diff options
Diffstat (limited to 'kernel')
77 files changed, 2083 insertions, 1663 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 305f11dbef2..19fad003b19 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,9 +11,7 @@ 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_FTRACE +ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files CFLAGS_REMOVE_lockdep.o = -pg CFLAGS_REMOVE_lockdep_proc.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-$(CONFIG_FREEZER) += freezer.o @@ -88,7 +86,7 @@ obj-$(CONFIG_MARKERS) += marker.o obj-$(CONFIG_TRACEPOINTS) += tracepoint.o obj-$(CONFIG_LATENCYTOP) += latencytop.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o -obj-$(CONFIG_FTRACE) += trace/ +obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o diff --git a/kernel/audit.c b/kernel/audit.c index 4414e93d875..ce6d8ea3131 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 f7921a2ecf1..8b509441f49 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; @@ -532,7 +549,7 @@ void audit_trim_trees(void) list_add(&cursor, &tree_list); while (cursor.next != &tree_list) { struct audit_tree *tree; - struct nameidata nd; + struct path path; struct vfsmount *root_mnt; struct node *node; struct list_head list; @@ -544,12 +561,12 @@ void audit_trim_trees(void) list_add(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); - err = path_lookup(tree->pathname, 0, &nd); + err = kern_path(tree->pathname, 0, &path); if (err) goto skip_it; - root_mnt = collect_mounts(nd.path.mnt, nd.path.dentry); - path_put(&nd.path); + root_mnt = collect_mounts(path.mnt, path.dentry); + path_put(&path); if (!root_mnt) goto skip_it; @@ -580,19 +597,19 @@ skip_it: } static int is_under(struct vfsmount *mnt, struct dentry *dentry, - struct nameidata *nd) + struct path *path) { - if (mnt != nd->path.mnt) { + if (mnt != path->mnt) { for (;;) { if (mnt->mnt_parent == mnt) return 0; - if (mnt->mnt_parent == nd->path.mnt) + if (mnt->mnt_parent == path->mnt) break; mnt = mnt->mnt_parent; } dentry = mnt->mnt_mountpoint; } - return is_subdir(dentry, nd->path.dentry); + return is_subdir(dentry, path->dentry); } int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) @@ -618,7 +635,7 @@ void audit_put_tree(struct audit_tree *tree) int audit_add_tree_rule(struct audit_krule *rule) { struct audit_tree *seed = rule->tree, *tree; - struct nameidata nd; + struct path path; struct vfsmount *mnt, *p; struct list_head list; int err; @@ -637,11 +654,11 @@ int audit_add_tree_rule(struct audit_krule *rule) /* do not set rule->tree yet */ mutex_unlock(&audit_filter_mutex); - err = path_lookup(tree->pathname, 0, &nd); + err = kern_path(tree->pathname, 0, &path); if (err) goto Err; - mnt = collect_mounts(nd.path.mnt, nd.path.dentry); - path_put(&nd.path); + mnt = collect_mounts(path.mnt, path.dentry); + path_put(&path); if (!mnt) { err = -ENOMEM; goto Err; @@ -690,29 +707,29 @@ int audit_tag_tree(char *old, char *new) { struct list_head cursor, barrier; int failed = 0; - struct nameidata nd; + struct path path; struct vfsmount *tagged; struct list_head list; struct vfsmount *mnt; struct dentry *dentry; int err; - err = path_lookup(new, 0, &nd); + err = kern_path(new, 0, &path); if (err) return err; - tagged = collect_mounts(nd.path.mnt, nd.path.dentry); - path_put(&nd.path); + tagged = collect_mounts(path.mnt, path.dentry); + path_put(&path); if (!tagged) return -ENOMEM; - err = path_lookup(old, 0, &nd); + err = kern_path(old, 0, &path); if (err) { drop_collected_mounts(tagged); return err; } - mnt = mntget(nd.path.mnt); - dentry = dget(nd.path.dentry); - path_put(&nd.path); + mnt = mntget(path.mnt); + dentry = dget(path.dentry); + path_put(&path); if (dentry == tagged->mnt_root && dentry == mnt->mnt_root) follow_up(&mnt, &dentry); @@ -733,7 +750,7 @@ int audit_tag_tree(char *old, char *new) list_add(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); - err = path_lookup(tree->pathname, 0, &nd); + err = kern_path(tree->pathname, 0, &path); if (err) { put_tree(tree); mutex_lock(&audit_filter_mutex); @@ -741,15 +758,15 @@ int audit_tag_tree(char *old, char *new) } spin_lock(&vfsmount_lock); - if (!is_under(mnt, dentry, &nd)) { + if (!is_under(mnt, dentry, &path)) { spin_unlock(&vfsmount_lock); - path_put(&nd.path); + path_put(&path); put_tree(tree); mutex_lock(&audit_filter_mutex); continue; } spin_unlock(&vfsmount_lock); - path_put(&nd.path); + path_put(&path); list_for_each_entry(p, &list, mnt_list) { failed = tag_chunk(p->mnt_root->d_inode, tree); @@ -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 b7d354e2b0e..9fd85a4640a 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 cf5bc2f5f9c..2a3f0afc4d2 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 046c1609606..8185a0f0959 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; @@ -2104,7 +2107,7 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos) down_read(&cgrp->pids_mutex); if (pid) { int end = cgrp->pids_length; - int i; + while (index < end) { int mid = (index + end) / 2; if (cgrp->tasks_pids[mid] == pid) { @@ -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 e9505695449..fb249e2bcad 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -162,9 +162,13 @@ static int freezer_can_attach(struct cgroup_subsys *ss, struct task_struct *task) { struct freezer *freezer; - int retval; - /* Anything frozen can't move or be moved to/from */ + /* + * Anything frozen can't move or be moved to/from. + * + * Since orig_freezer->state == FROZEN means that @task has been + * frozen, so it's sufficient to check the latter condition. + */ if (is_task_frozen_enough(task)) return -EBUSY; @@ -173,25 +177,31 @@ static int freezer_can_attach(struct cgroup_subsys *ss, if (freezer->state == CGROUP_FROZEN) return -EBUSY; - retval = 0; - task_lock(task); - freezer = task_freezer(task); - if (freezer->state == CGROUP_FROZEN) - retval = -EBUSY; - task_unlock(task); - return retval; + return 0; } 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); - BUG_ON(freezer->state == CGROUP_FROZEN); + /* + * 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); + /* Locking avoids race with FREEZING -> THAWED transitions. */ if (freezer->state == CGROUP_FREEZING) freeze_task(task, true); @@ -276,25 +286,18 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) return num_cant_freeze_now ? -EBUSY : 0; } -static int unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) +static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) { struct cgroup_iter it; struct task_struct *task; cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { - int do_wake; - - task_lock(task); - do_wake = __thaw_process(task); - task_unlock(task); - if (do_wake) - wake_up_process(task); + thaw_process(task); } cgroup_iter_end(cgroup, &it); - freezer->state = CGROUP_THAWED; - return 0; + freezer->state = CGROUP_THAWED; } static int freezer_change_state(struct cgroup *cgroup, @@ -304,27 +307,22 @@ static int freezer_change_state(struct cgroup *cgroup, int retval = 0; freezer = cgroup_freezer(cgroup); + spin_lock_irq(&freezer->lock); + update_freezer_state(cgroup, freezer); if (goal_state == freezer->state) goto out; - switch (freezer->state) { + + switch (goal_state) { case CGROUP_THAWED: - retval = try_to_freeze_cgroup(cgroup, freezer); + unfreeze_cgroup(cgroup, freezer); break; - case CGROUP_FREEZING: - if (goal_state == CGROUP_FROZEN) { - /* Userspace is retrying after - * "/bin/echo FROZEN > freezer.state" returned -EBUSY */ - retval = try_to_freeze_cgroup(cgroup, freezer); - break; - } - /* state == FREEZING and goal_state == THAWED, so unfreeze */ case CGROUP_FROZEN: - retval = unfreeze_cgroup(cgroup, freezer); + retval = try_to_freeze_cgroup(cgroup, freezer); break; default: - break; + BUG(); } out: spin_unlock_irq(&freezer->lock); @@ -344,7 +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; @@ -363,6 +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 86d49045dae..8ea32e8d68b 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 3e00526f52e..96c0ba13b8c 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/exec_domain.c b/kernel/exec_domain.c index 0d407e88673..0511716e942 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -12,7 +12,9 @@ #include <linux/kmod.h> #include <linux/module.h> #include <linux/personality.h> +#include <linux/proc_fs.h> #include <linux/sched.h> +#include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/sysctl.h> #include <linux/types.h> @@ -173,20 +175,39 @@ __set_personality(u_long personality) return 0; } -int -get_exec_domain_list(char *page) +#ifdef CONFIG_PROC_FS +static int execdomains_proc_show(struct seq_file *m, void *v) { struct exec_domain *ep; - int len = 0; read_lock(&exec_domains_lock); - for (ep = exec_domains; ep && len < PAGE_SIZE - 80; ep = ep->next) - len += sprintf(page + len, "%d-%d\t%-16s\t[%s]\n", + for (ep = exec_domains; ep; ep = ep->next) + seq_printf(m, "%d-%d\t%-16s\t[%s]\n", ep->pers_low, ep->pers_high, ep->name, module_name(ep->module)); read_unlock(&exec_domains_lock); - return (len); + return 0; +} + +static