run(rcu_torture_writer, NULL, - "rcu_torture_writer"); + writer_task = kthread_create(rcu_torture_writer, NULL, + "rcu_torture_writer"); if (IS_ERR(writer_task)) { firsterr = PTR_ERR(writer_task); VERBOSE_PRINTK_ERRSTRING("Failed to create writer"); writer_task = NULL; goto unwind; } + wake_up_process(writer_task); fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]), GFP_KERNEL); if (fakewriter_tasks == NULL) { @@ -2102,14 +2152,15 @@ rcu_torture_init(void) } if (shutdown_secs > 0) { shutdown_time = jiffies + shutdown_secs * HZ; - shutdown_task = kthread_run(rcu_torture_shutdown, NULL, - "rcu_torture_shutdown"); + shutdown_task = kthread_create(rcu_torture_shutdown, NULL, + "rcu_torture_shutdown"); if (IS_ERR(shutdown_task)) { firsterr = PTR_ERR(shutdown_task); VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown"); shutdown_task = NULL; goto unwind; } + wake_up_process(shutdown_task); } i = rcu_torture_onoff_init(); if (i != 0) { diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4b97bba7396..4fb2376ddf0 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -52,6 +52,7 @@ #include <linux/prefetch.h> #include <linux/delay.h> #include <linux/stop_machine.h> +#include <linux/random.h> #include "rcutree.h" #include <trace/events/rcu.h> @@ -60,36 +61,44 @@ /* Data structures. */ -static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; - -#define RCU_STATE_INITIALIZER(structname) { \ - .level = { &structname##_state.node[0] }, \ - .levelcnt = { \ - NUM_RCU_LVL_0, /* root of hierarchy. */ \ - NUM_RCU_LVL_1, \ - NUM_RCU_LVL_2, \ - NUM_RCU_LVL_3, \ - NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ - }, \ +static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; +static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; + +#define RCU_STATE_INITIALIZER(sname, cr) { \ + .level = { &sname##_state.node[0] }, \ + .call = cr, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ - .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \ - .orphan_nxttail = &structname##_state.orphan_nxtlist, \ - .orphan_donetail = &structname##_state.orphan_donelist, \ - .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.fqslock), \ - .n_force_qs = 0, \ - .n_force_qs_ngp = 0, \ - .name = #structname, \ + .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.onofflock), \ + .orphan_nxttail = &sname##_state.orphan_nxtlist, \ + .orphan_donetail = &sname##_state.orphan_donelist, \ + .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ + .name = #sname, \ } -struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched); +struct rcu_state rcu_sched_state = + RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched); DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); -struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh); +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; +LIST_HEAD(rcu_struct_flavors); + +/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ +static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; +module_param(rcu_fanout_leaf, int, 0444); +int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; +static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ + NUM_RCU_LVL_0, + NUM_RCU_LVL_1, + NUM_RCU_LVL_2, + NUM_RCU_LVL_3, + NUM_RCU_LVL_4, +}; +int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ /* * The rcu_scheduler_active variable transitions from zero to one just @@ -125,13 +134,12 @@ static int rcu_scheduler_fully_active __read_mostly; */ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); -DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); #endif /* #ifdef CONFIG_RCU_BOOST */ -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); @@ -147,13 +155,6 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); unsigned long rcutorture_testseq; unsigned long rcutorture_vernum; -/* State information for rcu_barrier() and friends. */ - -static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; -static atomic_t rcu_barrier_cpu_count; -static DEFINE_MUTEX(rcu_barrier_mutex); -static struct completion rcu_barrier_completion; - /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node @@ -174,8 +175,6 @@ void rcu_sched_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu); - rdp->passed_quiesce_gpnum = rdp->gpnum; - barrier(); if (rdp->passed_quiesce == 0) trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; @@ -185,8 +184,6 @@ void rcu_bh_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesce_gpnum = rdp->gpnum; - barrier(); if (rdp->passed_quiesce == 0) trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; @@ -209,15 +206,18 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(1), +#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE) + .ignore_user_qs = true, +#endif }; static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static int qhimark = 10000; /* If this many pending, ignore blimit. */ static int qlowmark = 100; /* Once only this many pending, use blimit. */ -module_param(blimit, int, 0); -module_param(qhimark, int, 0); -module_param(qlowmark, int, 0); +module_param(blimit, int, 0444); +module_param(qhimark, int, 0444); +module_param(qlowmark, int, 0444); int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; @@ -225,7 +225,14 @@ int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_suppress, int, 0644); module_param(rcu_cpu_stall_timeout, int, 0644); -static void force_quiescent_state(struct rcu_state *rsp, int relaxed); +static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS; +static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS; + +module_param(jiffies_till_first_fqs, ulong, 0644); +module_param(jiffies_till_next_fqs, ulong, 0644); + +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)); +static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(int cpu); /* @@ -251,7 +258,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); */ void rcu_bh_force_quiescent_state(void) { - force_quiescent_state(&rcu_bh_state, 0); + force_quiescent_state(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); @@ -285,7 +292,7 @@ EXPORT_SYMBOL_GPL(rcutorture_record_progress); */ void rcu_sched_force_quiescent_state(void) { - force_quiescent_state(&rcu_sched_state, 0); + force_quiescent_state(&rcu_sched_state); } EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); @@ -304,7 +311,9 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) static int cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { - return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp); + return *rdp->nxttail[RCU_DONE_TAIL + + ACCESS_ONCE(rsp->completed) != rdp->completed] && + !rcu_gp_in_progress(rsp); } /* @@ -316,49 +325,21 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) } /* - * If the specified CPU is offline, tell the caller that it is in - * a quiescent state. Otherwise, whack it with a reschedule IPI. - * Grace periods can end up waiting on an offline CPU when that - * CPU is in the process of coming online -- it will be added to the - * rcu_node bitmasks before it actually makes it online. The same thing - * can happen while a CPU is in the process of coming online. Because this - * race is quite rare, we check for it after detecting that the grace - * period has been delayed rather than checking each and every CPU - * each and every time we start a new grace period. - */ -static int rcu_implicit_offline_qs(struct rcu_data *rdp) -{ - /* - * If the CPU is offline for more than a jiffy, it is in a quiescent - * state. We can trust its state not to change because interrupts - * are disabled. The reason for the jiffy's worth of slack is to - * handle CPUs initializing on the way up and finding their way - * to the idle loop on the way down. - */ - if (cpu_is_offline(rdp->cpu) && - ULONG_CMP_LT(rdp->rsp->gp_start + 2, jiffies)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); - rdp->offline_fqs++; - return 1; - } - return 0; -} - -/* - * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle + * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state * * If the new value of the ->dynticks_nesting counter now is zero, * we really have entered idle, and must do the appropriate accounting. * The caller must have disabled interrupts. */ -static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) +static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval, + bool user) { trace_rcu_dyntick("Start", oldval, 0); - if (!is_idle_task(current)) { + if (!user && !is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -371,7 +352,7 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); /* - * The idle task is not permitted to enter the idle loop while + * It is illegal to enter an extended quiescent state while * in an RCU read-side critical section. */ rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), @@ -382,6 +363,25 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) "Illegal idle entry in RCU-sched read-side critical section."); } +/* + * Enter an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + */ +static void rcu_eqs_enter(bool user) +{ + long long oldval; + struct rcu_dynticks *rdtp; + + rdtp = &__get_cpu_var(rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) + rdtp->dynticks_nesting = 0; + else + rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; + rcu_eqs_enter_common(rdtp, oldval, user); +} + /** * rcu_idle_enter - inform RCU that current CPU is entering idle * @@ -397,21 +397,70 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) void rcu_idle_enter(void) { unsigned long flags; - long long oldval; + + local_irq_save(flags); + rcu_eqs_enter(false); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(rcu_idle_enter); + +#ifdef CONFIG_RCU_USER_QS +/** + * rcu_user_enter - inform RCU that we are resuming userspace. + * + * Enter RCU idle mode right before resuming userspace. No use of RCU + * is permitted between this call and rcu_user_exit(). This way the + * CPU doesn't need to maintain the tick for RCU maintenance purposes + * when the CPU runs in userspace. + */ +void rcu_user_enter(void) +{ + unsigned long flags; struct rcu_dynticks *rdtp; + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + WARN_ON_ONCE(!current->mm); + local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); - if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) - rdtp->dynticks_nesting = 0; - else - rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; - rcu_idle_enter_common(rdtp, oldval); + if (!rdtp->ignore_user_qs && !rdtp->in_user) { + rdtp->in_user = true; + rcu_eqs_enter(true); + } local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(rcu_idle_enter); + +/** + * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace + * after the current irq returns. + * + * This is similar to rcu_user_enter() but in the context of a non-nesting + * irq. After this call, RCU enters into idle mode when the interrupt + * returns. + */ +void rcu_user_enter_after_irq(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + /* Ensure this irq is interrupting a non-idle RCU state. */ + WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK)); + rdtp->dynticks_nesting = 1; + local_irq_restore(flags); +} +#endif /* CONFIG_RCU_USER_QS */ /** * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle @@ -443,18 +492,19 @@ void rcu_irq_exit(void) if (rdtp->dynticks_nesting) trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting); else - rcu_idle_enter_common(rdtp, oldval); + rcu_eqs_enter_common(rdtp, oldval, true); local_irq_restore(flags); } /* - * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle + * rcu_eqs_exit_common - current CPU moving away from extended quiescent state * * If the new value of the ->dynticks_nesting counter was previously zero, * we really have exited idle, and must do the appropriate accounting. * The caller must have disabled interrupts. */ -static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) +static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval, + int user) { smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */ atomic_inc(&rdtp->dynticks); @@ -463,18 +513,37 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); rcu_cleanup_after_idle(smp_processor_id()); trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting); - if (!is_idle_task(current)) { + if (!user && !is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on exit: not idle task", oldval, rdtp->dynticks_nesting); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ } } +/* + * Exit an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + */ +static void rcu_eqs_exit(bool user) +{ + struct rcu_dynticks *rdtp; + long long oldval; + + rdtp = &__get_cpu_var(rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE(oldval < 0); + if (oldval & DYNTICK_TASK_NEST_MASK) + rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + else + rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; + rcu_eqs_exit_common(rdtp, oldval, user); +} + /** * rcu_idle_exit - inform RCU that current CPU is leaving idle * @@ -489,21 +558,67 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) void rcu_idle_exit(void) { unsigned long flags; + + local_irq_save(flags); + rcu_eqs_exit(false); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(rcu_idle_exit); + +#ifdef CONFIG_RCU_USER_QS +/** + * rcu_user_exit - inform RCU that we are exiting userspace. + * + * Exit RCU idle mode while entering the kernel because it can + * run a RCU read side critical section anytime. + */ +void rcu_user_exit(void) +{ + unsigned long flags; struct rcu_dynticks *rdtp; - long long oldval; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE(oldval < 0); - if (oldval & DYNTICK_TASK_NEST_MASK) - rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; - else - rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_idle_exit_common(rdtp, oldval); + if (rdtp->in_user) { + rdtp->in_user = false; + rcu_eqs_exit(true); + } local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(rcu_idle_exit); + +/** + * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace + * idle mode after the current non-nesting irq returns. + * + * This is similar to rcu_user_exit() but in the context of an irq. + * This is called when the irq has interrupted a userspace RCU idle mode + * context. When the current non-nesting interrupt returns after this call, + * the CPU won't restore the RCU idle mode. + */ +void rcu_user_exit_after_irq(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + /* Ensure we are interrupting an RCU idle mode. */ + WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK); + rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE; + local_irq_restore(flags); +} +#endif /* CONFIG_RCU_USER_QS */ /** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle @@ -538,7 +653,7 @@ void rcu_irq_enter(void) if (oldval) trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting); else - rcu_idle_exit_common(rdtp, oldval); + rcu_eqs_exit_common(rdtp, oldval, true); local_irq_restore(flags); } @@ -585,8 +700,6 @@ void rcu_nmi_exit(void) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } -#ifdef CONFIG_PROVE_RCU - /** * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle * @@ -604,7 +717,22 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#ifdef CONFIG_HOTPLUG_CPU +#ifdef CONFIG_RCU_USER_QS +void rcu_user_hooks_switch(struct task_struct *prev, + struct task_struct *next) +{ + struct rcu_dynticks *rdtp; + + /* Interrupts are disabled in context switch */ + rdtp = &__get_cpu_var(rcu_dynticks); + if (!rdtp->ignore_user_qs) { + clear_tsk_thread_flag(prev, TIF_NOHZ); + set_tsk_thread_flag(next, TIF_NOHZ); + } +} +#endif /* #ifdef CONFIG_RCU_USER_QS */ + +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* * Is the current CPU online? Disable preemption to avoid false positives @@ -645,9 +773,7 @@ bool rcu_lockdep_current_cpu_online(void) } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ /** * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle @@ -676,7 +802,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) * Return true if the specified CPU has passed through a quiescent * state by virtue of being in or having passed through an dynticks * idle state since the last call to dyntick_save_progress_counter() - * for this same CPU. + * for this same CPU, or by virtue of having been offline. */ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { @@ -700,8 +826,26 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 1; } - /* Go check for the CPU being offline. */ - return rcu_implicit_offline_qs(rdp); + /* + * Check for the CPU being offline, but only if the grace period + * is old enough. We don't need to worry about the CPU changing + * state: If we see it offline even once, it has been through a + * quiescent state. + * + * The reason for insisting that the grace period be at least + * one jiffy old is that CPUs that are not quite online and that + * have just gone offline can still execute RCU read-side critical + * sections. + */ + if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies)) + return 0; /* Grace period is not old enough. */ + barrier(); + if (cpu_is_offline(rdp->cpu)) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); + rdp->offline_fqs++; + return 1; + } + return 0; } static int jiffies_till_stall_check(void) @@ -733,7 +877,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) int cpu; long delta; unsigned long flags; - int ndetected; + int ndetected = 0; struct rcu_node *rnp = rcu_get_root(rsp); /* Only let one CPU complain about others per time interval. */ @@ -758,14 +902,15 @@ static void print_other_cpu_stall(struct rcu_state *rsp) rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave(&rnp->lock, flags); ndetected += rcu_print_task_stall(rnp); + if (rnp->qsmask != 0) { + for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) + if (rnp->qsmask & (1UL << cpu)) { + print_cpu_stall_info(rsp, + rnp->grplo + cpu); + ndetected++; + } + } raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (rnp->qsmask == 0) - continue; - for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) - if (rnp->qsmask & (1UL << cpu)) { - print_cpu_stall_info(rsp, rnp->grplo + cpu); - ndetected++; - } } /* @@ -774,7 +919,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) */ rnp = rcu_get_root(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); - ndetected = rcu_print_task_stall(rnp); + ndetected += rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); print_cpu_stall_info_end(); @@ -785,11 +930,11 @@ static void print_other_cpu_stall(struct rcu_state *rsp) else if (!trigger_all_cpu_backtrace()) dump_stack(); - /* If so configured, complain about tasks blocking the grace period. */ + /* Complain about tasks blocking the grace period. */ rcu_print_detail_task_stall(rsp); - force_quiescent_state(rsp, 0); /* Kick them all. */ + force_quiescent_state(rsp); /* Kick them all. */ } static void print_cpu_stall(struct rcu_state *rsp) @@ -830,7 +975,8 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) j = ACCESS_ONCE(jiffies); js = ACCESS_ONCE(rsp->jiffies_stall); rnp = rdp->mynode; - if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) { + if (rcu_gp_in_progress(rsp) && + (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); @@ -860,9 +1006,10 @@ static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) */ void rcu_cpu_stall_reset(void) { - rcu_sched_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_bh_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_preempt_stall_reset(); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rsp->jiffies_stall = jiffies + ULONG_MAX / 2; } static struct notifier_block rcu_panic_block = { @@ -891,11 +1038,8 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct */ rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart"); - if (rnp->qsmask & rdp->grpmask) { - rdp->qs_pending = 1; - rdp->passed_quiesce = 0; - } else - rdp->qs_pending = 0; + rdp->passed_quiesce = 0; + rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); } } @@ -937,6 +1081,18 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) } /* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + int i; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; +} + +/* * Advance this CPU's callbacks, but only if the current grace period * has ended. This may be called only from the CPU to whom the rdp * belongs. In addition, the corresponding leaf rcu_node structure's @@ -963,10 +1119,13 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat * our behalf. Catch up with this state to avoid noting * spurious new grace periods. If another grace period * has started, then rnp->gpnum will have advanced, so - * we will detect this later on. + * we will detect this later on. Of course, any quiescent + * states we found for the old GP are now invalid. */ - if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) + if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) { rdp->gpnum = rdp->completed; + rdp->passed_quiesce = 0; + } /* * If RCU does not need a quiescent state from this CPU, @@ -1010,97 +1169,56 @@ rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat /* Prior grace period ended, so advance callbacks for current CPU. */ __rcu_process_gp_end(rsp, rnp, rdp); - /* - * Because this CPU just now started the new grace period, we know - * that all of its callbacks will be covered by this upcoming grace - * period, even the ones that were registered arbitrarily recently. - * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. - * - * Other CPUs cannot be sure exactly when the grace period started. - * Therefore, their recently registered callbacks must pass through - * an additional RCU_NEXT_READY stage, so that they will be handled - * by the next RCU grace period. - */ - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - /* Set state so that this CPU will detect the next quiescent state. */ __note_new_gpnum(rsp, rnp, rdp); } /* - * Start a new RCU grace period if warranted, re-initializing the hierarchy - * in preparation for detecting the next grace period. The caller must hold - * the root node's ->lock, which is released before return. Hard irqs must - * be disabled. - * - * Note that it is legal for a dying CPU (which is marked as offline) to - * invoke this function. This can happen when the dying CPU reports its - * quiescent state. + * Initialize a new grace period. */ -static void -rcu_start_gp(struct rcu_state *rsp, unsigned long flags) - __releases(rcu_get_root(rsp)->lock) +static int rcu_gp_init(struct rcu_state *rsp) { - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); - if (!rcu_scheduler_fully_active || - !cpu_needs_another_gp(rsp, rdp)) { - /* - * Either the scheduler hasn't yet spawned the first - * non-idle task or this CPU does not need another - * grace period. Either way, don't start a new grace - * period. - */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } + raw_spin_lock_irq(&rnp->lock); + rsp->gp_flags = 0; /* Clear all flags: New grace period. */ - if (rsp->fqs_active) { - /* - * This CPU needs a grace period, but force_quiescent_state() - * is running. Tell it to start one on this CPU's behalf. - */ - rsp->fqs_need_gp = 1; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; + if (rcu_gp_in_progress(rsp)) { + /* Grace period already in progress, don't start another. */ + raw_spin_unlock_irq(&rnp->lock); + return 0; } /* Advance to a new grace period and initialize state. */ rsp->gpnum++; trace_rcu_grace_period(rsp->name, rsp->gpnum, "start"); - WARN_ON_ONCE(rsp->fqs_state == RCU_GP_INIT); - rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */ - rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); - raw_spin_unlock(&rnp->lock); /* leave irqs disabled. */ + raw_spin_unlock_irq(&rnp->lock); /* Exclude any concurrent CPU-hotplug operations. */ - raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */ + get_online_cpus(); /* * Set the quiescent-state-needed bits in all the rcu_node - * structures for all currently online CPUs in breadth-first - * order, starting from the root rcu_node structure. This - * operation relies on the layout of the hierarchy within the - * rsp->node[] array. Note that other CPUs will access only - * the leaves of the hierarchy, which still indicate that no + * structures for all currently online CPUs in breadth-first order, + * starting from the root rcu_node structure, relying on the layout + * of the tree within the rsp->node[] array. Note that other CPUs + * will access only the leaves of the hierarchy, thus seeing that no * grace period is in progress, at least until the corresponding * leaf node has been initialized. In addition, we have excluded * CPU-hotplug operations. * - * Note that the grace period cannot complete until we finish - * the initialization process, as there will be at least one - * qsmask bit set in the root node until that time, namely the - * one corresponding to this CPU, due to the fact that we have - * irqs disabled. + * The grace period cannot complete until the initialization + * process finishes, because this kthread handles both. */ rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + raw_spin_lock_irq(&rnp->lock); + rdp = this_cpu_ptr(rsp->rda); rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; + WARN_ON_ONCE(rnp->completed != rsp->completed); rnp->completed = rsp->completed; if (rnp == rdp->mynode) rcu_start_gp_per_cpu(rsp, rnp, rdp); @@ -1108,37 +1226,54 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) trace_rcu_grace_period_init(rsp->name, rnp->gpnum, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_irq(&rnp->lock); +#ifdef CONFIG_PROVE_RCU_DELAY + if ((random32() % (rcu_num_nodes * 8)) == 0) + schedule_timeout_uninterruptible(2); +#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ + cond_resched(); } - rnp = rcu_get_root(rsp); - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + put_online_cpus(); + return 1; } /* - * Report a full set of quiescent states to the specified rcu_state - * data structure. This involves cleaning up after the prior grace - * period and letting rcu_start_gp() start up the next grace period - * if one is needed. Note that the caller must hold rnp->lock, as - * required by rcu_start_gp(), which will release it. + * Do one round of quiescent-state forcing. */ -static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) - __releases(rcu_get_root(rsp)->lock) +int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) { - unsigned long gp_duration; + int fqs_state = fqs_state_in; struct rcu_node *rnp = rcu_get_root(rsp); - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + rsp->n_force_qs++; + if (fqs_state == RCU_SAVE_DYNTICK) { + /* Collect dyntick-idle snapshots. */ + force_qs_rnp(rsp, dyntick_save_progress_counter); + fqs_state = RCU_FORCE_QS; + } else { + /* Handle dyntick-idle and offline CPUs. */ + force_qs_rnp(rsp, rcu_implicit_dynticks_qs); + } + /* Clear flag to prevent immediate re-entry. */ + if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + raw_spin_lock_irq(&rnp->lock); + rsp->gp_flags &= ~RCU_GP_FLAG_FQS; + raw_spin_unlock_irq(&rnp->lock); + } + return fqs_state; +} - /* - * Ensure that all grace-period and pre-grace-period activity - * is seen before the assignment to rsp->completed. - */ - smp_mb(); /* See above block comment. */ +/* + * Clean up after the old grace period. + */ +static void rcu_gp_cleanup(struct rcu_state *rsp) +{ + unsigned long gp_duration; + struct rcu_data *rdp; + struct rcu_node *rnp = rcu_get_root(rsp); + + raw_spin_lock_irq(&rnp->lock); gp_duration = jiffies - rsp->gp_start; if (gp_duration > rsp->gp_max) rsp->gp_max = gp_duration; @@ -1150,35 +1285,149 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * they can do to advance the grace period. It is therefore * safe for us to drop the lock in order to mark the grace * period as completed in all of the rcu_node structures. - * - * But if this CPU needs another grace period, it will take - * care of this while initializing the next grace period. - * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL - * because the callbacks have not yet been advanced: Those - * callbacks are waiting on the grace period that just now - * completed. */ - if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) { - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_irq(&rnp->lock); - /* - * Propagate new ->completed value to rcu_node structures - * so that other CPUs don't have to wait until the start - * of the next grace period to process their callbacks. - */ - rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rnp->completed = rsp->gpnum; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - } - rnp = rcu_get_root(rsp); - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + /* + * Propagate new ->completed value to rcu_node structures so + * that other CPUs don't have to wait until the start of the next + * grace period to process their callbacks. This also avoids + * some nasty RCU grace-period initialization races by forcing + * the end of the current grace period to be completely recorded in + * all of the rcu_node structures before the beginning of the next + * grace period is recorded in any of the rcu_node structures. + */ + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock_irq(&rnp->lock); + rnp->completed = rsp->gpnum; + raw_spin_unlock_irq(&rnp->lock); + cond_resched(); } + rnp = rcu_get_root(rsp); + raw_spin_lock_irq(&rnp->lock); - rsp->completed = rsp->gpnum; /* Declare the grace period complete. */ + rsp->completed = rsp->gpnum; /* Declare grace period done. */ trace_rcu_grace_period(rsp->name, rsp->completed, "end"); rsp->fqs_state = RCU_GP_IDLE; - rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ + rdp = this_cpu_ptr(rsp->rda); + if (cpu_needs_another_gp(rsp, rdp)) + rsp->gp_flags = 1; + raw_spin_unlock_irq(&rnp->lock); +} + +/* + * Body of kthread that handles grace periods. + */ +static int __noreturn rcu_gp_kthread(void *arg) +{ + int fqs_state; + unsigned long j; + int ret; + struct rcu_state *rsp = arg; + struct rcu_node *rnp = rcu_get_root(rsp); + + for (;;) { + + /* Handle grace-period start. */ + for (;;) { + wait_event_interruptible(rsp->gp_wq, + rsp->gp_flags & + RCU_GP_FLAG_INIT); + if ((rsp->gp_flags & RCU_GP_FLAG_INIT) && + rcu_gp_init(rsp)) + break; + cond_resched(); + flush_signals(current); + } + + /* Handle quiescent-state forcing. */ + fqs_state = RCU_SAVE_DYNTICK; + j = jiffies_till_first_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_first_fqs = HZ; + } + for (;;) { + rsp->jiffies_force_qs = jiffies + j; + ret = wait_event_interruptible_timeout(rsp->gp_wq, + (rsp->gp_flags & RCU_GP_FLAG_FQS) || + (!ACCESS_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)), + j); + /* If grace period done, leave loop. */ + if (!ACCESS_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)) + break; + /* If time for quiescent-state forcing, do it. */ + if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) { + fqs_state = rcu_gp_fqs(rsp, fqs_state); + cond_resched(); + } else { + /* Deal with stray signal. */ + cond_resched(); + flush_signals(current); + } + j = jiffies_till_next_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_next_fqs = HZ; + } else if (j < 1) { + j = 1; + jiffies_till_next_fqs = 1; + } + } + + /* Handle grace-period end. */ + rcu_gp_cleanup(rsp); + } +} + +/* + * Start a new RCU grace period if warranted, re-initializing the hierarchy + * in preparation for detecting the next grace period. The caller must hold + * the root node's ->lock, which is released before return. Hard irqs must + * be disabled. + * + * Note that it is legal for a dying CPU (which is marked as offline) to + * invoke this function. This can happen when the dying CPU reports its + * quiescent state. + */ +static void +rcu_start_gp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + struct rcu_node *rnp = rcu_get_root(rsp); + + if (!rsp->gp_kthread || + !cpu_needs_another_gp(rsp, rdp)) { + /* + * Either we have not yet spawned the grace-period + * task or this CPU does not need another grace period. + * Either way, don't start a new grace period. + */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + rsp->gp_flags = RCU_GP_FLAG_INIT; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + wake_up(&rsp->gp_wq); +} + +/* + * Report a full set of quiescent states to the specified rcu_state + * data structure. This involves cleaning up after the prior grace + * period and letting rcu_start_gp() start up the next grace period + * if one is needed. Note that the caller must hold rnp->lock, as + * required by rcu_start_gp(), which will release it. + */ +static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } /* @@ -1247,7 +1496,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * based on quiescent states detected in an earlier grace period! */ static void -rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastgp) +rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; unsigned long mask; @@ -1255,7 +1504,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long las rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); - if (lastgp != rnp->gpnum || rnp->completed == rnp->gpnum) { + if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum || + rnp->completed == rnp->gpnum) { /* * The grace period in which this quiescent state was @@ -1314,7 +1564,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Tell RCU we are done (but rcu_report_qs_rdp() will be the * judge of that). */ - rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesce_gpnum); + rcu_report_qs_rdp(rdp->cpu, rsp, rdp); } #ifdef CONFIG_HOTPLUG_CPU @@ -1328,8 +1578,6 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - int i; - /* * Orphan the callbacks. First adjust the counts. This is safe * because ->onofflock excludes _rcu_barrier()'s adoption of @@ -1340,7 +1588,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->qlen += rdp->qlen; rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; } /* @@ -1369,9 +1617,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, } /* Finally, initialize the rcu_data structure's list to empty. */ - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); } /* @@ -1383,17 +1629,6 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp) int i; struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); - /* - * If there is an rcu_barrier() operation in progress, then - * only the task doing that operation is permitted to adopt - * callbacks. To do otherwise breaks rcu_barrier() and friends - * by causing them to fail to wait for the callbacks in the - * orphanage. - */ - if (rsp->rcu_barrier_in_progress && - rsp->rcu_barrier_in_progress != current) - return; - /* Do the accounting first. */ rdp->qlen_lazy += rsp->qlen_lazy; rdp->qlen += rsp->qlen; @@ -1448,9 +1683,8 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, * including orphaning the outgoing CPU's RCU callbacks, and also - * adopting them, if there is no _rcu_barrier() instance running. - * There can only be one CPU hotplug operation at a time, so no other - * CPU can be attempting to update rcu_cpu_kthread_task. + * adopting them. There can only be one CPU hotplug operation at a time, + * so no other CPU can be attempting to update rcu_cpu_kthread_task. */ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { @@ -1461,8 +1695,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ /* Adjust any no-longer-needed kthreads. */ - rcu_stop_cpu_kthread(cpu); - rcu_node_kthread_setaffinity(rnp, -1); + rcu_boost_kthread_setaffinity(rnp, -1); /* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */ @@ -1505,14 +1738,16 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); + WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", + cpu, rdp->qlen, rdp->nxtlist); + init_callback_list(rdp); + /* Disallow further callbacks on this CPU. */ + rdp->nxttail[RCU_NEXT_TAIL] = NULL; } #else /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_adopt_orphan_cbs(struct rcu_state *rsp) -{ -} - static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { } @@ -1592,7 +1827,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - rdp->qlen -= count; + ACCESS_ONCE(rdp->qlen) -= count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -1605,6 +1840,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rdp->n_force_qs_snap = rsp->n_force_qs; } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = rdp->qlen; + WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0)); local_irq_restore(flags); @@ -1676,6 +1912,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) struct rcu_node *rnp; rcu_for_each_leaf_node(rsp, rnp) { + cond_resched(); mask = 0; raw_spin_lock_irqsave(&rnp->lock, flags); if (!rcu_gp_in_progress(rsp)) { @@ -1712,74 +1949,39 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) * Force quiescent states on reluctant CPUs, and also detect which * CPUs are in dyntick-idle mode. */ -static void force_quiescent_state(struct rcu_state *rsp, int relaxed) +static void force_quiescent_state(struct rcu_state *rsp) { unsigned long flags; - struct rcu_node *rnp = rcu_get_root(rsp); - - trace_rcu_utilization("Start fqs"); - if (!rcu_gp_in_progress(rsp)) { - trace_rcu_utilization("End fqs"); - return; /* No grace period in progress, nothing to force. */ - } - if (!raw_spin_trylock_irqsave(&rsp->fqslock, flags)) { - rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */ - trace_rcu_utilization("End fqs"); - return; /* Someone else is already on the job. */ - } - if (relaxed && ULONG_CMP_GE(rsp->jiffies_force_qs, jiffies)) - goto unlock_fqs_ret; /* no emergency and done recently. */ - rsp->n_force_qs++; - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; - if(!rcu_gp_in_progress(rsp)) { - rsp->n_force_qs_ngp++; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - goto unlock_fqs_ret; /* no GP in progress, time updated. */ - } - rsp->fqs_active = 1; - switch (rsp->fqs_state) { - case RCU_GP_IDLE: - case RCU_GP_INIT: - - break; /* grace period idle or initializing, ignore. */ - - case RCU_SAVE_DYNTICK: - if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK) - break; /* So gcc recognizes the dead code. */ - - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - - /* Record dyntick-idle state. */ - force_qs_rnp(rsp, dyntick_save_progress_counter); - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - if (rcu_gp_in_progress(rsp)) - rsp->fqs_state = RCU_FORCE_QS; - break; - - case RCU_FORCE_QS: - - /* Check dyntick-idle state, send IPI to laggarts. */ - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - force_qs_rnp(rsp, rcu_implicit_dynticks_qs); - - /* Leave state in case more forcing is required. */ - - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - break; + bool ret; + struct rcu_node *rnp; + struct rcu_node *rnp_old = NULL; + + /* Funnel through hierarchy to reduce memory contention. */ + rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + for (; rnp != NULL; rnp = rnp->parent) { + ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || + !raw_spin_trylock(&rnp->fqslock); + if (rnp_old != NULL) + raw_spin_unlock(&rnp_old->fqslock); + if (ret) { + rsp->n_force_qs_lh++; + return; + } + rnp_old = rnp; } - rsp->fqs_active = 0; - if (rsp->fqs_need_gp) { - raw_spin_unlock(&rsp->fqslock); /* irqs remain disabled */ - rsp->fqs_need_gp = 0; - rcu_start_gp(rsp, flags); /* releases rnp->lock */ - trace_rcu_utilization("End fqs"); - return; + /* rnp_old == rcu_get_root(rsp), rnp == NULL. */ + + /* Reached the root of the rcu_node tree, acquire lock. */ + raw_spin_lock_irqsave(&rnp_old->lock, flags); + raw_spin_unlock(&rnp_old->fqslock); + if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + rsp->n_force_qs_lh++; + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + return; /* Someone beat us to it. */ } - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ -unlock_fqs_ret: - raw_spin_unlock_irqrestore(&rsp->fqslock, flags); - trace_rcu_utilization("End fqs"); + rsp->gp_flags |= RCU_GP_FLAG_FQS; + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } /* @@ -1788,20 +1990,14 @@ unlock_fqs_ret: * whom the rdp belongs. */ static void -__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +__rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); WARN_ON_ONCE(rdp->beenonline == 0); /* - * If an RCU GP has gone long enough, go check for dyntick - * idle CPUs and, if needed, send resched IPIs. - */ - if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); - - /* * Advance callbacks in response to end of earlier grace * period that some other CPU ended. */ @@ -1826,11 +2022,13 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_process_callbacks(struct softirq_action *unused) { + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; trace_rcu_utilization("Start RCU core"); - __rcu_process_callbacks(&rcu_sched_state, - &__get_cpu_var(rcu_sched_data)); - __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); - rcu_preempt_process_callbacks(); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); trace_rcu_utilization("End RCU core"); } @@ -1857,6 +2055,55 @@ static void invoke_rcu_core(void) raise_softirq(RCU_SOFTIRQ); } +/* + * Handle any core-RCU processing