diff options
Diffstat (limited to 'kernel')
49 files changed, 955 insertions, 396 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 9a3ec66..19fad00 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,8 +11,6 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o -CFLAGS_REMOVE_sched.o = -mno-spe - ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files CFLAGS_REMOVE_lockdep.o = -pg @@ -21,7 +19,7 @@ CFLAGS_REMOVE_mutex-debug.o = -pg CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_sched_clock.o = -pg -CFLAGS_REMOVE_sched.o = -mno-spe -pg +CFLAGS_REMOVE_sched.o = -pg endif obj-$(CONFIG_FREEZER) += freezer.o diff --git a/kernel/audit.c b/kernel/audit.c index 4414e93..ce6d8ea 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -61,8 +61,11 @@ #include "audit.h" -/* No auditing will take place until audit_initialized != 0. +/* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. * (Initialization happens after skb_init is called.) */ +#define AUDIT_DISABLED -1 +#define AUDIT_UNINITIALIZED 0 +#define AUDIT_INITIALIZED 1 static int audit_initialized; #define AUDIT_OFF 0 @@ -965,6 +968,9 @@ static int __init audit_init(void) { int i; + 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, @@ -976,7 +982,7 @@ static int __init audit_init(void) skb_queue_head_init(&audit_skb_queue); skb_queue_head_init(&audit_skb_hold_queue); - audit_initialized = 1; + audit_initialized = AUDIT_INITIALIZED; audit_enabled = audit_default; audit_ever_enabled |= !!audit_default; @@ -999,13 +1005,21 @@ __initcall(audit_init); static int __init audit_enable(char *str) { audit_default = !!simple_strtol(str, NULL, 0); - printk(KERN_INFO "audit: %s%s\n", - audit_default ? "enabled" : "disabled", - audit_initialized ? "" : " (after initialization)"); - if (audit_initialized) { + if (!audit_default) + audit_initialized = AUDIT_DISABLED; + + printk(KERN_INFO "audit: %s", audit_default ? "enabled" : "disabled"); + + if (audit_initialized == AUDIT_INITIALIZED) { audit_enabled = audit_default; audit_ever_enabled |= !!audit_default; + } else if (audit_initialized == AUDIT_UNINITIALIZED) { + printk(" (after initialization)"); + } else { + printk(" (until reboot)"); } + printk("\n"); + return 1; } @@ -1107,9 +1121,7 @@ unsigned int audit_serial(void) static inline void audit_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { - if (ctx) - auditsc_get_stamp(ctx, t, serial); - else { + if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { *t = CURRENT_TIME; *serial = audit_serial(); } @@ -1146,7 +1158,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int reserve; unsigned long timeout_start = jiffies; - if (!audit_initialized) + if (audit_initialized != AUDIT_INITIALIZED) return NULL; if (unlikely(audit_filter_type(type))) diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 8ba0e0d..8b50944 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -24,6 +24,7 @@ struct audit_chunk { struct list_head trees; /* with root here */ int dead; int count; + atomic_long_t refs; struct rcu_head head; struct node { struct list_head list; @@ -56,7 +57,8 @@ static LIST_HEAD(prune_list); * tree is refcounted; one reference for "some rules on rules_list refer to * it", one for each chunk with pointer to it. * - * chunk is refcounted by embedded inotify_watch. + * chunk is refcounted by embedded inotify_watch + .refs (non-zero refcount + * of watch contributes 1 to .refs). * * node.index allows to get from node.list to containing chunk. * MSB of that sucker is stolen to mark taggings that we might have to @@ -121,6 +123,7 @@ static struct audit_chunk *alloc_chunk(int count) INIT_LIST_HEAD(&chunk->hash); INIT_LIST_HEAD(&chunk->trees); chunk->count = count; + atomic_long_set(&chunk->refs, 1); for (i = 0; i < count; i++) { INIT_LIST_HEAD(&chunk->owners[i].list); chunk->owners[i].index = i; @@ -129,9 +132,8 @@ static struct audit_chunk *alloc_chunk(int count) return chunk; } -static void __free_chunk(struct rcu_head *rcu) +static void free_chunk(struct audit_chunk *chunk) { - struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head); int i; for (i = 0; i < chunk->count; i++) { @@ -141,14 +143,16 @@ static void __free_chunk(struct rcu_head *rcu) kfree(chunk); } -static inline void free_chunk(struct audit_chunk *chunk) +void audit_put_chunk(struct audit_chunk *chunk) { - call_rcu(&chunk->head, __free_chunk); + if (atomic_long_dec_and_test(&chunk->refs)) + free_chunk(chunk); } -void audit_put_chunk(struct audit_chunk *chunk) +static void __put_chunk(struct rcu_head *rcu) { - put_inotify_watch(&chunk->watch); + struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head); + audit_put_chunk(chunk); } enum {HASH_SIZE = 128}; @@ -176,7 +180,7 @@ struct audit_chunk *audit_tree_lookup(const struct inode *inode) list_for_each_entry_rcu(p, list, hash) { if (p->watch.inode == inode) { - get_inotify_watch(&p->watch); + atomic_long_inc(&p->refs); return p; } } @@ -194,17 +198,49 @@ int audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree) /* tagging and untagging inodes with trees */ -static void untag_chunk(struct audit_chunk *chunk, struct node *p) +static struct audit_chunk *find_chunk(struct node *p) +{ + int index = p->index & ~(1U<<31); + p -= index; + return container_of(p, struct audit_chunk, owners[0]); +} + +static void untag_chunk(struct node *p) { + struct audit_chunk *chunk = find_chunk(p); struct audit_chunk *new; struct audit_tree *owner; int size = chunk->count - 1; int i, j; + if (!pin_inotify_watch(&chunk->watch)) { + /* + * Filesystem is shutting down; all watches are getting + * evicted, just take it off the node list for this + * tree and let the eviction logics take care of the + * rest. + */ + owner = p->owner; + if (owner->root == chunk) { + list_del_init(&owner->same_root); + owner->root = NULL; + } + list_del_init(&p->list); + p->owner = NULL; + put_tree(owner); + return; + } + + spin_unlock(&hash_lock); + + /* + * pin_inotify_watch() succeeded, so the watch won't go away + * from under us. + */ mutex_lock(&chunk->watch.inode->inotify_mutex); if (chunk->dead) { mutex_unlock(&chunk->watch.inode->inotify_mutex); - return; + goto out; } owner = p->owner; @@ -221,7 +257,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct node *p) inotify_evict_watch(&chunk->watch); mutex_unlock(&chunk->watch.inode->inotify_mutex); put_inotify_watch(&chunk->watch); - return; + goto out; } new = alloc_chunk(size); @@ -263,7 +299,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct node *p) inotify_evict_watch(&chunk->watch); mutex_unlock(&chunk->watch.inode->inotify_mutex); put_inotify_watch(&chunk->watch); - return; + goto out; Fallback: // do the best we can @@ -277,6 +313,9 @@ Fallback: put_tree(owner); spin_unlock(&hash_lock); mutex_unlock(&chunk->watch.inode->inotify_mutex); +out: + unpin_inotify_watch(&chunk->watch); + spin_lock(&hash_lock); } static int create_chunk(struct inode *inode, struct audit_tree *tree) @@ -387,13 +426,6 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) return 0; } -static struct audit_chunk *find_chunk(struct node *p) -{ - int index = p->index & ~(1U<<31); - p -= index; - return container_of(p, struct audit_chunk, owners[0]); -} - static void kill_rules(struct audit_tree *tree) { struct audit_krule *rule, *next; @@ -431,17 +463,10 @@ static void prune_one(struct audit_tree *victim) spin_lock(&hash_lock); while (!list_empty(&victim->chunks)) { struct node *p; - struct audit_chunk *chunk; p = list_entry(victim->chunks.next, struct node, list); - chunk = find_chunk(p); - get_inotify_watch(&chunk->watch); - spin_unlock(&hash_lock); - - untag_chunk(chunk, p); - put_inotify_watch(&chunk->watch); - spin_lock(&hash_lock); + untag_chunk(p); } spin_unlock(&hash_lock); put_tree(victim); @@ -469,7 +494,6 @@ static void trim_marked(struct audit_tree *tree) while (!list_empty(&tree->chunks)) { struct node *node; - struct audit_chunk *chunk; node = list_entry(tree->chunks.next, struct node, list); @@ -477,14 +501,7 @@ static void trim_marked(struct audit_tree *tree) if (!(node->index & (1U<<31))) break; - chunk = find_chunk(node); - get_inotify_watch(&chunk->watch); - spin_unlock(&hash_lock); - - untag_chunk(chunk, node); - - put_inotify_watch(&chunk->watch); - spin_lock(&hash_lock); + untag_chunk(node); } if (!tree->root && !tree->goner) { tree->goner = 1; @@ -878,7 +895,7 @@ static void handle_event(struct inotify_watch *watch, u32 wd, u32 mask, static void destroy_watch(struct inotify_watch *watch) { struct audit_chunk *chunk = container_of(watch, struct audit_chunk, watch); - free_chunk(chunk); + call_rcu(&chunk->head, __put_chunk); } static const struct inotify_operations rtree_inotify_ops = { diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b7d354e..9fd85a4 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1094,8 +1094,8 @@ static void audit_inotify_unregister(struct list_head *in_list) list_for_each_entry_safe(p, n, in_list, ilist) { list_del(&p->ilist); inotify_rm_watch(audit_ih, &p->wdata); - /* the put matching the get in audit_do_del_rule() */ - put_inotify_watch(&p->wdata); + /* the unpin matching the pin in audit_do_del_rule() */ + unpin_inotify_watch(&p->wdata); } } @@ -1389,9 +1389,13 @@ static inline int audit_del_rule(struct audit_entry *entry, /* Put parent on the inotify un-registration * list. Grab a reference before releasing * audit_filter_mutex, to be released in - * audit_inotify_unregister(). */ - list_add(&parent->ilist, &inotify_list); - get_inotify_watch(&parent->wdata); + * audit_inotify_unregister(). + * If filesystem is going away, just leave + * the sucker alone, eviction will take + * care of it. + */ + if (pin_inotify_watch(&parent->wdata)) + list_add(&parent->ilist, &inotify_list); } } } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index