int execdomains_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, execdomains_proc_show, NULL); +} + +static const struct file_operations execdomains_proc_fops = { + .open = execdomains_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_execdomains_init(void) +{ + proc_create("execdomains", 0, NULL, &execdomains_proc_fops); + return 0; } +module_init(proc_execdomains_init); +#endif asmlinkage long sys_personality(u_long personality) diff --git a/kernel/exit.c b/kernel/exit.c index 80137a5d946..2d8be7ebb0f 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 4d093552dd6..495da2e9a8b 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); @@ -1018,6 +1032,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; + p->default_timer_slack_ns = current->timer_slack_ns; + #ifdef CONFIG_DETECT_SOFTLOCKUP p->last_switch_count = 0; p->last_switch_timestamp = 0; @@ -1385,6 +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/freezer.c b/kernel/freezer.c index ba6248b323e..2f4936cf708 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -121,16 +121,7 @@ void cancel_freezing(struct task_struct *p) } } -/* - * Wake up a frozen process - * - * task_lock() is needed to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. - */ -int __thaw_process(struct task_struct *p) +static int __thaw_process(struct task_struct *p) { if (frozen(p)) { p->flags &= ~PF_FROZEN; @@ -140,6 +131,15 @@ int __thaw_process(struct task_struct *p) return 0; } +/* + * Wake up a frozen process + * + * task_lock() is needed to prevent the race with refrigerator() which may + * occur if the freezing of tasks fails. Namely, without the lock, if the + * freezing of tasks failed, thaw_tasks() might have run before a task in + * refrigerator() could call frozen_process(), in which case the task would be + * frozen and no one would thaw it. + */ int thaw_process(struct task_struct *p) { task_lock(p); diff --git a/kernel/futex.c b/kernel/futex.c index 7d1136e97c1..8af10027514 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1296,13 +1296,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, if (!abs_time) schedule(); else { + unsigned long slack; + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); hrtimer_init_sleeper(&t, current); - t.timer.expires = *abs_time; + hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack); - hrtimer_start(&t.timer, t.timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); if (!hrtimer_active(&t.timer)) t.task = NULL; @@ -1404,7 +1407,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); hrtimer_init_sleeper(to, current); - to->timer.expires = *time; + hrtimer_set_expires(&to->timer, *time); } q.pi_state = NULL; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 95978f48e03..47e63349d1b 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -517,7 +517,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) if (!base->first) continue; timer = rb_entry(base->first, struct hrtimer, node); - expires = ktime_sub(timer->expires, base->offset); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires.tv64 < cpu_base->expires_next.tv64) cpu_base->expires_next = expires; } @@ -539,10 +539,10 @@ static int hrtimer_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base) { ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next; - ktime_t expires = ktime_sub(timer->expires, base->offset); + ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); int res; - WARN_ON_ONCE(timer->expires.tv64 < 0); + WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * When the callback is running, we do not reprogram the clock event @@ -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 ! @@ -795,7 +786,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) u64 orun = 1; ktime_t delta; - delta = ktime_sub(now, timer->expires); + delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta.tv64 < 0) return 0; @@ -807,8 +798,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); - timer->expires = ktime_add_ns(timer->expires, incr * orun); - if (timer->expires.tv64 > now.tv64) + hrtimer_add_expires_ns(timer, incr * orun); + if (hrtimer_get_expires_tv64(timer) > now.tv64) return orun; /* * This (and the ktime_add() below) is the @@ -816,7 +807,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) */ orun++; } - timer->expires = ktime_add_safe(timer->expires, interval); + hrtimer_add_expires(timer, interval); return orun; } @@ -848,7 +839,8 @@ static void enqueue_hrtimer(struct hrtimer *timer, * We dont care about collisions. Nodes with * the same expiry