required by a call_rcu() invocation. + */ +static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, + struct rcu_head *head, unsigned long flags) +{ + /* + * If called from an extended quiescent state, invoke the RCU + * core in order to force a re-evaluation of RCU's idleness. + */ + if (rcu_is_cpu_idle() && cpu_online(smp_processor_id())) + invoke_rcu_core(); + + /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) + return; + + /* + * Force the grace period if too many callbacks or too long waiting. + * Enforce hysteresis, and don't invoke force_quiescent_state() + * if some other CPU has recently done so. Also, don't bother + * invoking force_quiescent_state() if the newly enqueued callback + * is the only one waiting for a grace period to complete. + */ + if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { + + /* Are we ignoring a completed grace period? */ + rcu_process_gp_end(rsp, rdp); + check_for_new_grace_period(rsp, rdp); + + /* Start a new grace period if one not already started. */ + if (!rcu_gp_in_progress(rsp)) { + unsigned long nestflag; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + raw_spin_lock_irqsave(&rnp_root->lock, nestflag); + rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ + } else { + /* Give the grace period a kick. */ + rdp->blimit = LONG_MAX; + if (rsp->n_force_qs == rdp->n_force_qs_snap && + *rdp->nxttail[RCU_DONE_TAIL] != head) + force_quiescent_state(rsp); + rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->qlen_last_fqs_check = rdp->qlen; + } + } +} + static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp, bool lazy) @@ -1869,8 +2116,6 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), head->func = func; head->next = NULL; - smp_mb(); /* Ensure RCU update seen before callback registry. */ - /* * Opportunistically note grace-period endings and beginnings. * Note that we might see a beginning right after we see an @@ -1881,7 +2126,13 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ - rdp->qlen++; + if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL)) { + /* _call_rcu() is illegal on offline CPU; leak the callback. */ + WARN_ON_ONCE(1); + local_irq_restore(flags); + return; + } + ACCESS_ONCE(rdp->qlen)++; if (lazy) rdp->qlen_lazy++; else @@ -1896,43 +2147,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), else trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); - /* If interrupts were disabled, don't dive into RCU core. */ - if (irqs_disabled_flags(flags)) { - local_irq_restore(flags); - return; - } - - /* - * Force the grace period if too many callbacks or too long waiting. - * Enforce hysteresis, and don't invoke force_quiescent_state() - * if some other CPU has recently done so. Also, don't bother - * invoking force_quiescent_state() if the newly enqueued callback - * is the only one waiting for a grace period to complete. - */ - if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { - - /* Are we ignoring a completed grace period? */ - rcu_process_gp_end(rsp, rdp); - check_for_new_grace_period(rsp, rdp); - - /* Start a new grace period if one not already started. */ - if (!rcu_gp_in_progress(rsp)) { - unsigned long nestflag; - struct rcu_node *rnp_root = rcu_get_root(rsp); - - raw_spin_lock_irqsave(&rnp_root->lock, nestflag); - rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ - } else { - /* Give the grace period a kick. */ - rdp->blimit = LONG_MAX; - if (rsp->n_force_qs == rdp->n_force_qs_snap && - *rdp->nxttail[RCU_DONE_TAIL] != head) - force_quiescent_state(rsp, 0); - rdp->n_force_qs_snap = rsp->n_force_qs; - rdp->qlen_last_fqs_check = rdp->qlen; - } - } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); + /* Go handle any RCU core processing required. */ + __call_rcu_core(rsp, rdp, head, flags); local_irq_restore(flags); } @@ -1962,28 +2178,16 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * occasionally incorrectly indicate that there are multiple CPUs online * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. - * - * Of course, sampling num_online_cpus() with preemption enabled can - * give erroneous results if there are concurrent CPU-hotplug operations. - * For example, given a demonic sequence of preemptions in num_online_cpus() - * and CPU-hotplug operations, there could be two or more CPUs online at - * all times, but num_online_cpus() might well return one (or even zero). - * - * However, all such demonic sequences require at least one CPU-offline - * operation. Furthermore, rcu_blocking_is_gp() giving the wrong answer - * is only a problem if there is an RCU read-side critical section executing - * throughout. But RCU-sched and RCU-bh read-side critical sections - * disable either preemption or bh, which prevents a CPU from going offline. - * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return - * that there is only one CPU when in fact there was more than one throughout - * is when there were no RCU readers in the system. If there are no - * RCU readers, the grace period by definition can be of zero length, - * regardless of the number of online CPUs. */ static inline int rcu_blocking_is_gp(void) { + int ret; + might_sleep(); /* Check for RCU read-side critical section. */ - return num_online_cpus() <= 1; + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; } /** @@ -2118,9 +2322,9 @@ void synchronize_sched_expedited(void) put_online_cpus(); /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_sched(); return; } @@ -2182,17 +2386,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && rdp->qs_pending && !rdp->passed_quiesce) { - - /* - * If force_quiescent_state() coming soon and this CPU - * needs a quiescent state, and this is either RCU-sched - * or RCU-bh, force a local reschedule. - */ rdp->n_rp_qs_pending++; - if (!rdp->preemptible && - ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1, - jiffies)) - set_need_resched(); } else if (rdp->qs_pending && rdp->passed_quiesce) { rdp->n_rp_report_qs++; return 1; @@ -2222,13 +2416,6 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) return 1; } - /* Has an RCU GP gone long enough to send resched IPIs &c? */ - if (rcu_gp_in_progress(rsp) && - ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) { - rdp->n_rp_need_fqs++; - return 1; - } - /* nothing to do */ rdp->n_rp_need_nothing++; return 0; @@ -2241,9 +2428,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) */ static int rcu_pending(int cpu) { - return __rcu_pending(&rcu_sched_state, &per_cpu(rcu_sched_data, cpu)) || - __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)) || - rcu_preempt_pending(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + if (__rcu_pending(rsp, per_cpu_ptr(rsp->rda, cpu))) + return 1; + return 0; } /* @@ -2253,20 +2443,41 @@ static int rcu_pending(int cpu) */ static int rcu_cpu_has_callbacks(int cpu) { + struct rcu_state *rsp; + /* RCU callbacks either ready or pending? */ - return per_cpu(rcu_sched_data, cpu).nxtlist || - per_cpu(rcu_bh_data, cpu).nxtlist || - rcu_preempt_cpu_has_callbacks(cpu); + for_each_rcu_flavor(rsp) + if (per_cpu_ptr(rsp->rda, cpu)->nxtlist) + return 1; + return 0; +} + +/* + * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * the compiler is expected to optimize this away. + */ +static void _rcu_barrier_trace(struct rcu_state *rsp, char *s, + int cpu, unsigned long done) +{ + trace_rcu_barrier(rsp->name, s, cpu, + atomic_read(&rsp->barrier_cpu_count), done); } /* * RCU callback function for _rcu_barrier(). If we are last, wake * up the task executing _rcu_barrier(). */ -static void rcu_barrier_callback(struct rcu_head *notused) +static void rcu_barrier_callback(struct rcu_head *rhp) { - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) - complete(&rcu_barrier_completion); + struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); + struct rcu_state *rsp = rdp->rsp; + + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { + _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done); + complete(&rsp->barrier_completion); + } else { + _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done); + } } /* @@ -2274,112 +2485,108 @@ static void rcu_barrier_callback(struct rcu_head *notused) */ static void rcu_barrier_func(void *type) { - int cpu = smp_processor_id(); - struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu); - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head)); + struct rcu_state *rsp = type; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); - atomic_inc(&rcu_barrier_cpu_count); - call_rcu_func = type; - call_rcu_func(head, rcu_barrier_callback); + _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); + atomic_inc(&rsp->barrier_cpu_count); + rsp->call(&rdp->barrier_head, rcu_barrier_callback); } /* * Orchestrate the specified type of RCU barrier, waiting for all * RCU callbacks of the specified type to complete. */ -static void _rcu_barrier(struct rcu_state *rsp, - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head))) +static void _rcu_barrier(struct rcu_state *rsp) { int cpu; - unsigned long flags; struct rcu_data *rdp; - struct rcu_head rh; + unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); + unsigned long snap_done; - init_rcu_head_on_stack(&rh); + _rcu_barrier_trace(rsp, "Begin", -1, snap); /* Take mutex to serialize concurrent rcu_barrier() requests. */ - mutex_lock(&rcu_barrier_mutex); + mutex_lock(&rsp->barrier_mutex); - smp_mb(); /* Prevent any prior operations from leaking in. */ + /* + * Ensure that all prior references, including to ->n_barrier_done, + * are ordered before the _rcu_barrier() machinery. + */ + smp_mb(); /* See above block comment. */ + + /* + * Recheck ->n_barrier_done to see if others did our work for us. + * This means checking ->n_barrier_done for an even-to-odd-to-even + * transition. The "if" expression below therefore rounds the old + * value up to the next even number and adds two before comparing. + */ + snap_done = ACCESS_ONCE(rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "Check", -1, snap_done); + if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) { + _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done); + smp_mb(); /* caller's subsequent code after above check. */ + mutex_unlock(&rsp->barrier_mutex); + return; + } + + /* + * Increment ->n_barrier_done to avoid duplicate work. Use + * ACCESS_ONCE() to prevent the compiler from speculating + * the increment to precede the early-exit check. + */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); + _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); + smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ /* * Initialize the count to one rather than to zero in order to * avoid a too-soon return to zero in case of a short grace period - * (or preemption of this task). Also flag this task as doing - * an rcu_barrier(). This will prevent anyone else from adopting - * orphaned callbacks, which could cause otherwise failure if a - * CPU went offline and quickly came back online. To see this, - * consider the following sequence of events: - * - * 1. We cause CPU 0 to post an rcu_barrier_callback() callback. - * 2. CPU 1 goes offline, orphaning its callbacks. - * 3. CPU 0 adopts CPU 1's orphaned callbacks. - * 4. CPU 1 comes back online. - * 5. We cause CPU 1 to post an rcu_barrier_callback() callback. - * 6. Both rcu_barrier_callback() callbacks are invoked, awakening - * us -- but before CPU 1's orphaned callbacks are invoked!!! + * (or preemption of this task). Exclude CPU-hotplug operations + * to ensure that no offline CPU has callbacks queued. */ - init_completion(&rcu_barrier_completion); - atomic_set(&rcu_barrier_cpu_count, 1); - raw_spin_lock_irqsave(&rsp->onofflock, flags); - rsp->rcu_barrier_in_progress = current; - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + init_completion(&rsp->barrier_completion); + atomic_set(&rsp->barrier_cpu_count, 1); + get_online_cpus(); /* - * Force every CPU with callbacks to register a new callback - * that will tell us when all the preceding callbacks have - * been invoked. If an offline CPU has callbacks, wait for - * it to either come back online or to finish orphaning those - * callbacks. + * Force each CPU with callbacks to register a new callback. + * When that callback is invoked, we will know that all of the + * corresponding CPU's preceding callbacks have been invoked. */ - for_each_possible_cpu(cpu) { - preempt_disable(); + for_each_online_cpu(cpu) { rdp = per_cpu_ptr(rsp->rda, cpu); - if (cpu_is_offline(cpu)) { - preempt_enable(); - while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen)) - schedule_timeout_interruptible(1); - } else if (ACCESS_ONCE(rdp->qlen)) { - smp_call_function_single(cpu, rcu_barrier_func, - (void *)call_rcu_func, 1); - preempt_enable(); + if (ACCESS_ONCE(rdp->qlen)) { + _rcu_barrier_trace(rsp, "OnlineQ", cpu, + rsp->n_barrier_done); + smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); } else { - preempt_enable(); + _rcu_barrier_trace(rsp, "OnlineNQ", cpu, + rsp->n_barrier_done); } } - - /* - * Now that all online CPUs have rcu_barrier_callback() callbacks - * posted, we can adopt all of the orphaned callbacks and place - * an rcu_barrier_callback() callback after them. When that is done, - * we are guaranteed to have an rcu_barrier_callback() callback - * following every callback that could possibly have been - * registered before _rcu_barrier() was called. - */ - raw_spin_lock_irqsave(&rsp->onofflock, flags); - rcu_adopt_orphan_cbs(rsp); - rsp->rcu_barrier_in_progress = NULL; - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); - atomic_inc(&rcu_barrier_cpu_count); - smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */ - call_rcu_func(&rh, rcu_barrier_callback); + put_online_cpus(); /* * Now that we have an rcu_barrier_callback() callback on each * CPU, and thus each counted, remove the initial count. */ - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) - complete(&rcu_barrier_completion); + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) + complete(&rsp->barrier_completion); + + /* Increment ->n_barrier_done to prevent duplicate work. */ + smp_mb(); /* Keep increment after above mechanism. */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); + _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); + smp_mb(); /* Keep increment before caller's subsequent code. */ /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ - wait_for_completion(&rcu_barrier_completion); + wait_for_completion(&rsp->barrier_completion); /* Other rcu_barrier() invocations can now safely proceed. */ - mutex_unlock(&rcu_barrier_mutex); - - destroy_rcu_head_on_stack(&rh); + mutex_unlock(&rsp->barrier_mutex); } /** @@ -2387,7 +2594,7 @@ static void _rcu_barrier(struct rcu_state *rsp, */ void rcu_barrier_bh(void) { - _rcu_barrier(&rcu_bh_state, call_rcu_bh); + _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); @@ -2396,7 +2603,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_bh); */ void rcu_barrier_sched(void) { - _rcu_barrier(&rcu_sched_state, call_rcu_sched); + _rcu_barrier(&rcu_sched_state); } EXPORT_SYMBOL_GPL(rcu_barrier_sched); @@ -2407,21 +2614,21 @@ static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; - int i; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); +#ifdef CONFIG_RCU_USER_QS + WARN_ON_ONCE(rdp->dynticks->in_user); +#endif rdp->cpu = cpu; rdp->rsp = rsp; raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -2448,6 +2655,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; + init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); @@ -2480,7 +2688,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->completed = rnp->completed; rdp->passed_quiesce = 0; rdp->qs_pending = 0; - rdp->passed_quiesce_gpnum = rnp->gpnum - 1; trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl"); } raw_spin_unlock(&rnp->lock); /* irqs already disabled. */ @@ -2492,9 +2699,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) static void __cpuinit rcu_prepare_cpu(int cpu) { - rcu_init_percpu_data(cpu, &rcu_sched_state, 0); - rcu_init_percpu_data(cpu, &rcu_bh_state, 0); - rcu_preempt_init_percpu_data(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_init_percpu_data(cpu, rsp, + strcmp(rsp->name, "rcu_preempt") == 0); } /* @@ -2506,6 +2715,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, long cpu = (long)hcpu; struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); struct rcu_node *rnp = rdp->mynode; + struct rcu_state *rsp; trace_rcu_utilization("Start CPU hotplug"); switch (action) { @@ -2516,12 +2726,10 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, break; case CPU_ONLINE: case CPU_DOWN_FAILED: - rcu_node_kthread_setaffinity(rnp, -1); - rcu_cpu_kthread_setrt(cpu, 1); + rcu_boost_kthread_setaffinity(rnp, -1); break; case CPU_DOWN_PREPARE: - rcu_node_kthread_setaffinity(rnp, cpu); - rcu_cpu_kthread_setrt(cpu, 0); + rcu_boost_kthread_setaffinity(rnp, cpu); break; case CPU_DYING: case CPU_DYING_FROZEN: @@ -2530,18 +2738,16 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, * touch any data without introducing corruption. We send the * dying CPU's callbacks to an arbitrarily chosen online CPU. */ - rcu_cleanup_dying_cpu(&rcu_bh_state); - rcu_cleanup_dying_cpu(&rcu_sched_state); - rcu_preempt_cleanup_dying_cpu(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - rcu_cleanup_dead_cpu(cpu, &rcu_bh_state); - rcu_cleanup_dead_cpu(cpu, &rcu_sched_state); - rcu_preempt_cleanup_dead_cpu(cpu); + for_each_rcu_flavor(rsp) + rcu_cleanup_dead_cpu(cpu, rsp); break; default: break; @@ -2551,6 +2757,28 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, } /* + * Spawn the kthread that handles this RCU flavor's grace periods. + */ +static int __init rcu_spawn_gp_kthread(void) +{ + unsigned long flags; + struct rcu_node *rnp; + struct rcu_state *rsp; + struct task_struct *t; + + for_each_rcu_flavor(rsp) { + t = kthread_run(rcu_gp_kthread, rsp, rsp->name); + BUG_ON(IS_ERR(t)); + rnp = rcu_get_root(rsp); + raw_spin_lock_irqsave(&rnp->lock, flags); + rsp->gp_kthread = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + return 0; +} +early_initcall(rcu_spawn_gp_kthread); + +/* * This function is invoked towards the end of the scheduler's initialization * process. Before this is called, the idle task might contain * RCU read-side critical sections (during which time, this idle @@ -2574,9 +2802,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) { int i; - for (i = NUM_RCU_LVLS - 1; i > 0; i--) + for (i = rcu_num_lvls - 1; i > 0; i--) rsp->levelspread[i] = CONFIG_RCU_FANOUT; - rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF; + rsp->levelspread[0] = rcu_fanout_leaf; } #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ static void __init rcu_init_levelspread(struct rcu_state *rsp) @@ -2585,8 +2813,8 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) int cprv; int i; - cprv = NR_CPUS; - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + cprv = nr_cpu_ids; + for (i = rcu_num_lvls - 1; i >= 0; i--) { ccur = rsp->levelcnt[i]; rsp->levelspread[i] = (cprv + ccur - 1) / ccur; cprv = ccur; @@ -2600,10 +2828,14 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) static void __init rcu_init_one(struct rcu_state *rsp, struct rcu_data __percpu *rda) { - static char *buf[] = { "rcu_node_level_0", - "rcu_node_level_1", - "rcu_node_level_2", - "rcu_node_level_3" }; /* Match MAX_RCU_LVLS */ + static char *buf[] = { "rcu_node_0", + "rcu_node_1", + "rcu_node_2", + "rcu_node_3" }; /* Match MAX_RCU_LVLS */ + static char *fqs[] = { "rcu_node_fqs_0", + "rcu_node_fqs_1", + "rcu_node_fqs_2", + "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ int cpustride = 1; int i; int j; @@ -2613,20 +2845,26 @@ static void __init rcu_init_one(struct rcu_state *rsp, /* Initialize the level-tracking arrays. */ - for (i = 1; i < NUM_RCU_LVLS; i++) + for (i = 0; i < rcu_num_lvls; i++) + rsp->levelcnt[i] = num_rcu_lvl[i]; + for (i = 1; i < rcu_num_lvls; i++) rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; rcu_init_levelspread(rsp); /* Initialize the elements themselves, starting from the leaves. */ - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { cpustride *= rsp->levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { raw_spin_lock_init(&rnp->lock); lockdep_set_class_and_name(&rnp->lock, &rcu_node_class[i], buf[i]); - rnp->gpnum = 0; + raw_spin_lock_init(&rnp->fqslock); + lockdep_set_class_and_name(&rnp->fqslock, + &rcu_fqs_class[i], fqs[i]); + rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -2649,13 +2887,76 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; - rnp = rsp->level[NUM_RCU_LVLS - 1]; + init_waitqueue_head(&rsp->gp_wq); + rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; per_cpu_ptr(rsp->rda, i)->mynode = rnp; rcu_boot_init_percpu_data(i, rsp); } + list_add(&rsp->flavors, &rcu_struct_flavors); +} + +/* + * Compute the rcu_node tree geometry from kernel parameters. This cannot + * replace the definitions in rcutree.h because those are needed to size + * the ->node array in the rcu_state structure. + */ +static void __init rcu_init_geometry(void) +{ + int i; + int j; + int n = nr_cpu_ids; + int rcu_capacity[MAX_RCU_LVLS + 1]; + + /* If the compile-time values are accurate, just leave. */ + if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF && + nr_cpu_ids == NR_CPUS) + return; + + /* + * Compute number of nodes that can be handled an rcu_node tree + * with the given number of levels. Setting rcu_capacity[0] makes + * some of the arithmetic easier. + */ + rcu_capacity[0] = 1; + rcu_capacity[1] = rcu_fanout_leaf; + for (i = 2; i <= MAX_RCU_LVLS; i++) + rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT; + + /* + * The boot-time rcu_fanout_leaf parameter is only permitted + * to increase the leaf-level fanout, not decrease it. Of course, + * the leaf-level fanout cannot exceed the number of bits in + * the rcu_node masks. Finally, the tree must be able to accommodate + * the configured number of CPUs. Complain and fall back to the + * compile-time values if these limits are exceeded. + */ + if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF || + rcu_fanout_leaf > sizeof(unsigned long) * 8 || + n > rcu_capacity[MAX_RCU_LVLS]) { + WARN_ON(1); + return; + } + + /* Calculate the number of rcu_nodes at each level of the tree. */ + for (i = 1; i <= MAX_RCU_LVLS; i++) + if (n <= rcu_capacity[i]) { + for (j = 0; j <= i; j++) + num_rcu_lvl[j] = + DIV_ROUND_UP(n, rcu_capacity[i - j]); + rcu_num_lvls = i; + for (j = i + 1; j <= MAX_RCU_LVLS; j++) + num_rcu_lvl[j] = 0; + break; + } + + /* Calculate the total number of rcu_node structures. */ + rcu_num_nodes = 0; + for (i = 0; i <= MAX_RCU_LVLS; i++) + rcu_num_nodes += num_rcu_lvl[i]; + rcu_num_nodes -= n; } void __init rcu_init(void) @@ -2663,6 +2964,7 @@ void __init rcu_init(void) int cpu; rcu_bootup_announce(); + rcu_init_geometry(); rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 19b61ac1079..5faf05d6832 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -42,28 +42,28 @@ #define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) #if NR_CPUS <= RCU_FANOUT_1 -# define NUM_RCU_LVLS 1 +# define RCU_NUM_LVLS 1 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 (NR_CPUS) # define NUM_RCU_LVL_2 0 # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_2 -# define NUM_RCU_LVLS 2 +# define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_3 -# define NUM_RCU_LVLS 3 +# define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_3 (NR_CPUS) # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_4 -# define NUM_RCU_LVLS 4 +# define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) @@ -76,6 +76,9 @@ #define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) +extern int rcu_num_lvls; +extern int rcu_num_nodes; + /* * Dynticks per-CPU state. */ @@ -97,7 +100,12 @@ struct rcu_dynticks { /* # times non-lazy CBs posted to CPU. */ unsigned long nonlazy_posted_snap; /* idle-period nonlazy_posted snapshot. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ +#ifdef CONFIG_RCU_USER_QS + bool ignore_user_qs; /* Treat userspace as extended QS or not */ + bool in_user; /* Is the CPU in userland from RCU POV? */ +#endif }; /* RCU's kthread states for tracing. */ @@ -192,12 +200,7 @@ struct rcu_node { /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ #endif /* #ifdef CONFIG_RCU_BOOST */ - struct task_struct *node_kthread_task; - /* kthread that takes care of this rcu_node */ - /* structure, for example, awakening the */ - /* per-CPU kthreads as needed. */ - unsigned int node_kthread_status; - /* State of node_kthread_task for tracing. */ + raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; } ____cacheline_internodealigned_in_smp; /* @@ -206,7 +209,7 @@ struct rcu_node { */ #define rcu_for_each_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* * Do a breadth-first scan of the non-leaf rcu_node structures for the @@ -215,7 +218,7 @@ struct rcu_node { */ #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++) /* * Scan the leaves of the rcu_node hierarchy for the specified rcu_state @@ -224,8 +227,8 @@ struct rcu_node { * It is still a leaf node, even if it is also the root node. */ #define rcu_for_each_leaf_node(rsp, rnp) \ - for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ @@ -241,8 +244,6 @@ struct rcu_data { /* in order to detect GP end. */ unsigned long gpnum; /* Highest gp number that this CPU */ /* is aware of having started. */ - unsigned long passed_quiesce_gpnum; - /* gpnum at time of quiescent state. */ bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ @@ -308,9 +309,14 @@ struct rcu_data { unsigned long n_rp_cpu_needs_gp; unsigned long n_rp_gp_completed; unsigned long n_rp_gp_started; - unsigned long n_rp_need_fqs; unsigned long n_rp_need_nothing; + /* 6) _rcu_barrier() and OOM callbacks. */ + struct rcu_head barrier_head; +#ifdef CONFIG_RCU_FAST_NO_HZ + struct rcu_head oom_head; +#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + int cpu; struct rcu_state *rsp; }; @@ -357,29 +363,28 @@ do { \ */ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ - struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */ + struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ - u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */ + u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ + void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ + void (*func)(struct rcu_head *head)); /* The following fields are guarded by the root rcu_node's lock. */ u8 fqs_state ____cacheline_internodealigned_in_smp; /* Force QS state. */ - u8 fqs_active; /* force_quiescent_state() */ - /* is running. */ - u8 fqs_need_gp; /* A CPU was prevented from */ - /* starting a new grace */ - /* period because */ - /* force_quiescent_state() */ - /* was running. */ u8 boost; /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ + struct task_struct *gp_kthread; /* Task for grace periods. */ + wait_queue_head_t gp_wq; /* Where GP task waits. */ + int gp_flags; /* Commands for GP task. */ /* End of fields guarded by root rcu_node's lock. */ - raw_spinlock_t onofflock; /* exclude on/offline and */ + raw_spinlock_t onofflock ____cacheline_internodealigned_in_smp; + /* exclude on/offline and */ /* starting new GP. */ struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */ /* need a grace period. */ @@ -389,11 +394,11 @@ struct rcu_state { struct rcu_head **orphan_donetail; /* Tail of above. */ long qlen_lazy; /* Number of lazy callbacks. */ long qlen; /* Total number of callbacks. */ - struct task_struct *rcu_barrier_in_progress; - /* Task doing rcu_barrier(), */ - /* or NULL if no barrier. */ - raw_spinlock_t fqslock; /* Only one task forcing */ - /* quiescent states. */ + struct mutex barrier_mutex; /* Guards barrier fields. */ + atomic_t barrier_cpu_count; /* # CPUs waiting on. */ + struct completion barrier_completion; /* Wake at barrier end. */ + unsigned long n_barrier_done; /* ++ at start and end of */ + /* _rcu_barrier(). */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ unsigned long n_force_qs; /* Number of calls to */ @@ -409,8 +414,17 @@ struct rcu_state { unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ char *name; /* Name of structure. */ + struct list_head flavors; /* List of RCU flavors. */ }; +/* Values for rcu_state structure's gp_flags field. */ +#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ +#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ + +extern struct list_head rcu_struct_flavors; +#define for_each_rcu_flavor(rsp) \ + list_for_each_entry((rsp), &rcu_struct_flavors, flavors) + /* Return values for rcu_preempt_offline_tasks(). */ #define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ @@ -449,29 +463,21 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); -static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); -static void rcu_preempt_stall_reset(void); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_preempt_cleanup_dead_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); -static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ -static int rcu_preempt_pending(int cpu); -static int rcu_preempt_cpu_has_callbacks(int cpu); -static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void rcu_preempt_cleanup_dying_cpu(void); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); @@ -479,15 +485,9 @@ static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void); -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, - cpumask_var_t cm); static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp, - int rnp_index); -static void invoke_rcu_node_kthread(struct rcu_node *rnp); -static void rcu_yield(void (*f)(unsigned long), unsigned long arg); + struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ -static void rcu_cpu_kthread_setrt(int cpu, int to_rt); static void __cpuinit rcu_prepare_kthreads(int cpu); static void rcu_prepare_for_idle_init(int cpu); static void rcu_cleanup_after_idle(int cpu); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3e4899459f3..f9211548818 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -25,6 +25,8 @@ */ #include <linux/delay.h> +#include <linux/oom.h> +#include <linux/smpboot.h> #define RCU_KTHREAD_PRIO 1 @@ -68,17 +70,21 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n"); #endif #if NUM_RCU_LVL_4 != 0 - printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); + printk(KERN_INFO "\tFour-level hierarchy is enabled.\n"); #endif + if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) + printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + if (nr_cpu_ids != NR_CPUS) + printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); } #ifdef CONFIG_TREE_PREEMPT_RCU -struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt); +struct rcu_state rcu_preempt_state = + RCU_STATE_INITIALIZER(rcu_preempt, call_rcu); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -114,7 +120,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); */ void rcu_force_quiescent_state(void) { - force_quiescent_state(&rcu_preempt_state, 0); + force_quiescent_state(&rcu_preempt_state); } EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); @@ -132,8 +138,6 @@ static void rcu_preempt_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - rdp->passed_quiesce_gpnum = rdp->gpnum; - barrier(); if (rdp->passed_quiesce == 0) trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; @@ -233,18 +237,6 @@ static void rcu_preempt_note_context_switch(int cpu) } /* - * Tree-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutree.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. @@ -310,7 +302,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -398,8 +390,9 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) rnp->grphi, !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rnp, flags); - } else + } else { raw_spin_unlock_irqrestore(&rnp->lock, flags); + } #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ @@ -418,38 +411,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } } -/* - * Tree-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* @@ -461,9 +422,11 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) unsigned long flags; struct task_struct *t; - if (!rcu_preempt_blocked_readers_cgp(rnp)) - return; raw_spin_lock_irqsave(&rnp->lock, flags); + if (!rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } t = list_entry(rnp->gp_tasks, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) @@ -540,16 +503,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* - * Suppress preemptible RCU's CPU stall warnings by pushing the - * time of the next stall-warning message comfortably far into the - * future. - */ -static void rcu_preempt_stall_reset(void) -{ - rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2; -} - -/* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be @@ -633,31 +586,29 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ } + rnp->gp_tasks = NULL; + rnp->exp_tasks = NULL; #ifdef CONFIG_RCU_BOOST - /* In case root is being boosted and leaf is not. */ + rnp->boost_tasks = NULL; + /* + * In case root is being boosted and leaf was not. Make sure + * that we boost the tasks blocking the current grace period + * in this case. + */ raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ if (rnp_root->boost_tasks != NULL && - rnp_root->boost_tasks != rnp_root->gp_tasks) + rnp_root->boost_tasks != rnp_root->gp_tasks && + rnp_root->boost_tasks != rnp_root->exp_tasks) rnp_root->boost_tasks = rnp_root->gp_tasks; raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ #endif /* #ifdef CONFIG_RCU_BOOST */ - rnp->gp_tasks = NULL; - rnp->exp_tasks = NULL; return retval; } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Do CPU-offline processing for preemptible RCU. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ - rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state); -} - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, * which is checked elsewhere. @@ -677,15 +628,6 @@ static void rcu_preempt_check_callbacks(int cpu) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } -/* - * Process callbacks for preemptible RCU. - */ -static void rcu_preempt_process_callbacks(void) -{ - __rcu_process_callbacks(&rcu_preempt_state, - &__get_cpu_var(rcu_preempt_data)); -} - #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void) @@ -742,7 +684,7 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); -static long sync_rcu_preempt_exp_count; +static unsigned long sync_rcu_preempt_exp_count; static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* @@ -824,9 +766,9 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) int must_wait = 0; raw_spin_lock_irqsave(&rnp->lock, flags); - if (list_empty(&rnp->blkd_tasks)) + if (list_empty(&rnp->blkd_tasks)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - else { + } else { rnp->exp_tasks = rnp->blkd_tasks.next; rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ must_wait = 1; @@ -857,7 +799,7 @@ void synchronize_rcu_expedited(void) unsigned long flags; struct rcu_node *rnp; struct rcu_state *rsp = &rcu_preempt_state; - long snap; + unsigned long snap; int trycount = 0; smp_mb(); /* Caller's modifications seen first by other CPUs. */ @@ -865,33 +807,47 @@ void synchronize_rcu_expedited(void) smp_mb(); /* Above access cannot bleed into critical section. */ /* + * Block CPU-hotplug operations. This means that any CPU-hotplug + * operation that finds an rcu_node structure with tasks in the + * process of being boosted will know that all tasks blocking + * this expedited grace period will already be in the process of + * being boosted. This simplifies the process of moving tasks + * from leaf to root rcu_node structures. + */ + get_online_cpus(); + + /* * Acquire lock, falling back to synchronize_rcu() if too many * lock-acquisition failures. Of course, if someone does the * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (trycount++ < 10) + if (ULONG_CMP_LT(snap, + ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + put_online_cpus(); + goto mb_ret; /* Others did our work for us. */ + } + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { + put_online_cpus(); synchronize_rcu(); return; } - if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) - goto mb_ret; /* Others did our work for us. */ } - if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) + if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + put_online_cpus(); goto unlock_mb_ret; /* Others did our work for us. */ + } /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); - raw_spin_lock_irqsave(&rsp->onofflock, flags); - /* Initialize ->expmask for all non-leaf rcu_node structures. */ rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + raw_spin_lock_irqsave(&rnp->lock, flags); rnp->expmask = rnp->qsmaskinit; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* Snapshot current state of ->blkd_tasks lists. */ @@ -900,7 +856,7 @@ void synchronize_rcu_expedited(void) if (NUM_RCU_NODES > 1) sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp)); - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + put_online_cpus(); /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); @@ -917,51 +873,16 @@ mb_ret: } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -/* - * Check to see if there is any immediate preemptible-RCU-related work - * to be done. - */ -static int rcu_preempt_pending(int cpu) -{ - return __rcu_pending(&rcu_preempt_state, - &per_cpu(rcu_preempt_data, cpu)); -} - -/* - * Does preemptible RCU have callbacks on this CPU? - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return !!per_cpu(rcu_preempt_data, cpu).nxtlist; -} - /** * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. */ void rcu_barrier(void) { - _rcu_barrier(&rcu_preempt_state, call_rcu); + _rcu_barrier(&rcu_preempt_state); } EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Initialize preemptible RCU's per-CPU data. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ - rcu_init_percpu_data(cpu, &rcu_preempt_state, 1); -} - -/* - * Move preemptible RCU's callbacks from dying CPU to other online CPU - * and record a quiescent state. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ - rcu_cleanup_dying_cpu(&rcu_preempt_state); -} - -/* * Initialize preemptible RCU's state structures. */ static void __init __rcu_init_preempt(void) @@ -1046,14 +967,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* - * Because preemptible RCU does not exist, there is no need to suppress - * its CPU stall warnings. - */ -static void rcu_preempt_stall_reset(void) -{ -} - -/* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. @@ -1081,14 +994,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptible RCU does not exist, it never needs CPU-offline - * processing. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ -} - -/* * Because preemptible RCU does not exist, it never has any callbacks * to check. */ @@ -1097,14 +1002,6 @@ static void rcu_preempt_check_callbacks(int cpu) } /* - * Because preemptible RCU does not exist, it never has any callbacks - * to process. - */ -static void rcu_preempt_process_callbacks(void) -{ -} - -/* * Queue an RCU callback for lazy invocation after a grace period. * This will likely be later named something like "call_rcu_lazy()", * but this change will require some way of tagging the lazy RCU @@ -1145,22 +1042,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptible RCU does not exist, it never has any work to do. - */ -static int rcu_preempt_pending(int cpu) -{ - return 0; -} - -/* - * Because preemptible RCU does not exist, it never has callbacks - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return 0; -} - -/* * Because preemptible RCU does not exist, rcu_barrier() is just * another name for rcu_barrier_sched(). */ @@ -1171,21 +1052,6 @@ void rcu_barrier(void) EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Because preemptible RCU does not exist, there is no per-CPU - * data to initialize. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ -} - -/* - * Because there is no preemptible RCU, there is no cleanup to do. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ -} - -/* * Because preemptible RCU does not exist, it need not be initialized. */ static void __init __rcu_init_preempt(void) @@ -1225,6 +1091,16 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp) #endif /* #else #ifdef CONFIG_RCU_TRACE */ +static void rcu_wake_cond(struct task_struct *t, int status) +{ + /* + * If the thread is yielding, only wake it when this + * is invoked from idle + */ + if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) + wake_up_process(t); +} + /* * Carry out RCU priority boosting on the task indicated by ->exp_tasks * or ->boost_tasks, advancing the pointer to the next task in the @@ -1297,17 +1173,6 @@ static int rcu_boost(struct rcu_node *rnp) } /* - * Timer handler to initiate waking up of boost kthreads that - * have yielded the CPU due to excessive numbers of tasks to - * boost. We wake up the per-rcu_node kthread, which in turn - * will wake up the booster kthread. - */ -static void rcu_boost_kthread_timer(unsigned long arg) -{ - invoke_rcu_node_kthread((struct rcu_node *)arg); -} - -/* * Priority-boosting kthread. One per leaf rcu_node and one for the * root rcu_node. */ @@ -1330,8 +1195,9 @@ static int rcu_boost_kthread(void *arg) else spincnt = 0; if (spincnt > 10) { + rnp->boost_kthread_status = RCU_KTHREAD_YIELDING; trace_rcu_utilization("End boost kthread@rcu_yield"); - rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp); + schedule_timeout_interruptible(2); trace_rcu_utilization("Start boost kthread@rcu_yield"); spincnt = 0; } @@ -1347,9 +1213,9 @@ static int rcu_boost_kthread(void *arg) * kthread to start boosting them. If there is an expedited grace * period in progress, it is always time to boost. * - * The caller must hold rnp->lock, which this function releases, - * but irqs remain disabled. The ->boost_kthread_task is immortal, - * so we don't need to worry about it going away. + * The caller must hold rnp->lock, which this function releases. + * The ->boost_kthread_task is immortal, so we don't need to worry + * about it going away. */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) { @@ -1369,8 +1235,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) rnp->boost_tasks = rnp->gp_tasks; raw_spin_unlock_irqrestore(&rnp->lock, flags); t = rnp->boost_kthread_task; - if (t != NULL) - wake_up_process(t); + if (t) + rcu_wake_cond(t, rnp->boost_kthread_status); } else { rcu_initiate_boost_trace(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -1387,8 +1253,10 @@ static void invoke_rcu_callbacks_kthread(void) local_irq_save(flags); __this_cpu_write(rcu_cpu_has_work, 1); if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && - current != __this_cpu_read(rcu_cpu_kthread_task)) - wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); + current != __this_cpu_read(rcu_cpu_kthread_task)) { + rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), + __this_cpu_read(rcu_cpu_kthread_status)); + } local_irq_restore(flags); } @@ -1401,21 +1269,6 @@ static bool rcu_is_callbacks_kthread(void) return __get_cpu_var(rcu_cpu_kthread_task) == current; } -/* - * Set the affinity of the boost kthread. The CPU-hotplug locks are - * held, so no one should be messing with the existence of the boost - * kthread. - */ -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, - cpumask_var_t cm) -{ - struct task_struct *t; - - t = rnp->boost_kthread_task; - if (t != NULL) - set_cpus_allowed_ptr(rnp->boost_kthread_task, cm); -} - #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* @@ -1432,15 +1285,19 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * Returns zero if all is well, a negated errno otherwise. */ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp, - int rnp_index) + struct rcu_node *rnp) { + int rnp_index = rnp - &rsp->node[0]; unsigned long flags; struct sched_param sp; struct task_struct *t; if (&rcu_preempt_state != rsp) return 0; + + if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0) + return 0; + rsp->boost = 1; if (rnp->boost_kthread_task != NULL) return 0; @@ -1457,25 +1314,6 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, return 0; } -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Stop the RCU's per-CPU kthread when its CPU goes offline,. - */ -static void rcu_stop_cpu_kthread(int cpu) -{ - struct task_struct *t; - - /* Stop the CPU's kthread. */ - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t != NULL) { - per_cpu(rcu_cpu_kthread_task, cpu) = NULL; - kthread_stop(t); - } -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - static void rcu_kthread_do_work(void) { rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); @@ -1483,112 +1321,22 @@ static void rcu_kthread_do_work(void) rcu_preempt_do_callbacks(); } -/* - * Wake up the specified per-rcu_node-structure kthread. - * Because the per-rcu_node kthreads are immortal, we don't need - * to do anything to keep them alive. - */ -static void invoke_rcu_node_kthread(struct rcu_node *rnp) -{ - struct task_struct *t; - - t = rnp->node_kthread_task; - if (t != NULL) - wake_up_process(t); -} - -/* - * Set the specified CPU's kthread to run RT or not, as specified by - * the to_rt argument. The CPU-hotplug locks are held, so the task - * is not going away. - */ -static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +static void rcu_cpu_kthread_setup(unsigned int cpu) { - int policy; struct sched_param sp; - struct task_struct *t; - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t == NULL) - return; - if (to_rt) { - policy = SCHED_FIFO; - sp.sched_priority = RCU_KTHREAD_PRIO; - } else { - policy = SCHED_NORMAL; - sp.sched_priority = 0; - } - sched_setscheduler_nocheck(t, policy, &sp); -} - -/* - * Timer handler to initiate the waking up of per-CPU kthreads that - * have yielded the CPU due to excess numbers of RCU callbacks. - * We wake up the per-rcu_node kthread, which in turn will wake up - * the booster kthread. - */ -static void rcu_cpu_kthread_timer(unsigned long arg) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); - struct rcu_node *rnp = rdp->mynode; - - atomic_or(rdp->grpmask, &rnp->wakemask); - invoke_rcu_node_kthread(rnp); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); } -/* - * Drop to non-real-time priority and yield, but only after posting a - * timer that will cause us to regain our real-time priority if we - * remain preempted. Either way, we restore our real-time priority - * before returning. - */ -static void rcu_yield(void (*f)(unsigned long), unsigned long arg) +static void rcu_cpu_kthread_park(unsigned int cpu) { - struct sched_param sp; - struct timer_list yield_timer; - int prio = current->rt_priority; - - setup_timer_on_stack(&yield_timer, f, arg); - mod_timer(&yield_timer, jiffies + 2); - sp.sched_priority = 0; - sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); - set_user_nice(current, 19); - schedule(); - set_user_nice(current, 0); - sp.sched_priority = prio; - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); - del_timer(&yield_timer); + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; } -/* - * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. - * This can happen while the corresponding CPU is either coming online - * or going offline. We cannot wait until the CPU is fully online - * before starting the kthread, because the various notifier functions - * can wait for RCU grace periods. So we park rcu_cpu_kthread() until - * the corresponding CPU is online. - * - * Return 1 if the kthread needs to stop, 0 otherwise. - * - * Caller must disable bh. This function can momentarily enable it. - */ -static int rcu_cpu_kthread_should_stop(int cpu) +static int rcu_cpu_kthread_should_run(unsigned int cpu) { - while (cpu_is_offline(cpu) || - !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || - smp_processor_id() != cpu) { - if (kthread_should_stop()) - return 1; - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; - per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); - local_bh_enable(); - schedule_timeout_uninterruptible(1); - if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - local_bh_disable(); - } - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - return 0; + return __get_cpu_var(rcu_cpu_has_work); } /* @@ -1596,138 +1344,35 @@ static int rcu_cpu_kthread_should_stop(int cpu) * RCU softirq used in flavors and configurations of RCU that do not * support RCU priority boosting. */ -static int rcu_cpu_kthread(void *arg) +static void rcu_cpu_kthread(unsigned int cpu) { - int cpu = (int)(long)arg; - unsigned long flags; - int spincnt = 0; - unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); - char work; - char *workp = &per_cpu(rcu_cpu_has_work, cpu); + unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status); + char work, *workp = &__get_cpu_var(rcu_cpu_has_work); + int spincnt; - trace_rcu_utilization("Start CPU kthread@init"); - for (;;) { - *statusp = RCU_KTHREAD_WAITING; - trace_rcu_utilization("End CPU kthread@rcu_wait"); - rcu_wait(*workp != 0 || kthread_should_stop()); + for (spincnt = 0; spincnt < 10; spincnt++) { trace_rcu_utilization("Start CPU kthread@rcu_wait"); local_bh_disable(); - if (rcu_cpu_kthread_should_stop(cpu)) { - local_bh_enable(); - break; - } *statusp = RCU_KTHREAD_RUNNING; - per_cpu(rcu_cpu_kthread_loops, cpu)++; - local_irq_save(flags); + this_cpu_inc(rcu_cpu_kthread_loops); + local_irq_disable(); work = *workp; *workp = 0; - local_irq_restore(flags); + local_irq_enable(); if (work) rcu_kthread_do_work(); local_bh_enable(); - if (*workp != 0) - spincnt++; - else - spincnt = 0; - if (spincnt > 10) { - *statusp = RCU_KTHREAD_YIELDING; - trace_rcu_utilization("End CPU kthread@rcu_yield"); - rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); - trace_rcu_utilization("Start CPU kthread@rcu_yield"); - spincnt = 0; - } - } - *statusp = RCU_KTHREAD_STOPPED; - trace_rcu_utilization("End CPU kthread@term"); - return 0; -} - -/* - * Spawn a per-CPU kthread, setting up affinity and priority. - * Because the CPU hotplug lock is held, no other CPU will be attempting - * to manipulate rcu_cpu_kthread_task. There might be another CPU - * attempting to access it during boot, but the locking in kthread_bind() - * will enforce sufficient ordering. - * - * Please note that we cannot simply refuse to wake up the per-CPU - * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state, - * which can result in softlockup complaints if the task ends up being - * idle for more than a couple of minutes. - * - * However, please note also that we cannot bind the per-CPU kthread to its - * CPU until that CPU is fully online. We also cannot wait until the - * CPU is fully online before we create its per-CPU kthread, as this would - * deadlock the system when CPU notifiers tried waiting for grace - * periods. So we bind the per-CPU kthread to its CPU only if the CPU - * is online. If its CPU is not yet fully online, then the code in - * rcu_cpu_kthread() will wait until it is fully online, and then do - * the binding. - */ -static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) -{ - struct sched_param sp; - struct task_struct *t; - - if (!rcu_scheduler_fully_active || - per_cpu(rcu_cpu_kthread_task, cpu) != NULL) - return 0; - t = kthread_create_on_node(rcu_cpu_kthread, - (void *)(long)cpu, - cpu_to_node(cpu), - "rcuc/%d", cpu); - if (IS_ERR(t)) - return PTR_ERR(t); - if (cpu_online(cpu)) - kthread_bind(t, cpu); - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - per_cpu(rcu_cpu_kthread_task, cpu) = t; - wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */ - return 0; -} - -/* - * Per-rcu_node kthread, which is in charge of waking up the per-CPU - * kthreads when needed. We ignore requests to wake up kthreads - * for offline CPUs, which is OK because force_quiescent_state() - * takes care of this case. - */ -static int rcu_node_kthread(void *arg) -{ - int cpu; - unsigned long flags; - unsigned long mask; - struct rcu_node *rnp = (struct rcu_node *)arg; - struct sched_param sp; - struct task_struct *t; - - for (;;) { - rnp->node_kthread_status = RCU_KTHREAD_WAITING; - rcu_wait(atomic_read(&rnp->wakemask) != 0); - rnp->node_kthread_status = RCU_KTHREAD_RUNNING; - raw_spin_lock_irqsave(&rnp->lock, flags); - mask = atomic_xchg(&rnp->wakemask, 0); - rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { - if ((mask & 0x1) == 0) - continue; - preempt_disable(); - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (!cpu_online(cpu) || t == NULL) { - preempt_enable(); - continue; - } - per_cpu(rcu_cpu_has_work, cpu) = 1; - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - preempt_enable(); + if (*workp == 0) { + trace_rcu_utilization("End CPU kthread@rcu_wait"); + *statusp = RCU_KTHREAD_WAITING; + return; } } - /* NOTREACHED */ - rnp->node_kthread_status = RCU_KTHREAD_STOPPED; - return 0; + *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization("Start CPU kthread@rcu_yield"); + schedule_timeout_interruptible(2); + trace_rcu_utilization("End CPU kthread@rcu_yield"); + *statusp = RCU_KTHREAD_WAITING; } /* @@ -1739,17 +1384,17 @@ static int rcu_node_kthread(void *arg) * no outgoing CPU. If there are no CPUs left in the affinity set, * this function allows the kthread to execute on any CPU. */ -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { + struct task_struct *t = rnp->boost_kthread_task; + unsigned long mask = rnp->qsmaskinit; cpumask_var_t cm; int cpu; - unsigned long mask = rnp->qsmaskinit; - if (rnp->node_kthread_task == NULL) + if (!t) return; - if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) return; - cpumask_clear(cm); for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) if ((mask & 0x1) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); @@ -1759,62 +1404,36 @@ static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) cpumask_clear_cpu(cpu, cm); WARN_ON_ONCE(cpumask_weight(cm) == 0); } - set_cpus_allowed_ptr(rnp->node_kthread_task, cm); - rcu_boost_kthread_setaffinity(rnp, cm); + set_cpus_allowed_ptr(t, cm); free_cpumask_var(cm); } -/* - * Spawn a per-rcu_node kthread, setting priority and affinity. - * Called during boot before online/offline can happen, or, if - * during runtime, with the main CPU-hotplug locks held. So only - * one of these can be executing at a time. - */ -static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, - struct rcu_node *rnp) -{ - unsigned long flags; - int rnp_index = rnp - &rsp->node[0]; - struct sched_param sp; - struct task_struct *t; - - if (!rcu_scheduler_fully_active || - rnp->qsmaskinit == 0) - return 0; - if (rnp->node_kthread_task == NULL) { - t = kthread_create(rcu_node_kthread, (void *)rnp, - "rcun/%d", rnp_index); - if (IS_ERR(t)) - return PTR_ERR(t); - raw_spin_lock_irqsave(&rnp->lock, flags); - rnp->node_kthread_task = t; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - sp.sched_priority = 99; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ - } - return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); -} +static struct smp_hotplug_thread rcu_cpu_thread_spec = { + .store = &rcu_cpu_kthread_task, + .thread_should_run = rcu_cpu_kthread_should_run, + .thread_fn = rcu_cpu_kthread, + .thread_comm = "rcuc/%u", + .setup = rcu_cpu_kthread_setup, + .park = rcu_cpu_kthread_park, +}; /* * Spawn all kthreads -- called as soon as the scheduler is running. */ static int __init rcu_spawn_kthreads(void) { - int cpu; struct rcu_node *rnp; + int cpu; rcu_scheduler_fully_active = 1; - for_each_possible_cpu(cpu) { + for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; - if (cpu_online(cpu)) - (void)rcu_spawn_one_cpu_kthread(cpu); - } + BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); rnp = rcu_get_root(rcu_state); - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); if (NUM_RCU_NODES > 1) { rcu_for_each_leaf_node(rcu_state, rnp) - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); } return 0; } @@ -1826,11 +1445,8 @@ static void __cpuinit rcu_prepare_kthreads(int cpu) struct rcu_node *rnp = rdp->mynode; /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ - if (rcu_scheduler_fully_active) { - (void)rcu_spawn_one_cpu_kthread(cpu); - if (rnp->node_kthread_task == NULL) - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - } + if (rcu_scheduler_fully_active) + (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1854,19 +1470,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } -#ifdef CONFIG_HOTPLUG_CPU - -static void rcu_stop_cpu_kthread(int cpu) -{ -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) -{ -} - -static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } @@ -1968,9 +1572,11 @@ static void rcu_idle_count_callbacks_posted(void) */ #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ -#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ +extern int tick_nohz_enabled; + /* * Does the specified flavor of RCU have non-lazy callbacks pending on * the specified CPU? Both RCU flavor and CPU are specified by the @@ -2047,10 +1653,13 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) return 1; } /* Set up for the possibility that RCU will post a timer. */ - if (rcu_cpu_has_nonlazy_callbacks(cpu)) - *delta_jiffies = RCU_IDLE_GP_DELAY; - else - *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + *delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies, + RCU_IDLE_GP_DELAY) - jiffies; + } else { + *delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY; + *delta_jiffies = round_jiffies(*delta_jiffies) - jiffies; + } return 0; } @@ -2109,6 +1718,7 @@ static void rcu_cleanup_after_idle(int cpu) del_timer(&rdtp->idle_gp_timer); trace_rcu_prep_idle("Cleanup after idle"); + rdtp->tick_nohz_enabled_snap = ACCESS_ONCE(tick_nohz_enabled); } /* @@ -2134,6 +1744,38 @@ static void rcu_prepare_for_idle(int cpu) { struct timer_list *tp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + int tne; + + /* Handle nohz enablement switches conservatively. */ + tne = ACCESS_ONCE(tick_nohz_enabled); + if (tne != rdtp->tick_nohz_enabled_snap) { + if (rcu_cpu_has_callbacks(cpu)) + invoke_rcu_core(); /* force nohz to see update. */ + rdtp->tick_nohz_enabled_snap = tne; + return; + } + if (!tne) + return; + + /* Adaptive-tick mode, where usermode execution is idle to RCU. */ + if (!is_idle_task(current)) { + rdtp->dyntick_holdoff = jiffies - 1; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + trace_rcu_prep_idle("User dyntick with callbacks"); + rdtp->idle_gp_timer_expires = + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); + } else if (rcu_cpu_has_callbacks(cpu)) { + rdtp->idle_gp_timer_expires = + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); + trace_rcu_prep_idle("User dyntick with lazy callbacks"); + } else { + return; + } + tp = &rdtp->idle_gp_timer; + mod_timer_pinned(tp, rdtp->idle_gp_timer_expires); + return; + } /* * If this is an idle re-entry, for example, due to use of @@ -2187,10 +1829,11 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_nonlazy_callbacks(cpu)) { trace_rcu_prep_idle("Dyntick with callbacks"); rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_GP_DELAY; + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); } else { rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_LAZY_GP_DELAY; + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); trace_rcu_prep_idle("Dyntick with lazy callbacks"); } tp = &rdtp->idle_gp_timer; @@ -2212,16 +1855,16 @@ static void rcu_prepare_for_idle(int cpu) #ifdef CONFIG_TREE_PREEMPT_RCU if (per_cpu(rcu_preempt_data, cpu).nxtlist) { rcu_preempt_qs(cpu); - force_quiescent_state(&rcu_preempt_state, 0); + force_quiescent_state(&rcu_preempt_state); } #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ if (per_cpu(rcu_sched_data, cpu).nxtlist) { rcu_sched_qs(cpu); - force_quiescent_state(&rcu_sched_state, 0); + force_quiescent_state(&rcu_sched_state); } if (per_cpu(rcu_bh_data, cpu).nxtlist) { rcu_bh_qs(cpu); - force_quiescent_state(&rcu_bh_state, 0); + force_quiescent_state(&rcu_bh_state); } /* @@ -2231,8 +1874,9 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_callbacks(cpu)) { trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - } else + } else { trace_rcu_prep_idle("Callbacks drained"); + } } /* @@ -2248,6 +1892,88 @@ static void rcu_idle_count_callbacks_posted(void) __this_cpu_add(rcu_dynticks.nonlazy_posted, 1); } +/* + * Data for flushing lazy RCU callbacks at OOM time. + */ +static atomic_t oom_callback_count; +static DECLARE_WAIT_QUEUE_HEAD(oom_callback_wq); + +/* + * RCU OOM callback -- decrement the outstanding count and deliver the + * wake-up if we are the last one. + */ +static void rcu_oom_callback(struct rcu_head *rhp) +{ + if (atomic_dec_and_test(&oom_callback_count)) + wake_up(&oom_callback_wq); +} + +/* + * Post an rcu_oom_notify callback on the current CPU if it has at + * least one lazy callback. This will unnecessarily post callbacks + * to CPUs that already have a non-lazy callback at the end of their + * callback list, but this is an infrequent operation, so accept some + * extra overhead to keep things simple. + */ +static void rcu_oom_notify_cpu(void *unused) +{ + struct rcu_state *rsp; + struct rcu_data *rdp; + + for_each_rcu_flavor(rsp) { + rdp = __this_cpu_ptr(rsp->rda); + if (rdp->qlen_lazy != 0) { + atomic_inc(&oom_callback_count); + rsp->call(&rdp->oom_head, rcu_oom_callback); + } + } +} + +/* + * If low on memory, ensure that each CPU has a non-lazy callback. + * This will wake up CPUs that have only lazy callbacks, in turn + * ensuring that they free up the corresponding memory in a timely manner. + * Because an uncertain amount of memory will be freed in some uncertain + * timeframe, we do not claim to have freed anything. + */ +static int rcu_oom_notify(struct notifier_block *self, + unsigned long notused, void *nfreed) +{ + int cpu; + + /* Wait for callbacks from earlier instance to complete. */ + wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0); + + /* + * Prevent premature wakeup: ensure that all increments happen + * before there is a chance of the counter reaching zero. + */ + atomic_set(&oom_callback_count, 1); + + get_online_cpus(); + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); + cond_resched(); + } + put_online_cpus(); + + /* Unconditionally decrement: no need to wake ourselves up. */ + atomic_dec(&oom_callback_count); + + return NOTIFY_OK; +} + +static struct notifier_block rcu_oom_nb = { + .notifier_call = rcu_oom_notify +}; + +static int __init rcu_register_oom_notifier(void) +{ + register_oom_notifier(&rcu_oom_nb); + return 0; +} +early_initcall(rcu_register_oom_notifier); + #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ #ifdef CONFIG_RCU_CPU_STALL_INFO @@ -2258,17 +1984,22 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); struct timer_list *tltp = &rdtp->idle_gp_timer; + char c; - sprintf(cp, "drain=%d %c timer=%lu", - rdtp->dyntick_drain, - rdtp->dyntick_holdoff == jiffies ? 'H' : '.', - timer_pending(tltp) ? tltp->expires - jiffies : -1); + c = rdtp->dyntick_holdoff == jiffies ? 'H' : '.'; + if (timer_pending(tltp)) + sprintf(cp, "drain=%d %c timer=%lu", + rdtp->dyntick_drain, c, tltp->expires - jiffies); + else + sprintf(cp, "drain=%d %c timer not pending", + rdtp->dyntick_drain, c); } #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { + *cp = '\0'; } #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ @@ -2329,11 +2060,10 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp) /* Increment ->ticks_this_gp for all flavors of RCU. */ static void increment_cpu_stall_ticks(void) { - __get_cpu_var(rcu_sched_data).ticks_this_gp++; - __get_cpu_var(rcu_bh_data).ticks_this_gp++; -#ifdef CONFIG_TREE_PREEMPT_RCU - __get_cpu_var(rcu_preempt_data).ticks_this_gp++; -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + __this_cpu_ptr(rsp->rda)->ticks_this_gp++; } #else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index d4bc16ddd1d..693513bc50e 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,6 +46,31 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +static int show_rcubarrier(struct seq_file *m, void *unused) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + seq_printf(m, "%s: bcc: %d nbd: %lu\n", + rsp->name, + atomic_read(&rsp->barrier_cpu_count), + rsp->n_barrier_done); + return 0; +} + +static int rcubarrier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcubarrier, NULL); +} + +static const struct file_operations rcubarrier_fops = { + .owner = THIS_MODULE, + .open = rcubarrier_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + #ifdef CONFIG_RCU_BOOST static char convert_kthread_status(unsigned int kthread_status) @@ -61,12 +86,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%lu g=%lu pq=%d pgp=%lu qp=%d", + seq_printf(m, "%3d%cc=%lu g=%lu pq=%d qp=%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', rdp->completed, rdp->gpnum, - rdp->passed_quiesce, rdp->passed_quiesce_gpnum, - rdp->qs_pending); + rdp->passed_quiesce, rdp->qs_pending); seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, @@ -83,11 +107,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->nxttail[RCU_WAIT_TAIL]], ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); #ifdef CONFIG_RCU_BOOST - seq_printf(m, " kt=%d/%c/%d ktl=%x", + seq_printf(m, " kt=%d/%c ktl=%x", per_cpu(rcu_cpu_has_work, rdp->cpu), convert_kthread_status(per_cpu(rcu_cpu_kthread_status, rdp->cpu)), - per_cpu(rcu_cpu_kthread_cpu, rdp->cpu), per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); #endif /* #ifdef CONFIG_RCU_BOOST */ seq_printf(m, " b=%ld", rdp->blimit); @@ -95,24 +118,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } -#define PRINT_RCU_DATA(name, func, m) \ - do { \ - int _p_r_d_i; \ - \ - for_each_possible_cpu(_p_r_d_i) \ - func(m, &per_cpu(name, _p_r_d_i)); \ - } while (0) - static int show_rcudata(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data, m); - seq_puts(m, "rcu_bh:\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m); + int cpu; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -133,12 +148,11 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%d,%s,%lu,%lu,%d,%lu,%d", + seq_printf(m, "%d,%s,%lu,%lu,%d,%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"", rdp->completed, rdp->gpnum, - rdp->passed_quiesce, rdp->passed_quiesce_gpnum, - rdp->qs_pending); + rdp->passed_quiesce, rdp->qs_pending); seq_printf(m, ",%d,%llx,%d,%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, @@ -166,21 +180,21 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { - seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); + int cpu; + struct rcu_state *rsp; + + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); #ifdef CONFIG_RCU_BOOST seq_puts(m, "\"kt\",\"ktl\""); #endif /* #ifdef CONFIG_RCU_BOOST */ seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "\"rcu_preempt:\"\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "\"rcu_sched:\"\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data_csv, m); - seq_puts(m, "\"rcu_bh:\"\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m); + for_each_rcu_flavor(rsp) { + seq_printf(m, "\"%s:\"\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data_csv(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -201,8 +215,7 @@ static const struct file_operations rcudata_csv_fops = { static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) { - seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu " - "j=%04x bt=%04x\n", + seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", rnp->grplo, rnp->grphi, "T."[list_empty(&rnp->blkd_tasks)], "N."[!rnp->gp_tasks], @@ -210,11 +223,11 @@ static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) "B."[!rnp->boost_tasks], convert_kthread_status(rnp->boost_kthread_status), rnp->n_tasks_boosted, rnp->n_exp_boosts, - rnp->n_normal_boosts, + rnp->n_normal_boosts); + seq_printf(m, "j=%04x bt=%04x\n", (int)(jiffies & 0xffff), (int)(rnp->boost_time & 0xffff)); - seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", - " balk", + seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", rnp->n_balk_blkd_tasks, rnp->n_balk_exp_gp_tasks, rnp->n_balk_boost_tasks, @@ -270,15 +283,15 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp; gpnum = rsp->gpnum; - seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x " - "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", - rsp->completed, gpnum, rsp->fqs_state, + seq_printf(m, "%s: c=%lu g=%lu s=%d jfq=%ld j=%x ", + rsp->name, rsp->completed, gpnum, rsp->fqs_state, (long)(rsp->jiffies_force_qs - jiffies), - (int)(jiffies & 0xffff), + (int)(jiffies & 0xffff)); + seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen); - for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) { + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { if (rnp->level != level) { seq_puts(m, "\n"); level = rnp->level; @@ -295,14 +308,10 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) static int show_rcuhier(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_one_rcu_state(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_one_rcu_state(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_one_rcu_state(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + print_one_rcu_state(m, rsp); return 0; } @@ -343,11 +352,10 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) static int show_rcugp(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - show_one_rcugp(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - show_one_rcugp(m, &rcu_sched_state); - show_one_rcugp(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + show_one_rcugp(m, rsp); return 0; } @@ -366,44 +374,35 @@ static const struct file_operations rcugp_fops = { static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) { - seq_printf(m, "%3d%cnp=%ld " - "qsp=%ld rpq=%ld cbr=%ld cng=%ld " - "gpc=%ld gps=%ld nf=%ld nn=%ld\n", + seq_printf(m, "%3d%cnp=%ld ", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', - rdp->n_rcu_pending, + rdp->n_rcu_pending); + seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", rdp->n_rp_qs_pending, rdp->n_rp_report_qs, rdp->n_rp_cb_ready, - rdp->n_rp_cpu_needs_gp, + rdp->n_rp_cpu_needs_gp); + seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n", rdp->n_rp_gp_completed, rdp->n_rp_gp_started, - rdp->n_rp_need_fqs, rdp->n_rp_need_nothing); } -static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp) +static int show_rcu_pending(struct seq_file *m, void *unused) { int cpu; struct rcu_data *rdp; - - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - if (rdp->beenonline) - print_one_rcu_pending(m, rdp); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->beenonline) + print_one_rcu_pending(m, rdp); + } } -} - -static int show_rcu_pending(struct seq_file *m, void *unused) -{ -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_rcu_pendings(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_rcu_pendings(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_rcu_pendings(m, &rcu_bh_state); return 0; } @@ -453,6 +452,11 @@ static int __init rcutree_trace_init(void) if (!rcudir) goto free_out; + retval = debugfs_create_file("rcubarrier", 0444, rcudir, + NULL, &rcubarrier_fops); + if (!retval) + goto free_out; + retval = debugfs_create_file("rcudata", 0444, rcudir, NULL, &rcudata_fops); if (!retval) diff --git a/kernel/resource.c b/kernel/resource.c index e1d2b8ee76d..34d45886ee8 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -7,6 +7,8 @@ * Arbitrary resource management. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/export.h> #include <linux/errno.h> #include <linux/ioport.h> @@ -722,14 +724,12 @@ int adjust_resource(struct resource *res, resource_size_t start, resource_size_t write_lock(&resource_lock); + if (!parent) + goto skip; + if ((start < parent->start) || (end > parent->end)) goto out; - for (tmp = res->child; tmp; tmp = tmp->sibling) { - if ((tmp->start < start) || (tmp->end > end)) - goto out; - } - if (res->sibling && (res->sibling->start <= end)) goto out; @@ -741,6 +741,11 @@ int adjust_resource(struct resource *res, resource_size_t start, resource_size_t goto out; } +skip: + for (tmp = res->child; tmp; tmp = tmp->sibling) + if ((tmp->start < start) || (tmp->end > end)) + goto out; + res->start = start; res->end = end; result = 0; @@ -788,8 +793,28 @@ void __init reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name) { + int abort = 0; + write_lock(&resource_lock); - __reserve_region_with_split(root, start, end, name); + if (root->start > start || root->end < end) { + pr_err("requested range [0x%llx-0x%llx] not in root %pr\n", + (unsigned long long)start, (unsigned long long)end, + root); + if (start > root->end || end < root->start) + abort = 1; + else { + if (end > root->end) + end = root->end; + if (start < root->start) + start = root->start; + pr_err("fixing request to [0x%llx-0x%llx]\n", + (unsigned long long)start, + (unsigned long long)end); + } + dump_stack(); + } + if (!abort) + __reserve_region_with_split(root, start, end, name); write_unlock(&resource_lock); } diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 173ea52f3af..f06d249e103 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o +obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o obj-$(CONFIG_SMP) += cpupri.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 468bdd44c1b..c1774723643 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -740,126 +740,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -#ifdef CONFIG_IRQ_TIME_ACCOUNTING - -/* - * There are no locks covering percpu hardirq/softirq time. - * They are only modified in account_system_vtime, on corresponding CPU - * with interrupts disabled. So, writes are safe. - * They are read and saved off onto struct rq in update_rq_clock(). - * This may result in other CPU reading this CPU's irq time and can - * race with irq/account_system_vtime on this CPU. We would either get old - * or new value with a side effect of accounting a slice of irq time to wrong - * task when irq is in progress while we read rq->clock. That is a worthy - * compromise in place of having locks on each irq in account_system_time. - */ -static DEFINE_PER_CPU(u64, cpu_hardirq_time); -static DEFINE_PER_CPU(u64, cpu_softirq_time); - -static DEFINE_PER_CPU(u64, irq_start_time); -static int sched_clock_irqtime; - -void enable_sched_clock_irqtime(void) -{ - sched_clock_irqtime = 1; -} - -void disable_sched_clock_irqtime(void) -{ - sched_clock_irqtime = 0; -} - -#ifndef CONFIG_64BIT -static DEFINE_PER_CPU(seqcount_t, irq_time_seq); - -static inline void irq_time_write_begin(void) -{ - __this_cpu_inc(irq_time_seq.sequence); - smp_wmb(); -} - -static inline void irq_time_write_end(void) -{ - smp_wmb(); - __this_cpu_inc(irq_time_seq.sequence); -} - -static inline u64 irq_time_read(int cpu) -{ - u64 irq_time; - unsigned seq; - - do { - seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); - irq_time = per_cpu(cpu_softirq_time, cpu) + - per_cpu(cpu_hardirq_time, cpu); - } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); - - return irq_time; -} -#else /* CONFIG_64BIT */ -static inline void irq_time_write_begin(void) -{ -} - -static inline void irq_time_write_end(void) -{ -} - -static inline u64 irq_time_read(int cpu) -{ - return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); -} -#endif /* CONFIG_64BIT */ - -/* - * Called before incrementing preempt_count on {soft,}irq_enter - * and before decrementing preempt_count on {soft,}irq_exit. - */ -void account_system_vtime(struct task_struct *curr) -{ - unsigned long flags; - s64 delta; - int cpu; - - if (!sched_clock_irqtime) - return; - - local_irq_save(flags); - - cpu = smp_processor_id(); - delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); - __this_cpu_add(irq_start_time, delta); - - irq_time_write_begin(); - /* - * We do not account for softirq time from ksoftirqd here. - * We want to continue accounting softirq time to ksoftirqd thread - * in that case, so as not to confuse scheduler with a special task - * that do not consume any time, but still wants to run. - */ - if (hardirq_count()) - __this_cpu_add(cpu_hardirq_time, delta); - else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) - __this_cpu_add(cpu_softirq_time, delta); - - irq_time_write_end(); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(account_system_vtime); - -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -#ifdef CONFIG_PARAVIRT -static inline u64 steal_ticks(u64 steal) -{ - if (unlikely(steal > NSEC_PER_SEC)) - return div_u64(steal, TICK_NSEC); - - return __iter_div_u64_rem(steal, TICK_NSEC, &steal); -} -#endif - static void update_rq_clock_task(struct rq *rq, s64 delta) { /* @@ -920,43 +800,6 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif } -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -static int irqtime_account_hi_update(void) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - unsigned long flags; - u64 latest_ns; - int ret = 0; - - local_irq_save(flags); - latest_ns = this_cpu_read(cpu_hardirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) - ret = 1; - local_irq_restore(flags); - return ret; -} - -static int irqtime_account_si_update(void) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - unsigned long flags; - u64 latest_ns; - int ret = 0; - - local_irq_save(flags); - latest_ns = this_cpu_read(cpu_softirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) - ret = 1; - local_irq_restore(flags); - return ret; -} - -#else /* CONFIG_IRQ_TIME_ACCOUNTING */ - -#define sched_clock_irqtime (0) - -#endif - void sched_set_stop_task(int cpu, struct task_struct *stop) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1096,7 +939,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. * * sched_move_task() holds both and thus holding either pins the cgroup, - * see set_task_rq(). + * see task_group(). * * Furthermore, all task_rq users should acquire both locks, see * task_rq_lock(). @@ -1518,25 +1361,6 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu) smp_send_reschedule(cpu); } -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -static int ttwu_activate_remote(struct task_struct *p, int wake_flags) -{ - struct rq *rq; - int ret = 0; - - rq = __task_rq_lock(p); - if (p->on_cpu) { - ttwu_activate(rq, p, ENQUEUE_WAKEUP); - ttwu_do_wakeup(rq, p, wake_flags); - ret = 1; - } - __task_rq_unlock(rq); - - return ret; - -} -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ - bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); @@ -1597,21 +1421,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. */ - while (p->on_cpu) { -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - /* - * In case the architecture enables interrupts in - * context_switch(), we cannot busy wait, since that - * would lead to deadlocks when an interrupt hits and - * tries to wake up @prev. So bail and do a complete - * remote wakeup. - */ - if (ttwu_activate_remote(p, wake_flags)) - goto stat; -#else + while (p->on_cpu) cpu_relax(); -#endif - } /* * Pairs with the smp_wmb() in finish_lock_switch(). */ @@ -1910,12 +1721,12 @@ static inline void prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { + trace_sched_switch(prev, next); sched_info_switch(prev, next); perf_event_task_sched_out(prev, next); fire_sched_out_preempt_notifiers(prev, next); prepare_lock_switch(rq, next); prepare_arch_switch(next); - trace_sched_switch(prev, next); } /** @@ -1953,14 +1764,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) * Manfred Spraul <manfred@colorfullife.com> */ prev_state = prev->state; + vtime_task_switch(prev); finish_arch_switch(prev); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_disable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ perf_event_task_sched_in(prev, current); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_enable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); finish_arch_post_lock_switch(); @@ -2081,6 +1887,7 @@ context_switch(struct rq *rq, struct task_struct *prev, #endif /* Here we just switch the register state and the stack. */ + rcu_switch(prev, next); switch_to(prev, next, prev); barrier(); @@ -2809,398 +2616,6 @@ unsigned long long task_sched_runtime(struct task_struct *p) return ns; } -#ifdef CONFIG_CGROUP_CPUACCT -struct cgroup_subsys cpuacct_subsys; -struct cpuacct root_cpuacct; -#endif - -static inline void task_group_account_field(struct task_struct *p, int index, - u64 tmp) -{ -#ifdef CONFIG_CGROUP_CPUACCT - struct kernel_cpustat *kcpustat; - struct cpuacct *ca; -#endif - /* - * Since all updates are sure to touch the root cgroup, we - * get ourselves ahead and touch it first. If the root cgroup - * is the only cgroup, then nothing else should be necessary. - * - */ - __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; - -#ifdef CONFIG_CGROUP_CPUACCT - if (unlikely(!cpuacct_subsys.active)) - return; - - rcu_read_lock(); - ca = task_ca(p); - while (ca && (ca != &root_cpuacct)) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += tmp; - ca = parent_ca(ca); - } - rcu_read_unlock(); -#endif -} - - -/* - * Account user cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in user space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_user_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - int index; - - /* Add user time to process. */ - p->utime += cputime; - p->utimescaled += cputime_scaled; - account_group_user_time(p, cputime); - - index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; - - /* Add user time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); - - /* Account for user time used */ - acct_update_integrals(p); -} - -/* - * Account guest cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in virtual machine since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -static void account_guest_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - - /* Add guest time to process. */ - p->utime += cputime; - p->utimescaled += cputime_scaled; - account_group_user_time(p, cputime); - p->gtime += cputime; - - /* Add guest time to cpustat. */ - if (TASK_NICE(p) > 0) { - cpustat[CPUTIME_NICE] += (__force u64) cputime; - cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; - } else { - cpustat[CPUTIME_USER] += (__force u64) cputime; - cpustat[CPUTIME_GUEST] += (__force u64) cputime; - } -} - -/* - * Account system cpu time to a process and desired cpustat field - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - * @target_cputime64: pointer to cpustat field that has to be updated - */ -static inline -void __account_system_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled, int index) -{ - /* Add system time to process. */ - p->stime += cputime; - p->stimescaled += cputime_scaled; - account_group_system_time(p, cputime); - - /* Add system time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); - - /* Account for system time used */ - acct_update_integrals(p); -} - -/* - * Account system cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime, cputime_t cputime_scaled) -{ - int index; - - if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { - account_guest_time(p, cputime, cputime_scaled); - return; - } - - if (hardirq_count() - hardirq_offset) - index = CPUTIME_IRQ; - else if (in_serving_softirq()) - index = CPUTIME_SOFTIRQ; - else - index = CPUTIME_SYSTEM; - - __account_system_time(p, cputime, cputime_scaled, index); -} - -/* - * Account for involuntary wait time. - * @cputime: the cpu time spent in involuntary wait - */ -void account_steal_time(cputime_t cputime) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - - cpustat[CPUTIME_STEAL] += (__force u64) cputime; -} - -/* - * Account for idle time. - * @cputime: the cpu time spent in idle wait - */ -void account_idle_time(cputime_t cputime) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - struct rq *rq = this_rq(); - - if (atomic_read(&rq->nr_iowait) > 0) - cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; - else - cpustat[CPUTIME_IDLE] += (__force u64) cputime; -} - -static __always_inline bool steal_account_process_tick(void) -{ -#ifdef CONFIG_PARAVIRT - if (static_key_false(¶virt_steal_enabled)) { - u64 steal, st = 0; - - steal = paravirt_steal_clock(smp_processor_id()); - steal -= this_rq()->prev_steal_time; - - st = steal_ticks(steal); - this_rq()->prev_steal_time += st * TICK_NSEC; - - account_steal_time(st); - return st; - } -#endif - return false; -} - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -/* - * Account a tick to a process and cpustat - * @p: the process that the cpu time gets accounted to - * @user_tick: is the tick from userspace - * @rq: the pointer to rq - * - * Tick demultiplexing follows the order - * - pending hardirq update - * - pending softirq update - * - user_time - * - idle_time - * - system time - * - check for guest_time - * - else account as system_time - * - * Check for hardirq is done both for system and user time as there is - * no timer going off while we are on hardirq and hence we may never get an - * opportunity to update it solely in system time. - * p->stime and friends are only updated on system time and not on irq - * softirq as those do not count in task exec_runtime any more. - */ -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - u64 *cpustat = kcpustat_this_cpu->cpustat; - - if (steal_account_process_tick()) - return; - - if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; - } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; - } else if (this_cpu_ksoftirqd() == p) { - /* - * ksoftirqd time do not get accounted in cpu_softirq_time. - * So, we have to handle it separately here. - * Also, p->stime needs to be updated for ksoftirqd. - */ - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SOFTIRQ); - } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); - } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); - } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); - } -} - -static void irqtime_account_idle_ticks(int ticks) -{ - int i; - struct rq *rq = this_rq(); - - for (i = 0; i < ticks; i++) - irqtime_account_process_tick(current, 0, rq); -} -#else /* CONFIG_IRQ_TIME_ACCOUNTING */ -static void irqtime_account_idle_ticks(int ticks) {} -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -/* - * Account a single tick of cpu time. - * @p: the process that the cpu time gets accounted to - * @user_tick: indicates if the tick is a user or a system tick - */ -void account_process_tick(struct task_struct *p, int user_tick) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - struct rq *rq = this_rq(); - - if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); - return; - } - - if (steal_account_process_tick()) - return; - - if (user_tick) - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, - one_jiffy_scaled); - else - account_idle_time(cputime_one_jiffy); -} - -/* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* - * Account multiple ticks of idle time. - * @ticks: number of stolen ticks - */ -void account_idle_ticks(unsigned long ticks) -{ - - if (sched_clock_irqtime) { - irqtime_account_idle_ticks(ticks); - return; - } - - account_idle_time(jiffies_to_cputime(ticks)); -} - -#endif - -/* - * Use precise platform statistics if available: - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - *ut = p->utime; - *st = p->stime; -} - -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct task_cputime cputime; - - thread_group_cputime(p, &cputime); - - *ut = cputime.utime; - *st = cputime.stime; -} -#else - -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) -#endif - -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - cputime_t rtime, utime = p->utime, total = utime + p->stime; - - /* - * Use CFS's precise accounting: - */ - rtime = nsecs_to_cputime(p->se.sum_exec_runtime); - - if (total) { - u64 temp = (__force u64) rtime; - - temp *= (__force u64) utime; - do_div(temp, (__force u32) total); - utime = (__force cputime_t) temp; - } else - utime = rtime; - - /* - * Compare with previous values, to keep monotonicity: - */ - p->prev_utime = max(p->prev_utime, utime); - p->prev_stime = max(p->prev_stime, rtime - p->prev_utime); - - *ut = p->prev_utime; - *st = p->prev_stime; -} - -/* - * Must be called with siglock held. - */ -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct signal_struct *sig = p->signal; - struct task_cputime cputime; - cputime_t rtime, utime, total; - - thread_group_cputime(p, &cputime); - - total = cputime.utime + cputime.stime; - rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - - if (total) { - u64 temp = (__force u64) rtime; - - temp *= (__force u64) cputime.utime; - do_div(temp, (__force u32) total); - utime = (__force cputime_t) temp; - } else - utime = rtime; - - sig->prev_utime = max(sig->prev_utime, utime); - sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime); - - *ut = sig->prev_utime; - *st = sig->prev_stime; -} -#endif - /* * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. @@ -3361,6 +2776,40 @@ pick_next_task(struct rq *rq) /* * __schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space */ static void __sched __schedule(void) { @@ -3462,6 +2911,21 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); +#ifdef CONFIG_RCU_USER_QS +asmlinkage void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + */ + rcu_user_exit(); + schedule(); + rcu_user_enter(); +} +#endif + /** * schedule_preempt_disabled - called with preemption disabled * @@ -3563,6 +3027,7 @@ asmlinkage void __sched preempt_schedule_irq(void) /* Catch callers which need to be fixed */ BUG_ON(ti->preempt_count || !irqs_disabled()); + rcu_user_exit(); do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); @@ -4340,9 +3805,7 @@ recheck: */ if (unlikely(policy == p->policy && (!rt_policy(policy) || param->sched_priority == p->rt_priority))) { - - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return 0; } @@ -4864,13 +4327,6 @@ again: */ if (preempt && rq != p_rq) resched_task(p_rq->curr); - } else { - /* - * We might have set it in task_yield_fair(), but are - * not going to schedule(), so don't want to skip - * the next update. - */ - rq->skip_clock_update = 0; } out: @@ -5300,27 +4756,17 @@ void idle_task_exit(void) } /* - * While a dead CPU has no uninterruptible tasks queued at this point, - * it might still have a nonzero ->nr_uninterruptible counter, because - * for performance reasons the counter is not stricly tracking tasks to - * their home CPUs. So we just add the counter to another CPU's counter, - * to keep the global sum constant after CPU-down: - */ -static void migrate_nr_uninterruptible(struct rq *rq_src) -{ - struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); - - rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; - rq_src->nr_uninterruptible = 0; -} - -/* - * remove the tasks which were accounted by rq from calc_load_tasks. + * Since this CPU is going 'away' for a while, fold any nr_active delta + * we might have. Assumes we're called after migrate_tasks() so that the + * nr_active count is stable. + * + * Also see the comment "Global load-average calculations". */ -static void calc_global_load_remove(struct rq *rq) +static void calc_load_migrate(struct rq *rq) { - atomic_long_sub(rq->calc_load_active, &calc_load_tasks); - rq->calc_load_active = 0; + long delta = calc_load_fold_active(rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks); } /* @@ -5348,9 +4794,6 @@ static void migrate_tasks(unsigned int dead_cpu) */ rq->stop = NULL; - /* Ensure any throttled groups are reachable by pick_next_task */ - unthrottle_offline_cfs_rqs(rq); - for ( ; ; ) { /* * There's this thread running, bail when that's the only @@ -5425,16 +4868,25 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; } +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX; + static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler) + umode_t mode, proc_handler *proc_handler, + bool load_idx) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } } static struct ctl_table * @@ -5446,30 +4898,30 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return NULL; set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[9], "cache_nice_tries", &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[11], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring); + CORENAME_MAX_SIZE, 0444, proc_dostring, false); /* &table[12] is terminator */ return table; @@ -5613,9 +5065,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_tasks(cpu); BUG_ON(rq->nr_running != 1); /* the migration thread */ raw_spin_unlock_irqrestore(&rq->lock, flags); + break; - migrate_nr_uninterruptible(rq); - calc_global_load_remove(rq); + case CPU_DEAD: + calc_load_migrate(rq); break; #endif } @@ -6547,7 +6000,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) | 0*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE | 0*SD_WAKE_AFFINE - | 0*SD_PREFER_LOCAL | 0*SD_SHARE_CPUPOWER | 0*SD_SHARE_PKG_RESOURCES | 1*SD_SERIALIZE @@ -7097,34 +6549,66 @@ match2: mutex_unlock(&sched_domains_mutex); } +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ + /* * Update cpusets according to cpu_active mask. If cpusets are * disabled, cpuset_update_active_cpus() becomes a simple wrapper * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. */ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED_FROZEN: + + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + break; + } + + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + case CPU_ONLINE: case CPU_DOWN_FAILED: - cpuset_update_active_cpus(); - return NOTIFY_OK; + cpuset_update_active_cpus(true); + break; default: return NOTIFY_DONE; } + return NOTIFY_OK; } static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { case CPU_DOWN_PREPARE: - cpuset_update_active_cpus(); - return NOTIFY_OK; + cpuset_update_active_cpus(false); + break; + case CPU_DOWN_PREPARE_FROZEN: + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + break; default: return NOTIFY_DONE; } + return NOTIFY_OK; } void __init sched_init_smp(void) @@ -7179,6 +6663,7 @@ int in_sched_functions(unsigned long addr) #ifdef CONFIG_CGROUP_SCHED struct task_group root_task_group; +LIST_HEAD(task_groups); #endif DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask); @@ -7589,6 +7074,7 @@ void sched_destroy_group(struct task_group *tg) */ void sched_move_task(struct task_struct *tsk) { + struct task_group *tg; int on_rq, running; unsigned long flags; struct rq *rq; @@ -7603,6 +7089,12 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); + tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id, + lockdep_is_held(&tsk->sighand->siglock)), + struct task_group, css); + tg = autogroup_task_group(tsk, tg); + tsk->sched_task_group = tg; + #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_move_group) tsk->sched_class->task_move_group(tsk, on_rq); @@ -8305,6 +7797,8 @@ struct cgroup_subsys cpu_cgroup_subsys = { * (balbir@in.ibm.com). */ +struct cpuacct root_cpuacct; + /* create a new cpu accounting group */ static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp) { diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index d72586fdf66..23aa789c53e 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -65,8 +65,8 @@ static int convert_prio(int prio) int cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask) { - int idx = 0; - int task_pri = convert_prio(p->prio); + int idx = 0; + int task_pri = convert_prio(p->prio); if (task_pri >= MAX_RT_PRIO) return 0; @@ -137,9 +137,9 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, */ void cpupri_set(struct cpupri *cp, int cpu, int newpri) { - int *currpri = &cp->cpu_to_pri[cpu]; - int oldpri = *currpri; - int do_mb = 0; + int *currpri = &cp->cpu_to_pri[cpu]; + int oldpri = *currpri; + int do_mb = 0; newpri = convert_prio(newpri); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c new file mode 100644 index 00000000000..81b763ba58a --- /dev/null +++ b/kernel/sched/cputime.c @@ -0,0 +1,530 @@ +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/tsacct_kern.h> +#include <linux/kernel_stat.h> +#include <linux/static_key.h> +#include "sched.h" + + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in vtime_account, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/vtime_account on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +DEFINE_PER_CPU(u64, cpu_hardirq_time); +DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +DEFINE_PER_CPU(seqcount_t, irq_time_seq); +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void vtime_account(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account); + +static int irqtime_account_hi_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_hardirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +static int irqtime_account_si_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_softirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#define sched_clock_irqtime (0) + +#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */ + +static inline void task_group_account_field(struct task_struct *p, int index, + u64 tmp) +{ +#ifdef CONFIG_CGROUP_CPUACCT + struct kernel_cpustat *kcpustat; + struct cpuacct *ca; +#endif + /* + * Since all updates are sure to touch the root cgroup, we + * get ourselves ahead and touch it first. If the root cgroup + * is the only cgroup, then nothing else should be necessary. + * + */ + __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; + +#ifdef CONFIG_CGROUP_CPUACCT + if (unlikely(!cpuacct_subsys.active)) + return; + + rcu_read_lock(); + ca = task_ca(p); + while (ca && (ca != &root_cpuacct)) { + kcpustat = this_cpu_ptr(ca->cpustat); + kcpustat->cpustat[index] += tmp; + ca = parent_ca(ca); + } + rcu_read_unlock(); +#endif +} + +/* + * Account user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + int index; + + /* Add user time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + + index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + + /* Add user time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for user time used */ + acct_update_integrals(p); +} + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + /* Add guest time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + p->gtime += cputime; + + /* Add guest time to cpustat. */ + if (TASK_NICE(p) > 0) { + cpustat[CPUTIME_NICE] += (__force u64) cputime; + cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; + } else { + cpustat[CPUTIME_USER] += (__force u64) cputime; + cpustat[CPUTIME_GUEST] += (__force u64) cputime; + } +} + +/* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, int index) +{ + /* Add system time to process. */ + p->stime += cputime; + p->stimescaled += cputime_scaled; + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for system time used */ + acct_update_integrals(p); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + int index; + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { + account_guest_time(p, cputime, cputime_scaled); + return; + } + + if (hardirq_count() - hardirq_offset) + index = CPUTIME_IRQ; + else if (in_serving_softirq()) + index = CPUTIME_SOFTIRQ; + else + index = CPUTIME_SYSTEM; + + __account_system_time(p, cputime, cputime_scaled, index); +} + +/* + * Account for involuntary wait time. + * @cputime: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + cpustat[CPUTIME_STEAL] += (__force u64) cputime; +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +void account_idle_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; + else + cpustat[CPUTIME_IDLE] += (__force u64) cputime; +} + +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_key_false(¶virt_steal_enabled)) { + u64 steal, st = 0; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + st = steal_ticks(steal); + this_rq()->prev_steal_time += st * TICK_NSEC; + + account_steal_time(st); + return st; + } +#endif + return false; +} + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * Account a tick to a process and cpustat + * @p: the process that the cpu time gets accounted to + * @user_tick: is the tick from userspace + * @rq: the pointer to rq + * + * Tick demultiplexing follows the order + * - pending hardirq update + * - pending softirq update + * - user_time + * - idle_time + * - system time + * - check for guest_time + * - else account as system_time + * + * Check for hardirq is done both for system and user time as there is + * no timer going off while we are on hardirq and hence we may never get an + * opportunity to update it solely in system time. + * p->stime and friends are only updated on system time and not on irq + * softirq as those do not count in task exec_runtime any more. + */ +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + u64 *cpustat = kcpustat_this_cpu->cpustat; + + if (steal_account_process_tick()) + return; + + if (irqtime_account_hi_update()) { + cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; + } else if (irqtime_account_si_update()) { + cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; + } else if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + * Also, p->stime needs to be updated for ksoftirqd. + */ + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + CPUTIME_SOFTIRQ); + } else if (user_tick) { + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else if (p == rq->idle) { + account_idle_time(cputime_one_jiffy); + } else if (p->flags & PF_VCPU) { /* System time or guest time */ + account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else { + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + CPUTIME_SYSTEM); + } +} + +static void irqtime_account_idle_ticks(int ticks) +{ + int i; + struct rq *rq = this_rq(); + + for (i = 0; i < ticks; i++) + irqtime_account_process_tick(current, 0, rq); +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ +static void irqtime_account_idle_ticks(int ticks) {} +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) {} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + struct rq *rq = this_rq(); + + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq); + return; + } + + if (steal_account_process_tick()) + return; + + if (user_tick) + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, + one_jiffy_scaled); + else + account_idle_time(cputime_one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + + account_idle_time(jiffies_to_cputime(ticks)); +} + +#endif + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} + +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} + +/* + * Archs that account the whole time spent in the idle task + * (outside irq) as idle time can rely on this and just implement + * vtime_account_system() and vtime_account_idle(). Archs that + * have other meaning of the idle time (s390 only includes the + * time spent by the CPU when it's in low power mode) must override + * vtime_account(). + */ +#ifndef __ARCH_HAS_VTIME_ACCOUNT +void vtime_account(struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + + if (in_interrupt() || !is_idle_task(tsk)) + vtime_account_system(tsk); + else + vtime_account_idle(tsk); + + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account); +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ + +#else + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) +{ + u64 temp = (__force u64) rtime; + + temp *= (__force u64) utime; + + if (sizeof(cputime_t) == 4) + temp = div_u64(temp, (__force u32) total); + else + temp = div64_u64(temp, (__force u64) total); + + return (__force cputime_t) temp; +} + +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + cputime_t rtime, utime = p->utime, total = utime + p->stime; + + /* + * Use CFS's precise accounting: + */ + rtime = nsecs_to_cputime(p->se.sum_exec_runtime); + + if (total) + utime = scale_utime(utime, rtime, total); + else + utime = rtime; + + /* + * Compare with previous values, to keep monotonicity: + */ + p->prev_utime = max(p->prev_utime, utime); + p->prev_stime = max(p->prev_stime, rtime - p->prev_utime); + + *ut = p->prev_utime; + *st = p->prev_stime; +} + +/* + * Must be called with siglock held. + */ +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct signal_struct *sig = p->signal; + struct task_cputime cputime; + cputime_t rtime, utime, total; + + thread_group_cputime(p, &cputime); + + total = cputime.utime + cputime.stime; + rtime = nsecs_to_cputime(cputime.sum_exec_runtime); + + if (total) + utime = scale_utime(cputime.utime, rtime, total); + else + utime = rtime; + + sig->prev_utime = max(sig->prev_utime, utime); + sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime); + + *ut = sig->prev_utime; + *st = sig->prev_stime; +} +#endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c099cc6eebe..6b800a14b99 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -597,7 +597,7 @@ calc_delta_fair(unsigned long delta, struct sched_entity *se) /* * The idea is to set a period in which each task runs once. * - * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch + * When there are too many tasks (sched_nr_latency) we have to stretch * this period because otherwise the slices get too small. * * p = (nr <= nl) ? l : l*nr/nl @@ -2052,7 +2052,7 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_cancel(&cfs_b->slack_timer); } -void unthrottle_offline_cfs_rqs(struct rq *rq) +static void unthrottle_offline_cfs_rqs(struct rq *rq) { struct cfs_rq *cfs_rq; @@ -2106,7 +2106,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) return NULL; } static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} -void unthrottle_offline_cfs_rqs(struct rq *rq) {} +static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {} #endif /* CONFIG_CFS_BANDWIDTH */ @@ -2700,7 +2700,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) int prev_cpu = task_cpu(p); int new_cpu = cpu; int want_affine = 0; - int want_sd = 1; int sync = wake_flags & WF_SYNC; if (p->nr_cpus_allowed == 1) @@ -2718,48 +2717,21 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) continue; /* - * If power savings logic is enabled for a domain, see if we - * are not overloaded, if so, don't balance wider. - */ - if (tmp->flags & (SD_PREFER_LOCAL)) { - unsigned long power = 0; - unsigned long nr_running = 0; - unsigned long capacity; - int i; - - for_each_cpu(i, sched_domain_span(tmp)) { - power += power_of(i); - nr_running += cpu_rq(i)->cfs.nr_running; - } - - capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - - if (nr_running < capacity) - want_sd = 0; - } - - /* * If both cpu and prev_cpu are part of this domain, * cpu is a valid SD_WAKE_AFFINE target. */ if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { affine_sd = tmp; - want_affine = 0; - } - - if (!want_sd && !want_affine) break; + } - if (!(tmp->flags & sd_flag)) - continue; - - if (want_sd) + if (tmp->flags & sd_flag) sd = tmp; } if (affine_sd) { - if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) + if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) prev_cpu = cpu; new_cpu = select_idle_sibling(p, prev_cpu); @@ -3068,18 +3040,24 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10; #define LBF_ALL_PINNED 0x01 #define LBF_NEED_BREAK 0x02 +#define LBF_SOME_PINNED 0x04 struct lb_env { struct sched_domain *sd; - int src_cpu; struct rq *src_rq; + int src_cpu; int dst_cpu; struct rq *dst_rq; + struct cpumask *dst_grpmask; + int new_dst_cpu; enum cpu_idle_type idle; long imbalance; + /* The set of CPUs under consideration for load-balancing */ + struct cpumask *cpus; + unsigned int flags; unsigned int loop; @@ -3145,9 +3123,31 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 3) are cache-hot on their current CPU. */ if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { + int new_dst_cpu; + schedstat_inc(p, se.statistics.nr_failed_migrations_affine); + + /* + * Remember if this task can be migrated to any other cpu in + * our sched_group. We may want to revisit it if we couldn't + * meet load balance goals by pulling other tasks on src_cpu. + * + * Also avoid computing new_dst_cpu if we have already computed + * one in current iteration. + */ + if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED)) + return 0; + + new_dst_cpu = cpumask_first_and(env->dst_grpmask, + tsk_cpus_allowed(p)); + if (new_dst_cpu < nr_cpu_ids) { + env->flags |= LBF_SOME_PINNED; + env->new_dst_cpu = new_dst_cpu; + } return 0; } + + /* Record that we found atleast one task that could run on dst_cpu */ env->flags &= ~LBF_ALL_PINNED; if (task_running(env->src_rq, p)) { @@ -3373,6 +3373,14 @@ static int tg_load_down(struct task_group *tg, void *data) static void update_h_load(long cpu) { + struct rq *rq = cpu_rq(cpu); + unsigned long now = jiffies; + + if (rq->h_load_throttle == now) + return; + + rq->h_load_throttle = now; + rcu_read_lock(); walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); rcu_read_unlock(); @@ -3636,14 +3644,12 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) * @group: sched_group whose statistics are to be updated. * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. - * @cpus: Set of cpus considered for load balancing. * @balance: Should we balance. * @sgs: variable to hold the statistics for this group. */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, - int local_group, const struct cpumask *cpus, - int *balance, struct sg_lb_stats *sgs) + int local_group, int *balance, struct sg_lb_stats *sgs) { unsigned long nr_running, max_nr_running, min_nr_running; unsigned long load, max_cpu_load, min_cpu_load; @@ -3660,7 +3666,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, max_nr_running = 0; min_nr_running = ~0UL; - for_each_cpu_and(i, sched_group_cpus(group), cpus) { + for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { struct rq *rq = cpu_rq(i); nr_running = rq->nr_running; @@ -3784,13 +3790,11 @@ static bool update_sd_pick_busiest(struct lb_env *env, /** * update_sd_lb_stats - Update sched_domain's statistics for load balancing. * @env: The load balancing environment. - * @cpus: Set of cpus considered for load balancing. * @balance: Should we balance. * @sds: variable to hold the statistics for this sched_domain. */ static inline void update_sd_lb_stats(struct lb_env *env, - const struct cpumask *cpus, - int *balance, struct sd_lb_stats *sds) + int *balance, struct sd_lb_stats *sds) { struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; @@ -3807,8 +3811,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg)); memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(env, sg, load_idx, local_group, - cpus, balance, &sgs); + update_sg_lb_stats(env, sg, load_idx, local_group, balance, &sgs); if (local_group && !(*balance)) return; @@ -4044,7 +4047,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * to restore balance. * * @env: The load balancing environment. - * @cpus: The set of CPUs under consideration for load-balancing. * @balance: Pointer to a variable indicating if this_cpu * is the appropriate cpu to perform load balancing at this_level. * @@ -4054,7 +4056,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * put to idle by rebalancing its tasks onto our group. */ static struct sched_group * -find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance) +find_busiest_group(struct lb_env *env, int *balance) { struct sd_lb_stats sds; @@ -4064,7 +4066,7 @@ find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance) * Compute the various statistics relavent for load balancing at * this level. */ - update_sd_lb_stats(env, cpus, balance, &sds); + update_sd_lb_stats(env, balance, &sds); /* * this_cpu is not the appropriate cpu to perform load balancing at @@ -4144,8 +4146,7 @@ ret: * find_busiest_queue - find the busiest runqueue among the cpus in group. */ static struct rq *find_busiest_queue(struct lb_env *env, - struct sched_group *group, - const struct cpumask *cpus) + struct sched_group *group) { struct rq *busiest = NULL, *rq; unsigned long max_load = 0; @@ -4160,7 +4161,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (!capacity) capacity = fix_small_capacity(env->sd, group); - if (!cpumask_test_cpu(i, cpus)) + if (!cpumask_test_cpu(i, env->cpus)) continue; rq = cpu_rq(i); @@ -4227,7 +4228,8 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, int *balance) { - int ld_moved, active_balance = 0; + int ld_moved, cur_ld_moved, active_balance = 0; + int lb_iterations, max_lb_iterations; struct sched_group *group; struct rq *busiest; unsigned long flags; @@ -4237,16 +4239,19 @@ static int load_balance(int this_cpu, struct rq *this_rq, .sd = sd, .dst_cpu = this_cpu, .dst_rq = this_rq, + .dst_grpmask = sched_group_cpus(sd->groups), .idle = idle, .loop_break = sched_nr_migrate_break, + .cpus = cpus, }; cpumask_copy(cpus, cpu_active_mask); + max_lb_iterations = cpumask_weight(env.dst_grpmask); schedstat_inc(sd, lb_count[idle]); redo: - group = find_busiest_group(&env, cpus, balance); + group = find_busiest_group(&env, balance); if (*balance == 0) goto out_balanced; @@ -4256,17 +4261,18 @@ redo: goto out_balanced; } - busiest = find_busiest_queue(&env, group, cpus); + busiest = find_busiest_queue(&env, group); if (!busiest) { schedstat_inc(sd, lb_nobusyq[idle]); goto out_balanced; } - BUG_ON(busiest == this_rq); + BUG_ON(busiest == env.dst_rq); schedstat_add(sd, lb_imbalance[idle], env.imbalance); ld_moved = 0; + lb_iterations = 1; if (busiest->nr_running > 1) { /* * Attempt to move tasks. If find_busiest_group has found @@ -4279,13 +4285,18 @@ redo: env.src_rq = busiest; env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); + update_h_load(env.src_cpu); more_balance: local_irq_save(flags); - double_rq_lock(this_rq, busiest); - if (!env.loop) - update_h_load(env.src_cpu); - ld_moved += move_tasks(&env); - double_rq_unlock(this_rq, busiest); + double_rq_lock(env.dst_rq, busiest); + + /* + * cur_ld_moved - load moved in current iteration + * ld_moved - cumulative load moved across iterations + */ + cur_ld_moved = move_tasks(&env); + ld_moved += cur_ld_moved; + double_rq_unlock(env.dst_rq, busiest); local_irq_restore(flags); if (env.flags & LBF_NEED_BREAK) { @@ -4296,14 +4307,51 @@ more_balance: /* * some other cpu did the load balance for us. */ - if (ld_moved && this_cpu != smp_processor_id()) - resched_cpu(this_cpu); + if (cur_ld_moved && env.dst_cpu != smp_processor_id()) + resched_cpu(env.dst_cpu); + + /* + * Revisit (affine) tasks on src_cpu that couldn't be moved to + * us and move them to an alternate dst_cpu in our sched_group + * where they can run. The upper limit on how many times we + * iterate on same src_cpu is dependent on number of cpus in our + * sched_group. + * + * This changes load balance semantics a bit on who can move + * load to a given_cpu. In addition to the given_cpu itself + * (or a ilb_cpu acting on its behalf where given_cpu is + * nohz-idle), we now have balance_cpu in a position to move + * load to given_cpu. In rare situations, this may cause + * conflicts (balance_cpu and given_cpu/ilb_cpu deciding + * _independently_ and at _same_ time to move some load to + * given_cpu) causing exceess load to be moved to given_cpu. + * This however should not happen so much in practice and + * moreover subsequent load balance cycles should correct the + * excess load moved. + */ + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 && + lb_iterations++ < max_lb_iterations) { + + env.dst_rq = cpu_rq(env.new_dst_cpu); + env.dst_cpu = env.new_dst_cpu; + env.flags &= ~LBF_SOME_PINNED; + env.loop = 0; + env.loop_break = sched_nr_migrate_break; + /* + * Go back to "more_balance" rather than "redo" since we + * need to continue with same src_cpu. + */ + goto more_balance; + } /* All tasks on this runqueue were pinned by CPU affinity */ if (unlikely(env.flags & LBF_ALL_PINNED)) { cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) + if (!cpumask_empty(cpus)) { + env.loop = 0; + env.loop_break = sched_nr_migrate_break; goto redo; + } goto out_balanced; } } @@ -4569,7 +4617,7 @@ static void nohz_balancer_kick(int cpu) return; } -static inline void clear_nohz_tick_stopped(int cpu) +static inline void nohz_balance_exit_idle(int cpu) { if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); @@ -4609,28 +4657,23 @@ void set_cpu_sd_state_idle(void) } /* - * This routine will record that this cpu is going idle with tick stopped. + * This routine will record that the cpu is going idle with tick stopped. * This info will be used in performing idle load balancing in the future. */ -void select_nohz_load_balancer(int stop_tick) +void nohz_balance_enter_idle(int cpu) { - int cpu = smp_processor_id(); - /* * If this cpu is going down, then nothing needs to be done. */ if (!cpu_active(cpu)) return; - if (stop_tick) { - if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) - return; + if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) + return; - cpumask_set_cpu(cpu, nohz.idle_cpus_mask); - atomic_inc(&nohz.nr_cpus); - set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); - } - return; + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); + atomic_inc(&nohz.nr_cpus); + set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, @@ -4638,7 +4681,7 @@ static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, { switch (action & ~CPU_TASKS_FROZEN) { case CPU_DYING: - clear_nohz_tick_stopped(smp_processor_id()); + nohz_balance_exit_idle(smp_processor_id()); return NOTIFY_OK; default: return NOTIFY_DONE; @@ -4760,14 +4803,15 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) if (need_resched()) break; - raw_spin_lock_irq(&this_rq->lock); - update_rq_clock(this_rq); - update_idle_cpu_load(this_rq); - raw_spin_unlock_irq(&this_rq->lock); + rq = cpu_rq(balance_cpu); + + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); rebalance_domains(balance_cpu, CPU_IDLE); - rq = cpu_rq(balance_cpu); if (time_after(this_rq->next_balance, rq->next_balance)) this_rq->next_balance = rq->next_balance; } @@ -4798,7 +4842,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu) * busy tick after returning from idle, we will update the busy stats. */ set_cpu_sd_state_busy(); - clear_nohz_tick_stopped(cpu); + nohz_balance_exit_idle(cpu); /* * None are in tickless mode and hence no need for NOHZ idle load @@ -4891,6 +4935,9 @@ static void rq_online_fair(struct rq *rq) static void rq_offline_fair(struct rq *rq) { update_sysctl(); + + /* Ensure any throttled groups are reachable by pick_next_task */ + unthrottle_offline_cfs_rqs(rq); } #endif /* CONFIG_SMP */ diff --git a/kernel/sched/features.h b/kernel/sched/features.h index de00a486c5c..eebefcad702 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -12,14 +12,6 @@ SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true) SCHED_FEAT(START_DEBIT, true) /* - * Based on load and program behaviour, see if it makes sense to place - * a newly woken task on the same cpu as the task that woke it -- - * improve cache locality. Typically used with SYNC wakeups as - * generated by pipes and the like, see also SYNC_WAKEUPS. - */ -SCHED_FEAT(AFFINE_WAKEUPS, true) - -/* * Prefer to schedule the task we woke last (assuming it failed * wakeup-preemption), since its likely going to consume data we * touched, increases cache locality. @@ -42,7 +34,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true) /* * Use arch dependent cpu power functions */ -SCHED_FEAT(ARCH_POWER, false) +SCHED_FEAT(ARCH_POWER, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 573e1ca0110..418feb01344 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -691,6 +691,7 @@ balanced: * runtime - in which case borrowing doesn't make sense. */ rt_rq->rt_runtime = RUNTIME_INF; + rt_rq->rt_throttled = 0; raw_spin_unlock(&rt_rq->rt_runtime_lock); raw_spin_unlock(&rt_b->rt_runtime_lock); } @@ -788,6 +789,19 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) const struct cpumask *span; span = sched_rt_period_mask(); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * FIXME: isolated CPUs should really leave the root task group, + * whether they are isolcpus or were isolated via cpusets, lest + * the timer run on a CPU which does not service all runqueues, + * potentially leaving other CPUs indefinitely throttled. If + * isolation is really required, the user will turn the throttle + * off to kill the perturbations it causes anyway. Meanwhile, + * this maintains functionality for boot and/or troubleshooting. + */ + if (rt_b == &root_task_group.rt_bandwidth) + span = cpu_online_mask; +#endif for_each_cpu(i, span) { int enqueue = 0; struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); @@ -1618,11 +1632,6 @@ static int push_rt_task(struct rq *rq) if (!next_task) return 0; -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - if (unlikely(task_running(rq, next_task))) - return 0; -#endif - retry: if (unlikely(next_task == rq->curr)) { WARN_ON(1); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 55844f24435..7a7db09cfab 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -80,7 +80,7 @@ extern struct mutex sched_domains_mutex; struct cfs_rq; struct rt_rq; -static LIST_HEAD(task_groups); +extern struct list_head task_groups; struct cfs_bandwidth { #ifdef CONFIG_CFS_BANDWIDTH @@ -374,7 +374,11 @@ struct rq { #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; -#endif +#ifdef CONFIG_SMP + unsigned long h_load_throttle; +#endif /* CONFIG_SMP */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ + #ifdef CONFIG_RT_GROUP_SCHED struct list_head leaf_rt_rq_list; #endif @@ -538,22 +542,19 @@ extern int group_balance_cpu(struct sched_group *sg); /* * Return the group to which this tasks belongs. * - * We use task_subsys_state_check() and extend the RCU verification with - * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each - * task it moves into the cgroup. Therefore by holding either of those locks, - * we pin the task to the current cgroup. + * We cannot use task_subsys_state() and friends because the cgroup + * subsystem changes that value before the cgroup_subsys::attach() method + * is called, therefore we cannot pin it and might observe the wrong value. + * + * The same is true for autogroup's p->signal->autogroup->tg, the autogroup + * core changes this before calling sched_move_task(). + * + * Instead we use a 'copy' which is updated from sched_move_task() while + * holding both task_struct::pi_lock and rq::lock. */ static inline struct task_group *task_group(struct task_struct *p) { - struct task_group *tg; - struct cgroup_subsys_state *css; - - css = task_subsys_state_check(p, cpu_cgroup_subsys_id, - lockdep_is_held(&p->pi_lock) || - lockdep_is_held(&task_rq(p)->lock)); - tg = container_of(css, struct task_group, css); - - return autogroup_task_group(p, tg); + return p->sched_task_group; } /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ @@ -736,11 +737,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) */ next->on_cpu = 1; #endif -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - raw_spin_unlock_irq(&rq->lock); -#else raw_spin_unlock(&rq->lock); -#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) @@ -754,9 +751,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) smp_wmb(); prev->on_cpu = 0; #endif -#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); -#endif } #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ @@ -890,6 +885,9 @@ struct cpuacct { struct kernel_cpustat __percpu *cpustat; }; +extern struct cgroup_subsys cpuacct_subsys; +extern struct cpuacct root_cpuacct; + /* return cpu accounting group corresponding