cf5bc2f..2a3f0af 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1459,7 +1459,6 @@ void audit_free(struct task_struct *tsk) /** * audit_syscall_entry - fill in an audit record at syscall entry - * @tsk: task being audited * @arch: architecture type * @major: major syscall type (function) * @a1: additional syscall register 1 @@ -1548,9 +1547,25 @@ void audit_syscall_entry(int arch, int major, context->ppid = 0; } +void audit_finish_fork(struct task_struct *child) +{ + struct audit_context *ctx = current->audit_context; + struct audit_context *p = child->audit_context; + if (!p || !ctx || !ctx->auditable) + return; + p->arch = ctx->arch; + p->major = ctx->major; + memcpy(p->argv, ctx->argv, sizeof(ctx->argv)); + p->ctime = ctx->ctime; + p->dummy = ctx->dummy; + p->auditable = ctx->auditable; + p->in_syscall = ctx->in_syscall; + p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL); + p->ppid = current->pid; +} + /** * audit_syscall_exit - deallocate audit context after a system call - * @tsk: task being audited * @valid: success/failure flag * @return_code: syscall return value * @@ -1942,15 +1957,18 @@ EXPORT_SYMBOL_GPL(__audit_inode_child); * * Also sets the context as auditable. */ -void auditsc_get_stamp(struct audit_context *ctx, +int auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { + if (!ctx->in_syscall) + return 0; if (!ctx->serial) ctx->serial = audit_serial(); t->tv_sec = ctx->ctime.tv_sec; t->tv_nsec = ctx->ctime.tv_nsec; *serial = ctx->serial; ctx->auditable = 1; + return 1; } /* global counter which is incremented every time something logs in */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 35eebd5..8185a0f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -702,7 +702,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, * any child cgroups exist. This is theoretically supportable * but involves complex error handling, so it's being left until * later */ - if (!list_empty(&cgrp->children)) + if (root->number_of_cgroups > 1) return -EBUSY; /* Process each subsystem */ @@ -2039,10 +2039,13 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) struct cgroup *cgrp; struct cgroup_iter it; struct task_struct *tsk; + /* - * Validate dentry by checking the superblock operations + * Validate dentry by checking the superblock operations, + * and make sure it's a directory. */ - if (dentry->d_sb->s_op != &cgroup_ops) + if (dentry->d_sb->s_op != &cgroup_ops || + !S_ISDIR(dentry->d_inode->i_mode)) goto err; ret = 0; @@ -2472,10 +2475,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) mutex_unlock(&cgroup_mutex); return -EBUSY; } - - parent = cgrp->parent; - root = cgrp->root; - sb = root->sb; + mutex_unlock(&cgroup_mutex); /* * Call pre_destroy handlers of subsys. Notify subsystems @@ -2483,7 +2483,14 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) */ cgroup_call_pre_destroy(cgrp); - if (cgroup_has_css_refs(cgrp)) { + mutex_lock(&cgroup_mutex); + parent = cgrp->parent; + root = cgrp->root; + sb = root->sb; + + if (atomic_read(&cgrp->count) + || !list_empty(&cgrp->children) + || cgroup_has_css_refs(cgrp)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } @@ -2497,7 +2504,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) list_del(&cgrp->sibling); spin_lock(&cgrp->dentry->d_lock); d = dget(cgrp->dentry); - cgrp->dentry = NULL; spin_unlock(&d->d_lock); cgroup_d_remove_dir(d); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 7fa476f..fb249e2 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -184,9 +184,20 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) { struct freezer *freezer; - task_lock(task); + /* + * No lock is needed, since the task isn't on tasklist yet, + * so it can't be moved to another cgroup, which means the + * freezer won't be removed and will be valid during this + * function call. + */ freezer = task_freezer(task); - task_unlock(task); + + /* + * The root cgroup is non-freezable, so we can skip the + * following check. + */ + if (!freezer->css.cgroup->parent) + return; spin_lock_irq(&freezer->lock); BUG_ON(freezer->state == CGROUP_FROZEN); @@ -331,7 +342,7 @@ static int freezer_write(struct cgroup *cgroup, else if (strcmp(buffer, freezer_state_strs[CGROUP_FROZEN]) == 0) goal_state = CGROUP_FROZEN; else - return -EIO; + return -EINVAL; if (!cgroup_lock_live_group(cgroup)) return -ENODEV; @@ -350,6 +361,8 @@ static struct cftype files[] = { static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup) { + if (!cgroup->parent) + return 0; return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files)); } diff --git a/kernel/cpu.c b/kernel/cpu.c index 86d4904..8ea32e8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -462,7 +462,7 @@ out: * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ -void notify_cpu_starting(unsigned int cpu) +void __cpuinit notify_cpu_starting(unsigned int cpu) { unsigned long val = CPU_STARTING; @@ -499,3 +499,6 @@ const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); + +const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; +EXPORT_SYMBOL(cpu_all_bits); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3e00526..96c0ba1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -36,6 +36,7 @@ #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> +#include <linux/memory.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/namei.h> @@ -584,10 +585,9 @@ static int generate_sched_domains(cpumask_t **domains, int i, j, k; /* indices for partition finding loops */ cpumask_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ - int ndoms; /* number of sched domains in result */ + int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] cpumask_t slot */ - ndoms = 0; doms = NULL; dattr = NULL; csa = NULL; @@ -674,10 +674,8 @@ restart: * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL); - if (!doms) { - ndoms = 0; + if (!doms) goto done; - } /* * The rest of the code, including the scheduler, can deal with @@ -732,6 +730,13 @@ restart: done: kfree(csa); + /* + * Fallback to the default domain if kmalloc() failed. + * See comments in partition_sched_domains(). + */ + if (doms == NULL) + ndoms = 1; + *domains = doms; *attributes = dattr; return ndoms; @@ -2011,12 +2016,23 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, * Call this routine anytime after node_states[N_HIGH_MEMORY] changes. * See also the previous routine cpuset_track_online_cpus(). */ -void cpuset_track_online_nodes(void) +static int cpuset_track_online_nodes(struct notifier_block *self, + unsigned long action, void *arg) { cgroup_lock(); - top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; - scan_for_empty_cpusets(&top_cpuset); + switch (action) { + case MEM_ONLINE: + top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; + break; + case MEM_OFFLINE: + top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; + scan_for_empty_cpusets(&top_cpuset); + break; + default: + break; + } cgroup_unlock(); + return NOTIFY_OK; } #endif @@ -2032,6 +2048,7 @@ void __init cpuset_init_smp(void) top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; hotcpu_notifier(cpuset_track_online_cpus, 0); + hotplug_memory_notifier(cpuset_track_online_nodes, 10); } /** diff --git a/kernel/exit.c b/kernel/exit.c index 80137a5..2d8be7e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -40,7 +40,6 @@ #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> -#include <linux/compat.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> @@ -141,6 +140,11 @@ static void __exit_signal(struct task_struct *tsk) if (sig) { flush_sigqueue(&sig->shared_pending); taskstats_tgid_free(sig); + /* + * Make sure ->signal can't go away under rq->lock, + * see account_group_exec_runtime(). + */ + task_rq_unlock_wait(tsk); __cleanup_signal(sig); } } @@ -1054,14 +1058,6 @@ NORET_TYPE void do_exit(long code) exit_itimers(tsk->signal); } acct_collect(code, group_dead); -#ifdef CONFIG_FUTEX - if (unlikely(tsk->robust_list)) - exit_robust_list(tsk); -#ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) - compat_exit_robust_list(tsk); -#endif -#endif if (group_dead) tty_audit_exit(); if (unlikely(tsk->audit_context)) diff --git a/kernel/fork.c b/kernel/fork.c index f608356..495da2e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -40,6 +40,7 @@ #include <linux/jiffies.h> #include <linux/tracehook.h> #include <linux/futex.h> +#include <linux/compat.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> @@ -314,17 +315,20 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; + struct address_space *mapping = file->f_mapping; + get_file(file); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); - - /* insert tmp into the share list, just after mpnt */ - spin_lock(&file->f_mapping->i_mmap_lock); + spin_lock(&mapping->i_mmap_lock); + if (tmp->vm_flags & VM_SHARED) + mapping->i_mmap_writable++; tmp->vm_truncate_count = mpnt->vm_truncate_count; - flush_dcache_mmap_lock(file->f_mapping); + flush_dcache_mmap_lock(mapping); + /* insert tmp into the share list, just after mpnt */ vma_prio_tree_add(tmp, mpnt); - flush_dcache_mmap_unlock(file->f_mapping); - spin_unlock(&file->f_mapping->i_mmap_lock); + flush_dcache_mmap_unlock(mapping); + spin_unlock(&mapping->i_mmap_lock); } /* @@ -519,6 +523,16 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) { struct completion *vfork_done = tsk->vfork_done; + /* Get rid of any futexes when releasing the mm */ +#ifdef CONFIG_FUTEX + if (unlikely(tsk->robust_list)) + exit_robust_list(tsk); +#ifdef CONFIG_COMPAT + if (unlikely(tsk->compat_robust_list)) + compat_exit_robust_list(tsk); +#endif +#endif + /* Get rid of any cached register state */ deactivate_mm(tsk, mm); @@ -1387,6 +1401,7 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } + audit_finish_fork(p); tracehook_report_clone(trace, regs, clone_flags, nr, p); /* diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 2b465df..47e6334 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -664,14 +664,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, /* Timer is expired, act upon the callback mode */ switch(timer->cb_mode) { - case HRTIMER_CB_IRQSAFE_NO_RESTART: - debug_hrtimer_deactivate(timer); - /* - * We can call the callback from here. No restart - * happens, so no danger of recursion - */ - BUG_ON(timer->function(timer) != HRTIMER_NORESTART); - return 1; case HRTIMER_CB_IRQSAFE_PERCPU: case HRTIMER_CB_IRQSAFE_UNLOCKED: /* @@ -683,7 +675,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, */ debug_hrtimer_deactivate(timer); return 1; - case HRTIMER_CB_IRQSAFE: case HRTIMER_CB_SOFTIRQ: /* * Move everything else into the softirq pending list ! @@ -1209,6 +1200,7 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base) enum hrtimer_restart (*fn)(struct hrtimer *); struct hrtimer *timer; int restart; + int emulate_hardirq_ctx = 0; timer = list_entry(cpu_base->cb_pending.next, struct hrtimer, cb_entry); @@ -1217,10 +1209,24 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base) timer_stats_account_hrtimer(timer); fn = timer->function; + /* + * A timer might have been added to the cb_pending list + * when it was migrated during a cpu-offline operation. + * Emulate hardirq context for such timers. + */ + if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU || + timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) + emulate_hardirq_ctx = 1; + __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0); spin_unlock_irq(&cpu_base->lock); - restart = fn(timer); + if (unlikely(emulate_hardirq_ctx)) { + local_irq_disable(); + restart = fn(timer); + local_irq_enable(); + } else + restart = fn(timer); spin_lock_irq(&cpu_base->lock); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index c9767e6..64c1c72 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -25,6 +25,8 @@ static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif +extern int irq_select_affinity_usr(unsigned int irq); + /* * Debugging printout: */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c498a1b..801addd 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -82,24 +82,27 @@ int irq_can_set_affinity(unsigned int irq) int irq_set_affinity(unsigned int irq, cpumask_t cpumask) { struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; if (!desc->chip->set_affinity) return -EINVAL; + spin_lock_irqsave(&desc->lock, flags); + #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); desc->affinity = cpumask; desc->chip->set_affinity(irq, cpumask); - spin_unlock_irqrestore(&desc->lock, flags); - } else - set_pending_irq(irq, cpumask); + } else { + desc->status |= IRQ_MOVE_PENDING; + desc->pending_mask = cpumask; + } #else desc->affinity = cpumask; desc->chip->set_affinity(irq, cpumask); #endif + desc->status |= IRQ_AFFINITY_SET; + spin_unlock_irqrestore(&desc->lock, flags); return 0; } @@ -107,24 +110,59 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask) /* * Generic version of the affinity autoselector. */ -int irq_select_affinity(unsigned int irq) +int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) { cpumask_t mask; - struct irq_desc *desc; if (!irq_can_set_affinity(irq)) return 0; cpus_and(mask, cpu_online_map, irq_default_affinity); - desc = irq_to_desc(irq); + /* + * Preserve an userspace affinity setup, but make sure that + * one of the targets is online. + */ + if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { + if (cpus_intersects(desc->affinity, cpu_online_map)) + mask = desc->affinity; + else + desc->status &= ~IRQ_AFFINITY_SET; + } + desc->affinity = mask; desc->chip->set_affinity(irq, mask); return 0; } +#else +static inline int do_irq_select_affinity(unsigned int irq, struct irq_desc *d) +{ + return irq_select_affinity(irq); +} #endif +/* + * Called when affinity is set via /proc/irq + */ +int irq_select_affinity_usr(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + int ret; + + spin_lock_irqsave(&desc->lock, flags); + ret = do_irq_select_affinity(irq, desc); + spin_unlock_irqrestore(&desc->lock, flags); + + return ret; +} + +#else +static inline int do_irq_select_affinity(int irq, struct irq_desc *desc) +{ + return 0; +} #endif /** @@ -327,7 +365,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, * IRQF_TRIGGER_* but the PIC does not support multiple * flow-types? */ - pr_warning("No set_type function for IRQ %d (%s)\n", irq, + pr_debug("No set_type function for IRQ %d (%s)\n", irq, chip ? (chip->name ? : "unknown") : "unknown"); return 0; } @@ -445,8 +483,12 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) /* Undo nested disables: */ desc->depth = 1; + /* Exclude IRQ from balancing if requested */ + if (new->flags & IRQF_NOBALANCING) + desc->status |= IRQ_NO_BALANCING; + /* Set default affinity mask once everything is setup */ - irq_select_affinity(irq); + do_irq_select_affinity(irq, desc); } else if ((new->flags & IRQF_TRIGGER_MASK) && (new->flags & IRQF_TRIGGER_MASK) @@ -459,10 +501,6 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) *p = new; - /* Exclude IRQ from balancing */ - if (new->flags & IRQF_NOBALANCING) - desc->status |= IRQ_NO_BALANCING; - /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; desc->irqs_unhandled = 0; diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 90b920d..9db681d 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -1,17 +1,6 @@ #include <linux/irq.h> -void set_pending_irq(unsigned int irq, cpumask_t mask) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); - desc->status |= IRQ_MOVE_PENDING; - desc->pending_mask = mask; - spin_unlock_irqrestore(&desc->lock, flags); -} - void move_masked_irq(int irq) { struct irq_desc *desc = irq_to_desc(irq); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 4d161c7..d257e7d 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -62,7 +62,7 @@ static ssize_t irq_affinity_proc_write(struct file *file, if (!cpus_intersects(new_value, cpu_online_map)) /* Special case for empty set - allow the architecture code to set default SMP affinity. */ - return irq_select_affinity(irq) ? -EINVAL : count; + return irq_select_affinity_usr(irq) ? -EINVAL : count; irq_set_affinity(irq, new_value); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 5072cf1..7b8b0f2 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -304,17 +304,24 @@ int sprint_symbol(char *buffer, unsigned long address) char *modname; const char *name; unsigned long offset, size; - char namebuf[KSYM_NAME_LEN]; + int len; - name = kallsyms_lookup(address, &size, &offset, &modname, namebuf); + name = kallsyms_lookup(address, &size, &offset, &modname, buffer); if (!name) return sprintf(buffer, "0x%lx", address); + if (name != buffer) + strcpy(buffer, name); + len = strlen(buffer); + buffer += len; + if (modname) - return sprintf(buffer, "%s+%#lx/%#lx [%s]", name, offset, - size, modname); + len += sprintf(buffer, "+%#lx/%#lx [%s]", + offset, size, modname); else - return sprintf(buffer, "%s+%#lx/%#lx", name, offset, size); + len += sprintf(buffer, "+%#lx/%#lx", offset, size); + + return len; } /* Look up a kernel symbol and print it to the kernel messages. */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 8b57a25..9f8a3f2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -72,7 +72,7 @@ static bool kprobe_enabled; DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { - spinlock_t lock ____cacheline_aligned; + spinlock_t lock ____cacheline_aligned_in_smp; } kretprobe_table_locks[KPROBE_TABLE_SIZE]; static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) @@ -613,30 +613,37 @@ static int __kprobes __register_kprobe(struct kprobe *p, return -EINVAL; p->addr = addr; - if (!kernel_text_address((unsigned long) p->addr) || - in_kprobes_functions((unsigned long) p->addr)) + preempt_disable(); + if (!__kernel_text_address((unsigned long) p->addr) || + in_kprobes_functions((unsigned long) p->addr)) { + preempt_enable(); return -EINVAL; + } p->mod_refcounted = 0; /* * Check if are we probing a module. */ - probed_mod = module_text_address((unsigned long) p->addr); + probed_mod = __module_text_address((unsigned long) p->addr); if (probed_mod) { - struct module *calling_mod = module_text_address(called_from); + struct module *calling_mod; + calling_mod = __module_text_address(called_from); /* * We must allow modules to probe themself and in this case * avoid incrementing the module refcount, so as to allow * unloading of self probing modules. */ if (calling_mod && calling_mod != probed_mod) { - if (unlikely(!try_module_get(probed_mod))) + if (unlikely(!try_module_get(probed_mod))) { + preempt_enable(); return -EINVAL; + } p->mod_refcounted = 1; } else probed_mod = NULL; } + preempt_enable(); p->nmissed = 0; INIT_LIST_HEAD(&p->list); @@ -718,6 +725,10 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) struct kprobe *old_p; if (p->mod_refcounted) { + /* + * Since we've already incremented refcount, + * we don't need to disable preemption. + */ mod = module_text_address((unsigned long)p->addr); if (mod) module_put(mod); diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 5e7b45c..449db46 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -191,7 +191,7 @@ static int lstats_show(struct seq_file *m, void *v) latency_record[i].time, latency_record[i].max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { - char sym[KSYM_NAME_LEN]; + char sym[KSYM_SYMBOL_LEN]; char *c; if (!latency_record[i].backtrace[q]) break; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 