to this container */ static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) { @@ -916,6 +914,16 @@ extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} #endif +#ifdef CONFIG_PARAVIRT +static inline u64 steal_ticks(u64 steal) +{ + if (unlikely(steal > NSEC_PER_SEC)) + return div_u64(steal, TICK_NSEC); + + return __iter_div_u64_rem(steal, TICK_NSEC, &steal); +} +#endif + static inline void inc_nr_running(struct rq *rq) { rq->nr_running++; @@ -1143,7 +1151,6 @@ extern void print_rt_stats(struct seq_file *m, int cpu); extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); -extern void unthrottle_offline_cfs_rqs(struct rq *rq); extern void account_cfs_bandwidth_used(int enabled, int was_enabled); @@ -1156,3 +1163,53 @@ enum rq_nohz_flag_bits { #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) #endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +DECLARE_PER_CPU(u64, cpu_hardirq_time); +DECLARE_PER_CPU(u64, cpu_softirq_time); + +#ifndef CONFIG_64BIT +DECLARE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 7b386e86fd2..da5eb5bed84 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -27,8 +27,10 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - if (stop && stop->on_rq) + if (stop && stop->on_rq) { + stop->se.exec_start = rq->clock_task; return stop; + } return NULL; } @@ -52,6 +54,21 @@ static void yield_task_stop(struct rq *rq) static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) { + struct task_struct *curr = rq->curr; + u64 delta_exec; + + delta_exec = rq->clock_task - curr->se.exec_start; + if (unlikely((s64)delta_exec < 0)) + delta_exec = 0; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq->clock_task; + cpuacct_charge(curr, delta_exec); } static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued) @@ -60,6 +77,9 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued) static void set_curr_task_stop(struct rq *rq) { + struct task_struct *stop = rq->stop; + + stop->se.exec_start = rq->clock_task; } static void switched_to_stop(struct rq *rq, struct task_struct *p) diff --git a/kernel/signal.c b/kernel/signal.c index 677102789cf..2c681f11b7d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1971,6 +1971,8 @@ static void ptrace_do_notify(int signr, int exit_code, int why) void ptrace_notify(int exit_code) { BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); + if (unlikely(current->task_works)) + task_work_run(); spin_lock_irq(¤t->sighand->siglock); ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED); @@ -2191,6 +2193,9 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct signal_struct *signal = current->signal; int signr; + if (unlikely(current->task_works)) + task_work_run(); + if (unlikely(uprobe_deny_signal())) return 0; diff --git a/kernel/smp.c b/kernel/smp.c index d0ae5b24875..29dd40a9f2f 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -581,26 +581,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait) return 0; } EXPORT_SYMBOL(smp_call_function); - -void ipi_call_lock(void) -{ - raw_spin_lock(&call_function.lock); -} - -void ipi_call_unlock(void) -{ - raw_spin_unlock(&call_function.lock); -} - -void ipi_call_lock_irq(void) -{ - raw_spin_lock_irq(&call_function.lock); -} - -void ipi_call_unlock_irq(void) -{ - raw_spin_unlock_irq(&call_function.lock); -} #endif /* USE_GENERIC_SMP_HELPERS */ /* Setup configured maximum number of CPUs to activate */ diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 98f60c5caa1..d6c5fc05424 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -1,14 +1,22 @@ /* * Common SMP CPU bringup/teardown functions */ +#include <linux/cpu.h> #include <linux/err.h> #include <linux/smp.h> #include <linux/init.h> +#include <linux/list.h> +#include <linux/slab.h> #include <linux/sched.h> +#include <linux/export.h> #include <linux/percpu.h> +#include <linux/kthread.h> +#include <linux/smpboot.h> #include "smpboot.h" +#ifdef CONFIG_SMP + #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD /* * For the hotplug case we keep the task structs around and reuse @@ -65,3 +73,228 @@ void __init idle_threads_init(void) } } #endif + +#endif /* #ifdef CONFIG_SMP */ + +static LIST_HEAD(hotplug_threads); +static DEFINE_MUTEX(smpboot_threads_lock); + +struct smpboot_thread_data { + unsigned int cpu; + unsigned int status; + struct smp_hotplug_thread *ht; +}; + +enum { + HP_THREAD_NONE = 0, + HP_THREAD_ACTIVE, + HP_THREAD_PARKED, +}; + +/** + * smpboot_thread_fn - percpu hotplug thread loop function + * @data: thread data pointer + * + * Checks for thread stop and park conditions. Calls the necessary + * setup, cleanup, park and unpark functions for the registered + * thread. + * + * Returns 1 when the thread should exit, 0 otherwise. + */ +static int smpboot_thread_fn(void *data) +{ + struct smpboot_thread_data *td = data; + struct smp_hotplug_thread *ht = td->ht; + + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + preempt_disable(); + if (kthread_should_stop()) { + set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->cleanup) + ht->cleanup(td->cpu, cpu_online(td->cpu)); + kfree(td); + return 0; + } + + if (kthread_should_park()) { + __set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->park && td->status == HP_THREAD_ACTIVE) { + BUG_ON(td->cpu != smp_processor_id()); + ht->park(td->cpu); + td->status = HP_THREAD_PARKED; + } + kthread_parkme(); + /* We might have been woken for stop */ + continue; + } + + BUG_ON(td->cpu != smp_processor_id()); + + /* Check for state change setup */ + switch (td->status) { + case HP_THREAD_NONE: + preempt_enable(); + if (ht->setup) + ht->setup(td->cpu); + td->status = HP_THREAD_ACTIVE; + preempt_disable(); + break; + case HP_THREAD_PARKED: + preempt_enable(); + if (ht->unpark) + ht->unpark(td->cpu); + td->status = HP_THREAD_ACTIVE; + preempt_disable(); + break; + } + + if (!ht->thread_should_run(td->cpu)) { + preempt_enable(); + schedule(); + } else { + set_current_state(TASK_RUNNING); + preempt_enable(); + ht->thread_fn(td->cpu); + } + } +} + +static int +__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + struct smpboot_thread_data *td; + + if (tsk) + return 0; + + td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu)); + if (!td) + return -ENOMEM; + td->cpu = cpu; + td->ht = ht; + + tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu, + ht->thread_comm); + if (IS_ERR(tsk)) { + kfree(td); + return PTR_ERR(tsk); + } + + get_task_struct(tsk); + *per_cpu_ptr(ht->store, cpu) = tsk; + return 0; +} + +int smpboot_create_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + int ret = 0; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry(cur, &hotplug_threads, list) { + ret = __smpboot_create_thread(cur, cpu); + if (ret) + break; + } + mutex_unlock(&smpboot_threads_lock); + return ret; +} + +static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + kthread_unpark(tsk); +} + +void smpboot_unpark_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry(cur, &hotplug_threads, list) + smpboot_unpark_thread(cur, cpu); + mutex_unlock(&smpboot_threads_lock); +} + +static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (tsk) + kthread_park(tsk); +} + +void smpboot_park_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry_reverse(cur, &hotplug_threads, list) + smpboot_park_thread(cur, cpu); + mutex_unlock(&smpboot_threads_lock); +} + +static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) +{ + unsigned int cpu; + + /* We need to destroy also the parked threads of offline cpus */ + for_each_possible_cpu(cpu) { + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (tsk) { + kthread_stop(tsk); + put_task_struct(tsk); + *per_cpu_ptr(ht->store, cpu) = NULL; + } + } +} + +/** + * smpboot_register_percpu_thread - Register a per_cpu thread related to hotplug + * @plug_thread: Hotplug thread descriptor + * + * Creates and starts the threads on all online cpus. + */ +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + unsigned int cpu; + int ret = 0; + + mutex_lock(&smpboot_threads_lock); + for_each_online_cpu(cpu) { + ret = __smpboot_create_thread(plug_thread, cpu); + if (ret) { + smpboot_destroy_threads(plug_thread); + goto out; + } + smpboot_unpark_thread(plug_thread, cpu); + } + list_add(&plug_thread->list, &hotplug_threads); +out: + mutex_unlock(&smpboot_threads_lock); + return ret; +} +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); + +/** + * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug + * @plug_thread: Hotplug thread descriptor + * + * Stops all threads on all possible cpus. + */ +void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + get_online_cpus(); + mutex_lock(&smpboot_threads_lock); + list_del(&plug_thread->list); + smpboot_destroy_threads(plug_thread); + mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 80c0acfb847..72415a0eb95 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -3,8 +3,6 @@ struct task_struct; -int smpboot_prepare(unsigned int cpu); - #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD struct task_struct *idle_thread_get(unsigned int cpu); void idle_thread_set_boot_cpu(void); @@ -15,4 +13,8 @@ static inline void idle_thread_set_boot_cpu(void) { } static inline void idle_threads_init(void) { } #endif +int smpboot_create_threads(unsigned int cpu); +void smpboot_park_threads(unsigned int cpu); +void smpboot_unpark_threads(unsigned int cpu); + #endif diff --git a/kernel/softirq.c b/kernel/softirq.c index 671f9594e36..cc96bdc0c2c 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -23,6 +23,7 @@ #include <linux/rcupdate.h> #include <linux/ftrace.h> #include <linux/smp.h> +#include <linux/smpboot.h> #include <linux/tick.h> #define CREATE_TRACE_POINTS @@ -210,9 +211,17 @@ asmlinkage void __do_softirq(void) __u32 pending; int max_restart = MAX_SOFTIRQ_RESTART; int cpu; + unsigned long old_flags = current->flags; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the + * softirq. A softirq handled such as network RX might set PF_MEMALLOC + * again if the socket is related to swap + */ + current->flags &= ~PF_MEMALLOC; pending = local_softirq_pending(); - account_system_vtime(current); + vtime_account(current); __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); @@ -263,8 +272,9 @@ restart: lockdep_softirq_exit(); - account_system_vtime(current); + vtime_account(current); __local_bh_enable(SOFTIRQ_OFFSET); + tsk_restore_flags(current, old_flags, PF_MEMALLOC); } #ifndef __ARCH_HAS_DO_SOFTIRQ @@ -331,7 +341,7 @@ static inline void invoke_softirq(void) */ void irq_exit(void) { - account_system_vtime(current); + vtime_account(current); trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) @@ -733,49 +743,22 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } -static int run_ksoftirqd(void * __bind_cpu) +static int ksoftirqd_should_run(unsigned int cpu) { - set_current_state(TASK_INTERRUPTIBLE); - - while (!kthread_should_stop()) { - preempt_disable(); - if (!local_softirq_pending()) { - schedule_preempt_disabled(); - } - - __set_current_state(TASK_RUNNING); - - while (local_softirq_pending()) { - /* Preempt disable stops cpu going offline. - If already offline, we'll be on wrong CPU: - don't process */ - if (cpu_is_offline((long)__bind_cpu)) - goto wait_to_die; - local_irq_disable(); - if (local_softirq_pending()) - __do_softirq(); - local_irq_enable(); - sched_preempt_enable_no_resched(); - cond_resched(); - preempt_disable(); - rcu_note_context_switch((long)__bind_cpu); - } - preempt_enable(); - set_current_state(TASK_INTERRUPTIBLE); - } - __set_current_state(TASK_RUNNING); - return 0; + return local_softirq_pending(); +} -wait_to_die: - preempt_enable(); - /* Wait for kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - schedule(); - set_current_state(TASK_INTERRUPTIBLE); +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (local_softirq_pending()) { + __do_softirq(); + rcu_note_context_switch(cpu); + local_irq_enable(); + cond_resched(); + return; } - __set_current_state(TASK_RUNNING); - return 0; + local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU @@ -841,50 +824,14 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - int hotcpu = (unsigned long)hcpu; - struct task_struct *p; - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - p = kthread_create_on_node(run_ksoftirqd, - hcpu, - cpu_to_node(hotcpu), - "ksoftirqd/%d", hotcpu); - if (IS_ERR(p)) { - printk("ksoftirqd for %i failed\n", hotcpu); - return notifier_from_errno(PTR_ERR(p)); - } - kthread_bind(p, hotcpu); - per_cpu(ksoftirqd, hotcpu) = p; - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - wake_up_process(per_cpu(ksoftirqd, hotcpu)); - break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!per_cpu(ksoftirqd, hotcpu)) - break; - /* Unbind so it can run. Fall thru. */ - kthread_bind(per_cpu(ksoftirqd, hotcpu), - cpumask_any(cpu_online_mask)); case CPU_DEAD: - case CPU_DEAD_FROZEN: { - static const struct sched_param param = { - .sched_priority = MAX_RT_PRIO-1 - }; - - p = per_cpu(ksoftirqd, hotcpu); - per_cpu(ksoftirqd, hotcpu) = NULL; - sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); - kthread_stop(p); - takeover_tasklets(hotcpu); + case CPU_DEAD_FROZEN: + takeover_tasklets((unsigned long)hcpu); break; - } #endif /* CONFIG_HOTPLUG_CPU */ - } + } return NOTIFY_OK; } @@ -892,14 +839,19 @@ static struct notifier_block __cpuinitdata cpu_nfb = { .notifier_call = cpu_callback }; +static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", +}; + static __init int spawn_ksoftirqd(void) { - void *cpu = (void *)(long)smp_processor_id(); - int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); - - BUG_ON(err != NOTIFY_OK); - cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); register_cpu_notifier(&cpu_nfb); + + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); + return 0; } early_initcall(spawn_ksoftirqd); diff --git a/kernel/sys.c b/kernel/sys.c index 2d39a84cd85..241507f23ec 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2015,7 +2015,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, break; } me->pdeath_signal = arg2; - error = 0; break; case PR_GET_PDEATHSIG: error = put_user(me->pdeath_signal, (int __user *)arg2); @@ -2029,7 +2028,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, break; } set_dumpable(me->mm, arg2); - error = 0; break; case PR_SET_UNALIGN: @@ -2056,10 +2054,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; - else - error = 0; break; - case PR_SET_NAME: comm[sizeof(me->comm)-1] = 0; if (strncpy_from_user(comm, (char __user *)arg2, @@ -2067,20 +2062,19 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EFAULT; set_task_comm(me, comm); proc_comm_connector(me); - return 0; + break; case PR_GET_NAME: get_task_comm(comm, me); if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) return -EFAULT; - return 0; + break; case PR_GET_ENDIAN: error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: error = SET_ENDIAN(me, arg2); break; - case PR_GET_SECCOMP: error = prctl_get_seccomp(); break; @@ -2108,7 +2102,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, current->default_timer_slack_ns; else current->timer_slack_ns = arg2; - error = 0; break; case PR_MCE_KILL: if (arg4 | arg5) @@ -2134,7 +2127,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, default: return -EINVAL; } - error = 0; break; case PR_MCE_KILL_GET: if (arg2 | arg3 | arg4 | arg5) @@ -2153,7 +2145,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; - error = 0; break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, @@ -2195,46 +2186,52 @@ static void argv_cleanup(struct subprocess_info *info) argv_free(info->argv); } -/** - * orderly_poweroff - Trigger an orderly system poweroff - * @force: force poweroff if command execution fails - * - * This may be called from any context to trigger a system shutdown. - * If the orderly shutdown fails, it will force an immediate shutdown. - */ -int orderly_poweroff(bool force) +static int __orderly_poweroff(void) { int argc; - char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc); + char **argv; static char *envp[] = { "HOME=/", "PATH=/sbin:/bin:/usr/sbin:/usr/bin", NULL }; - int ret = -ENOMEM; + int ret; + argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc); if (argv == NULL) { printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n", __func__, poweroff_cmd); - goto out; + return -ENOMEM; } ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_NO_WAIT, NULL, argv_cleanup, NULL); -out: - if (likely(!ret)) - return 0; - if (ret == -ENOMEM) argv_free(argv); - if (force) { + return ret; +} + +/** + * orderly_poweroff - Trigger an orderly system poweroff + * @force: force poweroff if command execution fails + * + * This may be called from any context to trigger a system shutdown. + * If the orderly shutdown fails, it will force an immediate shutdown. + */ +int orderly_poweroff(bool force) +{ + int ret = __orderly_poweroff(); + + if (ret && force) { printk(KERN_WARNING "Failed to start orderly shutdown: " "forcing the issue\n"); - /* I guess this should try to kick off some daemon to - sync and poweroff asap. Or not even bother syncing - if we're doing an emergency shutdown? */ + /* + * I guess this should try to kick off some daemon to sync and + * poweroff asap. Or not even bother syncing if we're doing an + * emergency shutdown? + */ emergency_sync(); kernel_power_off(); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4ab11879aeb..81c7b1a1a30 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -30,6 +30,7 @@ #include <linux/security.h> #include <linux/ctype.h> #include <linux/kmemcheck.h> +#include <linux/kmemleak.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> @@ -174,6 +175,11 @@ static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif +static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +static int proc_dostring_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + #ifdef CONFIG_MAGIC_SYSRQ /* Note: sysrq code uses it's own private copy */ static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE; @@ -301,7 +307,7 @@ static struct ctl_table kern_table[] = { .extra2 = &max_sched_tunable_scaling, }, { - .procname = "sched_migration_cost", + .procname = "sched_migration_cost_ns", .data = &sysctl_sched_migration_cost, .maxlen = sizeof(unsigned int), .mode = 0644, @@ -315,14 +321,14 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, { - .procname = "sched_time_avg", + .procname = "sched_time_avg_ms", .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .procname = "sched_shares_window", + .procname = "sched_shares_window_ns", .data = &sysctl_sched_shares_window, .maxlen = sizeof(unsigned int), .mode = 0644, @@ -410,7 +416,7 @@ static struct ctl_table kern_table[] = { .data = core_pattern, .maxlen = CORENAME_MAX_SIZE, .mode = 0644, - .proc_handler = proc_dostring, + .proc_handler = proc_dostring_coredump, }, { .procname = "core_pipe_limit", @@ -1095,11 +1101,9 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, }, { - .procname = "nr_pdflush_threads", - .data = &nr_pdflush_threads, - .maxlen = sizeof nr_pdflush_threads, - .mode = 0444 /* read-only*/, - .proc_handler = proc_dointvec, + .procname = "nr_pdflush_threads", + .mode = 0444 /* read-only */, + .proc_handler = pdflush_proc_obsolete, }, { .procname = "swappiness", @@ -1494,11 +1498,29 @@ static struct ctl_table fs_table[] = { #endif #endif { + .procname = "protected_symlinks", + .data = &sysctl_protected_symlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "protected_hardlinks", + .data = &sysctl_protected_hardlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax_coredump, .extra1 = &zero, .extra2 = &two, }, @@ -1551,7 +1573,10 @@ static struct ctl_table dev_table[] = { int __init sysctl_init(void) { - register_sysctl_table(sysctl_base_table); + struct ctl_table_header *hdr; + + hdr = register_sysctl_table(sysctl_base_table); + kmemleak_not_leak(hdr); return 0; } @@ -2009,6 +2034,34 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, do_proc_dointvec_minmax_conv, ¶m); } +static void validate_coredump_safety(void) +{ + if (suid_dumpable == SUID_DUMPABLE_SAFE && + core_pattern[0] != '/' && core_pattern[0] != '|') { + printk(KERN_WARNING "Unsafe core_pattern used with "\ + "suid_dumpable=2. Pipe handler or fully qualified "\ + "core dump path required.\n"); + } +} + +static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!error) + validate_coredump_safety(); + return error; +} + +static int proc_dostring_coredump(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dostring(table, write, buffer, lenp, ppos); + if (!error) + validate_coredump_safety(); + return error; +} + static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos, diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index a650694883a..65bdcf198d4 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -147,7 +147,7 @@ static const struct bin_table bin_vm_table[] = { { CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" }, /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */ /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */ - { CTL_INT, VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" }, + /* VM_NR_PDFLUSH_THREADS "nr_pdflush_threads" no longer used */ { CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, /* VM_PAGEBUF unused */ /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */ diff --git a/kernel/task_work.c b/kernel/task_work.c index 82d1c794066..65bd3c92d6f 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -2,83 +2,91 @@ #include <linux/task_work.h> #include <linux/tracehook.h> +static struct callback_head work_exited; /* all we need is ->next == NULL */ + int -task_work_add(struct task_struct *task, struct task_work *twork, bool notify) +task_work_add(struct task_struct *task, struct callback_head *work, bool notify) { - unsigned long flags; - int err = -ESRCH; + struct callback_head *head; -#ifndef TIF_NOTIFY_RESUME - if (notify) - return -ENOTSUPP; -#endif - /* - * We must not insert the new work if the task has already passed - * exit_task_work(). We rely on do_exit()->raw_spin_unlock_wait() - * and check PF_EXITING under pi_lock. - */ - raw_spin_lock_irqsave(&task->pi_lock, flags); - if (likely(!(task->flags & PF_EXITING))) { - hlist_add_head(&twork->hlist, &task->task_works); - err = 0; - } - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + do { + head = ACCESS_ONCE(task->task_works); + if (unlikely(head == &work_exited)) + return -ESRCH; + work->next = head; + } while (cmpxchg(&task->task_works, head, work) != head); - /* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */ - if (likely(!err) && notify) + if (notify) set_notify_resume(task); - return err; + return 0; } -struct task_work * +struct callback_head * task_work_cancel(struct task_struct *task, task_work_func_t func) { + struct callback_head **pprev = &task->task_works; + struct callback_head *work = NULL; unsigned long flags; - struct task_work *twork; - struct hlist_node *pos; - + /* + * If cmpxchg() fails we continue without updating pprev. + * Either we raced with task_work_add() which added the + * new entry before this work, we will find it again. Or + * we raced with task_work_run(), *pprev == NULL/exited. + */ raw_spin_lock_irqsave(&task->pi_lock, flags); - hlist_for_each_entry(twork, pos, &task->task_works, hlist) { - if (twork->func == func) { - hlist_del(&twork->hlist); - goto found; - } + while ((work = ACCESS_ONCE(*pprev))) { + read_barrier_depends(); + if (work->func != func) + pprev = &work->next; + else if (cmpxchg(pprev, work, work->next) == work) + break; } - twork = NULL; - found: raw_spin_unlock_irqrestore(&task->pi_lock, flags); - return twork; + return work; } void task_work_run(void) { struct task_struct *task = current; - struct hlist_head task_works; - struct hlist_node *pos; - - raw_spin_lock_irq(&task->pi_lock); - hlist_move_list(&task->task_works, &task_works); - raw_spin_unlock_irq(&task->pi_lock); - - if (unlikely(hlist_empty(&task_works))) - return; - /* - * We use hlist to save the space in task_struct, but we want fifo. - * Find the last entry, the list should be short, then process them - * in reverse order. - */ - for (pos = task_works.first; pos->next; pos = pos->next) - ; + struct callback_head *work, *head, *next; for (;;) { - struct hlist_node **pprev = pos->pprev; - struct task_work *twork = container_of(pos, struct task_work, - hlist); - twork->func(twork); + /* + * work->func() can do task_work_add(), do not set + * work_exited unless the list is empty. + */ + do { + work = ACCESS_ONCE(task->task_works); + head = !work && (task->flags & PF_EXITING) ? + &work_exited : NULL; + } while (cmpxchg(&task->task_works, work, head) != work); - if (pprev == &task_works.first) + if (!work) break; - pos = container_of(pprev, struct hlist_node, next); + /* + * Synchronize with task_work_cancel(). It can't remove + * the first entry == work, cmpxchg(task_works) should + * fail, but it can play with *work and other entries. + */ + raw_spin_unlock_wait(&task->pi_lock); + smp_mb(); + + /* Reverse the list to run the works in fifo order */ + head = NULL; + do { + next = work->next; + work->next = head; + head = work; + work = next; + } while (work); + + work = head; + do { + next = work->next; + work->func(work); + work = next; + cond_resched(); + } while (work); } } diff --git a/kernel/taskstats.c b/kernel/taskstats.c index e66046456f4..d0a32796550 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -436,6 +436,11 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, sizeof(struct cgroupstats)); + if (na == NULL) { + rc = -EMSGSIZE; + goto err; + } + stats = nla_data(na); memset(stats, 0, sizeof(*stats)); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a470154e040..46da0537c10 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -37,7 +37,7 @@ * requested HZ value. It is also not recommended * for "tick-less" systems. */ -#define NSEC_PER_JIFFY ((u32)((((u64)NSEC_PER_SEC)<<8)/ACTHZ)) +#define NSEC_PER_JIFFY ((u32)((((u64)NSEC_PER_SEC)<<8)/SHIFTED_HZ)) /* Since jiffies uses a simple NSEC_PER_JIFFY multiplier * conversion, the .shift value could be zero. However diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index b7fbadc5c97..24174b4d669 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -28,7 +28,7 @@ DEFINE_SPINLOCK(ntp_lock); /* USER_HZ period (usecs): */ unsigned long tick_usec = TICK_USEC; -/* ACTHZ period (nsecs): */ +/* SHIFTED_HZ period (nsecs): */ unsigned long tick_nsec; static u64 tick_length; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 41be02250e0..f423bdd035c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -105,7 +105,7 @@ static ktime_t tick_init_jiffy_update(void) /* * NO HZ enabled ? */ -static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_enabled __read_mostly = 1; /* * Enable / Disable tickless mode @@ -372,7 +372,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { - select_nohz_load_balancer(1); + nohz_balance_enter_idle(cpu); calc_load_enter_idle(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); @@ -436,7 +436,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(local_softirq_pending() && cpu_online(cpu))) { static int ratelimit; - if (ratelimit < 10) { + if (ratelimit < 10 && + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", (unsigned int) local_softirq_pending()); ratelimit++; @@ -569,10 +570,10 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ - select_nohz_load_balancer(0); tick_do_update_jiffies64(now); update_cpu_load_nohz(); + calc_load_exit_idle(); touch_softlockup_watchdog(); /* * Cancel the scheduled timer and restore the tick diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f045cc50832..d3b91e75cec 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -65,14 +65,14 @@ struct timekeeper { * used instead. */ struct timespec wall_to_monotonic; - /* time spent in suspend */ - struct timespec total_sleep_time; - /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ - struct timespec raw_time; /* Offset clock monotonic -> clock realtime */ ktime_t offs_real; + /* time spent in suspend */ + struct timespec total_sleep_time; /* Offset clock monotonic -> clock boottime */ ktime_t offs_boot; + /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ + struct timespec raw_time; /* Seqlock for all timekeeper values */ seqlock_t lock; }; @@ -108,13 +108,39 @@ static struct timespec tk_xtime(struct timekeeper *tk) static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts) { tk->xtime_sec = ts->tv_sec; - tk->xtime_nsec = ts->tv_nsec << tk->shift; + tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts) { tk->xtime_sec += ts->tv_sec; - tk->xtime_nsec += ts->tv_nsec << tk->shift; + tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift; + tk_normalize_xtime(tk); +} + +static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm) +{ + struct timespec tmp; + + /* + * Verify consistency of: offset_real = -wall_to_monotonic + * before modifying anything + */ + set_normalized_timespec(&tmp, -tk->wall_to_monotonic.tv_sec, + -tk->wall_to_monotonic.tv_nsec); + WARN_ON_ONCE(tk->offs_real.tv64 != timespec_to_ktime(tmp).tv64); + tk->wall_to_monotonic = wtm; + set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec); + tk->offs_real = timespec_to_ktime(tmp); +} + +static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t) +{ + /* Verify consistency before modifying */ + WARN_ON_ONCE(tk->offs_boot.tv64 != timespec_to_ktime(tk->total_sleep_time).tv64); + + tk->total_sleep_time = t; + tk->offs_boot = timespec_to_ktime(t); } /** @@ -217,14 +243,6 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) return nsec + arch_gettimeoffset(); } -static void update_rt_offset(struct timekeeper *tk) -{ - struct timespec tmp, *wtm = &tk->wall_to_monotonic; - - set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec); - tk->offs_real = timespec_to_ktime(tmp); -} - /* must hold write on timekeeper.lock */ static void timekeeping_update(struct timekeeper *tk, bool clearntp) { @@ -234,12 +252,10 @@ static void timekeeping_update(struct timekeeper *tk, bool clearntp) tk->ntp_error = 0; ntp_clear(); } - update_rt_offset(tk); xt = tk_xtime(tk); update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); } - /** * timekeeping_forward_now - update clock to the current time * @@ -261,7 +277,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk->xtime_nsec += cycle_delta * tk->mult; /* If arch requires, add in gettimeoffset() */ - tk->xtime_nsec += arch_gettimeoffset() << tk->shift; + tk->xtime_nsec += (u64)arch_gettimeoffset() << tk->shift; tk_normalize_xtime(tk); @@ -277,38 +293,39 @@ static void timekeeping_forward_now(struct timekeeper *tk) */ void getnstimeofday(struct timespec *ts) { + struct timekeeper *tk = &timekeeper; unsigned long seq; s64 nsecs = 0; WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - ts->tv_sec = timekeeper.xtime_sec; - ts->tv_nsec = timekeeping_get_ns(&timekeeper); + ts->tv_sec = tk->xtime_sec; + nsecs = timekeeping_get_ns(tk); - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); + ts->tv_nsec = 0; timespec_add_ns(ts, nsecs); } EXPORT_SYMBOL(getnstimeofday); ktime_t ktime_get(void) { + struct timekeeper *tk = &timekeeper; unsigned int seq; s64 secs, nsecs; WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&timekeeper.lock); - secs = timekeeper.xtime_sec + - timekeeper.wall_to_monotonic.tv_sec; - nsecs = timekeeping_get_ns(&timekeeper) + - timekeeper.wall_to_monotonic.tv_nsec; + seq = read_seqbegin(&tk->lock); + secs = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; + nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec; - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); /* * Use ktime_set/ktime_add_ns to create a proper ktime on * 32-bit architectures without CONFIG_KTIME_SCALAR. @@ -327,21 +344,24 @@ EXPORT_SYMBOL_GPL(ktime_get); */ void ktime_get_ts(struct timespec *ts) { + struct timekeeper *tk = &timekeeper; struct timespec tomono; + s64 nsec; unsigned int seq; WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&timekeeper.lock); - ts->tv_sec = timekeeper.xtime_sec; - ts->tv_nsec = timekeeping_get_ns(&timekeeper); - tomono = timekeeper.wall_to_monotonic; + seq = read_seqbegin(&tk->lock); + ts->tv_sec = tk->xtime_sec; + nsec = timekeeping_get_ns(tk); + tomono = tk->wall_to_monotonic; - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); - set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, - ts->tv_nsec + tomono.tv_nsec); + ts->tv_sec += tomono.tv_sec; + ts->tv_nsec = 0; + timespec_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts); @@ -358,22 +378,23 @@ EXPORT_SYMBOL_GPL(ktime_get_ts); */ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) { + struct timekeeper *tk = &timekeeper; unsigned long seq; s64 nsecs_raw, nsecs_real; WARN_ON_ONCE(timekeeping_suspended); do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - *ts_raw = timekeeper.raw_time; - ts_real->tv_sec = timekeeper.xtime_sec; + *ts_raw = tk->raw_time; + ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; - nsecs_raw = timekeeping_get_ns_raw(&timekeeper); - nsecs_real = timekeeping_get_ns(&timekeeper); + nsecs_raw = timekeeping_get_ns_raw(tk); + nsecs_real = timekeeping_get_ns(tk); - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -406,28 +427,28 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(const struct timespec *tv) { + struct timekeeper *tk = &timekeeper; struct timespec ts_delta, xt; unsigned long flags; - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) + if (!timespec_valid_strict(tv)) return -EINVAL; - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); - timekeeping_forward_now(&timekeeper); + timekeeping_forward_now(tk); - xt = tk_xtime(&timekeeper); + xt = tk_xtime(tk); ts_delta.tv_sec = tv->tv_sec - xt.tv_sec; ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec; - timekeeper.wall_to_monotonic = - timespec_sub(timekeeper.wall_to_monotonic, ts_delta); + tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, ts_delta)); - tk_set_xtime(&timekeeper, tv); + tk_set_xtime(tk, tv); - timekeeping_update(&timekeeper, true); + timekeeping_update(tk, true); - write_sequnlock_irqrestore(&timekeeper.lock, flags); + write_sequnlock_irqrestore(&tk->lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -436,7 +457,6 @@ int do_settimeofday(const struct timespec *tv) } EXPORT_SYMBOL(do_settimeofday); - /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @tv: pointer to the timespec variable containing the offset @@ -445,28 +465,37 @@ EXPORT_SYMBOL(do_settimeofday); */ int timekeeping_inject_offset(struct timespec *ts) { + struct timekeeper *tk = &timekeeper; unsigned long flags; + struct timespec tmp; + int ret = 0; if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); - timekeeping_forward_now(&timekeeper); + timekeeping_forward_now(tk); + /* Make sure the proposed value is valid */ + tmp = timespec_add(tk_xtime(tk), *ts); + if (!timespec_valid_strict(&tmp)) { + ret = -EINVAL; + goto error; + } - tk_xtime_add(&timekeeper, ts); - timekeeper.wall_to_monotonic = - timespec_sub(timekeeper.wall_to_monotonic, *ts); + tk_xtime_add(tk, ts); + tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); - timekeeping_update(&timekeeper, true); +error: /* even if we error out, we forwarded the time, so call update */ + timekeeping_update(tk, true); - write_sequnlock_irqrestore(&timekeeper.lock, flags); + write_sequnlock_irqrestore(&tk->lock, flags); /* signal hrtimers about time change */ clock_was_set(); - return 0; + return ret; } EXPORT_SYMBOL(timekeeping_inject_offset); @@ -477,23 +506,24 @@ EXPORT_SYMBOL(timekeeping_inject_offset); */ static int change_clocksource(void *data) { + struct timekeeper *tk = &timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); - timekeeping_forward_now(&timekeeper); + timekeeping_forward_now(tk); if (!new->enable || new->enable(new) == 0) { - old = timekeeper.clock; - tk_setup_internals(&timekeeper, new); + old = tk->clock; + tk_setup_internals(tk, new); if (old->disable) old->disable(old); } - timekeeping_update(&timekeeper, true); + timekeeping_update(tk, true); - write_sequnlock_irqrestore(&timekeeper.lock, flags); + write_sequnlock_irqrestore(&tk->lock, flags); return 0; } @@ -507,7 +537,9 @@ static int change_clocksource(void *data) */ void timekeeping_notify(struct clocksource *clock) { - if (timekeeper.clock == clock) + struct timekeeper *tk = &timekeeper; + + if (tk->clock == clock) return; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); @@ -536,35 +568,36 @@ EXPORT_SYMBOL_GPL(ktime_get_real); */ void getrawmonotonic(struct timespec *ts) { + struct timekeeper *tk = &timekeeper; unsigned long seq; s64 nsecs; do { - seq = read_seqbegin(&timekeeper.lock); - nsecs = timekeeping_get_ns_raw(&timekeeper); - *ts = timekeeper.raw_time; + seq = read_seqbegin(&tk->lock); + nsecs = timekeeping_get_ns_raw(tk); + *ts = tk->raw_time; - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); timespec_add_ns(ts, nsecs); } EXPORT_SYMBOL(getrawmonotonic); - /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { + struct timekeeper *tk = &timekeeper; unsigned long seq; int ret; do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); return ret; } @@ -574,15 +607,16 @@ int timekeeping_valid_for_hres(void) */ u64 timekeeping_max_deferment(void) { + struct timekeeper *tk = &timekeeper; unsigned long seq; u64 ret; do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - ret = timekeeper.clock->max_idle_ns; + ret = tk->clock->max_idle_ns; - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); return ret; } @@ -622,46 +656,56 @@ void __attribute__((weak)) read_boot_clock(struct timespec *ts) */ void __init timekeeping_init(void) { + struct timekeeper *tk = &timekeeper; struct clocksource *clock; unsigned long flags; - struct timespec now, boot; + struct timespec now, boot, tmp; read_persistent_clock(&now); + if (!timespec_valid_strict(&now)) { + pr_warn("WARNING: Persistent clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + now.tv_sec = 0; + now.tv_nsec = 0; + } + read_boot_clock(&boot); + if (!timespec_valid_strict(&boot)) { + pr_warn("WARNING: Boot clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + boot.tv_sec = 0; + boot.tv_nsec = 0; + } - seqlock_init(&timekeeper.lock); + seqlock_init(&tk->lock); ntp_init(); - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); - tk_setup_internals(&timekeeper, clock); + tk_setup_internals(tk, clock); - tk_set_xtime(&timekeeper, &now); - timekeeper.raw_time.tv_sec = 0; - timekeeper.raw_time.tv_nsec = 0; + tk_set_xtime(tk, &now); + tk->raw_time.tv_sec = 0; + tk->raw_time.tv_nsec = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) - boot = tk_xtime(&timekeeper); - - set_normalized_timespec(&timekeeper.wall_to_monotonic, - -boot.tv_sec, -boot.tv_nsec); - update_rt_offset(&timekeeper); - timekeeper.total_sleep_time.tv_sec = 0; - timekeeper.total_sleep_time.tv_nsec = 0; - write_sequnlock_irqrestore(&timekeeper.lock, flags); + boot = tk_xtime(tk); + + set_normalized_timespec(&tmp, -boot.tv_sec, -boot.tv_nsec); + tk_set_wall_to_mono(tk, tmp); + + tmp.tv_sec = 0; + tmp.tv_nsec = 0; + tk_set_sleep_time(tk, tmp); + + write_sequnlock_irqrestore(&tk->lock, flags); } /* time in seconds when suspend began */ static struct timespec timekeeping_suspend_time; -static void update_sleep_time(struct timespec t) -{ - timekeeper.total_sleep_time = t; - timekeeper.offs_boot = timespec_to_ktime(t); -} - /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @delta: pointer to a timespec delta value @@ -672,18 +716,16 @@ static void update_sleep_time(struct timespec t) static void __timekeeping_inject_sleeptime(struct timekeeper *tk, struct timespec *delta) { - if (!timespec_valid(delta)) { + if (!timespec_valid_strict(delta)) { printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } - tk_xtime_add(tk, delta); - tk->wall_to_monotonic = timespec_sub(tk->wall_to_monotonic, *delta); - update_sleep_time(timespec_add(tk->total_sleep_time, *delta)); + tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta)); + tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta)); } - /** * timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec delta value @@ -696,6 +738,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ void timekeeping_inject_sleeptime(struct timespec *delta) { + struct timekeeper *tk = &timekeeper; unsigned long flags; struct timespec ts; @@ -704,21 +747,20 @@ void timekeeping_inject_sleeptime(struct timespec *delta) if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) return; - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); - timekeeping_forward_now(&timekeeper); + timekeeping_forward_now(tk); - __timekeeping_inject_sleeptime(&timekeeper, delta); + __timekeeping_inject_sleeptime(tk, delta); - timekeeping_update(&timekeeper, true); + timekeeping_update(tk, true); - write_sequnlock_irqrestore(&timekeeper.lock, flags); + write_sequnlock_irqrestore(&tk->lock, flags); /* signal hrtimers about time change */ clock_was_set(); } - /** * timekeeping_resume - Resumes the generic timekeeping subsystem. * @@ -728,6 +770,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) */ static void timekeeping_resume(void) { + struct timekeeper *tk = &timekeeper; unsigned long flags; struct timespec ts; @@ -735,18 +778,18 @@ static void timekeeping_resume(void) clocksource_resume(); - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); - __timekeeping_inject_sleeptime(&timekeeper, &ts); + __timekeeping_inject_sleeptime(tk, &ts); } /* re-base the last cycle value */ - timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); - timekeeper.ntp_error = 0; + tk->clock->cycle_last = tk->clock->read(tk->clock); + tk->ntp_error = 0; timekeeping_suspended = 0; - timekeeping_update(&timekeeper, false); - write_sequnlock_irqrestore(&timekeeper.lock, flags); + timekeeping_update(tk, false); + write_sequnlock_irqrestore(&tk->lock, flags); touch_softlockup_watchdog(); @@ -758,14 +801,15 @@ static void timekeeping_resume(void) static int timekeeping_suspend(void) { + struct timekeeper *tk = &timekeeper; unsigned long flags; struct timespec delta, delta_delta; static struct timespec old_delta; read_persistent_clock(&timekeeping_suspend_time); - write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeping_forward_now(&timekeeper); + write_seqlock_irqsave(&tk->lock, flags); + timekeeping_forward_now(tk); timekeeping_suspended = 1; /* @@ -774,7 +818,7 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(tk_xtime(&timekeeper), timekeeping_suspend_time); + delta = timespec_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* @@ -787,7 +831,7 @@ static int timekeeping_suspend(void) timekeeping_suspend_time = timespec_add(timekeeping_suspend_time, delta_delta); } - write_sequnlock_irqrestore(&timekeeper.lock, flags); + write_sequnlock_irqrestore(&tk->lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); clocksource_suspend(); @@ -898,27 +942,29 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * the error. This causes the likely below to be unlikely. * * The proper fix is to avoid rounding up by using - * the high precision timekeeper.xtime_nsec instead of + * the high precision tk->xtime_nsec instead of * xtime.tv_nsec everywhere. Fixing this will take some * time. */ if (likely(error <= interval)) adj = 1; else - adj = timekeeping_bigadjust(tk, error, &interval, - &offset); - } else if (error < -interval) { - /* See comment above, this is just switched for the negative */ - error >>= 2; - if (likely(error >= -interval)) { - adj = -1; - interval = -interval; - offset = -offset; - } else - adj = timekeeping_bigadjust(tk, error, &interval, - &offset); - } else - return; + adj = timekeeping_bigadjust(tk, error, &interval, &offset); + } else { + if (error < -interval) { + /* See comment above, this is just switched for the negative */ + error >>= 2; + if (likely(error >= -interval)) { + adj = -1; + interval = -interval; + offset = -offset; + } else { + adj = timekeeping_bigadjust(tk, error, &interval, &offset); + } + } else { + goto out_adjust; + } + } if (unlikely(tk->clock->maxadj && (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) { @@ -981,6 +1027,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) tk->xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; +out_adjust: /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource @@ -1003,7 +1050,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) } - /** * accumulate_nsecs_to_secs - Accumulates nsecs into secs * @@ -1024,15 +1070,21 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); - tk->xtime_sec += leap; - tk->wall_to_monotonic.tv_sec -= leap; - if (leap) - clock_was_set_delayed(); + if (unlikely(leap)) { + struct timespec ts; + + tk->xtime_sec += leap; + + ts.tv_sec = leap; + ts.tv_nsec = 0; + tk_set_wall_to_mono(tk, + timespec_sub(tk->wall_to_monotonic, ts)); + clock_was_set_delayed(); + } } } - /** * logarithmic_accumulation - shifted accumulation of cycles * @@ -1076,7 +1128,6 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, return offset; } - /** * update_wall_time - Uses the current clocksource to increment the wall time * @@ -1084,25 +1135,30 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, static void update_wall_time(void) { struct clocksource *clock; + struct timekeeper *tk = &timekeeper; cycle_t offset; int shift = 0, maxshift; unsigned long flags; s64 remainder; - write_seqlock_irqsave(&timekeeper.lock, flags); + write_seqlock_irqsave(&tk->lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; - clock = timekeeper.clock; + clock = tk->clock; #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET - offset = timekeeper.cycle_interval; + offset = tk->cycle_interval; #else offset = (clock->read(clock) - clock->cycle_last) & clock->mask; #endif + /* Check if there's really nothing to do */ + if (offset < tk->cycle_interval) + goto out; + /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, @@ -1111,19 +1167,19 @@ static void update_wall_time(void) * chunk in one go, and then try to consume the next smaller * doubled multiple. */ - shift = ilog2(offset) - ilog2(timekeeper.cycle_interval); + shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); - while (offset >= timekeeper.cycle_interval) { - offset = logarithmic_accumulation(&timekeeper, offset, shift); - if(offset < timekeeper.cycle_interval<<shift) + while (offset >= tk->cycle_interval) { + offset = logarithmic_accumulation(tk, offset, shift); + if (offset < tk->cycle_interval<<shift) shift--; } /* correct the clock when NTP error is too big */ - timekeeping_adjust(&timekeeper, offset); + timekeeping_adjust(tk, offset); /* @@ -1135,21 +1191,21 @@ static void update_wall_time(void) * the vsyscall implementations are converted to use xtime_nsec * (shifted nanoseconds), this can be killed. */ - remainder = timekeeper.xtime_nsec & ((1 << timekeeper.shift) - 1); - timekeeper.xtime_nsec -= remainder; - timekeeper.xtime_nsec += 1 << timekeeper.shift; - timekeeper.ntp_error += remainder << timekeeper.ntp_error_shift; + remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); + tk->xtime_nsec -= remainder; + tk->xtime_nsec += 1ULL << tk->shift; + tk->ntp_error += remainder << tk->ntp_error_shift; /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ - accumulate_nsecs_to_secs(&timekeeper); + accumulate_nsecs_to_secs(tk); - timekeeping_update(&timekeeper, false); + timekeeping_update(tk, false); out: - write_sequnlock_irqrestore(&timekeeper.lock, flags); + write_sequnlock_irqrestore(&tk->lock, flags); } @@ -1166,18 +1222,18 @@ out: */ void getboottime(struct timespec *ts) { + struct timekeeper *tk = &timekeeper; struct timespec boottime = { - .tv_sec = timekeeper.wall_to_monotonic.tv_sec + - timekeeper.total_sleep_time.tv_sec, - .tv_nsec = timekeeper.wall_to_monotonic.tv_nsec + - timekeeper.total_sleep_time.tv_nsec + .tv_sec = tk->wall_to_monotonic.tv_sec + + tk->total_sleep_time.tv_sec, + .tv_nsec = tk->wall_to_monotonic.tv_nsec + + tk->total_sleep_time.tv_nsec }; set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); } EXPORT_SYMBOL_GPL(getboottime); - /** * get_monotonic_boottime - Returns monotonic time since boot * @ts: pointer to the timespec to be set @@ -1189,22 +1245,25 @@ EXPORT_SYMBOL_GPL(getboottime); */ void get_monotonic_boottime(struct timespec *ts) { + struct timekeeper *tk = &timekeeper; struct timespec tomono, sleep; + s64 nsec; unsigned int seq; WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&timekeeper.lock); - ts->tv_sec = timekeeper.xtime_sec; - ts->tv_nsec = timekeeping_get_ns(&timekeeper); - tomono = timekeeper.wall_to_monotonic; - sleep = timekeeper.total_sleep_time; + seq = read_seqbegin(&tk->lock); + ts->tv_sec = tk->xtime_sec; + nsec = timekeeping_get_ns(tk); + tomono = tk->wall_to_monotonic; + sleep = tk->total_sleep_time; - } while (read_seqretry(&timekeeper.lock, seq)); + } while (read_seqretry(&tk->lock, seq)); - set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, - ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec); + ts->tv_sec += tomono.tv_sec + sleep.tv_sec; + ts->tv_nsec = 0; + timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec); } EXPORT_SYMBOL_GPL(get_monotonic_boottime); @@ -1231,31 +1290,38 @@ EXPORT_SYMBOL_GPL(ktime_get_boottime); */ void monotonic_to_bootbased(struct timespec *ts) { - *ts = timespec_add(*ts, timekeeper.total_sleep_time); + struct timekeeper *tk = &timekeeper; + + *ts = timespec_add(*ts, tk->total_sleep_time); } EXPORT_SYMBOL_GPL(monotonic_to_bootbased); unsigned long get_seconds(void) { - return timekeeper.xtime_sec; + struct timekeeper *tk = &timekeeper; + + return tk->xtime_sec; } EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - return tk_xtime(&timekeeper); + struct timekeeper *tk = &timekeeper; + + return tk_xtime(tk); } struct timespec current_kernel_time(void) { + struct timekeeper *tk = &timekeeper; struct timespec now; unsigned long seq; do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - now = tk_xtime(&timekeeper); - } while (read_seqretry(&timekeeper.lock, seq)); + now = tk_xtime(tk); + } while (read_seqretry(&tk->lock, seq)); return now; } @@ -1263,15 +1329,16 @@ EXPORT_SYMBOL(current_kernel_time); struct timespec get_monotonic_coarse(void) { + struct timekeeper *tk = &timekeeper; struct timespec now, mono; unsigned long seq; do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - now = tk_xtime(&timekeeper); - mono = timekeeper.wall_to_monotonic; - } while (read_seqretry(&timekeeper.lock, seq)); + now = tk_xtime(tk); + mono = tk->wall_to_monotonic; + } while (read_seqretry(&tk->lock, seq)); set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); @@ -1300,14 +1367,15 @@ void do_timer(unsigned long ticks) void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, struct timespec *wtom, struct timespec *sleep) { + struct timekeeper *tk = &timekeeper; unsigned long seq; do { - seq = read_seqbegin(&timekeeper.lock); - *xtim = tk_xtime(&timekeeper); - *wtom = timekeeper.wall_to_monotonic; - *sleep = timekeeper.total_sleep_time; - } while (read_seqretry(&timekeeper.lock, seq)); + seq = read_seqbegin(&tk->lock); + *xtim = tk_xtime(tk); + *wtom = tk->wall_to_monotonic; + *sleep = tk->total_sleep_time; + } while (read_seqretry(&tk->lock, seq)); } #ifdef CONFIG_HIGH_RES_TIMERS @@ -1321,19 +1389,20 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, */ ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot) { + struct timekeeper *tk = &timekeeper; ktime_t now; unsigned int seq; u64 secs, nsecs; do { - seq = read_seqbegin(&timekeeper.lock); + seq = read_seqbegin(&tk->lock); - secs = timekeeper.xtime_sec; - nsecs = timekeeping_get_ns(&timekeeper); + secs = tk->xtime_sec; + nsecs = timekeeping_get_ns(tk); - *offs_real = timekeeper.offs_real; - *offs_boot = timekeeper.offs_boot; - } while (read_seqretry(&timekeeper.lock, seq)); + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + } while (read_seqretry(&tk->lock, seq)); now = ktime_add_ns(ktime_set(secs, 0), nsecs); now = ktime_sub(now, *offs_real); @@ -1346,19 +1415,19 @@ ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot) */ ktime_t ktime_get_monotonic_offset(void) { + struct timekeeper *tk = &timekeeper; unsigned long seq; struct timespec wtom; do { - seq = read_seqbegin(&timekeeper.lock); - wtom = timekeeper.wall_to_monotonic; - } while (read_seqretry(&timekeeper.lock, seq)); + seq = read_seqbegin(&tk->lock); + wtom = tk->wall_to_monotonic; + } while (read_seqretry(&tk->lock, seq)); return timespec_to_ktime(wtom); } EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); - /** * xtime_update() - advances the timekeeping infrastructure * @ticks: number of ticks, that have elapsed since the last call. diff --git a/kernel/timer.c b/kernel/timer.c index 706fe4c53e8..d5de1b2292a 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1393,13 +1393,6 @@ SYSCALL_DEFINE1(alarm, unsigned int, seconds) #endif -#ifndef __alpha__ - -/* - * The Alpha uses getxpid, getxuid, and getxgid instead. Maybe this - * should be moved into arch/i386 instead? - */ - /** * sys_getpid - return the thread group id of the current process * @@ -1455,8 +1448,6 @@ SYSCALL_DEFINE0(getegid) return from_kgid_munged(current_user_ns(), current_egid()); } -#endif - static void process_timeout(unsigned long __data) { wake_up_process((struct task_struct *)__data); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8c4c07071cc..4cea4f41c1d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -49,6 +49,11 @@ config HAVE_SYSCALL_TRACEPOINTS help See Documentation/trace/ftrace-design.txt +config HAVE_FENTRY + bool + help + Arch supports the gcc options -pg with -mfentry + config HAVE_C_RECORDMCOUNT bool help @@ -57,8 +62,12 @@ config HAVE_C_RECORDMCOUNT config TRACER_MAX_TRACE bool +config TRACE_CLOCK + bool + config RING_BUFFER bool + select TRACE_CLOCK config FTRACE_NMI_ENTER bool @@ -109,6 +118,7 @@ config TRACING select NOP_TRACER select BINARY_PRINTF select EVENT_TRACING + select TRACE_CLOCK config GENERIC_TRACER bool diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index b831087c820..d7e2068e4b7 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -5,10 +5,12 @@ ifdef CONFIG_FUNCTION_TRACER ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +ifdef CONFIG_FTRACE_SELFTEST # selftest needs instrumentation CFLAGS_trace_selftest_dynamic.o = -pg obj-y += trace_selftest_dynamic.o endif +endif # If unlikely tracing is enabled, do not trace these files ifdef CONFIG_TRACING_BRANCHES @@ -17,11 +19,7 @@ endif CFLAGS_trace_events_filter.o := -I$(src) -# -# Make the trace clocks available generally: it's infrastructure -# relied on by ptrace for example: -# -obj-y += trace_clock.o +obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a008663d86c..9dcf15d3838 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -64,12 +64,20 @@ #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL) +static struct ftrace_ops ftrace_list_end __read_mostly = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; /* Quick disabling of function tracer. */ -int function_trace_stop; +int function_trace_stop __read_mostly; + +/* Current function tracing op */ +struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* List for set_ftrace_pid's pids. */ LIST_HEAD(ftrace_pids); @@ -86,22 +94,43 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops ftrace_list_end __read_mostly = { - .func = ftrace_stub, -}; - static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; -static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; -ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); +#else +/* See comment below, where ftrace_ops_list_func is defined */ +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); +#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +#endif + +/** + * ftrace_nr_registered_ops - return number of ops registered + * + * Returns the number of ftrace_ops registered and tracing functions + */ +int ftrace_nr_registered_ops(void) +{ + struct ftrace_ops *ops; + int cnt = 0; + + mutex_lock(&ftrace_lock); + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) + cnt++; + + mutex_unlock(&ftrace_lock); + + return cnt; +} /* * Traverse the ftrace_global_list, invoking all entries. The reason that we @@ -112,29 +141,29 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_global_list_func(unsigned long ip, - unsigned long parent_ip) +static void +ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) return; trace_recursion_set(TRACE_GLOBAL_BIT); op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); /*see above*/ }; trace_recursion_clear(TRACE_GLOBAL_BIT); } -static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { if (!test_tsk_trace_trace(current)) return; - ftrace_pid_function(ip, parent_ip); + ftrace_pid_function(ip, parent_ip, op, regs); } static void set_ftrace_pid_function(ftrace_func_t func) @@ -153,25 +182,9 @@ static void set_ftrace_pid_function(ftrace_func_t func) void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; - __ftrace_trace_function = ftrace_stub; - __ftrace_trace_function_delay = ftrace_stub; ftrace_pid_function = ftrace_stub; } -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST -/* - * For those archs that do not test ftrace_trace_stop in their - * mcount call site, we need to do it from C. - */ -static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) -{ - if (function_trace_stop) - return; - - __ftrace_trace_function(ip, parent_ip); -} -#endif - static void control_ops_disable_all(struct ftrace_ops *ops) { int cpu; @@ -230,28 +243,27 @@ static void update_ftrace_function(void) /* * If we are at the end of the list and this ops is - * not dynamic, then have the mcount trampoline call - * the function directly + * recursion safe and not dynamic and the arch supports passing ops, + * then have the mcount trampoline call the function directly. */ if (ftrace_ops_list == &ftrace_list_end || (ftrace_ops_list->next == &ftrace_list_end && - !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && + (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) && + !FTRACE_FORCE_LIST_FUNC)) { + /* Set the ftrace_ops that the arch callback uses */ + if (ftrace_ops_list == &global_ops) + function_trace_op = ftrace_global_list; + else + function_trace_op = ftrace_ops_list; func = ftrace_ops_list->func; - else + } else { + /* Just use the default ftrace_ops */ + function_trace_op = &ftrace_list_end; func = ftrace_ops_list_func; + } -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; -#else -#ifdef CONFIG_DYNAMIC_FTRACE - /* do not update till all functions have been modified */ - __ftrace_trace_function_delay = func; -#else - __ftrace_trace_function = func; -#endif - ftrace_trace_function = - (func == ftrace_stub) ? func : ftrace_test_stop_func; -#endif } static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) @@ -312,7 +324,7 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { - if (ftrace_disabled) + if (unlikely(ftrace_disabled)) return -ENODEV; if (FTRACE_WARN_ON(ops == &global_ops)) @@ -325,6 +337,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) return -EINVAL; +#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS + /* + * If the ftrace_ops specifies SAVE_REGS, then it only can be used + * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. + * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS && + !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)) + return -EINVAL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) + ops->flags |= FTRACE_OPS_FL_SAVE_REGS; +#endif + if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; @@ -773,7 +799,8 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) } static void -function_profile_call(unsigned long ip, unsigned long parent_ip) +function_profile_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; @@ -803,7 +830,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip) #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - function_profile_call(trace->func, 0); + function_profile_call(trace->func, 0, NULL, NULL); return 1; } @@ -863,6 +890,7 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int register_ftrace_profiler(void) @@ -1045,6 +1073,7 @@ static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, .filter_hash = EMPTY_HASH, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static DEFINE_MUTEX(ftrace_regex_lock); @@ -1525,6 +1554,12 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags++; if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) return; + /* + * If any ops wants regs saved for this function + * then all ops will get saved regs. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) return; @@ -1616,18 +1651,59 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) if (enable && (rec->flags & ~FTRACE_FL_MASK)) flag = FTRACE_FL_ENABLED; + /* + * If enabling and the REGS flag does not match the REGS_EN, then + * do not ignore this record. Set flags to fail the compare against + * ENABLED. + */ + if (flag && + (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN))) + flag |= FTRACE_FL_REGS; + /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) return FTRACE_UPDATE_IGNORE; if (flag) { - if (update) + /* Save off if rec is being enabled (for return value) */ + flag ^= rec->flags & FTRACE_FL_ENABLED; + + if (update) { rec->flags |= FTRACE_FL_ENABLED; - return FTRACE_UPDATE_MAKE_CALL; + if (flag & FTRACE_FL_REGS) { + if (rec->flags & FTRACE_FL_REGS) + rec->flags |= FTRACE_FL_REGS_EN; + else + rec->flags &= ~FTRACE_FL_REGS_EN; + } + } + + /* + * If this record is being updated from a nop, then + * return UPDATE_MAKE_CALL. + * Otherwise, if the EN flag is set, then return + * UPDATE_MODIFY_CALL_REGS to tell the caller to convert + * from the non-save regs, to a save regs function. + * Otherwise, + * return UPDATE_MODIFY_CALL to tell the caller to convert + * from the save regs, to a non-save regs function. + */ + if (flag & FTRACE_FL_ENABLED) + return FTRACE_UPDATE_MAKE_CALL; + else if (rec->flags & FTRACE_FL_REGS_EN) + return FTRACE_UPDATE_MODIFY_CALL_REGS; + else + return FTRACE_UPDATE_MODIFY_CALL; } - if (update) - rec->flags &= ~FTRACE_FL_ENABLED; + if (update) { + /* If there's no more users, clear all flags */ + if (!(rec->flags & ~FTRACE_FL_MASK)) + rec->flags = 0; + else + /* Just disable the record (keep REGS state) */ + rec->flags &= ~FTRACE_FL_ENABLED; + } return FTRACE_UPDATE_MAKE_NOP; } @@ -1662,13 +1738,17 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { + unsigned long ftrace_old_addr; unsigned long ftrace_addr; int ret; - ftrace_addr = (unsigned long)FTRACE_ADDR; - ret = ftrace_update_record(rec, enable); + if (rec->flags & FTRACE_FL_REGS) + ftrace_addr = (unsigned long)FTRACE_REGS_ADDR; + else + ftrace_addr = (unsigned long)FTRACE_ADDR; + switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; @@ -1678,6 +1758,15 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) case FTRACE_UPDATE_MAKE_NOP: return ftrace_make_nop(NULL, rec, ftrace_addr); + + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + if (rec->flags & FTRACE_FL_REGS) + ftrace_old_addr = (unsigned long)FTRACE_ADDR; + else + ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR; + + return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } return -1; /* unknow ftrace bug */ @@ -1882,16 +1971,6 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* - * For archs that call ftrace_test_stop_func(), we must - * wait till after we update all the function callers - * before we update the callback. This keeps different - * ops that record different functions from corrupting - * each other. - */ - __ftrace_trace_function = __ftrace_trace_function_delay; -#endif function_trace_stop--; ret = ftrace_arch_code_modify_post_process(); @@ -2441,8 +2520,9 @@ static int t_show(struct seq_file *m, void *v) seq_printf(m, "%ps", (void *)rec->ip); if (iter->flags & FTRACE_ITER_ENABLED) - seq_printf(m, " (%ld)", - rec->flags & ~FTRACE_FL_MASK); + seq_printf(m, " (%ld)%s", + rec->flags & ~FTRACE_FL_MASK, + rec->flags & FTRACE_FL_REGS ? " R" : ""); seq_printf(m, "\n"); return 0; @@ -2790,8 +2870,8 @@ static int __init ftrace_mod_cmd_init(void) } device_initcall(ftrace_mod_cmd_init); -static void -function_trace_probe_call(unsigned long ip, unsigned long parent_ip) +static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ftrace_func_probe *entry; struct hlist_head *hhd; @@ -3162,8 +3242,27 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable) +ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) +{ + struct ftrace_func_entry *entry; + + if (!ftrace_location(ip)) + return -EINVAL; + + if (remove) { + entry = ftrace_lookup_ip(hash, ip); + if (!entry) + return -ENOENT; + free_hash_entry(hash, entry); + return 0; + } + + return add_hash_entry(hash, ip); +} + +static int +ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, + unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -3192,6 +3291,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, ret = -EINVAL; goto out_regex_unlock; } + if (ip) { + ret = ftrace_match_addr(hash, ip, remove); + if (ret < 0) + goto out_regex_unlock; + } mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); @@ -3208,6 +3312,37 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, return ret; } +static int +ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, + int reset, int enable) +{ + return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); +} + +/** + * ftrace_set_filter_ip - set a function to filter on in ftrace by address + * @ops - the ops to set the filter with + * @ip - the address to add to or remove from the filter. + * @remove - non zero to remove the ip from the filter + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled + * If @ip is NULL, it failes to update filter. + */ +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset) +{ + return ftrace_set_addr(ops, ip, remove, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); + +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) +{ + return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable); +} + /** * ftrace_set_filter - set a function to filter on in ftrace * @ops - the ops to set the filter with @@ -3912,6 +4047,7 @@ void __init ftrace_init(void) static struct ftrace_ops global_ops = { .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int __init ftrace_nodyn_init(void) @@ -3942,10 +4078,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) #endif /* CONFIG_DYNAMIC_FTRACE */ static void -ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) return; @@ -3959,7 +4094,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) while (op != &ftrace_list_end) { if (!ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; @@ -3969,13 +4104,18 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops control_ops = { .func = ftrace_ops_control_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +static inline void +__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ignored, struct pt_regs *regs) { struct ftrace_ops *op; + if (function_trace_stop) + return; + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) return; @@ -3988,13 +4128,39 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); trace_recursion_clear(TRACE_INTERNAL_BIT); } +/* + * Some archs only support passing ip and parent_ip. Even though + * the list function ignores the op parameter, we do not want any + * C side effects, where a function is called without the caller + * sending a third parameter. + * Archs are to support both the regs and ftrace_ops at the same time. + * If they support ftrace_ops, it is assumed they support regs. + * If call backs want to use regs, they must either check for regs + * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS. + * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved. + * An architecture can pass partial regs with ftrace_ops and still + * set the ARCH_SUPPORT_FTARCE_OPS. + */ +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, regs); +} +#else +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); +} +#endif + static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -4299,16 +4465,12 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); - if (unlikely(ftrace_disabled)) - goto out_unlock; - ret = __register_ftrace_function(ops); if (!ret) ret = ftrace_startup(ops, 0); - - out_unlock: mutex_unlock(&ftrace_lock); + return ret; } EXPORT_SYMBOL_GPL(register_ftrace_function); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f765465bffe..b32ed0e385a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2816,7 +2816,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable); * to the buffer after this will fail and return NULL. * * This is different than ring_buffer_record_disable() as - * it works like an on/off switch, where as the disable() verison + * it works like an on/off switch, where as the disable() version * must be paired with a enable(). */ void ring_buffer_record_off(struct ring_buffer *buffer) @@ -2839,7 +2839,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_off); * ring_buffer_record_off(). * * This is different than ring_buffer_record_enable() as - * it works like an on/off switch, where as the enable() verison + * it works like an on/off switch, where as the enable() version * must be paired with a disable(). */ void ring_buffer_record_on(struct ring_buffer *buffer) @@ -3239,6 +3239,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) if (cpu_buffer->commit_page == cpu_buffer->reader_page) goto out; + /* Don't bother swapping if the ring buffer is empty */ + if (rb_num_of_entries(cpu_buffer) == 0) + goto out; + /* * Reset the reader page to size zero. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a7fa0702be1..1ec5c1dab62 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -328,7 +328,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | - TRACE_ITER_IRQ_INFO; + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); @@ -426,15 +426,15 @@ __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { - unsigned long threshhold; + unsigned long threshold; int ret; if (!str) return 0; - ret = strict_strtoul(str, 0, &threshhold); + ret = strict_strtoul(str, 0, &threshold); if (ret < 0) return 0; - tracing_thresh = threshhold * 1000; + tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); @@ -470,6 +470,7 @@ static const char *trace_options[] = { "overwrite", "disable_on_free", "irq-info", + "markers", NULL }; @@ -830,6 +831,8 @@ int register_tracer(struct tracer *type) current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ @@ -1708,9 +1711,11 @@ EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); + iter->idx++; - if (iter->buffer_iter[iter->cpu]) - ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); + if (buf_iter) + ring_buffer_read(buf_iter, NULL); } static struct trace_entry * @@ -1718,7 +1723,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; - struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu]; + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); @@ -1856,10 +1861,10 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) tr->data[cpu]->skipped_entries = 0; - if (!iter->buffer_iter[cpu]) + buf_iter = trace_buffer_iter(iter, cpu); + if (!buf_iter) return; - buf_iter = iter->buffer_iter[cpu]; ring_buffer_iter_reset(buf_iter); /* @@ -2205,13 +2210,15 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) int trace_empty(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { cpu = iter->cpu_file; - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2221,8 +2228,9 @@ int trace_empty(struct trace_iterator *iter) } for_each_tracing_cpu(cpu) { - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2381,6 +2389,11 @@ __tracing_open(struct inode *inode, struct file *file) if (!iter) return ERR_PTR(-ENOMEM); + iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), + GFP_KERNEL); + if (!iter->buffer_iter) + goto release; + /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. @@ -2441,6 +2454,8 @@ __tracing_open(struct inode *inode, struct file *file) fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); + kfree(iter->buffer_iter); +release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } @@ -2481,6 +2496,7 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); kfree(iter->trace); + kfree(iter->buffer_iter); seq_release_private(inode, file); return 0; } @@ -3172,10 +3188,10 @@ static int tracing_set_tracer(const char *buf) } destroy_trace_option_files(topts); - current_trace = t; + current_trace = &nop_trace; - topts = create_trace_option_files(current_trace); - if (current_trace->use_max_tr) { + topts = create_trace_option_files(t); + if (t->use_max_tr) { int cpu; /* we need to make per cpu buffer sizes equivalent */ for_each_tracing_cpu(cpu) { @@ -3195,6 +3211,7 @@ static int tracing_set_tracer(const char *buf) goto out; } + current_trace = t; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3870,6 +3887,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tracing_disabled) return -EINVAL; + if (!(trace_flags & TRACE_ITER_MARKERS)) + return -EINVAL; + if (cnt > TRACE_BUF_SIZE) cnt = TRACE_BUF_SIZE; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5aec220d2de..63a2da0b9a6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -317,6 +317,14 @@ struct tracer { #define TRACE_PIPE_ALL_CPU -1 +static inline struct ring_buffer_iter * +trace_buffer_iter(struct trace_iterator *iter, int cpu) +{ + if (iter->buffer_iter && iter->buffer_iter[cpu]) + return iter->buffer_iter[cpu]; + return NULL; +} + int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void trace_wake_up(void); @@ -464,11 +472,11 @@ extern void trace_find_cmdline(int pid, char comm[]); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +#endif #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); -#endif extern int ring_buffer_expanded; extern bool tracing_selftest_disabled; @@ -672,6 +680,7 @@ enum trace_iterator_flags { TRACE_ITER_OVERWRITE = 0x200000, TRACE_ITER_STOP_ON_FREE = 0x400000, TRACE_ITER_IRQ_INFO = 0x800000, + TRACE_ITER_MARKERS = 0x1000000, }; /* diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index fee3752ae8f..84b1e045fab 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -258,7 +258,8 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); #ifdef CONFIG_FUNCTION_TRACER static void -perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *pt_regs) { struct ftrace_entry *entry; struct hlist_head *head; @@ -281,7 +282,7 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) head = this_cpu_ptr(event_function.perf_events); perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, - 1, ®s, head); + 1, ®s, head, NULL); #undef ENTRY_SIZE } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 29111da1d10..d608d09d08c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1199,6 +1199,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return 0; } +static void event_remove(struct ftrace_event_call *call) +{ + ftrace_event_enable_disable(call, 0); + if (call->event.funcs) + __unregister_ftrace_event(&call->event); + list_del(&call->list); +} + +static int event_init(struct ftrace_event_call *call) +{ + int ret = 0; + + if (WARN_ON(!call->name)) + return -EINVAL; + + if (call->class->raw_init) { + ret = call->class->raw_init(call); + if (ret < 0 && ret != -ENOSYS) + pr_warn("Could not initialize trace events/%s\n", + call->name); + } + + return ret; +} + static int __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, const struct file_operations *id, @@ -1209,19 +1234,9 @@ __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, struct dentry *d_events; int ret; - /* The linker may leave blanks */ - if (!call->name) - return -EINVAL; - - if (call->class->raw_init) { - ret = call->class->raw_init(call); - if (ret < 0) { - if (ret != -ENOSYS) - pr_warning("Could not initialize trace events/%s\n", - call->name); - return ret; - } - } + ret = event_init(call); + if (ret < 0) + return ret; d_events = event_trace_events_dir(); if (!d_events) @@ -1272,13 +1287,10 @@ static void remove_subsystem_dir(const char *name) */ static void __trace_remove_event_call(struct ftrace_event_call *call) { - ftrace_event_enable_disable(call, 0); - if (call->event.funcs) - __unregister_ftrace_event(&call->event); - debugfs_remove_recursive(call->dir); - list_del(&call->list); + event_remove(call); trace_destroy_fields(call); destroy_preds(call); + debugfs_remove_recursive(call->dir); remove_subsystem_dir(call->class->system); } @@ -1450,15 +1462,43 @@ static __init int setup_trace_event(char *str) } __setup("trace_event=", setup_trace_event); +static __init int event_trace_enable(void) +{ + struct ftrace_event_call **iter, *call; + char *buf = bootup_event_buf; + char *token; + int ret; + + for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) { + + call = *iter; + ret = event_init(call); + if (!ret) + list_add(&call->list, &ftrace_events); + } + + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + ret = ftrace_set_clr_event(token, 1); + if (ret) + pr_warn("Failed to enable trace event: %s\n", token); + } + return 0; +} + static __init int event_trace_init(void) { - struct ftrace_event_call **call; + struct ftrace_event_call *call; struct dentry *d_tracer; struct dentry *entry; struct dentry *d_events; int ret; - char *buf = bootup_event_buf; - char *token; d_tracer = tracing_init_dentry(); if (!d_tracer) @@ -1497,24 +1537,19 @@ static __init int event_trace_init(void) if (trace_define_common_fields()) pr_warning("tracing: Failed to allocate common fields"); - for_each_event(call, __start_ftrace_events, __stop_ftrace_events) { - __trace_add_event_call(*call, NULL, &ftrace_event_id_fops, + /* + * Early initialization already enabled ftrace event. + * Now it's only necessary to create the event directory. + */ + list_for_each_entry(call, &ftrace_events, list) { + + ret = event_create_dir(call, d_events, + &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); - } - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; - if (!*token) - continue; - - ret = ftrace_set_clr_event(token, 1); - if (ret) - pr_warning("Failed to enable trace event: %s\n", token); + if (ret < 0) + event_remove(call); } ret = register_module_notifier(&trace_module_nb); @@ -1523,6 +1558,7 @@ static __init int event_trace_init(void) return 0; } +core_initcall(event_trace_enable); fs_initcall(event_trace_init); #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -1646,9 +1682,11 @@ static __init void event_trace_self_tests(void) event_test_stuff(); ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0); - if (WARN_ON_ONCE(ret)) + if (WARN_ON_ONCE(ret)) { pr_warning("error disabling system %s\n", system->name); + continue; + } pr_cont("OK\n"); } @@ -1681,7 +1719,8 @@ static __init void event_trace_self_tests(void) static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); static void -function_test_events_call(unsigned long ip, unsigned long parent_ip) +function_test_events_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ring_buffer_event *event; struct ring_buffer *buffer; @@ -1720,6 +1759,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __initdata = { .func = function_test_events_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static __init void event_trace_self_test_with_function(void) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 431dba8b754..c154797a7ff 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2002,7 +2002,7 @@ static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, static int __ftrace_function_set_filter(int filter, char *buf, int len, struct function_filter_data *data) { - int i, re_cnt, ret; + int i, re_cnt, ret = -EINVAL; int *reset; char **re; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index c7b0c6a7db0..483162a9f90 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -13,6 +13,7 @@ #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> +#include <linux/pstore.h> #include <linux/fs.h> #include "trace.h" @@ -48,7 +49,8 @@ static void function_trace_start(struct trace_array *tr) } static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -74,8 +76,18 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) preempt_enable_notrace(); } +/* Our two options */ +enum { + TRACE_FUNC_OPT_STACK = 0x1, + TRACE_FUNC_OPT_PSTORE = 0x2, +}; + +static struct tracer_flags func_flags; + static void -function_trace_call(unsigned long ip, unsigned long parent_ip) +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) + { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -97,6 +109,12 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { + /* + * So far tracing doesn't support multiple buffers, so + * we make an explicit call for now. + */ + if (unlikely(func_flags.val & TRACE_FUNC_OPT_PSTORE)) + pstore_ftrace_call(ip, parent_ip); pc = preempt_count(); trace_function(tr, ip, parent_ip, flags, pc); } @@ -106,7 +124,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) } static void -function_stack_trace_call(unsigned long ip, unsigned long parent_ip) +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -149,24 +168,22 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops trace_stack_ops __read_mostly = { .func = function_stack_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, -}; - -/* Our two options */ -enum { - TRACE_FUNC_OPT_STACK = 0x1, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct tracer_opt func_opts[] = { #ifdef CONFIG_STACKTRACE { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, #endif +#ifdef CONFIG_PSTORE_FTRACE + { TRACER_OPT(func_pstore, TRACE_FUNC_OPT_PSTORE) }, +#endif { } /* Always set a last empty entry */ }; @@ -204,10 +221,11 @@ static void tracing_stop_function_trace(void) static int func_set_flag(u32 old_flags, u32 bit, int set) { - if (bit == TRACE_FUNC_OPT_STACK) { + switch (bit) { + case TRACE_FUNC_OPT_STACK: /* do nothing if already set */ if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) - return 0; + break; if (set) { unregister_ftrace_function(&trace_ops); @@ -217,10 +235,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) register_ftrace_function(&trace_ops); } - return 0; + break; + case TRACE_FUNC_OPT_PSTORE: + break; + default: + return -EINVAL; } - return -EINVAL; + return 0; } static struct tracer function_trace __read_mostly = diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index a7d2a4c653d..99b4378393d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -143,7 +143,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, return; } -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY) /* * The arch may choose to record the frame pointer used * and check it here to make sure that it is what we expect it @@ -154,6 +154,9 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, * * Currently, x86_32 with optimize for size (-Os) makes the latest * gcc do the above. + * + * Note, -mfentry does not use frame pointers, and this test + * is not needed if CC_USING_FENTRY is set. */ if (unlikely(current->ret_stack[index].fp != frame_pointer)) { ftrace_graph_stop(); @@ -538,7 +541,7 @@ get_return_for_leaf(struct trace_iterator *iter, next = &data->ret; } else { - ring_iter = iter->buffer_iter[iter->cpu]; + ring_iter = trace_buffer_iter(iter, iter->cpu); /* First peek to compare current entry and the next one */ if (ring_iter) diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 99d20e92036..d98ee8283b2 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -136,7 +136,8 @@ static int func_prolog_dec(struct trace_array *tr, * irqsoff uses its own tracer function to keep the overhead down: */ static void -irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; @@ -153,7 +154,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b31d3d5699f..1a2117043bb 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1002,7 +1002,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head); + perf_trace_buf_submit(entry, size, rctx, + entry->ip, 1, regs, head, NULL); } /* Kretprobe profile handler */ @@ -1033,7 +1034,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head); + perf_trace_buf_submit(entry, size, rctx, + entry->ret_ip, 1, regs, head, NULL); } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index df611a0e76c..123b189c732 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1325,4 +1325,4 @@ __init static int init_events(void) return 0; } -device_initcall(init_events); +early_initcall(init_events); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ff791ea48b5..02170c00c41 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -108,7 +108,8 @@ out_enable: * wakeup uses its own tracer function to keep the overhead down: */ static void -wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; @@ -129,7 +130,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 288541f977f..2c00a691a54 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -103,54 +103,67 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) static int trace_selftest_test_probe1_cnt; static void trace_selftest_test_probe1_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe1_cnt++; } static int trace_selftest_test_probe2_cnt; static void trace_selftest_test_probe2_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe2_cnt++; } static int trace_selftest_test_probe3_cnt; static void trace_selftest_test_probe3_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe3_cnt++; } static int trace_selftest_test_global_cnt; static void trace_selftest_test_global_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_global_cnt++; } static int trace_selftest_test_dyn_cnt; static void trace_selftest_test_dyn_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_dyn_cnt++; } static struct ftrace_ops test_probe1 = { .func = trace_selftest_test_probe1_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe2 = { .func = trace_selftest_test_probe2_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe3 = { .func = trace_selftest_test_probe3_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_global = { - .func = trace_selftest_test_global_func, - .flags = FTRACE_OPS_FL_GLOBAL, + .func = trace_selftest_test_global_func, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static void print_counts(void) @@ -393,10 +406,253 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, return ret; } + +static int trace_selftest_recursion_cnt; +static void trace_selftest_test_recursion_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * This function is registered without the recursion safe flag. + * The ftrace infrastructure should provide the recursion + * protection. If not, this will crash the kernel! + */ + trace_selftest_recursion_cnt++; + DYN_FTRACE_TEST_NAME(); +} + +static void trace_selftest_test_recursion_safe_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * We said we would provide our own recursion. By calling + * this function again, we should recurse back into this function + * and count again. But this only happens if the arch supports + * all of ftrace features and nothing else is using the function + * tracing utility. + */ + if (trace_selftest_recursion_cnt++) + return; + DYN_FTRACE_TEST_NAME(); +} + +static struct ftrace_ops test_rec_probe = { + .func = trace_selftest_test_recursion_func, +}; + +static struct ftrace_ops test_recsafe_probe = { + .func = trace_selftest_test_recursion_safe_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static int +trace_selftest_function_recursion(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int cnt; + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion: "); + + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_rec_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_rec_probe); + + ret = -1; + if (trace_selftest_recursion_cnt != 1) { + pr_cont("*callback not called once (%d)* ", + trace_selftest_recursion_cnt); + goto out; + } + + trace_selftest_recursion_cnt = 1; + + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion safe: "); + + ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_recsafe_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_recsafe_probe); + + /* + * If arch supports all ftrace features, and no other task + * was on the list, we should be fine. + */ + if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC) + cnt = 2; /* Should have recursed */ + else + cnt = 1; + + ret = -1; + if (trace_selftest_recursion_cnt != cnt) { + pr_cont("*callback not called expected %d times (%d)* ", + cnt, trace_selftest_recursion_cnt); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} #else # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +# define trace_selftest_function_recursion() ({ 0; }) #endif /* CONFIG_DYNAMIC_FTRACE */ +static enum { + TRACE_SELFTEST_REGS_START, + TRACE_SELFTEST_REGS_FOUND, + TRACE_SELFTEST_REGS_NOT_FOUND, +} trace_selftest_regs_stat; + +static void trace_selftest_test_regs_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + if (pt_regs) + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND; + else + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND; +} + +static struct ftrace_ops test_regs_probe = { + .func = trace_selftest_test_regs_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS, +}; + +static int +trace_selftest_function_regs(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int supported = 0; + +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS + supported = 1; +#endif + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace regs%s: ", + !supported ? "(no arch support)" : ""); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1); + /* + * If DYNAMIC_FTRACE is not set, then we just trace all functions. + * This test really doesn't care. + */ + if (ret && ret != -ENODEV) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_regs_probe); + /* + * Now if the arch does not support passing regs, then this should + * have failed. + */ + if (!supported) { + if (!ret) { + pr_cont("*registered save-regs without arch support* "); + goto out; + } + test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED; + ret = register_ftrace_function(&test_regs_probe); + } + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_regs_probe); + + ret = -1; + + switch (trace_selftest_regs_stat) { + case TRACE_SELFTEST_REGS_START: + pr_cont("*callback never called* "); + goto out; + + case TRACE_SELFTEST_REGS_FOUND: + if (supported) + break; + pr_cont("*callback received regs without arch support* "); + goto out; + + case TRACE_SELFTEST_REGS_NOT_FOUND: + if (!supported) + break; + pr_cont("*callback received NULL regs* "); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} + /* * Simple verification test of ftrace function tracer. * Enable ftrace, sleep 1/10 second, and then read the trace @@ -442,7 +698,14 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ret = trace_selftest_startup_dynamic_tracing(trace, tr, DYN_FTRACE_TEST_NAME); + if (ret) + goto out; + ret = trace_selftest_function_recursion(); + if (ret) + goto out; + + ret = trace_selftest_function_regs(); out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; @@ -778,6 +1041,8 @@ static int trace_wakeup_test_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); schedule(); + complete(x); + /* we are awake, now wait to disappear */ while (!kthread_should_stop()) { /* @@ -821,24 +1086,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* reset the max latency */ tracing_max_latency = 0; - /* sleep to let the RT thread sleep too */ - msleep(100); + while (p->on_rq) { + /* + * Sleep to make sure the RT thread is asleep too. + * On virtual machines we can't rely on timings, + * but we want to make sure this test still works. + */ + msleep(100); + } - /* - * Yes this is slightly racy. It is possible that for some - * strange reason that the RT thread we created, did not - * call schedule for 100ms after doing the completion, - * and we do a wakeup on a task that already is awake. - * But that is extremely unlikely, and the worst thing that - * happens in such a case, is that we disable tracing. - * Honestly, if this race does happen something is horrible - * wrong with the system. - */ + init_completion(&isrt); wake_up_process(p); - /* give a little time to let the thread wake up */ - msleep(100); + /* Wait for the task to wake up */ + wait_for_completion(&isrt); /* stop the tracing. */ tracing_stop(); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index d4545f49242..0c1b165778e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -111,7 +111,8 @@ static inline void check_stack(void) } static void -stack_trace_call(unsigned long ip, unsigned long parent_ip) +stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { int cpu; @@ -136,6 +137,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static ssize_t diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 96fc7336909..2485a7d09b1 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -487,7 +487,7 @@ int __init init_ftrace_syscalls(void) return 0; } -core_initcall(init_ftrace_syscalls); +early_initcall(init_ftrace_syscalls); #ifdef CONFIG_PERF_EVENTS @@ -506,6 +506,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) int size; syscall_nr = syscall_get_nr(current, regs); + if (syscall_nr < 0) + return; if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) return; @@ -532,7 +534,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) (unsigned long *)&rec->args); head = this_cpu_ptr(sys_data->enter_event->perf_events); - perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head); + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } int perf_sysenter_enable(struct ftrace_event_call *call) @@ -580,6 +582,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) int size; syscall_nr = syscall_get_nr(current, regs); + if (syscall_nr < 0) + return; if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) return; @@ -608,7 +612,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) rec->ret = syscall_get_return_value(current, regs); head = this_cpu_ptr(sys_data->exit_event->perf_events); - perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head); + perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } int perf_sysexit_enable(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 2b36ac68549..03003cd7dd9 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -670,7 +670,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head); + perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL); out: preempt_enable(); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 4b1dfba70f7..9d4c8d5a1f5 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -22,6 +22,7 @@ #include <linux/notifier.h> #include <linux/module.h> #include <linux/sysctl.h> +#include <linux/smpboot.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> @@ -29,16 +30,18 @@ int watchdog_enabled = 1; int __read_mostly watchdog_thresh = 10; +static int __read_mostly watchdog_disabled; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); +static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); #ifdef CONFIG_HARDLOCKUP_DETECTOR static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); -static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif @@ -248,13 +251,15 @@ static void watchdog_overflow_callback(struct perf_event *event, __this_cpu_write(hard_watchdog_warn, false); return; } +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + static void watchdog_interrupt_count(void) { __this_cpu_inc(hrtimer_interrupts); } -#else -static inline void watchdog_interrupt_count(void) { return; } -#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + +static int watchdog_nmi_enable(unsigned int cpu); +static void watchdog_nmi_disable(unsigned int cpu); /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) @@ -327,49 +332,68 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } +static void watchdog_set_prio(unsigned int policy, unsigned int prio) +{ + struct sched_param param = { .sched_priority = prio }; -/* - * The watchdog thread - touches the timestamp. - */ -static int watchdog(void *unused) + sched_setscheduler(current, policy, ¶m); +} + +static void watchdog_enable(unsigned int cpu) { - struct sched_param param = { .sched_priority = 0 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - /* initialize timestamp */ - __touch_watchdog(); + if (!watchdog_enabled) { + kthread_park(current); + return; + } + + /* Enable the perf event */ + watchdog_nmi_enable(cpu); /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()), HRTIMER_MODE_REL_PINNED); - set_current_state(TASK_INTERRUPTIBLE); - /* - * Run briefly (kicked by the hrtimer callback function) once every - * get_sample_period() seconds (4 seconds by default) to reset the - * softlockup timestamp. If this gets delayed for more than - * 2*watchdog_thresh seconds then the debug-printout triggers in - * watchdog_timer_fn(). - */ - while (!kthread_should_stop()) { - __touch_watchdog(); - schedule(); + /* initialize timestamp */ + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + __touch_watchdog(); +} - if (kthread_should_stop()) - break; +static void watchdog_disable(unsigned int cpu) +{ + struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - set_current_state(TASK_INTERRUPTIBLE); - } - /* - * Drop the policy/priority elevation during thread exit to avoid a - * scheduling latency spike. - */ - __set_current_state(TASK_RUNNING); - sched_setscheduler(current, SCHED_NORMAL, ¶m); - return 0; + watchdog_set_prio(SCHED_NORMAL, 0); + hrtimer_cancel(hrtimer); + /* disable the perf event */ + watchdog_nmi_disable(cpu); } +static int watchdog_should_run(unsigned int cpu) +{ + return __this_cpu_read(hrtimer_interrupts) != + __this_cpu_read(soft_lockup_hrtimer_cnt); +} + +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every get_sample_period() seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static void watchdog(unsigned int cpu) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); +} #ifdef CONFIG_HARDLOCKUP_DETECTOR /* @@ -379,7 +403,7 @@ static int watchdog(void *unused) */ static unsigned long cpu0_err; -static int watchdog_nmi_enable(int cpu) +static int watchdog_nmi_enable(unsigned int cpu) { struct perf_event_attr *wd_attr; struct perf_event *event = per_cpu(watchdog_ev, cpu); @@ -433,7 +457,7 @@ out: return 0; } -static void watchdog_nmi_disable(int cpu) +static void watchdog_nmi_disable(unsigned int cpu) { struct perf_event *event = per_cpu(watchdog_ev, cpu); @@ -447,107 +471,35 @@ static void watchdog_nmi_disable(int cpu) return; } #else -static int watchdog_nmi_enable(int cpu) { return 0; } -static void watchdog_nmi_disable(int cpu) { return; } +static int watchdog_nmi_enable(unsigned int cpu) { return 0; } +static void watchdog_nmi_disable(unsigned int cpu) { return; } #endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* prepare/enable/disable routines */ -static void watchdog_prepare_cpu(int cpu) -{ - struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); - - WARN_ON(per_cpu(softlockup_watchdog, cpu)); - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; -} - -static int watchdog_enable(int cpu) -{ - struct task_struct *p = per_cpu(softlockup_watchdog, cpu); - int err = 0; - - /* enable the perf event */ - err = watchdog_nmi_enable(cpu); - - /* Regardless of err above, fall through and start softlockup */ - - /* create the watchdog thread */ - if (!p) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu); - if (IS_ERR(p)) { - pr_err("softlockup watchdog for %i failed\n", cpu); - if (!err) { - /* if hardlockup hasn't already set this */ - err = PTR_ERR(p); - /* and disable the perf event */ - watchdog_nmi_disable(cpu); - } - goto out; - } - sched_setscheduler(p, SCHED_FIFO, ¶m); - kthread_bind(p, cpu); - per_cpu(watchdog_touch_ts, cpu) = 0; - per_cpu(softlockup_watchdog, cpu) = p; - wake_up_process(p); - } - -out: - return err; -} - -static void watchdog_disable(int cpu) -{ - struct task_struct *p = per_cpu(softlockup_watchdog, cpu); - struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); - - /* - * cancel the timer first to stop incrementing the stats - * and waking up the kthread - */ - hrtimer_cancel(hrtimer); - - /* disable the perf event */ - watchdog_nmi_disable(cpu); - - /* stop the watchdog thread */ - if (p) { - per_cpu(softlockup_watchdog, cpu) = NULL; - kthread_stop(p); - } -} - /* sysctl functions */ #ifdef CONFIG_SYSCTL static void watchdog_enable_all_cpus(void) { - int cpu; - - watchdog_enabled = 0; - - for_each_online_cpu(cpu) - if (!watchdog_enable(cpu)) - /* if any cpu succeeds, watchdog is considered - enabled for the system */ - watchdog_enabled = 1; - - if (!watchdog_enabled) - pr_err("failed to be enabled on some cpus\n"); + unsigned int cpu; + if (watchdog_disabled) { + watchdog_disabled = 0; + for_each_online_cpu(cpu) + kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + } } static void watchdog_disable_all_cpus(void) { - int cpu; - - for_each_online_cpu(cpu) - watchdog_disable(cpu); + unsigned int cpu; - /* if all watchdogs are disabled, then they are disabled for the system */ - watchdog_enabled = 0; + if (!watchdog_disabled) { + watchdog_disabled = 1; + for_each_online_cpu(cpu) + kthread_park(per_cpu(softlockup_watchdog, cpu)); + } } - /* * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh */ @@ -557,73 +509,36 @@ int proc_dowatchdog(struct ctl_table *table, int write, { int ret; + if (watchdog_disabled < 0) + return -ENODEV; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) - goto out; + return ret; if (watchdog_enabled && watchdog_thresh) watchdog_enable_all_cpus(); else watchdog_disable_all_cpus(); -out: return ret; } #endif /* CONFIG_SYSCTL */ - -/* - * Create/destroy watchdog threads as CPUs come and go: - */ -static int __cpuinit -cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - watchdog_prepare_cpu(hotcpu); - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - if (watchdog_enabled) - watchdog_enable(hotcpu); - break; -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - watchdog_disable(hotcpu); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - watchdog_disable(hotcpu); - break; -#endif /* CONFIG_HOTPLUG_CPU */ - } - - /* - * hardlockup and softlockup are not important enough - * to block cpu bring up. Just always succeed and - * rely on printk output to flag problems. - */ - return NOTIFY_OK; -} - -static struct notifier_block __cpuinitdata cpu_nfb = { - .notifier_call = cpu_callback +static struct smp_hotplug_thread watchdog_threads = { + .store = &softlockup_watchdog, + .thread_should_run = watchdog_should_run, + .thread_fn = watchdog, + .thread_comm = "watchdog/%u", + .setup = watchdog_enable, + .park = watchdog_disable, + .unpark = watchdog_enable, }; void __init lockup_detector_init(void) { - void *cpu = (void *)(long)smp_processor_id(); - int err; - - err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); - WARN_ON(notifier_to_errno(err)); - - cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); - register_cpu_notifier(&cpu_nfb); - - return; + if (smpboot_register_percpu_thread(&watchdog_threads)) { + pr_err("Failed to create watchdog threads, disabled\n"); + watchdog_disabled = -ENODEV; + } } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9a3128dc67d..3c5a79e2134 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -45,32 +45,42 @@ #include "workqueue_sched.h" enum { - /* global_cwq flags */ - GCWQ_MANAGE_WORKERS = 1 << 0, /* need to manage workers */ - GCWQ_MANAGING_WORKERS = 1 << 1, /* managing workers */ - GCWQ_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ - GCWQ_FREEZING = 1 << 3, /* freeze in progress */ - GCWQ_HIGHPRI_PENDING = 1 << 4, /* highpri works on queue */ + /* + * global_cwq flags + * + * A bound gcwq is either associated or disassociated with its CPU. + * While associated (!DISASSOCIATED), all workers are bound to the + * CPU and none has %WORKER_UNBOUND set and concurrency management + * is in effect. + * + * While DISASSOCIATED, the cpu may be offline and all workers have + * %WORKER_UNBOUND set and concurrency management disabled, and may + * be executing on any CPU. The gcwq behaves as an unbound one. + * + * Note that DISASSOCIATED can be flipped only while holding + * managership of all pools on the gcwq to avoid changing binding + * state while create_worker() is in progress. + */ + GCWQ_DISASSOCIATED = 1 << 0, /* cpu can't serve workers */ + GCWQ_FREEZING = 1 << 1, /* freeze in progress */ + + /* pool flags */ + POOL_MANAGE_WORKERS = 1 << 0, /* need to manage workers */ + POOL_MANAGING_WORKERS = 1 << 1, /* managing workers */ /* worker flags */ WORKER_STARTED = 1 << 0, /* started */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ - WORKER_ROGUE = 1 << 4, /* not bound to any cpu */ WORKER_REBIND = 1 << 5, /* mom is home, come back */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ - WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND | - WORKER_CPU_INTENSIVE | WORKER_UNBOUND, + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_REBIND | WORKER_UNBOUND | + WORKER_CPU_INTENSIVE, - /* gcwq->trustee_state */ - TRUSTEE_START = 0, /* start */ - TRUSTEE_IN_CHARGE = 1, /* trustee in charge of gcwq */ - TRUSTEE_BUTCHER = 2, /* butcher workers */ - TRUSTEE_RELEASE = 3, /* release workers */ - TRUSTEE_DONE = 4, /* trustee is done */ + NR_WORKER_POOLS = 2, /* # worker pools per gcwq */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER, @@ -84,13 +94,13 @@ enum { (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ - TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give -20. */ RESCUER_NICE_LEVEL = -20, + HIGHPRI_NICE_LEVEL = -20, }; /* @@ -115,6 +125,8 @@ enum { */ struct global_cwq; +struct worker_pool; +struct idle_rebind; /* * The poor guys doing the actual heavy lifting. All on-duty workers @@ -131,12 +143,31 @@ struct worker { struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */ struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ - struct global_cwq *gcwq; /* I: the associated gcwq */ + struct worker_pool *pool; /* I: the associated pool */ /* 64 bytes boundary on 64bit, 32 on 32bit */ unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ - struct work_struct rebind_work; /* L: rebind worker to cpu */ + + /* for rebinding worker to CPU */ + struct idle_rebind *idle_rebind; /* L: for idle worker */ + struct work_struct rebind_work; /* L: for busy worker */ +}; + +struct worker_pool { + struct global_cwq *gcwq; /* I: the owning gcwq */ + unsigned int flags; /* X: flags */ + + struct list_head worklist; /* L: list of pending works */ + int nr_workers; /* L: total number of workers */ + int nr_idle; /* L: currently idle ones */ + + struct list_head idle_list; /* X: list of idle workers */ + struct timer_list idle_timer; /* L: worker idle timeout */ + struct timer_list mayday_timer; /* L: SOS timer for workers */ + + struct mutex manager_mutex; /* mutex manager should hold */ + struct ida worker_ida; /* L: for worker IDs */ }; /* @@ -146,27 +177,16 @@ struct worker { */ struct global_cwq { spinlock_t lock; /* the gcwq lock */ - struct list_head worklist; /* L: list of pending works */ unsigned int cpu; /* I: the associated cpu */ unsigned int flags; /* L: GCWQ_* flags */ - int nr_workers; /* L: total number of workers */ - int nr_idle; /* L: currently idle ones */ - - /* workers are chained either in the idle_list or busy_hash */ - struct list_head idle_list; /* X: list of idle workers */ + /* workers are chained either in busy_hash or pool idle_list */ struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE]; /* L: hash of busy workers */ - struct timer_list idle_timer; /* L: worker idle timeout */ - struct timer_list mayday_timer; /* L: SOS timer for dworkers */ - - struct ida worker_ida; /* L: for worker IDs */ + struct worker_pool pools[2]; /* normal and highpri pools */ - struct task_struct *trustee; /* L: for gcwq shutdown */ - unsigned int trustee_state; /* L: trustee state */ - wait_queue_head_t trustee_wait; /* trustee wait */ - struct worker *first_idle; /* L: first idle worker */ + wait_queue_head_t rebind_hold; /* rebind hold wait */ } ____cacheline_aligned_in_smp; /* @@ -175,7 +195,7 @@ struct global_cwq { * aligned at two's power of the number of flag bits. */ struct cpu_workqueue_struct { - struct global_cwq *gcwq; /* I: the associated gcwq */ + struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ @@ -264,6 +284,10 @@ EXPORT_SYMBOL_GPL(system_nrt_freezable_wq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> +#define for_each_worker_pool(pool, gcwq) \ + for ((pool) = &(gcwq)->pools[0]; \ + (pool) < &(gcwq)->pools[NR_WORKER_POOLS]; (pool)++) + #define for_each_busy_worker(worker, i, pos, gcwq) \ for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \ hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry) @@ -444,7 +468,7 @@ static bool workqueue_freezing; /* W: have wqs started freezing? */ * try_to_wake_up(). Put it in a separate cacheline. */ static DEFINE_PER_CPU(struct global_cwq, global_cwq); -static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, gcwq_nr_running); +static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, pool_nr_running[NR_WORKER_POOLS]); /* * Global cpu workqueue and nr_running counter for unbound gcwq. The @@ -452,10 +476,17 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, gcwq_nr_running); * workers have WORKER_UNBOUND set. */ static struct global_cwq unbound_global_cwq; -static atomic_t unbound_gcwq_nr_running = ATOMIC_INIT(0); /* always 0 */ +static atomic_t unbound_pool_nr_running[NR_WORKER_POOLS] = { + [0 ... NR_WORKER_POOLS - 1] = ATOMIC_INIT(0), /* always 0 */ +}; static int worker_thread(void *__worker); +static int worker_pool_pri(struct worker_pool *pool) +{ + return pool - pool->gcwq->pools; +} + static struct global_cwq *get_gcwq(unsigned int cpu) { if (cpu != WORK_CPU_UNBOUND) @@ -464,12 +495,15 @@ static struct global_cwq *get_gcwq(unsigned int cpu) return &unbound_global_cwq; } -static atomic_t *get_gcwq_nr_running(unsigned int cpu) +static atomic_t *get_pool_nr_running(struct worker_pool *pool) { + int cpu = pool->gcwq->cpu; + int idx = worker_pool_pri(pool); + if (cpu != WORK_CPU_UNBOUND) - return &per_cpu(gcwq_nr_running, cpu); + return &per_cpu(pool_nr_running, cpu)[idx]; else - return &unbound_gcwq_nr_running; + return &unbound_pool_nr_running[idx]; } static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, @@ -555,7 +589,7 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) if (data & WORK_STRUCT_CWQ) return ((struct cpu_workqueue_struct *) - (data & WORK_STRUCT_WQ_DATA_MASK))->gcwq; + (data & WORK_STRUCT_WQ_DATA_MASK))->pool->gcwq; cpu = data >> WORK_STRUCT_FLAG_BITS; if (cpu == WORK_CPU_NONE) @@ -566,60 +600,62 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) } /* - * Policy functions. These define the policies on how the global - * worker pool is managed. Unless noted otherwise, these functions - * assume that they're being called with gcwq->lock held. + * Policy functions. These define the policies on how the global worker + * pools are managed. Unless noted otherwise, these functions assume that + * they're being called with gcwq->lock held. */ -static bool __need_more_worker(struct global_cwq *gcwq) +static bool __need_more_worker(struct worker_pool *pool) { - return !atomic_read(get_gcwq_nr_running(gcwq->cpu)) || - gcwq->flags & GCWQ_HIGHPRI_PENDING; + return !atomic_read(get_pool_nr_running(pool)); } /* * Need to wake up a worker? Called from anything but currently * running workers. + * + * Note that, because unbound workers never contribute to nr_running, this + * function will always return %true for unbound gcwq as long as the + * worklist isn't empty. */ -static bool need_more_worker(struct global_cwq *gcwq) +static bool need_more_worker(struct worker_pool *pool) { - return !list_empty(&gcwq->worklist) && __need_more_worker(gcwq); + return !list_empty(&pool->worklist) && __need_more_worker(pool); } /* Can I start working? Called from busy but !running workers. */ -static bool may_start_working(struct global_cwq *gcwq) +static bool may_start_working(struct worker_pool *pool) { - return gcwq->nr_idle; + return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ -static bool keep_working(struct global_cwq *gcwq) +static bool keep_working(struct worker_pool *pool) { - atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); + atomic_t *nr_running = get_pool_nr_running(pool); - return !list_empty(&gcwq->worklist) && - (atomic_read(nr_running) <= 1 || - gcwq->flags & GCWQ_HIGHPRI_PENDING); + return !list_empty(&pool->worklist) && atomic_read(nr_running) <= 1; } /* Do we need a new worker? Called from manager. */ -static bool need_to_create_worker(struct global_cwq *gcwq) +static bool need_to_create_worker(struct worker_pool *pool) { - return need_more_worker(gcwq) && !may_start_working(gcwq); + return need_more_worker(pool) && !may_start_working(pool); } /* Do I need to be the manager? */ -static bool need_to_manage_workers(struct global_cwq *gcwq) +static bool need_to_manage_workers(struct worker_pool *pool) { - return need_to_create_worker(gcwq) || gcwq->flags & GCWQ_MANAGE_WORKERS; + return need_to_create_worker(pool) || + (pool->flags & POOL_MANAGE_WORKERS); } /* Do we have too many workers and should some go away? */ -static bool too_many_workers(struct global_cwq *gcwq) +static bool too_many_workers(struct worker_pool *pool) { - bool managing = gcwq->flags & GCWQ_MANAGING_WORKERS; - int nr_idle = gcwq->nr_idle + managing; /* manager is considered idle */ - int nr_busy = gcwq->nr_workers - nr_idle; + bool managing = pool->flags & POOL_MANAGING_WORKERS; + int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ + int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } @@ -629,26 +665,26 @@ static bool too_many_workers(struct global_cwq *gcwq) */ /* Return the first worker. Safe with preemption disabled */ -static struct worker *first_worker(struct global_cwq *gcwq) +static struct worker *first_worker(struct worker_pool *pool) { - if (unlikely(list_empty(&gcwq->idle_list))) + if (unlikely(list_empty(&pool->idle_list))) return NULL; - return list_first_entry(&gcwq->idle_list, struct worker, entry); + return list_first_entry(&pool->idle_list, struct worker, entry); } /** * wake_up_worker - wake up an idle worker - * @gcwq: gcwq to wake worker for + * @pool: worker pool to wake worker from * - * Wake up the first idle worker of @gcwq. + * Wake up the first idle worker of @pool. * * CONTEXT: * spin_lock_irq(gcwq->lock). */ -static void wake_up_worker(struct global_cwq *gcwq) +static void wake_up_worker(struct worker_pool *pool) { - struct worker *worker = first_worker(gcwq); + struct worker *worker = first_worker(pool); if (likely(worker)) wake_up_process(worker->task); @@ -670,7 +706,7 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) struct worker *worker = kthread_data(task); if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(get_gcwq_nr_running(cpu)); + atomic_inc(get_pool_nr_running(worker->pool)); } /** @@ -692,8 +728,8 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, unsigned int cpu) { struct worker *worker = kthread_data(task), *to_wakeup = NULL; - struct global_cwq *gcwq = get_gcwq(cpu); - atomic_t *nr_running = get_gcwq_nr_running(cpu); + struct worker_pool *pool = worker->pool; + atomic_t *nr_running = get_pool_nr_running(pool); if (worker->flags & WORKER_NOT_RUNNING) return NULL; @@ -706,14 +742,14 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, * worklist not empty test sequence is in insert_work(). * Please read comment there. * - * NOT_RUNNING is clear. This means that trustee is not in - * charge and we're running on the local cpu w/ rq lock held - * and preemption disabled, which in turn means that none else - * could be manipulating idle_list, so dereferencing idle_list - * without gcwq lock is safe. + * NOT_RUNNING is clear. This means that we're bound to and + * running on the local cpu w/ rq lock held and preemption + * disabled, which in turn means that none else could be + * manipulating idle_list, so dereferencing idle_list without gcwq + * lock is safe. */ - if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist)) - to_wakeup = first_worker(gcwq); + if (atomic_dec_and_test(nr_running) && !list_empty(&pool->worklist)) + to_wakeup = first_worker(pool); return to_wakeup ? to_wakeup->task : NULL; } @@ -733,7 +769,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, static inline void worker_set_flags(struct worker *worker, unsigned int flags, bool wakeup) { - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; WARN_ON_ONCE(worker->task != current); @@ -744,12 +780,12 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags, */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { - atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); + atomic_t *nr_running = get_pool_nr_running(pool); if (wakeup) { if (atomic_dec_and_test(nr_running) && - !list_empty(&gcwq->worklist)) - wake_up_worker(gcwq); + !list_empty(&pool->worklist)) + wake_up_worker(pool); } else atomic_dec(nr_running); } @@ -769,7 +805,7 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags, */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; WARN_ON_ONCE(worker->task != current); @@ -783,7 +819,7 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(get_gcwq_nr_running(gcwq->cpu)); + atomic_inc(get_pool_nr_running(pool)); } /** @@ -867,43 +903,6 @@ static struct worker *find_worker_executing_work(struct global_cwq *gcwq, } /** - * gcwq_determine_ins_pos - find insertion position - * @gcwq: gcwq of interest - * @cwq: cwq a work is being queued for - * - * A work for @cwq is about to be queued on @gcwq, determine insertion - * position for the work. If @cwq is for HIGHPRI wq, the work is - * queued at the head of the queue but in FIFO order with respect to - * other HIGHPRI works; otherwise, at the end of the queue. This - * function also sets GCWQ_HIGHPRI_PENDING flag to hint @gcwq that - * there are HIGHPRI works pending. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - * - * RETURNS: - * Pointer to inserstion position. - */ -static inline struct list_head *gcwq_determine_ins_pos(struct global_cwq *gcwq, - struct cpu_workqueue_struct *cwq) -{ - struct work_struct *twork; - - if (likely(!(cwq->wq->flags & WQ_HIGHPRI))) - return &gcwq->worklist; - - list_for_each_entry(twork, &gcwq->worklist, entry) { - struct cpu_workqueue_struct *tcwq = get_work_cwq(twork); - - if (!(tcwq->wq->flags & WQ_HIGHPRI)) - break; - } - - gcwq->flags |= GCWQ_HIGHPRI_PENDING; - return &twork->entry; -} - -/** * insert_work - insert a work into gcwq * @cwq: cwq @work belongs to * @work: work to insert @@ -920,7 +919,7 @@ static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { - struct global_cwq *gcwq = cwq->gcwq; + struct worker_pool *pool = cwq->pool; /* we own @work, set data and link */ set_work_cwq(work, cwq, extra_flags); @@ -940,8 +939,8 @@ static void insert_work(struct cpu_workqueue_struct *cwq, */ smp_mb(); - if (__need_more_worker(gcwq)) - wake_up_worker(gcwq); + if (__need_more_worker(pool)) + wake_up_worker(pool); } /* @@ -1043,7 +1042,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, if (likely(cwq->nr_active < cwq->max_active)) { trace_workqueue_activate_work(work); cwq->nr_active++; - worklist = gcwq_determine_ins_pos(gcwq, cwq); + worklist = &cwq->pool->worklist; } else { work_flags |= WORK_STRUCT_DELAYED; worklist = &cwq->delayed_works; @@ -1192,7 +1191,8 @@ EXPORT_SYMBOL_GPL(queue_delayed_work_on); */ static void worker_enter_idle(struct worker *worker) { - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; + struct global_cwq *gcwq = pool->gcwq; BUG_ON(worker->flags & WORKER_IDLE); BUG_ON(!list_empty(&worker->entry) && @@ -1200,27 +1200,24 @@ static void worker_enter_idle(struct worker *worker) /* can't use worker_set_flags(), also called from start_worker() */ worker->flags |= WORKER_IDLE; - gcwq->nr_idle++; + pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ - list_add(&worker->entry, &gcwq->idle_list); + list_add(&worker->entry, &pool->idle_list); - if (likely(!(worker->flags & WORKER_ROGUE))) { - if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) - mod_timer(&gcwq->idle_timer, - jiffies + IDLE_WORKER_TIMEOUT); - } else - wake_up_all(&gcwq->trustee_wait); + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* - * Sanity check nr_running. Because trustee releases gcwq->lock - * between setting %WORKER_ROGUE and zapping nr_running, the - * warning may trigger spuriously. Check iff trustee is idle. + * Sanity check nr_running. Because gcwq_unbind_fn() releases + * gcwq->lock between setting %WORKER_UNBOUND and zapping + * nr_running, the warning may trigger spuriously. Check iff + * unbind is not in progress. */ - WARN_ON_ONCE(gcwq->trustee_state == TRUSTEE_DONE && - gcwq->nr_workers == gcwq->nr_idle && - atomic_read(get_gcwq_nr_running(gcwq->cpu))); + WARN_ON_ONCE(!(gcwq->flags & GCWQ_DISASSOCIATED) && + pool->nr_workers == pool->nr_idle && + atomic_read(get_pool_nr_running(pool))); } /** @@ -1234,11 +1231,11 @@ static void worker_enter_idle(struct worker *worker) */ static void worker_leave_idle(struct worker *worker) { - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; BUG_ON(!(worker->flags & WORKER_IDLE)); worker_clr_flags(worker, WORKER_IDLE); - gcwq->nr_idle--; + pool->nr_idle--; list_del_init(&worker->entry); } @@ -1258,11 +1255,11 @@ static void worker_leave_idle(struct worker *worker) * verbatim as it's best effort and blocking and gcwq may be * [dis]associated in the meantime. * - * This function tries set_cpus_allowed() and locks gcwq and verifies - * the binding against GCWQ_DISASSOCIATED which is set during - * CPU_DYING and cleared during CPU_ONLINE, so if the worker enters - * idle state or fetches works without dropping lock, it can guarantee - * the scheduling requirement described in the first paragraph. + * This function tries set_cpus_allowed() and locks gcwq and verifies the + * binding against %GCWQ_DISASSOCIATED which is set during + * %CPU_DOWN_PREPARE and cleared during %CPU_ONLINE, so if the worker + * enters idle state or fetches works without dropping lock, it can + * guarantee the scheduling requirement described in the first paragraph. * * CONTEXT: * Might sleep. Called without any lock but returns with gcwq->lock @@ -1275,7 +1272,7 @@ static void worker_leave_idle(struct worker *worker) static bool worker_maybe_bind_and_lock(struct worker *worker) __acquires(&gcwq->lock) { - struct global_cwq *gcwq = worker->gcwq; + struct global_cwq *gcwq = worker->pool->gcwq; struct task_struct *task = worker->task; while (true) { @@ -1308,23 +1305,191 @@ __acquires(&gcwq->lock) } } +struct idle_rebind { + int cnt; /* # workers to be rebound */ + struct completion done; /* all workers rebound */ +}; + /* - * Function for worker->rebind_work used to rebind rogue busy workers - * to the associated cpu which is coming back online. This is - * scheduled by cpu up but can race with other cpu hotplug operations - * and may be executed twice without intervening cpu down. + * Rebind an idle @worker to its CPU. During CPU onlining, this has to + * happen synchronously for idle workers. worker_thread() will test + * %WORKER_REBIND before leaving idle and call this function. */ -static void worker_rebind_fn(struct work_struct *work) +static void idle_worker_rebind(struct worker *worker) +{ + struct global_cwq *gcwq = worker->pool->gcwq; + + /* CPU must be online at this point */ + WARN_ON(!worker_maybe_bind_and_lock(worker)); + if (!