06e1571..46a4041 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3276,10 +3276,10 @@ void __init lockdep_info(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); - printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); + printk("... MAX_LOCKDEP_SUBCLASSES: %lu\n", MAX_LOCKDEP_SUBCLASSES); printk("... MAX_LOCK_DEPTH: %lu\n", MAX_LOCK_DEPTH); printk("... MAX_LOCKDEP_KEYS: %lu\n", MAX_LOCKDEP_KEYS); - printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); + printk("... CLASSHASH_SIZE: %lu\n", CLASSHASH_SIZE); printk("... MAX_LOCKDEP_ENTRIES: %lu\n", MAX_LOCKDEP_ENTRIES); printk("... MAX_LOCKDEP_CHAINS: %lu\n", MAX_LOCKDEP_CHAINS); printk("... CHAINHASH_SIZE: %lu\n", CHAINHASH_SIZE); diff --git a/kernel/panic.c b/kernel/panic.c index 6513aac..4d50883 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -167,6 +167,7 @@ static const struct tnt tnts[] = { * 'M' - System experienced a machine check exception. * 'B' - System has hit bad_page. * 'U' - Userspace-defined naughtiness. + * 'D' - Kernel has oopsed before * 'A' - ACPI table overridden. * 'W' - Taint on warning. * 'C' - modules from drivers/staging are loaded. diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 153dcb2..4e5288a 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -311,7 +311,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock, struct task_cputime cputime; thread_group_cputime(p, &cputime); - switch (which_clock) { + switch (CPUCLOCK_WHICH(which_clock)) { default: return -EINVAL; case CPUCLOCK_PROF: @@ -1308,9 +1308,10 @@ static inline int task_cputime_expired(const struct task_cputime *sample, */ static inline int fastpath_timer_check(struct task_struct *tsk) { - struct signal_struct *sig = tsk->signal; + struct signal_struct *sig; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) return 0; if (!task_cputime_zero(&tsk->cputime_expires)) { @@ -1323,6 +1324,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) return 1; } + + sig = tsk->signal; if (!task_cputime_zero(&sig->cputime_expires)) { struct task_cputime group_sample; diff --git a/kernel/power/main.c b/kernel/power/main.c index 19122cf..b8f7ce9 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -174,7 +174,7 @@ static void suspend_test_finish(const char *label) * has some performance issues. The stack dump of a WARN_ON * is more likely to get the right attention than a printk... */ - WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000)); + WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label); } #else diff --git a/kernel/power/swap.c b/kernel/power/swap.c index b7713b5..6da1435 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -633,7 +633,7 @@ void swsusp_close(fmode_t mode) return; } - blkdev_put(resume_bdev, mode); /* move up */ + blkdev_put(resume_bdev, mode); } static int swsusp_header_init(void) diff --git a/kernel/profile.c b/kernel/profile.c index 9830a03..dc41827 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -351,7 +351,7 @@ out: put_cpu(); } -static int __devinit profile_cpu_callback(struct notifier_block *info, +static int __cpuinit profile_cpu_callback(struct notifier_block *info, unsigned long action, void *__cpu) { int node, cpu = (unsigned long)__cpu; @@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = { }; #ifdef CONFIG_SMP -static void __init profile_nop(void *unused) +static inline void profile_nop(void *unused) { } @@ -596,7 +596,7 @@ out_cleanup: #define create_hash_tables() ({ 0; }) #endif -int create_proc_profile(void) +int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */ { struct proc_dir_entry *entry; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1e68e4c..4c8bcd7 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -612,7 +612,7 @@ int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data) return (copied == sizeof(data)) ? 0 : -EIO; } -#if defined CONFIG_COMPAT && defined __ARCH_WANT_COMPAT_SYS_PTRACE +#if defined CONFIG_COMPAT #include <linux/compat.h> int compat_ptrace_request(struct task_struct *child, compat_long_t request, @@ -709,4 +709,4 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, unlock_kernel(); return ret; } -#endif /* CONFIG_COMPAT && __ARCH_WANT_COMPAT_SYS_PTRACE */ +#endif /* CONFIG_COMPAT */ diff --git a/kernel/relay.c b/kernel/relay.c index 8d13a78..09ac200 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -400,7 +400,7 @@ void relay_reset(struct rchan *chan) } mutex_lock(&relay_channels_mutex); - for_each_online_cpu(i) + for_each_possible_cpu(i) if (chan->buf[i]) __relay_reset(chan->buf[i], 0); mutex_unlock(&relay_channels_mutex); @@ -611,10 +611,9 @@ struct rchan *relay_open(const char *base_filename, return chan; free_bufs: - for_each_online_cpu(i) { - if (!chan->buf[i]) - break; - relay_close_buf(chan->buf[i]); + for_each_possible_cpu(i) { + if (chan->buf[i]) + relay_close_buf(chan->buf[i]); } kref_put(&chan->kref, relay_destroy_channel); @@ -1318,12 +1317,9 @@ static ssize_t relay_file_splice_read(struct file *in, if (ret < 0) break; else if (!ret) { - if (spliced) - break; - if (flags & SPLICE_F_NONBLOCK) { + if (flags & SPLICE_F_NONBLOCK) ret = -EAGAIN; - break; - } + break; } *ppos += ret; diff --git a/kernel/sched.c b/kernel/sched.c index e8819bc..e4bb1dd 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -397,9 +397,9 @@ struct cfs_rq { * 'curr' points to currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). */ - struct sched_entity *curr, *next; + struct sched_entity *curr, *next, *last; - unsigned long nr_spread_over; + unsigned int nr_spread_over; #ifdef CONFIG_FAIR_GROUP_SCHED struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ @@ -969,6 +969,14 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) } } +void task_rq_unlock_wait(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + + smp_mb(); /* spin-unlock-wait is not a full memory barrier */ + spin_unlock_wait(&rq->lock); +} + static void __task_rq_unlock(struct rq *rq) __releases(rq->lock) { @@ -1445,9 +1453,12 @@ static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); + unsigned long nr_running = ACCESS_ONCE(rq->nr_running); - if (rq->nr_running) - rq->avg_load_per_task = rq->load.weight / rq->nr_running; + if (nr_running) + rq->avg_load_per_task = rq->load.weight / nr_running; + else + rq->avg_load_per_task = 0; return rq->avg_load_per_task; } @@ -1805,7 +1816,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) /* * Buddy candidates are cache hot: */ - if (sched_feat(CACHE_HOT_BUDDY) && (&p->se == cfs_rq_of(&p->se)->next)) + if (sched_feat(CACHE_HOT_BUDDY) && + (&p->se == cfs_rq_of(&p->se)->next || + &p->se == cfs_rq_of(&p->se)->last)) return 1; if (p->sched_class != &fair_sched_class) @@ -5858,6 +5871,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; + spin_lock_irqsave(&rq->lock, flags); + __sched_fork(idle); idle->se.exec_start = sched_clock(); @@ -5865,7 +5880,6 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) idle->cpus_allowed = cpumask_of_cpu(cpu); __set_task_cpu(idle, cpu); - spin_lock_irqsave(&rq->lock, flags); rq->curr = rq->idle = idle; #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) idle->oncpu = 1; @@ -6573,7 +6587,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) req = list_entry(rq->migration_queue.next, struct migration_req, list); list_del_init(&req->list); + spin_unlock_irq(&rq->lock); complete(&req->done); + spin_lock_irq(&rq->lock); } spin_unlock_irq(&rq->lock); break; @@ -6875,15 +6891,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) struct sched_domain *tmp; /* Remove the sched domains which do not contribute to scheduling. */ - for (tmp = sd; tmp; tmp = tmp->parent) { + for (tmp = sd; tmp; ) { struct sched_domain *parent = tmp->parent; if (!parent) break; + if (sd_parent_degenerate(tmp, parent)) { tmp->parent = parent->parent; if (parent->parent) parent->parent->child = tmp; - } + } else + tmp = tmp->parent; } if (sd && sd_degenerate(sd)) { @@ -7672,6 +7690,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map, error: free_sched_groups(cpu_map, tmpmask); SCHED_CPUMASK_FREE((void *)allmasks); + kfree(rd); return -ENOMEM; #endif } @@ -7773,13 +7792,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * * The passed in 'doms_new' should be kmalloc'd. This routine takes * ownership of it and will kfree it when done with it. If the caller - * failed the kmalloc call, then it can pass in doms_new == NULL, - * and partition_sched_domains() will fallback to the single partition - * 'fallback_doms', it also forces the domains to be rebuilt. + * failed the kmalloc call, then it can pass in doms_new == NULL && + * ndoms_new == 1, and partition_sched_domains() will fallback to + * the single partition 'fallback_doms', it also forces the domains + * to be rebuilt. * - * If doms_new==NULL it will be replaced with cpu_online_map. - * ndoms_new==0 is a special case for destroying existing domains. - * It will not create the default domain. + * If doms_new == NULL it will be replaced with cpu_online_map. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. * * Call with hotplug lock held */ diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 8178724..e8ab096 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -118,13 +118,13 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now) /* * scd->clock = clamp(scd->tick_gtod + delta, - * max(scd->tick_gtod, scd->clock), - * max(scd->clock, scd->tick_gtod + TICK_NSEC)); + * max(scd->tick_gtod, scd->clock), + * scd->tick_gtod + TICK_NSEC); */ clock = scd->tick_gtod + delta; min_clock = wrap_max(scd->tick_gtod, scd->clock); - max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC); + max_clock = scd->tick_gtod + TICK_NSEC; clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 5ae1776..26ed8e3 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -144,7 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) last = __pick_last_entity(cfs_rq); if (last) max_vruntime = last->vruntime; - min_vruntime = rq->cfs.min_vruntime; + min_vruntime = cfs_rq->min_vruntime; rq0_min_vruntime = per_cpu(runqueues, 0).cfs.min_vruntime; spin_unlock_irqrestore(&rq->lock, flags); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime", @@ -161,26 +161,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SPLIT_NS(spread0)); SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); -#ifdef CONFIG_SCHEDSTATS -#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); - - P(yld_exp_empty); - P(yld_act_empty); - P(yld_both_empty); - P(yld_count); - P(sched_switch); - P(sched_count); - P(sched_goidle); - - P(ttwu_count); - P(ttwu_local); - - P(bkl_count); - -#undef P -#endif - SEQ_printf(m, " .%-30s: %ld\n", "nr_spread_over", + SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", cfs_rq->nr_spread_over); #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_SMP @@ -260,6 +242,25 @@ static void print_cpu(struct seq_file *m, int cpu) #undef P #undef PN +#ifdef CONFIG_SCHEDSTATS +#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); + + P(yld_exp_empty); + P(yld_act_empty); + P(yld_both_empty); + P(yld_count); + + P(sched_switch); + P(sched_count); + P(sched_goidle); + + P(ttwu_count); + P(ttwu_local); + + P(bkl_count); + +#undef P +#endif print_cfs_stats(m, cpu); print_rt_stats(m, cpu); @@ -422,10 +423,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #undef __P { + unsigned int this_cpu = raw_smp_processor_id(); u64 t0, t1; - t0 = sched_clock(); - t1 = sched_clock(); + t0 = cpu_clock(this_cpu); + t1 = cpu_clock(this_cpu); SEQ_printf(m, "%-35s:%21Ld\n", "clock-delta", (long long)(t1-t0)); } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ce514af..98345e4 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -341,23 +341,20 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) cfs_rq->rb_leftmost = next_node; } - if (cfs_rq->next == se) - cfs_rq->next = NULL; - rb_erase(&se->run_node, &cfs_rq->tasks_timeline); } -static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq) -{ - return cfs_rq->rb_leftmost; -} - static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq) { - return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node); + struct rb_node *left = cfs_rq->rb_leftmost; + + if (!left) + return NULL; + + return rb_entry(left, struct sched_entity, run_node); } -static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) +static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) { struct rb_node *last = rb_last(&cfs_rq->tasks_timeline); @@ -719,6 +716,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup) __enqueue_entity(cfs_rq, se); } +static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (cfs_rq->last == se) + cfs_rq->last = NULL; + + if (cfs_rq->next == se) + cfs_rq->next = NULL; +} + static void dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) { @@ -741,6 +747,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) #endif } + clear_buddies(cfs_rq, se); + if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); account_entity_dequeue(cfs_rq, se); @@ -794,24 +802,15 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) static int wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); -static struct sched_entity * -pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (!cfs_rq->next || wakeup_preempt_entity(cfs_rq->next, se) == 1) - return se; - - return cfs_rq->next; -} - static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) { - struct sched_entity *se = NULL; + struct sched_entity *se = __pick_next_entity(cfs_rq); - if (first_fair(cfs_rq)) { - se = __pick_next_entity(cfs_rq); - se = pick_next(cfs_rq, se); - set_next_entity(cfs_rq, se); - } + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1) + return cfs_rq->next; + + if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1) + return cfs_rq->last; return se; } @@ -983,6 +982,8 @@ static void yield_task_fair(struct rq *rq) if (unlikely(cfs_rq->nr_running == 1)) return; + clear_buddies(cfs_rq, se); + if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) { update_rq_clock(rq); /* @@ -1325,26 +1326,53 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) return 0; } +static void set_last_buddy(struct sched_entity *se) +{ + for_each_sched_entity(se) + cfs_rq_of(se)->last = se; +} + +static void set_next_buddy(struct sched_entity *se) +{ + for_each_sched_entity(se) + cfs_rq_of(se)->next = se; +} + /* * Preempt the current task with a newly woken task if needed: */ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) { struct task_struct *curr = rq->curr; - struct cfs_rq *cfs_rq = task_cfs_rq(curr); struct sched_entity *se = &curr->se, *pse = &p->se; if (unlikely(rt_prio(p->prio))) { + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + update_rq_clock(rq); update_curr(cfs_rq); resched_task(curr); return; } + if (unlikely(p->sched_class != &fair_sched_class)) + return; + if (unlikely(se == pse)) return; - cfs_rq_of(pse)->next = pse; + /* + * Only set the backward buddy when the current task is still on the + * rq. This can happen when a wakeup gets interleaved with schedule on + * the ->pre_schedule() or idle_balance() point, either of which can + * drop the rq lock. + * + * Also, during early boot the idle thread is in the fair class, for + * obvious reasons its a bad idea to schedule back to the idle thread. + */ + if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle)) + set_last_buddy(se); + set_next_buddy(pse); /* * We can come here with TIF_NEED_RESCHED already set from new task @@ -1396,6 +1424,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq) do { se = pick_next_entity(cfs_rq); + set_next_entity(cfs_rq, se); cfs_rq = group_cfs_rq(se); } while (cfs_rq); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index fda0162..da5d93b 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -12,3 +12,4 @@ SCHED_FEAT(LB_BIAS, 1) SCHED_FEAT(LB_WAKEUP_UPDATE, 1) SCHED_FEAT(ASYM_EFF_LOAD, 1) SCHED_FEAT(WAKEUP_OVERLAP, 0) +SCHED_FEAT(LAST_BUDDY, 1) diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index ee71bec..7dbf72a 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -298,9 +298,11 @@ static inline void account_group_user_time(struct task_struct *tsk, { struct signal_struct *sig; - sig = tsk->signal; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal */ + if (unlikely(tsk->exit_state)) return; + + sig = tsk->signal; if (sig->cputime.totals) { struct task_cputime *times; @@ -325,9 +327,11 @@ static inline void account_group_system_time(struct task_struct *tsk, { struct signal_struct *sig; - sig = tsk->signal; - if (unlikely(!sig)) + /* tsk == current, ensure it is safe to use ->signal */ + if (unlikely(tsk->exit_state)) return; + + sig = tsk->signal; if (sig->cputime.totals) { struct task_cputime *times; @@ -353,8 +357,11 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, struct signal_struct *sig; sig = tsk->signal; + /* see __exit_signal()->task_rq_unlock_wait() */ + barrier(); if (unlikely(!sig)) return; + if (sig->cputime.totals) { struct task_cputime *times; diff --git a/kernel/smp.c b/kernel/smp.c index f362a85..75c8dde 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -51,10 +51,6 @@ static void csd_flag_wait(struct call_single_data *data) { /* Wait for response */ do { - /* - * We need to see the flags store in the IPI handler - */ - smp_mb(); if (!(data->flags & CSD_FLAG_WAIT)) break; cpu_relax(); @@ -76,6 +72,11 @@ static void generic_exec_single(int cpu, struct call_single_data *data) list_add_tail(&data->list, &dst->list); spin_unlock_irqrestore(&dst->lock, flags); + /* + * Make the list addition visible before sending the ipi. + */ + smp_mb(); + if (ipi) arch_send_call_function_single_ipi(cpu); @@ -157,7 +158,7 @@ void generic_smp_call_function_single_interrupt(void) * Need to see other stores to list head for checking whether * list is empty without holding q->lock */ - smp_mb(); + smp_read_barrier_depends(); while (!list_empty(&q->list)) { unsigned int data_flags; @@ -191,7 +192,7 @@ void generic_smp_call_function_single_interrupt(void) /* * See comment on outer loop */ - smp_mb(); + smp_read_barrier_depends(); } } @@ -370,6 +371,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, list_add_tail_rcu(&data->csd.list, &call_function_queue); spin_unlock_irqrestore(&call_function_lock, flags); + /* + * Make the list addition visible before sending the ipi. + */ + smp_mb(); + /* Send a message to all CPUs in the map */ arch_send_call_function_ipi(mask); diff --git a/kernel/softirq.c b/kernel/softirq.c index 7110dae..e7c69a7 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -269,10 +269,11 @@ void irq_enter(void) { int cpu = smp_processor_id(); - if (idle_cpu(cpu) && !in_interrupt()) + if (idle_cpu(cpu) && !in_interrupt()) { + __irq_enter(); tick_check_idle(cpu); - - __irq_enter(); + } else + __irq_enter(); } #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 3953e4a..dc0b3be 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -188,7 +188,7 @@ static void check_hung_task(struct task_struct *t, unsigned long now) if ((long)(now - t->last_switch_timestamp) < sysctl_hung_task_timeout_secs) return; - if (sysctl_hung_task_warnings < 0) + if (!sysctl_hung_task_warnings) return; sysctl_hung_task_warnings--; diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 9bc4c00..24e8cea 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -112,7 +112,7 @@ static int chill(void *unused) int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) { struct work_struct *sm_work; - int i; + int i, ret; /* Set up initial state. */ mutex_lock(&lock); @@ -137,8 +137,9 @@ int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) /* This will release the thread on our CPU. */ put_cpu(); flush_workqueue(stop_machine_wq); + ret = active.fnret; mutex_unlock(&lock); - return active.fnret; + return ret; } int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a77b27b..e14a232 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -31,7 +31,7 @@ cond_syscall(sys_socketpair); cond_syscall(sys_bind); cond_syscall(sys_listen); cond_syscall(sys_accept); -cond_syscall(sys_paccept); +cond_syscall(sys_accept4); cond_syscall(sys_connect); cond_syscall(sys_getsockname); cond_syscall(sys_getpeername); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 9d048fa..3d56fe7 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -176,6 +176,9 @@ extern struct ctl_table random_table[]; #ifdef CONFIG_INOTIFY_USER extern struct ctl_table inotify_table[]; #endif +#ifdef CONFIG_EPOLL +extern struct ctl_table epoll_table[]; +#endif #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT int sysctl_legacy_va_layout; @@ -1325,6 +1328,13 @@ static struct ctl_table fs_table[] = { .child = inotify_table, }, #endif +#ifdef CONFIG_EPOLL + { + .procname = "epoll", + .mode = 0555, + .child = epoll_table, + }, +#endif #endif { .ctl_name = KERN_SETUID_DUMPABLE, diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 5bbb104..342fc9c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -568,6 +568,9 @@ static void tick_nohz_switch_to_nohz(void) */ static void tick_nohz_kick_tick(int cpu) { +#if 0 + /* Switch back to 2.6.27 behaviour */ + struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t delta, now; @@ -584,6 +587,7 @@ static void tick_nohz_kick_tick(int cpu) return; tick_nohz_restart(ts, now); +#endif } #else diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e7acfb4..fa05e88 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -518,6 +518,28 @@ void update_wall_time(void) /* correct the clock when NTP error is too big */ clocksource_adjust(offset); + /* + * Since in the loop above, we accumulate any amount of time + * in xtime_nsec over a second into xtime.tv_sec, its possible for + * xtime_nsec to be fairly small after the loop. Further, if we're + * slightly speeding the clocksource up in clocksource_adjust(), + * its possible the required corrective factor to xtime_nsec could + * cause it to underflow. + * + * Now, we cannot simply roll the accumulated second back, since + * the NTP subsystem has been notified via second_overflow. So + * instead we push xtime_nsec forward by the amount we underflowed, + * and add that amount into the error. + * + * We'll correct this error next time through this function, when + * xtime_nsec is not as small. + */ + if (unlikely((s64)clock->xtime_nsec < 0)) { + s64 neg = -(s64)clock->xtime_nsec; + clock->xtime_nsec = 0; + clock->error += neg << (NTP_SCALE_SHIFT - clock->shift); + } + /* store full nanoseconds into xtime after rounding it up and * add the remainder to the error difference. */ diff --git a/kernel/timer.c b/kernel/timer.c index 56becf3..dbd50fa 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -112,27 +112,8 @@ timer_set_base(struct timer_list *timer, struct tvec_base *new_base) tbase_get_deferrable(timer->base)); } -/** - * __round_jiffies - function to round jiffies to a full second - * @j: the time in (absolute) jiffies that should be rounded - * @cpu: the processor number on which the timeout will happen - * - * __round_jiffies() rounds an absolute time in the future (in jiffies) - * up or down to (approximately) full seconds. This is useful for timers - * for which the exact time they fire does not matter too much, as long as - * they fire approximately every X seconds. - * - * By rounding these timers to whole seconds, all such timers will fire - * at the same time, rather than at various times spread out. The goal - * of this is to have the CPU wake up less, which saves power. - * - * The exact rounding is skewed for each processor to avoid all - * processors firing at the exact same time, which could lead - * to lock contention or spurious cache line bouncing. - * - * The return value is the rounded version of the @j parameter. - */ -unsigned long __round_jiffies(unsigned long j, int cpu) +static unsigned long round_jiffies_common(unsigned long j, int cpu, + bool force_up) { int rem; unsigned long original = j; @@ -154,8 +135,9 @@ unsigned long __round_jiffies(unsigned long j, int cpu) * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. + * But never round down if @force_up is set. */ - if (rem < HZ/4) /* round down */ + if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; @@ -167,6 +149,31 @@ unsigned long __round_jiffies(unsigned long j, int cpu) return original; return j; } + +/** + * __round_jiffies - function to round jiffies to a full second + * @j: the time in (absolute) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * __round_jiffies() rounds an absolute time in the future (in jiffies) + * up or down to (approximately) full seconds. This is useful for timers + * for which the exact time they fire does not matter too much, as long as + * they fire approximately every X seconds. + * + * By rounding these timers to whole seconds, all such timers will fire + * at the same time, rather than at various times spread out. The goal + * of this is to have the CPU wake up less, which saves power. + * + * The exact rounding is skewed for each processor to avoid all + * processors firing at the exact same time, which could lead + * to lock contention or spurious cache line bouncing. + * + * The return value is the rounded version of the @j parameter. + */ +unsigned long __round_jiffies(unsigned long j, int cpu) +{ + return round_jiffies_common(j, cpu, false); +} EXPORT_SYMBOL_GPL(__round_jiffies); /** @@ -191,13 +198,10 @@ EXPORT_SYMBOL_GPL(__round_jiffies); */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { - /* - * In theory the following code can skip a jiffy in case jiffies - * increments right between the addition and the later subtraction. - * However since the entire point of this function is to use approximate - * timeouts, it's entirely ok to not handle that. - */ - return __round_jiffies(j + jiffies, cpu) - jiffies; + unsigned long j0 = jiffies; + + /* Use j0 because jiffies might change while we run */ + return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); @@ -218,7 +222,7 @@ EXPORT_SYMBOL_GPL(__round_jiffies_relative); */ unsigned long round_jiffies(unsigned long j) { - return __round_jiffies(j, raw_smp_processor_id()); + return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); @@ -243,6 +247,71 @@ unsigned long round_jiffies_relative(unsigned long j) } EXPORT_SYMBOL_GPL(round_jiffies_relative); +/** + * __round_jiffies_up - function to round jiffies up to a full second + * @j: the time in (absolute) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * This is the same as __round_jiffies() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long __round_jiffies_up(unsigned long j, int cpu) +{ + return round_jiffies_common(j, cpu, true); +} +EXPORT_SYMBOL_GPL(__round_jiffies_up); + +/** + * __round_jiffies_up_relative - function to round jiffies up to a full second + * @j: the time in (relative) jiffies that should be rounded + * @cpu: the processor number on which the timeout will happen + * + * This is the same as __round_jiffies_relative() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) +{ + unsigned long j0 = jiffies; + + /* Use j0 because jiffies might change while we run */ + return round_jiffies_common(j + j0, cpu, true) - j0; +} +EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); + +/** + * round_jiffies_up - function to round jiffies up to a full second + * @j: the time in (absolute) jiffies that should be rounded + * + * This is the same as round_jiffies() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long round_jiffies_up(unsigned long j) +{ + return round_jiffies_common(j, raw_smp_processor_id(), true); +} +EXPORT_SYMBOL_GPL(round_jiffies_up); + +/** + * round_jiffies_up_relative - function to round jiffies up to a full second + * @j: the time in (relative) jiffies that should be rounded + * + * This is the same as round_jiffies_relative() except that it will never + * round down. This is useful for timeouts for which the exact time + * of firing does not matter too much, as long as they don't fire too + * early. + */ +unsigned long round_jiffies_up_relative(unsigned long j) +{ + return __round_jiffies_up_relative(j, raw_smp_processor_id()); +} +EXPORT_SYMBOL_GPL(round_jiffies_up_relative); + static inline void set_running_timer(struct tvec_base *base, struct timer_list *timer) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index b58f43b..33dbefd 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -25,7 +25,7 @@ config TRACING bool select DEBUG_FS select RING_BUFFER - select STACKTRACE + select STACKTRACE if STACKTRACE_SUPPORT select TRACEPOINTS select NOP_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4a39d24..78db083 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -185,7 +185,6 @@ enum { }; static int ftrace_filtered; -static int tracing_on; static LIST_HEAD(ftrace_new_addrs); @@ -327,96 +326,89 @@ ftrace_record_ip(unsigned long ip) static int __ftrace_replace_code(struct dyn_ftrace *rec, - unsigned char *old, unsigned char *new, int enable) + unsigned char *nop, int enable) { unsigned long ip, fl; + unsigned char *call, *old, *new; ip = rec->ip; - if (ftrace_filtered && enable) { + /* + * If this record is not to be traced and + * it is not enabled then do nothing. + * + * If this record is not