--worker->idle_rebind->cnt) + complete(&worker->idle_rebind->done); + spin_unlock_irq(&worker->pool->gcwq->lock); + + /* we did our part, wait for rebind_workers() to finish up */ + wait_event(gcwq->rebind_hold, !(worker->flags & WORKER_REBIND)); + + /* + * rebind_workers() shouldn't finish until all workers passed the + * above WORKER_REBIND wait. Tell it when done. + */ + spin_lock_irq(&worker->pool->gcwq->lock); + if (!--worker->idle_rebind->cnt) + complete(&worker->idle_rebind->done); + spin_unlock_irq(&worker->pool->gcwq->lock); +} + +/* + * Function for @worker->rebind.work used to rebind unbound busy workers to + * the associated cpu which is coming back online. This is scheduled by + * cpu up but can race with other cpu hotplug operations and may be + * executed twice without intervening cpu down. + */ +static void busy_worker_rebind_fn(struct work_struct *work) { struct worker *worker = container_of(work, struct worker, rebind_work); - struct global_cwq *gcwq = worker->gcwq; + struct global_cwq *gcwq = worker->pool->gcwq; - if (worker_maybe_bind_and_lock(worker)) - worker_clr_flags(worker, WORKER_REBIND); + worker_maybe_bind_and_lock(worker); + + /* + * %WORKER_REBIND must be cleared even if the above binding failed; + * otherwise, we may confuse the next CPU_UP cycle or oops / get + * stuck by calling idle_worker_rebind() prematurely. If CPU went + * down again inbetween, %WORKER_UNBOUND would be set, so clearing + * %WORKER_REBIND is always safe. + */ + worker_clr_flags(worker, WORKER_REBIND); spin_unlock_irq(&gcwq->lock); } +/** + * rebind_workers - rebind all workers of a gcwq to the associated CPU + * @gcwq: gcwq of interest + * + * @gcwq->cpu is coming online. Rebind all workers to the CPU. Rebinding + * is different for idle and busy ones. + * + * The idle ones should be rebound synchronously and idle rebinding should + * be complete before any worker starts executing work items with + * concurrency management enabled; otherwise, scheduler may oops trying to + * wake up non-local idle worker from wq_worker_sleeping(). + * + * This is achieved by repeatedly requesting rebinding until all idle + * workers are known to have been rebound under @gcwq->lock and holding all + * idle workers from becoming busy until idle rebinding is complete. + * + * Once idle workers are rebound, busy workers can be rebound as they + * finish executing their current work items. Queueing the rebind work at + * the head of their scheduled lists is enough. Note that nr_running will + * be properbly bumped as busy workers rebind. + * + * On return, all workers are guaranteed to either be bound or have rebind + * work item scheduled. + */ +static void rebind_workers(struct global_cwq *gcwq) + __releases(&gcwq->lock) __acquires(&gcwq->lock) +{ + struct idle_rebind idle_rebind; + struct worker_pool *pool; + struct worker *worker; + struct hlist_node *pos; + int i; + + lockdep_assert_held(&gcwq->lock); + + for_each_worker_pool(pool, gcwq) + lockdep_assert_held(&pool->manager_mutex); + + /* + * Rebind idle workers. Interlocked both ways. We wait for + * workers to rebind via @idle_rebind.done. Workers will wait for + * us to finish up by watching %WORKER_REBIND. + */ + init_completion(&idle_rebind.done); +retry: + idle_rebind.cnt = 1; + INIT_COMPLETION(idle_rebind.done); + + /* set REBIND and kick idle ones, we'll wait for these later */ + for_each_worker_pool(pool, gcwq) { + list_for_each_entry(worker, &pool->idle_list, entry) { + unsigned long worker_flags = worker->flags; + + if (worker->flags & WORKER_REBIND) + continue; + + /* morph UNBOUND to REBIND atomically */ + worker_flags &= ~WORKER_UNBOUND; + worker_flags |= WORKER_REBIND; + ACCESS_ONCE(worker->flags) = worker_flags; + + idle_rebind.cnt++; + worker->idle_rebind = &idle_rebind; + + /* worker_thread() will call idle_worker_rebind() */ + wake_up_process(worker->task); + } + } + + if (--idle_rebind.cnt) { + spin_unlock_irq(&gcwq->lock); + wait_for_completion(&idle_rebind.done); + spin_lock_irq(&gcwq->lock); + /* busy ones might have become idle while waiting, retry */ + goto retry; + } + + /* all idle workers are rebound, rebind busy workers */ + for_each_busy_worker(worker, i, pos, gcwq) { + struct work_struct *rebind_work = &worker->rebind_work; + unsigned long worker_flags = worker->flags; + + /* morph UNBOUND to REBIND atomically */ + worker_flags &= ~WORKER_UNBOUND; + worker_flags |= WORKER_REBIND; + ACCESS_ONCE(worker->flags) = worker_flags; + + if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, + work_data_bits(rebind_work))) + continue; + + /* wq doesn't matter, use the default one */ + debug_work_activate(rebind_work); + insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work, + worker->scheduled.next, + work_color_to_flags(WORK_NO_COLOR)); + } + + /* + * All idle workers are rebound and waiting for %WORKER_REBIND to + * be cleared inside idle_worker_rebind(). Clear and release. + * Clearing %WORKER_REBIND from this foreign context is safe + * because these workers are still guaranteed to be idle. + * + * We need to make sure all idle workers passed WORKER_REBIND wait + * in idle_worker_rebind() before returning; otherwise, workers can + * get stuck at the wait if hotplug cycle repeats. + */ + idle_rebind.cnt = 1; + INIT_COMPLETION(idle_rebind.done); + + for_each_worker_pool(pool, gcwq) { + list_for_each_entry(worker, &pool->idle_list, entry) { + worker->flags &= ~WORKER_REBIND; + idle_rebind.cnt++; + } + } + + wake_up_all(&gcwq->rebind_hold); + + if (--idle_rebind.cnt) { + spin_unlock_irq(&gcwq->lock); + wait_for_completion(&idle_rebind.done); + spin_lock_irq(&gcwq->lock); + } +} + static struct worker *alloc_worker(void) { struct worker *worker; @@ -1333,7 +1498,7 @@ static struct worker *alloc_worker(void) if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); - INIT_WORK(&worker->rebind_work, worker_rebind_fn); + INIT_WORK(&worker->rebind_work, busy_worker_rebind_fn); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } @@ -1342,10 +1507,9 @@ static struct worker *alloc_worker(void) /** * create_worker - create a new workqueue worker - * @gcwq: gcwq the new worker will belong to - * @bind: whether to set affinity to @cpu or not + * @pool: pool the new worker will belong to * - * Create a new worker which is bound to @gcwq. The returned worker + * Create a new worker which is bound to @pool. The returned worker * can be started by calling start_worker() or destroyed using * destroy_worker(). * @@ -1355,16 +1519,17 @@ static struct worker *alloc_worker(void) * RETURNS: * Pointer to the newly created worker. */ -static struct worker *create_worker(struct global_cwq *gcwq, bool bind) +static struct worker *create_worker(struct worker_pool *pool) { - bool on_unbound_cpu = gcwq->cpu == WORK_CPU_UNBOUND; + struct global_cwq *gcwq = pool->gcwq; + const char *pri = worker_pool_pri(pool) ? "H" : ""; struct worker *worker = NULL; int id = -1; spin_lock_irq(&gcwq->lock); - while (ida_get_new(&gcwq->worker_ida, &id)) { + while (ida_get_new(&pool->worker_ida, &id)) { spin_unlock_irq(&gcwq->lock); - if (!ida_pre_get(&gcwq->worker_ida, GFP_KERNEL)) + if (!ida_pre_get(&pool->worker_ida, GFP_KERNEL)) goto fail; spin_lock_irq(&gcwq->lock); } @@ -1374,38 +1539,43 @@ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) if (!worker) goto fail; - worker->gcwq = gcwq; + worker->pool = pool; worker->id = id; - if (!on_unbound_cpu) + if (gcwq->cpu != WORK_CPU_UNBOUND) worker->task = kthread_create_on_node(worker_thread, - worker, - cpu_to_node(gcwq->cpu), - "kworker/%u:%d", gcwq->cpu, id); + worker, cpu_to_node(gcwq->cpu), + "kworker/%u:%d%s", gcwq->cpu, id, pri); else worker->task = kthread_create(worker_thread, worker, - "kworker/u:%d", id); + "kworker/u:%d%s", id, pri); if (IS_ERR(worker->task)) goto fail; + if (worker_pool_pri(pool)) + set_user_nice(worker->task, HIGHPRI_NICE_LEVEL); + /* - * A rogue worker will become a regular one if CPU comes - * online later on. Make sure every worker has - * PF_THREAD_BOUND set. + * Determine CPU binding of the new worker depending on + * %GCWQ_DISASSOCIATED. The caller is responsible for ensuring the + * flag remains stable across this function. See the comments + * above the flag definition for details. + * + * As an unbound worker may later become a regular one if CPU comes + * online, make sure every worker has %PF_THREAD_BOUND set. */ - if (bind && !on_unbound_cpu) + if (!(gcwq->flags & GCWQ_DISASSOCIATED)) { kthread_bind(worker->task, gcwq->cpu); - else { + } else { worker->task->flags |= PF_THREAD_BOUND; - if (on_unbound_cpu) - worker->flags |= WORKER_UNBOUND; + worker->flags |= WORKER_UNBOUND; } return worker; fail: if (id >= 0) { spin_lock_irq(&gcwq->lock); - ida_remove(&gcwq->worker_ida, id); + ida_remove(&pool->worker_ida, id); spin_unlock_irq(&gcwq->lock); } kfree(worker); @@ -1424,7 +1594,7 @@ fail: static void start_worker(struct worker *worker) { worker->flags |= WORKER_STARTED; - worker->gcwq->nr_workers++; + worker->pool->nr_workers++; worker_enter_idle(worker); wake_up_process(worker->task); } @@ -1440,7 +1610,8 @@ static void start_worker(struct worker *worker) */ static void destroy_worker(struct worker *worker) { - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; + struct global_cwq *gcwq = pool->gcwq; int id = worker->id; /* sanity check frenzy */ @@ -1448,9 +1619,9 @@ static void destroy_worker(struct worker *worker) BUG_ON(!list_empty(&worker->scheduled)); if (worker->flags & WORKER_STARTED) - gcwq->nr_workers--; + pool->nr_workers--; if (worker->flags & WORKER_IDLE) - gcwq->nr_idle--; + pool->nr_idle--; list_del_init(&worker->entry); worker->flags |= WORKER_DIE; @@ -1461,29 +1632,30 @@ static void destroy_worker(struct worker *worker) kfree(worker); spin_lock_irq(&gcwq->lock); - ida_remove(&gcwq->worker_ida, id); + ida_remove(&pool->worker_ida, id); } -static void idle_worker_timeout(unsigned long __gcwq) +static void idle_worker_timeout(unsigned long __pool) { - struct global_cwq *gcwq = (void *)__gcwq; + struct worker_pool *pool = (void *)__pool; + struct global_cwq *gcwq = pool->gcwq; spin_lock_irq(&gcwq->lock); - if (too_many_workers(gcwq)) { + if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ - worker = list_entry(gcwq->idle_list.prev, struct worker, entry); + worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) - mod_timer(&gcwq->idle_timer, expires); + mod_timer(&pool->idle_timer, expires); else { /* it's been idle for too long, wake up manager */ - gcwq->flags |= GCWQ_MANAGE_WORKERS; - wake_up_worker(gcwq); + pool->flags |= POOL_MANAGE_WORKERS; + wake_up_worker(pool); } } @@ -1500,7 +1672,7 @@ static bool send_mayday(struct work_struct *work) return false; /* mayday mayday mayday */ - cpu = cwq->gcwq->cpu; + cpu = cwq->pool->gcwq->cpu; /* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */ if (cpu == WORK_CPU_UNBOUND) cpu = 0; @@ -1509,37 +1681,38 @@ static bool send_mayday(struct work_struct *work) return true; } -static void gcwq_mayday_timeout(unsigned long __gcwq) +static void gcwq_mayday_timeout(unsigned long __pool) { - struct global_cwq *gcwq = (void *)__gcwq; + struct worker_pool *pool = (void *)__pool; + struct global_cwq *gcwq = pool->gcwq; struct work_struct *work; spin_lock_irq(&gcwq->lock); - if (need_to_create_worker(gcwq)) { + if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ - list_for_each_entry(work, &gcwq->worklist, entry) + list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } spin_unlock_irq(&gcwq->lock); - mod_timer(&gcwq->mayday_timer, jiffies + MAYDAY_INTERVAL); + mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary - * @gcwq: gcwq to create a new worker for + * @pool: pool to create a new worker for * - * Create a new worker for @gcwq if necessary. @gcwq is guaranteed to + * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is - * sent to all rescuers with works scheduled on @gcwq to resolve + * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be false and @@ -1554,52 +1727,54 @@ static void gcwq_mayday_timeout(unsigned long __gcwq) * false if no action was taken and gcwq->lock stayed locked, true * otherwise. */ -static bool maybe_create_worker(struct global_cwq *gcwq) +static bool maybe_create_worker(struct worker_pool *pool) __releases(&gcwq->lock) __acquires(&gcwq->lock) { - if (!need_to_create_worker(gcwq)) + struct global_cwq *gcwq = pool->gcwq; + + if (!need_to_create_worker(pool)) return false; restart: spin_unlock_irq(&gcwq->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ - mod_timer(&gcwq->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); + mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { struct worker *worker; - worker = create_worker(gcwq, true); + worker = create_worker(pool); if (worker) { - del_timer_sync(&gcwq->mayday_timer); + del_timer_sync(&pool->mayday_timer); spin_lock_irq(&gcwq->lock); start_worker(worker); - BUG_ON(need_to_create_worker(gcwq)); + BUG_ON(need_to_create_worker(pool)); return true; } - if (!need_to_create_worker(gcwq)) + if (!need_to_create_worker(pool)) break; __set_current_state(TASK_INTERRUPTIBLE); schedule_timeout(CREATE_COOLDOWN); - if (!need_to_create_worker(gcwq)) + if (!need_to_create_worker(pool)) break; } - del_timer_sync(&gcwq->mayday_timer); + del_timer_sync(&pool->mayday_timer); spin_lock_irq(&gcwq->lock); - if (need_to_create_worker(gcwq)) + if (need_to_create_worker(pool)) goto restart; return true; } /** * maybe_destroy_worker - destroy workers which have been idle for a while - * @gcwq: gcwq to destroy workers for + * @pool: pool to destroy workers for * - * Destroy @gcwq workers which have been idle for longer than + * Destroy @pool workers which have been idle for longer than * IDLE_WORKER_TIMEOUT. * * LOCKING: @@ -1610,19 +1785,19 @@ restart: * false if no action was taken and gcwq->lock stayed locked, true * otherwise. */ -static bool maybe_destroy_workers(struct global_cwq *gcwq) +static bool maybe_destroy_workers(struct worker_pool *pool) { bool ret = false; - while (too_many_workers(gcwq)) { + while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; - worker = list_entry(gcwq->idle_list.prev, struct worker, entry); + worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { - mod_timer(&gcwq->idle_timer, expires); + mod_timer(&pool->idle_timer, expires); break; } @@ -1655,31 +1830,59 @@ static bool maybe_destroy_workers(struct global_cwq *gcwq) */ static bool manage_workers(struct worker *worker) { - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; bool ret = false; - if (gcwq->flags & GCWQ_MANAGING_WORKERS) + if (pool->flags & POOL_MANAGING_WORKERS) return ret; - gcwq->flags &= ~GCWQ_MANAGE_WORKERS; - gcwq->flags |= GCWQ_MANAGING_WORKERS; + pool->flags |= POOL_MANAGING_WORKERS; /* - * Destroy and then create so that may_start_working() is true - * on return. + * To simplify both worker management and CPU hotplug, hold off + * management while hotplug is in progress. CPU hotplug path can't + * grab %POOL_MANAGING_WORKERS to achieve this because that can + * lead to idle worker depletion (all become busy thinking someone + * else is managing) which in turn can result in deadlock under + * extreme circumstances. Use @pool->manager_mutex to synchronize + * manager against CPU hotplug. + * + * manager_mutex would always be free unless CPU hotplug is in + * progress. trylock first without dropping @gcwq->lock. */ - ret |= maybe_destroy_workers(gcwq); - ret |= maybe_create_worker(gcwq); + if (unlikely(!mutex_trylock(&pool->manager_mutex))) { + spin_unlock_irq(&pool->gcwq->lock); + mutex_lock(&pool->manager_mutex); + /* + * CPU hotplug could have happened while we were waiting + * for manager_mutex. Hotplug itself can't handle us + * because manager isn't either on idle or busy list, and + * @gcwq's state and ours could have deviated. + * + * As hotplug is now excluded via manager_mutex, we can + * simply try to bind. It will succeed or fail depending + * on @gcwq's current state. Try it and adjust + * %WORKER_UNBOUND accordingly. + */ + if (worker_maybe_bind_and_lock(worker)) + worker->flags &= ~WORKER_UNBOUND; + else + worker->flags |= WORKER_UNBOUND; - gcwq->flags &= ~GCWQ_MANAGING_WORKERS; + ret = true; + } + + pool->flags &= ~POOL_MANAGE_WORKERS; /* - * The trustee might be waiting to take over the manager - * position, tell it we're done. + * Destroy and then create so that may_start_working() is true + * on return. */ - if (unlikely(gcwq->trustee)) - wake_up_all(&gcwq->trustee_wait); + ret |= maybe_destroy_workers(pool); + ret |= maybe_create_worker(pool); + pool->flags &= ~POOL_MANAGING_WORKERS; + mutex_unlock(&pool->manager_mutex); return ret; } @@ -1728,10 +1931,9 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) { struct work_struct *work = list_first_entry(&cwq->delayed_works, struct work_struct, entry); - struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); trace_workqueue_activate_work(work); - move_linked_works(work, pos, NULL); + move_linked_works(work, &cwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); cwq->nr_active++; } @@ -1804,7 +2006,8 @@ __releases(&gcwq->lock) __acquires(&gcwq->lock) { struct cpu_workqueue_struct *cwq = get_work_cwq(work); - struct global_cwq *gcwq = cwq->gcwq; + struct worker_pool *pool = worker->pool; + struct global_cwq *gcwq = pool->gcwq; struct hlist_head *bwh = busy_worker_head(gcwq, work); bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE; work_func_t f = work->func; @@ -1823,6 +2026,15 @@ __acquires(&gcwq->lock) lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* + * Ensure we're on the correct CPU. DISASSOCIATED test is + * necessary to avoid spurious warnings from rescuers servicing the + * unbound or a disassociated gcwq. + */ + WARN_ON_ONCE(!(worker->flags & (WORKER_UNBOUND | WORKER_REBIND)) && + !(gcwq->flags & GCWQ_DISASSOCIATED) && + raw_smp_processor_id() != gcwq->cpu); + + /* * A single work shouldn't be executed concurrently by * multiple workers on a single cpu. Check whether anyone is * already processing the work. If so, defer the work to the @@ -1846,27 +2058,19 @@ __acquires(&gcwq->lock) list_del_init(&work->entry); /* - * If HIGHPRI_PENDING, check the next work, and, if HIGHPRI, - * wake up another worker; otherwise, clear HIGHPRI_PENDING. - */ - if (unlikely(gcwq->flags & GCWQ_HIGHPRI_PENDING)) { - struct work_struct *nwork = list_first_entry(&gcwq->worklist, - struct work_struct, entry); - - if (!list_empty(&gcwq->worklist) && - get_work_cwq(nwork)->wq->flags & WQ_HIGHPRI) - wake_up_worker(gcwq); - else - gcwq->flags &= ~GCWQ_HIGHPRI_PENDING; - } - - /* * CPU intensive works don't participate in concurrency * management. They're the scheduler's responsibility. */ if (unlikely(cpu_intensive)) worker_set_flags(worker, WORKER_CPU_INTENSIVE, true); + /* + * Unbound gcwq isn't concurrency managed and work items should be + * executed ASAP. Wake up another worker if necessary. + */ + if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) + wake_up_worker(pool); + spin_unlock_irq(&gcwq->lock); work_clear_pending(work); @@ -1939,28 +2143,38 @@ static void process_scheduled_works(struct worker *worker) static int worker_thread(void *__worker) { struct worker *worker = __worker; - struct global_cwq *gcwq = worker->gcwq; + struct worker_pool *pool = worker->pool; + struct global_cwq *gcwq = pool->gcwq; /* tell the scheduler that this is a workqueue worker */ worker->task->flags |= PF_WQ_WORKER; woke_up: spin_lock_irq(&gcwq->lock); - /* DIE can be set only while we're idle, checking here is enough */ - if (worker->flags & WORKER_DIE) { + /* + * DIE can be set only while idle and REBIND set while busy has + * @worker->rebind_work scheduled. Checking here is enough. + */ + if (unlikely(worker->flags & (WORKER_REBIND | WORKER_DIE))) { spin_unlock_irq(&gcwq->lock); - worker->task->flags &= ~PF_WQ_WORKER; - return 0; + + if (worker->flags & WORKER_DIE) { + worker->task->flags &= ~PF_WQ_WORKER; + return 0; + } + + idle_worker_rebind(worker); + goto woke_up; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ - if (!need_more_worker(gcwq)) + if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ - if (unlikely(!may_start_working(gcwq)) && manage_workers(worker)) + if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* @@ -1979,7 +2193,7 @@ recheck: do { struct work_struct *work = - list_first_entry(&gcwq->worklist, + list_first_entry(&pool->worklist, struct work_struct, entry); if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) { @@ -1991,11 +2205,11 @@ recheck: move_linked_works(work, &worker->scheduled, NULL); process_scheduled_works(worker); } - } while (keep_working(gcwq)); + } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP, false); sleep: - if (unlikely(need_to_manage_workers(gcwq)) && manage_workers(worker)) + if (unlikely(need_to_manage_workers(pool)) && manage_workers(worker)) goto recheck; /* @@ -2053,14 +2267,15 @@ repeat: for_each_mayday_cpu(cpu, wq->mayday_mask) { unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu; struct cpu_workqueue_struct *cwq = get_cwq(tcpu, wq); - struct global_cwq *gcwq = cwq->gcwq; + struct worker_pool *pool = cwq->pool; + struct global_cwq *gcwq = pool->gcwq; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); mayday_clear_cpu(cpu, wq->mayday_mask); /* migrate to the target cpu if possible */ - rescuer->gcwq = gcwq; + rescuer->pool = pool; worker_maybe_bind_and_lock(rescuer); /* @@ -2068,7 +2283,7 @@ repeat: * process'em. */ BUG_ON(!list_empty(&rescuer->scheduled)); - list_for_each_entry_safe(work, n, &gcwq->worklist, entry) + list_for_each_entry_safe(work, n, &pool->worklist, entry) if (get_work_cwq(work) == cwq) move_linked_works(work, scheduled, &n); @@ -2079,8 +2294,8 @@ repeat: * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ - if (keep_working(gcwq)) - wake_up_worker(gcwq); + if (keep_working(pool)) + wake_up_worker(pool); spin_unlock_irq(&gcwq->lock); } @@ -2205,7 +2420,7 @@ static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, for_each_cwq_cpu(cpu, wq) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - struct global_cwq *gcwq = cwq->gcwq; + struct global_cwq *gcwq = cwq->pool->gcwq; spin_lock_irq(&gcwq->lock); @@ -2421,9 +2636,9 @@ reflush: struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); bool drained; - spin_lock_irq(&cwq->gcwq->lock); + spin_lock_irq(&cwq->pool->gcwq->lock); drained = !cwq->nr_active && list_empty(&cwq->delayed_works); - spin_unlock_irq(&cwq->gcwq->lock); + spin_unlock_irq(&cwq->pool->gcwq->lock); if (drained) continue; @@ -2463,7 +2678,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, */ smp_rmb(); cwq = get_work_cwq(work); - if (unlikely(!cwq || gcwq != cwq->gcwq)) + if (unlikely(!cwq || gcwq != cwq->pool->gcwq)) goto already_gone; } else if (wait_executing) { worker = find_worker_executing_work(gcwq, work); @@ -2984,13 +3199,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, if (flags & WQ_MEM_RECLAIM) flags |= WQ_RESCUER; - /* - * Unbound workqueues aren't concurrency managed and should be - * dispatched to workers immediately. - */ - if (flags & WQ_UNBOUND) - flags |= WQ_HIGHPRI; - max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); @@ -3011,9 +3219,10 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, for_each_cwq_cpu(cpu, wq) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); struct global_cwq *gcwq = get_gcwq(cpu); + int pool_idx = (bool)(flags & WQ_HIGHPRI); BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK); - cwq->gcwq = gcwq; + cwq->pool = &gcwq->pools[pool_idx]; cwq->wq = wq; cwq->flush_color = -1; cwq->max_active = max_active; @@ -3225,386 +3434,159 @@ EXPORT_SYMBOL_GPL(work_busy); * gcwqs serve mix of short, long and very long running works making * blocked draining impractical. * - * This is solved by allowing a gcwq to be detached from CPU, running - * it with unbound (rogue) workers and allowing it to be reattached - * later if the cpu comes back online. A separate thread is created - * to govern a gcwq in such state and is called the trustee of the - * gcwq. - * - * Trustee states and their descriptions. - * - * START Command state used on startup. On CPU_DOWN_PREPARE, a - * new trustee is started with this state. - * - * IN_CHARGE Once started, trustee will enter this state after - * assuming the manager role and making all existing - * workers rogue. DOWN_PREPARE waits for trustee to - * enter this state. After reaching IN_CHARGE, trustee - * tries to execute the pending worklist until it's empty - * and the state is set to BUTCHER, or the state is set - * to RELEASE. - * - * BUTCHER Command state which is set by the cpu callback after - * the cpu has went down. Once this state is set trustee - * knows that there will be no new works on the worklist - * and once the worklist is empty it can proceed to - * killing idle workers. - * - * RELEASE Command state which is set by the cpu callback if the - * cpu down has been canceled or it has come online - * again. After recognizing this state, trustee stops - * trying to drain or butcher and clears ROGUE, rebinds - * all remaining workers back to the cpu and releases - * manager role. - * - * DONE Trustee will enter this state after BUTCHER or RELEASE - * is complete. - * - * trustee CPU draining - * took over down complete - * START -----------> IN_CHARGE -----------> BUTCHER -----------> DONE - * | | ^ - * | CPU is back online v return workers | - * ----------------> RELEASE -------------- - */ - -/** - * trustee_wait_event_timeout - timed event wait for trustee - * @cond: condition to wait for - * @timeout: timeout in jiffies - * - * wait_event_timeout() for trustee to use. Handles locking and - * checks for RELEASE request. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by trustee. - * - * RETURNS: - * Positive indicating left time if @cond is satisfied, 0 if timed - * out, -1 if canceled. - */ -#define trustee_wait_event_timeout(cond, timeout) ({ \ - long __ret = (timeout); \ - while (!((cond) || (gcwq->trustee_state == TRUSTEE_RELEASE)) && \ - __ret) { \ - spin_unlock_irq(&gcwq->lock); \ - __wait_event_timeout(gcwq->trustee_wait, (cond) || \ - (gcwq->trustee_state == TRUSTEE_RELEASE), \ - __ret); \ - spin_lock_irq(&gcwq->lock); \ - } \ - gcwq->trustee_state == TRUSTEE_RELEASE ? -1 : (__ret); \ -}) - -/** - * trustee_wait_event - event wait for trustee - * @cond: condition to wait for - * - * wait_event() for trustee to use. Automatically handles locking and - * checks for CANCEL request. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by trustee. - * - * RETURNS: - * 0 if @cond is satisfied, -1 if canceled. + * This is solved by allowing a gcwq to be disassociated from the CPU + * running as an unbound one and allowing it to be reattached later if the + * cpu comes back online. */ -#define trustee_wait_event(cond) ({ \ - long __ret1; \ - __ret1 = trustee_wait_event_timeout(cond, MAX_SCHEDULE_TIMEOUT);\ - __ret1 < 0 ? -1 : 0; \ -}) -static int __cpuinit trustee_thread(void *__gcwq) +/* claim manager positions of all pools */ +static void gcwq_claim_management_and_lock(struct global_cwq *gcwq) { - struct global_cwq *gcwq = __gcwq; - struct worker *worker; - struct work_struct *work; - struct hlist_node *pos; - long rc; - int i; - - BUG_ON(gcwq->cpu != smp_processor_id()); + struct worker_pool *pool; + for_each_worker_pool(pool, gcwq) + mutex_lock_nested(&pool->manager_mutex, pool - gcwq->pools); spin_lock_irq(&gcwq->lock); - /* - * Claim the manager position and make all workers rogue. - * Trustee must be bound to the target cpu and can't be - * cancelled. - */ - BUG_ON(gcwq->cpu != smp_processor_id()); - rc = trustee_wait_event(!(gcwq->flags & GCWQ_MANAGING_WORKERS)); - BUG_ON(rc < 0); - - gcwq->flags |= GCWQ_MANAGING_WORKERS; - - list_for_each_entry(worker, &gcwq->idle_list, entry) - worker->flags |= WORKER_ROGUE; +} - for_each_busy_worker(worker, i, pos, gcwq) - worker->flags |= WORKER_ROGUE; +/* release manager positions */ +static void gcwq_release_management_and_unlock(struct global_cwq *gcwq) +{ + struct worker_pool *pool; - /* - * Call schedule() so that we cross rq->lock and thus can - * guarantee sched callbacks see the rogue flag. This is - * necessary as scheduler callbacks may be invoked from other - * cpus. - */ spin_unlock_irq(&gcwq->lock); - schedule(); - spin_lock_irq(&gcwq->lock); + for_each_worker_pool(pool, gcwq) + mutex_unlock(&pool->manager_mutex); +} - /* - * Sched callbacks are disabled now. Zap nr_running. After - * this, nr_running stays zero and need_more_worker() and - * keep_working() are always true as long as the worklist is - * not empty. - */ - atomic_set(get_gcwq_nr_running(gcwq->cpu), 0); +static void gcwq_unbind_fn(struct work_struct *work) +{ + struct global_cwq *gcwq = get_gcwq(smp_processor_id()); + struct worker_pool *pool; + struct worker *worker; + struct hlist_node *pos; + int i; - spin_unlock_irq(&gcwq->lock); - del_timer_sync(&gcwq->idle_timer); - spin_lock_irq(&gcwq->lock); + BUG_ON(gcwq->cpu != smp_processor_id()); - /* - * We're now in charge. Notify and proceed to drain. We need - * to keep the gcwq running during the whole CPU down - * procedure as other cpu hotunplug callbacks may need to - * flush currently running tasks. - */ - gcwq->trustee_state = TRUSTEE_IN_CHARGE; - wake_up_all(&gcwq->trustee_wait); + gcwq_claim_management_and_lock(gcwq); /* - * The original cpu is in the process of dying and may go away - * anytime now. When that happens, we and all workers would - * be migrated to other cpus. Try draining any left work. We - * want to get it over with ASAP - spam rescuers, wake up as - * many idlers as necessary and create new ones till the - * worklist is empty. Note that if the gcwq is frozen, there - * may be frozen works in freezable cwqs. Don't declare - * completion while frozen. + * We've claimed all manager positions. Make all workers unbound + * and set DISASSOCIATED. Before this, all workers except for the + * ones which are still executing works from before the last CPU + * down must be on the cpu. After this, they may become diasporas. */ - while (gcwq->nr_workers != gcwq->nr_idle || - gcwq->flags & GCWQ_FREEZING || - gcwq->trustee_state == TRUSTEE_IN_CHARGE) { - int nr_works = 0; - - list_for_each_entry(work, &gcwq->worklist, entry) { - send_mayday(work); - nr_works++; - } + for_each_worker_pool(pool, gcwq) + list_for_each_entry(worker, &pool->idle_list, entry) + worker->flags |= WORKER_UNBOUND; - list_for_each_entry(worker, &gcwq->idle_list, entry) { - if (!nr_works--) - break; - wake_up_process(worker->task); - } + for_each_busy_worker(worker, i, pos, gcwq) + worker->flags |= WORKER_UNBOUND; - if (need_to_create_worker(gcwq)) { - spin_unlock_irq(&gcwq->lock); - worker = create_worker(gcwq, false); - spin_lock_irq(&gcwq->lock); - if (worker) { - worker->flags |= WORKER_ROGUE; - start_worker(worker); - } - } + gcwq->flags |= GCWQ_DISASSOCIATED; - /* give a breather */ - if (trustee_wait_event_timeout(false, TRUSTEE_COOLDOWN) < 0) - break; - } + gcwq_release_management_and_unlock(gcwq); /* - * Either all works have been scheduled and cpu is down, or - * cpu down has already been canceled. Wait for and butcher - * all workers till we're canceled. + * Call schedule() so that we cross rq->lock and thus can guarantee + * sched callbacks see the %WORKER_UNBOUND flag. This is necessary + * as scheduler callbacks may be invoked from other cpus. */ - do { - rc = trustee_wait_event(!list_empty(&gcwq->idle_list)); - while (!list_empty(&gcwq->idle_list)) - destroy_worker(list_first_entry(&gcwq->idle_list, - struct worker, entry)); - } while (gcwq->nr_workers && rc >= 0); + schedule(); /* - * At this point, either draining has completed and no worker - * is left, or cpu down has been canceled or the cpu is being - * brought back up. There shouldn't be any idle one left. - * Tell the remaining busy ones to rebind once it finishes the - * currently scheduled works by scheduling the rebind_work. + * Sched callbacks are disabled now. Zap nr_running. After this, + * nr_running stays zero and need_more_worker() and keep_working() + * are always true as long as the worklist is not empty. @gcwq now + * behaves as unbound (in terms of concurrency management) gcwq + * which is served by workers tied to the CPU. + * + * On return from this function, the current worker would trigger + * unbound chain execution of pending work items if other workers + * didn't already. */ - WARN_ON(!list_empty(&gcwq->idle_list)); - - for_each_busy_worker(worker, i, pos, gcwq) { - struct work_struct *rebind_work = &worker->rebind_work; - - /* - * Rebind_work may race with future cpu hotplug - * operations. Use a separate flag to mark that - * rebinding is scheduled. - */ - worker->flags |= WORKER_REBIND; - worker->flags &= ~WORKER_ROGUE; - - /* queue rebind_work, wq doesn't matter, use the default one */ - if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, - work_data_bits(rebind_work))) - continue; - - debug_work_activate(rebind_work); - insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work, - worker->scheduled.next, - work_color_to_flags(WORK_NO_COLOR)); - } - - /* relinquish manager role */ - gcwq->flags &= ~GCWQ_MANAGING_WORKERS; - - /* notify completion */ - gcwq->trustee = NULL; - gcwq->trustee_state = TRUSTEE_DONE; - wake_up_all(&gcwq->trustee_wait); - spin_unlock_irq(&gcwq->lock); - return 0; + for_each_worker_pool(pool, gcwq) + atomic_set(get_pool_nr_running(pool), 0); } -/** - * wait_trustee_state - wait for trustee to enter the specified state - * @gcwq: gcwq the trustee of interest belongs to - * @state: target state to wait for - * - * Wait for the trustee to reach @state. DONE is already matched. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by cpu_callback. +/* + * Workqueues should be brought up before normal priority CPU notifiers. + * This will be registered high priority CPU notifier. */ -static void __cpuinit wait_trustee_state(struct global_cwq *gcwq, int state) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) -{ - if (!(gcwq->trustee_state == state || - gcwq->trustee_state == TRUSTEE_DONE)) { - spin_unlock_irq(&gcwq->lock); - __wait_event(gcwq->trustee_wait, - gcwq->trustee_state == state || - gcwq->trustee_state == TRUSTEE_DONE); - spin_lock_irq(&gcwq->lock); - } -} - -static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) { unsigned int cpu = (unsigned long)hcpu; struct global_cwq *gcwq = get_gcwq(cpu); - struct task_struct *new_trustee = NULL; - struct worker *uninitialized_var(new_worker); - unsigned long flags; + struct worker_pool *pool; - action &= ~CPU_TASKS_FROZEN; - - switch (action) { - case CPU_DOWN_PREPARE: - new_trustee = kthread_create(trustee_thread, gcwq, - "workqueue_trustee/%d\n", cpu); - if (IS_ERR(new_trustee)) - return notifier_from_errno(PTR_ERR(new_trustee)); - kthread_bind(new_trustee, cpu); - /* fall through */ + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - BUG_ON(gcwq->first_idle); - new_worker = create_worker(gcwq, false); - if (!new_worker) { - if (new_trustee) - kthread_stop(new_trustee); - return NOTIFY_BAD; - } - } - - /* some are called w/ irq disabled, don't disturb irq status */ - spin_lock_irqsave(&gcwq->lock, flags); + for_each_worker_pool(pool, gcwq) { + struct worker *worker; - switch (action) { - case CPU_DOWN_PREPARE: - /* initialize trustee and tell it to acquire the gcwq */ - BUG_ON(gcwq->trustee || gcwq->trustee_state != TRUSTEE_DONE); - gcwq->trustee = new_trustee; - gcwq->trustee_state = TRUSTEE_START; - wake_up_process(gcwq->trustee); - wait_trustee_state(gcwq, TRUSTEE_IN_CHARGE); - /* fall through */ - case CPU_UP_PREPARE: - BUG_ON(gcwq->first_idle); - gcwq->first_idle = new_worker; - break; + if (pool->nr_workers) + continue; - case CPU_DYING: - /* - * Before this, the trustee and all workers except for - * the ones which are still executing works from - * before the last CPU down must be on the cpu. After - * this, they'll all be diasporas. - */ - gcwq->flags |= GCWQ_DISASSOCIATED; - break; + worker = create_worker(pool); + if (!worker) + return NOTIFY_BAD; - case CPU_POST_DEAD: - gcwq->trustee_state = TRUSTEE_BUTCHER; - /* fall through */ - case CPU_UP_CANCELED: - destroy_worker(gcwq->first_idle); - gcwq->first_idle = NULL; + spin_lock_irq(&gcwq->lock); + start_worker(worker); + spin_unlock_irq(&gcwq->lock); + } break; case CPU_DOWN_FAILED: case CPU_ONLINE: + gcwq_claim_management_and_lock(gcwq); gcwq->flags &= ~GCWQ_DISASSOCIATED; - if (gcwq->trustee_state != TRUSTEE_DONE) { - gcwq->trustee_state = TRUSTEE_RELEASE; - wake_up_process(gcwq->trustee); - wait_trustee_state(gcwq, TRUSTEE_DONE); - } - - /* - * Trustee is done and there might be no worker left. - * Put the first_idle in and request a real manager to - * take a look. - */ - spin_unlock_irq(&gcwq->lock); - kthread_bind(gcwq->first_idle->task, cpu); - spin_lock_irq(&gcwq->lock); - gcwq->flags |= GCWQ_MANAGE_WORKERS; - start_worker(gcwq->first_idle); - gcwq->first_idle = NULL; + rebind_workers(gcwq); + gcwq_release_management_and_unlock(gcwq); break; } + return NOTIFY_OK; +} - spin_unlock_irqrestore(&gcwq->lock, flags); +/* + * Workqueues should be brought down after normal priority CPU notifiers. + * This will be registered as low priority CPU notifier. + */ +static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + struct work_struct unbind_work; - return notifier_from_errno(0); + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + /* unbinding should happen on the local CPU */ + INIT_WORK_ONSTACK(&unbind_work, gcwq_unbind_fn); + schedule_work_on(cpu, &unbind_work); + flush_work(&unbind_work); + break; + } + return NOTIFY_OK; } #ifdef CONFIG_SMP struct work_for_cpu { - struct completion completion; + struct work_struct work; long (*fn)(void *); void *arg; long ret; }; -static int do_work_for_cpu(void *_wfc) +static void work_for_cpu_fn(struct work_struct *work) { - struct work_for_cpu *wfc = _wfc; + struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); + wfc->ret = wfc->fn(wfc->arg); - complete(&wfc->completion); - return 0; } /** @@ -3619,19 +3601,11 @@ static int do_work_for_cpu(void *_wfc) */ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) { - struct task_struct *sub_thread; - struct work_for_cpu wfc = { - .completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion), - .fn = fn, - .arg = arg, - }; + struct work_for_cpu wfc = { .fn = fn, .arg = arg }; - sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu"); - if (IS_ERR(sub_thread)) - return PTR_ERR(sub_thread); - kthread_bind(sub_thread, cpu); - wake_up_process(sub_thread); - wait_for_completion(&wfc.completion); + INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); + schedule_work_on(cpu, &wfc.work); + flush_work(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); @@ -3746,6 +3720,7 @@ void thaw_workqueues(void) for_each_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); + struct worker_pool *pool; struct workqueue_struct *wq; spin_lock_irq(&gcwq->lock); @@ -3767,7 +3742,8 @@ void thaw_workqueues(void) cwq_activate_first_delayed(cwq); } - wake_up_worker(gcwq); + for_each_worker_pool(pool, gcwq) + wake_up_worker(pool); spin_unlock_irq(&gcwq->lock); } @@ -3783,46 +3759,57 @@ static int __init init_workqueues(void) unsigned int cpu; int i; - cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); + cpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); /* initialize gcwqs */ for_each_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); + struct worker_pool *pool; spin_lock_init(&gcwq->lock); - INIT_LIST_HEAD(&gcwq->worklist); gcwq->cpu = cpu; gcwq->flags |= GCWQ_DISASSOCIATED; - INIT_LIST_HEAD(&gcwq->idle_list); for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) INIT_HLIST_HEAD(&gcwq->busy_hash[i]); - init_timer_deferrable(&gcwq->idle_timer); - gcwq->idle_timer.function = idle_worker_timeout; - gcwq->idle_timer.data = (unsigned long)gcwq; + for_each_worker_pool(pool, gcwq) { + pool->gcwq = gcwq; + INIT_LIST_HEAD(&pool->worklist); + INIT_LIST_HEAD(&pool->idle_list); - setup_timer(&gcwq->mayday_timer, gcwq_mayday_timeout, - (unsigned long)gcwq); + init_timer_deferrable(&pool->idle_timer); + pool->idle_timer.function = idle_worker_timeout; + pool->idle_timer.data = (unsigned long)pool; - ida_init(&gcwq->worker_ida); + setup_timer(&pool->mayday_timer, gcwq_mayday_timeout, + (unsigned long)pool); - gcwq->trustee_state = TRUSTEE_DONE; - init_waitqueue_head(&gcwq->trustee_wait); + mutex_init(&pool->manager_mutex); + ida_init(&pool->worker_ida); + } + + init_waitqueue_head(&gcwq->rebind_hold); } /* create the initial worker */ for_each_online_gcwq_cpu(cpu) { struct global_cwq *gcwq = get_gcwq(cpu); - struct worker *worker; + struct worker_pool *pool; if (cpu != WORK_CPU_UNBOUND) gcwq->flags &= ~GCWQ_DISASSOCIATED; - worker = create_worker(gcwq, true); - BUG_ON(!worker); - spin_lock_irq(&gcwq->lock); - start_worker(worker); - spin_unlock_irq(&gcwq->lock); + + for_each_worker_pool(pool, gcwq) { + struct worker *worker; + + worker = create_worker(pool); + BUG_ON(!worker); + spin_lock_irq(&gcwq->lock); + start_worker(worker); + spin_unlock_irq(&gcwq->lock); + } } system_wq = alloc_workqueue("events", 0, 0); |