to be traced and + * it is enabled then disabled it. + * + */ + if (rec->flags & FTRACE_FL_NOTRACE) { + if (rec->flags & FTRACE_FL_ENABLED) + rec->flags &= ~FTRACE_FL_ENABLED; + else + return 0; + + } else if (ftrace_filtered && enable) { /* - * If filtering is on: - * - * If this record is set to be filtered and - * is enabled then do nothing. - * - * If this record is set to be filtered and - * it is not enabled, enable it. - * - * If this record is not set to be filtered - * and it is not enabled do nothing. - * - * If this record is set not to trace then - * do nothing. - * - * If this record is set not to trace and - * it is enabled then disable it. - * - * If this record is not set to be filtered and - * it is enabled, disable it. + * Filtering is on: */ - fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE | - FTRACE_FL_ENABLED); + fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED); - if ((fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) || - (fl == (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) || - !fl || (fl == FTRACE_FL_NOTRACE)) + /* Record is filtered and enabled, do nothing */ + if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) return 0; - /* - * If it is enabled disable it, - * otherwise enable it! - */ - if (fl & FTRACE_FL_ENABLED) { - /* swap new and old */ - new = old; - old = ftrace_call_replace(ip, FTRACE_ADDR); + /* Record is not filtered and is not enabled do nothing */ + if (!fl) + return 0; + + /* Record is not filtered but enabled, disable it */ + if (fl == FTRACE_FL_ENABLED) rec->flags &= ~FTRACE_FL_ENABLED; - } else { - new = ftrace_call_replace(ip, FTRACE_ADDR); + else + /* Otherwise record is filtered but not enabled, enable it */ rec->flags |= FTRACE_FL_ENABLED; - } } else { + /* Disable or not filtered */ if (enable) { - /* - * If this record is set not to trace and is - * not enabled, do nothing. - */ - fl = rec->flags & (FTRACE_FL_NOTRACE | FTRACE_FL_ENABLED); - if (fl == FTRACE_FL_NOTRACE) - return 0; - - new = ftrace_call_replace(ip, FTRACE_ADDR); - } else - old = ftrace_call_replace(ip, FTRACE_ADDR); - - if (enable) { + /* if record is enabled, do nothing */ if (rec->flags & FTRACE_FL_ENABLED) return 0; + rec->flags |= FTRACE_FL_ENABLED; + } else { + + /* if record is not enabled do nothing */ if (!(rec->flags & FTRACE_FL_ENABLED)) return 0; + rec->flags &= ~FTRACE_FL_ENABLED; } } + call = ftrace_call_replace(ip, FTRACE_ADDR); + + if (rec->flags & FTRACE_FL_ENABLED) { + old = nop; + new = call; + } else { + old = call; + new = nop; + } + return ftrace_modify_code(ip, old, new); } static void ftrace_replace_code(int enable) { int i, failed; - unsigned char *new = NULL, *old = NULL; + unsigned char *nop = NULL; struct dyn_ftrace *rec; struct ftrace_page *pg; - if (enable) - old = ftrace_nop_replace(); - else - new = ftrace_nop_replace(); + nop = ftrace_nop_replace(); for (pg = ftrace_pages_start; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { @@ -434,7 +426,7 @@ static void ftrace_replace_code(int enable) unfreeze_record(rec); } - failed = __ftrace_replace_code(rec, old, new, enable); + failed = __ftrace_replace_code(rec, nop, enable); if (failed && (rec->flags & FTRACE_FL_CONVERTED)) { rec->flags |= FTRACE_FL_FAILED; if ((system_state == SYSTEM_BOOTING) || @@ -506,13 +498,10 @@ static int __ftrace_modify_code(void *data) { int *command = data; - if (*command & FTRACE_ENABLE_CALLS) { + if (*command & FTRACE_ENABLE_CALLS) ftrace_replace_code(1); - tracing_on = 1; - } else if (*command & FTRACE_DISABLE_CALLS) { + else if (*command & FTRACE_DISABLE_CALLS) ftrace_replace_code(0); - tracing_on = 0; - } if (*command & FTRACE_UPDATE_TRACE_FUNC) ftrace_update_ftrace_func(ftrace_trace_function); @@ -538,8 +527,7 @@ static void ftrace_startup(void) mutex_lock(&ftrace_start_lock); ftrace_start++; - if (ftrace_start == 1) - command |= FTRACE_ENABLE_CALLS; + command |= FTRACE_ENABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -677,7 +665,7 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) cnt = num_to_init / ENTRIES_PER_PAGE; pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt); + num_to_init, cnt + 1); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -738,6 +726,9 @@ t_next(struct seq_file *m, void *v, loff_t *pos) ((iter->flags & FTRACE_ITER_FAILURES) && !(rec->flags & FTRACE_FL_FAILED)) || + ((iter->flags & FTRACE_ITER_FILTER) && + !(rec->flags & FTRACE_FL_FILTER)) || + ((iter->flags & FTRACE_ITER_NOTRACE) && !(rec->flags & FTRACE_FL_NOTRACE))) { rec = NULL; @@ -757,13 +748,11 @@ static void *t_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l = -1; - if (*pos != iter->pos) { - for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) - ; - } else { - l = *pos; - p = t_next(m, p, &l); - } + if (*pos > iter->pos) + *pos = iter->pos; + + l = *pos; + p = t_next(m, p, &l); return p; } @@ -774,15 +763,21 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; if (!rec) return 0; kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - seq_printf(m, "%s\n", str); + ret = seq_printf(m, "%s\n", str); + if (ret < 0) { + iter->pos--; + iter->idx--; + } return 0; } @@ -808,7 +803,7 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -895,7 +890,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; iter->flags = enable ? FTRACE_ITER_FILTER : FTRACE_ITER_NOTRACE; @@ -1186,7 +1181,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) mutex_lock(&ftrace_sysctl_lock); mutex_lock(&ftrace_start_lock); - if (iter->filtered && ftrace_start && ftrace_enabled) + if (ftrace_start && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); mutex_unlock(&ftrace_start_lock); mutex_unlock(&ftrace_sysctl_lock); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index cedf4e2..668bbb5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -16,14 +16,49 @@ #include <linux/list.h> #include <linux/fs.h> +#include "trace.h" + +/* Global flag to disable all recording to ring buffers */ +static int ring_buffers_off __read_mostly; + +/** + * tracing_on - enable all tracing buffers + * + * This function enables all tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + ring_buffers_off = 0; +} + +/** + * tracing_off - turn off all tracing buffers + * + * This function stops all tracing buffers from recording data. + * It does not disable any overhead the tracers themselves may + * be causing. This function simply causes all recording to + * the ring buffers to fail. + */ +void tracing_off(void) +{ + ring_buffers_off = 1; +} + /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 /* FIXME!!! */ u64 ring_buffer_time_stamp(int cpu) { + u64 time; + + preempt_disable_notrace(); /* shift to debug/test normalization and TIME_EXTENTS */ - return sched_clock() << DEBUG_SHIFT; + time = sched_clock() << DEBUG_SHIFT; + preempt_enable_notrace(); + + return time; } void ring_buffer_normalize_time_stamp(int cpu, u64 *ts) @@ -503,6 +538,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) LIST_HEAD(pages); int i, cpu; + /* + * Always succeed at resizing a non-existent buffer: + */ + if (!buffer) + return size; + size = DIV_ROUND_UP(size, BUF_PAGE_SIZE); size *= BUF_PAGE_SIZE; buffer_size = buffer->pages * BUF_PAGE_SIZE; @@ -576,6 +617,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) list_del_init(&page->list); free_buffer_page(page); } + mutex_unlock(&buffer->mutex); return -ENOMEM; } @@ -1022,8 +1064,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event; u64 ts, delta; int commit = 0; + int nr_loops = 0; again: + /* + * We allow for interrupts to reenter here and do a trace. + * If one does, it will cause this original code to loop + * back here. Even with heavy interrupts happening, this + * should only happen a few times in a row. If this happens + * 1000 times in a row, there must be either an interrupt + * storm or we have something buggy. + * Bail! + */ + if (unlikely(++nr_loops > 1000)) { + RB_WARN_ON(cpu_buffer, 1); + return NULL; + } + ts = ring_buffer_time_stamp(cpu_buffer->cpu); /* @@ -1045,7 +1102,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, /* Did the write stamp get updated already? */ if (unlikely(ts < cpu_buffer->write_stamp)) - goto again; + delta = 0; if (test_time_stamp(delta)) { @@ -1118,6 +1175,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, struct ring_buffer_event *event; int cpu, resched; + if (ring_buffers_off) + return NULL; + if (atomic_read(&buffer->record_disabled)) return NULL; @@ -1155,7 +1215,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, out: if (resched) - preempt_enable_notrace(); + preempt_enable_no_resched_notrace(); else preempt_enable_notrace(); return NULL; @@ -1234,6 +1294,9 @@ int ring_buffer_write(struct ring_buffer *buffer, int ret = -EBUSY; int cpu, resched; + if (ring_buffers_off) + return -EBUSY; + if (atomic_read(&buffer->record_disabled)) return -EBUSY; @@ -1532,10 +1595,23 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = NULL; unsigned long flags; + int nr_loops = 0; spin_lock_irqsave(&cpu_buffer->lock, flags); again: + /* + * This should normally only loop twice. But because the + * start of the reader inserts an empty page, it causes + * a case where we will loop three times. There should be no + * reason to loop four times (that I know of). + */ + if (unlikely(++nr_loops > 3)) { + RB_WARN_ON(cpu_buffer, 1); + reader = NULL; + goto out; + } + reader = cpu_buffer->reader_page; /* If there's more to read, return this page */ @@ -1665,6 +1741,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; struct buffer_page *reader; + int nr_loops = 0; if (!cpu_isset(cpu, buffer->cpumask)) return NULL; @@ -1672,6 +1749,19 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) cpu_buffer = buffer->buffers[cpu]; again: + /* + * We repeat when a timestamp is encountered. It is possible + * to get multiple timestamps from an interrupt entering just + * as one timestamp is about to be written. The max times + * that this can happen is the number of nested interrupts we + * can have. Nesting 10 deep of interrupts is clearly + * an anomaly. + */ + if (unlikely(++nr_loops > 10)) { + RB_WARN_ON(cpu_buffer, 1); + return NULL; + } + reader = rb_get_reader_page(cpu_buffer); if (!reader) return NULL; @@ -1722,6 +1812,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; + int nr_loops = 0; if (ring_buffer_iter_empty(iter)) return NULL; @@ -1730,6 +1821,19 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) buffer = cpu_buffer->buffer; again: + /* + * We repeat when a timestamp is encountered. It is possible + * to get multiple timestamps from an interrupt entering just + * as one timestamp is about to be written. The max times + * that this can happen is the number of nested interrupts we + * can have. Nesting 10 deep of interrupts is clearly + * an anomaly. + */ + if (unlikely(++nr_loops > 10)) { + RB_WARN_ON(cpu_buffer, 1); + return NULL; + } + if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -2014,3 +2118,69 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, return 0; } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + int *p = filp->private_data; + char buf[64]; + int r; + + /* !ring_buffers_off == tracing_on */ + r = sprintf(buf, "%d\n", !*p); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +rb_simple_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + int *p = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + /* !ring_buffers_off == tracing_on */ + *p = !val; + + (*ppos)++; + + return cnt; +} + +static struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, +}; + + +static __init int rb_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("tracing_on", 0644, d_tracer, + &ring_buffers_off, &rb_simple_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_on' entry\n"); + + return 0; +} + +fs_initcall(rb_init_debugfs); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8a499e2..d86e325 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -705,6 +705,7 @@ static void ftrace_trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { +#ifdef CONFIG_STACKTRACE struct ring_buffer_event *event; struct stack_entry *entry; struct stack_trace trace; @@ -730,6 +731,7 @@ static void ftrace_trace_stack(struct trace_array *tr, save_stack_trace(&trace); ring_buffer_unlock_commit(tr->buffer, event, irq_flags); +#endif } void __trace_stack(struct trace_array *tr, @@ -1086,17 +1088,20 @@ static void s_stop(struct seq_file *m, void *p) mutex_unlock(&trace_types_lock); } -#define KRETPROBE_MSG "[unknown/kretprobe'd]" - #ifdef CONFIG_KRETPROBES -static inline int kretprobed(unsigned long addr) +static inline const char *kretprobed(const char *name) { - return addr == (unsigned long)kretprobe_trampoline; + static const char tramp_name[] = "kretprobe_trampoline"; + int size = sizeof(tramp_name); + + if (strncmp(tramp_name, name, size) == 0) + return "[unknown/kretprobe'd]"; + return name; } #else -static inline int kretprobed(unsigned long addr) +static inline const char *kretprobed(const char *name) { - return 0; + return name; } #endif /* CONFIG_KRETPROBES */ @@ -1105,10 +1110,13 @@ seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) { #ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; + const char *name; kallsyms_lookup(address, NULL, NULL, NULL, str); - return trace_seq_printf(s, fmt, str); + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); #endif return 1; } @@ -1119,9 +1127,12 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt, { #ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; + const char *name; sprint_symbol(str, address); - return trace_seq_printf(s, fmt, str); + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); #endif return 1; } @@ -1375,10 +1386,7 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) seq_print_ip_sym(s, field->ip, sym_flags); trace_seq_puts(s, " ("); - if (kretprobed(field->parent_ip)) - trace_seq_puts(s, KRETPROBE_MSG); - else - seq_print_ip_sym(s, field->parent_ip, sym_flags); + seq_print_ip_sym(s, field->parent_ip, sym_flags); trace_seq_puts(s, ")\n"); break; } @@ -1494,12 +1502,9 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) ret = trace_seq_printf(s, " <-"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; - if (kretprobed(field->parent_ip)) - ret = trace_seq_puts(s, KRETPROBE_MSG); - else - ret = seq_print_ip_sym(s, - field->parent_ip, - sym_flags); + ret = seq_print_ip_sym(s, + field->parent_ip, + sym_flags); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -1750,7 +1755,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) return TRACE_TYPE_HANDLED; SEQ_PUT_FIELD_RET(s, entry->pid); - SEQ_PUT_FIELD_RET(s, iter->cpu); + SEQ_PUT_FIELD_RET(s, entry->cpu); SEQ_PUT_FIELD_RET(s, iter->ts); switch (entry->type) { @@ -1931,6 +1936,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) ring_buffer_read_finish(iter->buffer_iter[cpu]); } mutex_unlock(&trace_types_lock); + kfree(iter); return ERR_PTR(-ENOMEM); } @@ -2671,7 +2677,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, { unsigned long val; char buf[64]; - int ret; + int ret, cpu; struct trace_array *tr = filp->private_data; if (cnt >= sizeof(buf)) @@ -2699,6 +2705,14 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, goto out; } + /* disable all cpu buffers */ + for_each_tracing_cpu(cpu) { + if (global_trace.data[cpu]) + atomic_inc(&global_trace.data[cpu]->disabled); + if (max_tr.data[cpu]) + atomic_inc(&max_tr.data[cpu]->disabled); + } + if (val != global_trace.entries) { ret = ring_buffer_resize(global_trace.buffer, val); if (ret < 0) { @@ -2730,6 +2744,13 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, if (tracing_disabled) cnt = -ENOMEM; out: + for_each_tracing_cpu(cpu) { + if (global_trace.data[cpu]) + atomic_dec(&global_trace.data[cpu]->disabled); + if (max_tr.data[cpu]) + atomic_dec(&max_tr.data[cpu]->disabled); + } + max_tr.entries = global_trace.entries; mutex_unlock(&trace_types_lock); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index f284846..e62cbf7 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -18,12 +18,14 @@ struct header_iter { static struct trace_array *mmio_trace_array; static bool overrun_detected; +static unsigned long prev_overruns; static void mmio_reset_data(struct trace_array *tr) { int cpu; overrun_detected = false; + prev_overruns = 0; tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) @@ -128,16 +130,12 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { - int cpu; unsigned long cnt = 0; -/* FIXME: */ -#if 0 - for_each_online_cpu(cpu) { - cnt += iter->overrun[cpu]; - iter->overrun[cpu] = 0; - } -#endif - (void)cpu; + unsigned long over = ring_buffer_overruns(iter->tr->buffer); + + if (over > prev_overruns) + cnt = over - prev_overruns; + prev_overruns = over; return cnt; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index be682b6..3bdb44b 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -184,11 +184,16 @@ static struct file_operations stack_max_size_fops = { static void * t_next(struct seq_file *m, void *v, loff_t *pos) { - long i = (long)m->private; + long i; (*pos)++; - i++; + if (v == SEQ_START_TOKEN) + i = 0; + else { + i = *(long *)v; + i++; + } if (i >= max_stack_trace.nr_entries || stack_dump_trace[i] == ULONG_MAX) @@ -201,12 +206,15 @@ t_next(struct seq_file *m, void *v, loff_t *pos) static void *t_start(struct seq_file *m, loff_t *pos) { - void *t = &m->private; + void *t = SEQ_START_TOKEN; loff_t l = 0; local_irq_disable(); __raw_spin_lock(&max_stack_lock); + if (*pos == 0) + return SEQ_START_TOKEN; + for (; t && l < *pos; t = t_next(m, t, &l)) ; @@ -235,10 +243,10 @@ static int trace_lookup_stack(struct seq_file *m, long i) static int t_show(struct seq_file *m, void *v) { - long i = *(long *)v; + long i; int size; - if (i < 0) { + if (v == SEQ_START_TOKEN) { seq_printf(m, " Depth Size Location" " (%d entries)\n" " ----- ---- --------\n", @@ -246,6 +254,8 @@ static int t_show(struct seq_file *m, void *v) return 0; } + i = *(long *)v; + if (i >= max_stack_trace.nr_entries || stack_dump_trace[i] == ULONG_MAX) return 0; @@ -275,10 +285,6 @@ static int stack_trace_open(struct inode *inode, struct file *file) int ret; ret = seq_open(file, &stack_trace_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = (void *)-1; - } return ret; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f928f2a..d4dc69d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -970,6 +970,51 @@ undo: return ret; } +#ifdef CONFIG_SMP +struct work_for_cpu { + struct work_struct work; + long (*fn)(void *); + void *arg; + long ret; +}; + +static void do_work_for_cpu(struct work_struct *w) +{ + struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work); + + wfc->ret = wfc->fn(wfc->arg); +} + +/** + * work_on_cpu - run a function in user context on a particular cpu + * @cpu: the cpu to run on + * @fn: the function to run + * @arg: the function arg + * + * This will return -EINVAL in the cpu is not online, or the return value + * of @fn otherwise. + */ +long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +{ + struct work_for_cpu wfc; + + INIT_WORK(&wfc.work, do_work_for_cpu); + wfc.fn = fn; + wfc.arg = arg; + get_online_cpus(); + if (unlikely(!cpu_online(cpu))) + wfc.ret = -EINVAL; + else { + schedule_work_on(cpu, &wfc.work); + flush_work(&wfc.work); + } + put_online_cpus(); + + return wfc.ret; +} +EXPORT_SYMBOL_GPL(work_on_cpu); +#endif /* CONFIG_SMP */ + void __init init_workqueues(void) { cpu_populated_map = cpu_online_map; |