time stay together. */ - if (timer->expires.tv64 < entry->expires.tv64) { + if (hrtimer_get_expires_tv64(timer) < + hrtimer_get_expires_tv64(entry)) { link = &(*link)->rb_left; } else { link = &(*link)->rb_right; @@ -945,9 +937,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) } /** - * hrtimer_start - (re)start an relative timer on the current CPU + * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added * @tim: expiry time + * @delta_ns: "slack" range for the timer * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) * * Returns: @@ -955,7 +948,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) * 1 when the timer was active */ int -hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns, + const enum hrtimer_mode mode) { struct hrtimer_clock_base *base, *new_base; unsigned long flags; @@ -983,7 +977,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) #endif } - timer->expires = tim; + hrtimer_set_expires_range_ns(timer, tim, delta_ns); timer_stats_hrtimer_set_start_info(timer); @@ -1016,8 +1010,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) return ret; } +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); + +/** + * hrtimer_start - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + return hrtimer_start_range_ns(timer, tim, 0, mode); +} EXPORT_SYMBOL_GPL(hrtimer_start); + /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop @@ -1077,7 +1089,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) ktime_t rem; base = lock_hrtimer_base(timer, &flags); - rem = ktime_sub(timer->expires, base->get_time()); + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; @@ -1109,7 +1121,7 @@ ktime_t hrtimer_get_next_event(void) continue; timer = rb_entry(base->first, struct hrtimer, node); - delta.tv64 = timer->expires.tv64; + delta.tv64 = hrtimer_get_expires_tv64(timer); delta = ktime_sub(delta, base->get_time()); if (delta.tv64 < mindelta.tv64) mindelta.tv64 = delta.tv64; @@ -1188,6 +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); @@ -1196,10 +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); @@ -1310,10 +1337,23 @@ void hrtimer_interrupt(struct clock_event_device *dev) timer = rb_entry(node, struct hrtimer, node); - if (basenow.tv64 < timer->expires.tv64) { + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the + * earliest interrupt after their soft expiration. + * This allows us to avoid using a Priority Search + * Tree, which can answer a stabbing querry for + * overlapping intervals and instead use the simple + * BST we already have. + * We don't add extra wakeups by delaying timers that + * are right-of a not yet expired timer, because that + * timer will have to trigger a wakeup anyway. + */ + + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { ktime_t expires; - expires = ktime_sub(timer->expires, + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires.tv64 < expires_next.tv64) expires_next = expires; @@ -1349,6 +1389,30 @@ void hrtimer_interrupt(struct clock_event_device *dev) raise_softirq(HRTIMER_SOFTIRQ); } +/** + * hrtimer_peek_ahead_timers -- run soft-expired timers now + * + * hrtimer_peek_ahead_timers will peek at the timer queue of + * the current cpu and check if there are any timers for which + * the soft expires time has passed. If any such timers exist, + * they are run immediately and then removed from the timer queue. + * + */ +void hrtimer_peek_ahead_timers(void) +{ + struct tick_device *td; + unsigned long flags; + + if (!hrtimer_hres_active()) + return; + + local_irq_save(flags); + td = &__get_cpu_var(tick_cpu_device); + if (td && td->evtdev) + hrtimer_interrupt(td->evtdev); + local_irq_restore(flags); +} + static void run_hrtimer_softirq(struct softirq_action *h) { run_hrtimer_pending(&__get_cpu_var(hrtimer_bases)); @@ -1414,7 +1478,8 @@ void hrtimer_run_queues(void) struct hrtimer *timer; timer = rb_entry(node, struct hrtimer, node); - if (base->softirq_time.tv64 <= timer->expires.tv64) + if (base->softirq_time.tv64 <= + hrtimer_get_expires_tv64(timer)) break; if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) { @@ -1462,7 +1527,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod do { set_current_state(TASK_INTERRUPTIBLE); - hrtimer_start(&t->timer, t->timer.expires, mode); + hrtimer_start_expires(&t->timer, mode); if (!hrtimer_active(&t->timer)) t->task = NULL; @@ -1484,7 +1549,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp) struct timespec rmt; ktime_t rem; - rem = ktime_sub(timer->expires, timer->base->get_time()); + rem = hrtimer_expires_remaining(timer); if (rem.tv64 <= 0) return 0; rmt = ktime_to_timespec(rem); @@ -1503,7 +1568,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart) hrtimer_init_on_stack(&t.timer, restart->nanosleep.index, HRTIMER_MODE_ABS); - t.timer.expires.tv64 = restart->nanosleep.expires; + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); if (do_nanosleep(&t, HRTIMER_MODE_ABS)) goto out; @@ -1528,9 +1593,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; + unsigned long slack; + + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; hrtimer_init_on_stack(&t.timer, clockid, mode); - t.timer.expires = timespec_to_ktime(*rqtp); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); if (do_nanosleep(&t, mode)) goto out; @@ -1550,7 +1620,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.index = t.timer.base->index; restart->nanosleep.rmtp = rmtp; - restart->nanosleep.expires = t.timer.expires.tv64; + restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); ret = -ERESTART_RESTARTBLOCK; out: @@ -1752,3 +1822,103 @@ void __init hrtimers_init(void) #endif } +/** + * schedule_hrtimeout_range - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * The @delta argument gives the kernel the freedom to schedule the + * actual wakeup to a time that is both power and performance friendly. + * The kernel give the normal best effort behavior for "@expires+@delta", + * but may decide to fire the timer earlier, but no earlier than @expires. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode) +{ + struct hrtimer_sleeper t; + + /* + * Optimize when a zero timeout value is given. It does not + * matter whether this is an absolute or a relative time. + */ + if (expires && !expires->tv64) { + __set_current_state(TASK_RUNNING); + return 0; + } + + /* + * A NULL parameter means "inifinte" + */ + if (!expires) { + schedule(); + __set_current_state(TASK_RUNNING); + return -EINTR; + } + + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + + hrtimer_init_sleeper(&t, current); + + hrtimer_start_expires(&t.timer, mode); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) + schedule(); + + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + + __set_current_state(TASK_RUNNING); + + return !t.task ? 0 : -EINTR; +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); + +/** + * schedule_hrtimeout - sleep until timeout + * @expires: timeout value (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout(ktime_t *expires, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range(expires, 0, mode); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 4895fde4eb9..10b5092e9bf 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -76,6 +76,7 @@ void dynamic_irq_cleanup(unsigned int irq) desc->chip_data = NULL; desc->handle_irq = handle_bad_irq; desc->chip = &no_irq_chip; + desc->name = NULL; spin_unlock_irqrestore(&desc->lock, flags); } @@ -127,7 +128,7 @@ int set_irq_type(unsigned int irq, unsigned int type) return 0; spin_lock_irqsave(&desc->lock, flags); - ret = __irq_set_trigger(desc, irq, flags); + ret = __irq_set_trigger(desc, irq, type); spin_unlock_irqrestore(&desc->lock, flags); return ret; } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index c9767e64198..64c1c7253da 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 c498a1b8c62..801addda3c4 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 90b920d3f52..9db681d9581 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 fac014a81b2..d257e7d6a8a 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); @@ -220,7 +220,7 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action) } } -void register_default_affinity_proc(void) +static void register_default_affinity_proc(void) { #ifdef CONFIG_SMP proc_create("irq/default_smp_affinity", 0600, NULL, diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 5072cf1685a..7b8b0f21a5b 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 8b57a2597f2..9f8a3f25259 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 5e7b45c5692..449db466bdb 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 dbda475b13b..46a404173db 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2169,12 +2169,11 @@ void early_boot_irqs_on(void) /* * Hardirqs will be enabled: */ -void trace_hardirqs_on_caller(unsigned long a0) +void trace_hardirqs_on_caller(unsigned long ip) { struct task_struct *curr = current; - unsigned long ip; - time_hardirqs_on(CALLER_ADDR0, a0); + time_hardirqs_on(CALLER_ADDR0, ip); if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2188,7 +2187,6 @@ void trace_hardirqs_on_caller(unsigned long a0) } /* we'll do an OFF -> ON transition: */ curr->hardirqs_enabled = 1; - ip = (unsigned long) __builtin_return_address(0); if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; @@ -2224,11 +2222,11 @@ EXPORT_SYMBOL(trace_hardirqs_on); /* * Hardirqs were disabled: */ -void trace_hardirqs_off_caller(unsigned long a0) +void trace_hardirqs_off_caller(unsigned long ip) { struct task_struct *curr = current; - time_hardirqs_off(CALLER_ADDR0, a0); + time_hardirqs_off(CALLER_ADDR0, ip); if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2241,7 +2239,7 @@ void trace_hardirqs_off_caller(unsigned long a0) * We have done an ON -> OFF transition: */ curr->hardirqs_enabled = 0; - curr->hardirq_disable_ip = _RET_IP_; + curr->hardirq_disable_ip = ip; curr->hardirq_disable_event = ++curr->irq_events; debug_atomic_inc(&hardirqs_off_events); } else @@ -3278,10 +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); @@ -3417,9 +3415,10 @@ retry: } printk(" ignoring it.\n"); unlock = 0; + } else { + if (count != 10) + printk(KERN_CONT " locked it.\n"); } - if (count != 10) - printk(" locked it.\n"); do_each_thread(g, p) { /* diff --git a/kernel/module.c b/kernel/module.c index 0d8d21ee792..1f4cc00e0c2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -20,11 +20,13 @@ #include <linux/moduleloader.h> #include <linux/init.h> #include <linux/kallsyms.h> +#include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/elf.h> +#include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/fcntl.h> @@ -42,6 +44,7 @@ #include <linux/string.h> #include <linux/mutex.h> #include <linux/unwind.h> +#include <linux/rculist.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> #include <linux/license.h> @@ -63,7 +66,7 @@ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) /* List of modules, protected by module_mutex or preempt_disable - * (add/delete uses stop_machine). */ + * (delete uses stop_machine/add uses RCU list operations). */ static DEFINE_MUTEX(module_mutex); static LIST_HEAD(modules); @@ -132,6 +135,29 @@ static unsigned int find_sec(Elf_Ehdr *hdr, return 0; } +/* Find a module section, or NULL. */ +static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs, + const char *secstrings, const char *name) +{ + /* Section 0 has sh_addr 0. */ + return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr; +} + +/* Find a module section, or NULL. Fill in number of "objects" in section. */ +static void *section_objs(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings, + const char *name, + size_t object_size, + unsigned int *num) +{ + unsigned int sec = find_sec(hdr, sechdrs, secstrings, name); + + /* Section 0 has sh_addr 0 and sh_size 0. */ + *num = sechdrs[sec].sh_size / object_size; + return (void *)sechdrs[sec].sh_addr; +} + /* Provided by the linker */ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; @@ -218,7 +244,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr, if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) return true; - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { struct symsearch arr[] = { { mod->syms, mod->syms + mod->num_syms, mod->crcs, NOT_GPL_ONLY, false }, @@ -1394,17 +1420,6 @@ static void mod_kobject_remove(struct module *mod) } /* - * link the module with the whole machine is stopped with interrupts off - * - this defends against kallsyms not taking locks - */ -static int __link_module(void *_mod) -{ - struct module *mod = _mod; - list_add(&mod->list, &modules); - return 0; -} - -/* * unlink the module with the whole machine is stopped with interrupts off * - this defends against kallsyms not taking locks */ @@ -1789,32 +1804,20 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG -static void dynamic_printk_setup(Elf_Shdr *sechdrs, unsigned int verboseindex) +static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) { - struct mod_debug *debug_info; - unsigned long pos, end; - unsigned int num_verbose; - - pos = sechdrs[verboseindex].sh_addr; - num_verbose = sechdrs[verboseindex].sh_size / - sizeof(struct mod_debug); - end = pos + (num_verbose * sizeof(struct mod_debug)); +#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG + unsigned int i; - for (; pos < end; pos += sizeof(struct mod_debug)) { - debug_info = (struct mod_debug *)pos; - register_dynamic_debug_module(debug_info->modname, - debug_info->type, debug_info->logical_modname, - debug_info->flag_names, debug_info->hash, - debug_info->hash2); + for (i = 0; i < num; i++) { + register_dynamic_debug_module(debug[i].modname, + debug[i].type, + debug[i].logical_modname, + debug[i].flag_names, + debug[i].hash, debug[i].hash2); } -} -#else -static inline void dynamic_printk_setup(Elf_Shdr *sechdrs, - unsigned int verboseindex) -{ -} #endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +} static void *module_alloc_update_bounds(unsigned long size) { @@ -1843,37 +1846,14 @@ static noinline struct module *load_module(void __user *umod, unsigned int i; unsigned int symindex = 0; unsigned int strindex = 0; - unsigned int setupindex; - unsigned int exindex; - unsigned int exportindex; - unsigned int modindex; - unsigned int obsparmindex; - unsigned int infoindex; - unsigned int gplindex; - unsigned int crcindex; - unsigned int gplcrcindex; - unsigned int versindex; - unsigned int pcpuindex; - unsigned int gplfutureindex; - unsigned int gplfuturecrcindex; + unsigned int modindex, versindex, infoindex, pcpuindex; unsigned int unwindex = 0; -#ifdef CONFIG_UNUSED_SYMBOLS - unsigned int unusedindex; - unsigned int unusedcrcindex; - unsigned int unusedgplindex; - unsigned int unusedgplcrcindex; -#endif - unsigned int markersindex; - unsigned int markersstringsindex; - unsigned int verboseindex; - unsigned int tracepointsindex; - unsigned int tracepointsstringsindex; - unsigned int mcountindex; + unsigned int num_kp, num_mcount; + struct kernel_param *kp; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ - void *mseg; - struct exception_table_entry *extable; + unsigned long *mseg; mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -1937,6 +1917,7 @@ static noinline struct module *load_module(void __user *umod, err = -ENOEXEC; goto free_hdr; } + /* This is temporary: point mod into copy of data. */ mod = (void *)sechdrs[modindex].sh_addr; if (symindex == 0) { @@ -1946,22 +1927,6 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } - /* Optional sections */ - exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); - gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); - gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future"); - crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); - gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); - gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future"); -#ifdef CONFIG_UNUSED_SYMBOLS - unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused"); - unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl"); - unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused"); - unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); -#endif - setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); - exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); - obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); @@ -2117,42 +2082,57 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto cleanup; - /* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */ - mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms); - mod->syms = (void *)sechdrs[exportindex].sh_addr; - if (crcindex) - mod->crcs = (void *)sechdrs[crcindex].sh_addr; - mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms); - mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr; - if (gplcrcindex) - mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; - mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size / - sizeof(*mod->gpl_future_syms); - mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr; - if (gplfuturecrcindex) - mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr; + /* Now we've got everything in the final locations, we can + * find optional sections. */ + kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp), + &num_kp); + mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); + mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_gpl_future"); #ifdef CONFIG_UNUSED_SYMBOLS - mod->num_unused_syms = sechdrs[unusedindex].sh_size / - sizeof(*mod->unused_syms); - mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size / - sizeof(*mod->unused_gpl_syms); - mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr; - if (unusedcrcindex) - mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr; - mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr; - if (unusedgplcrcindex) - mod->unused_gpl_crcs - = (void *)sechdrs[unusedgplcrcindex].sh_addr; + mod->unused_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused_gpl"); +#endif + +#ifdef CONFIG_MARKERS + mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers", + sizeof(*mod->markers), &mod->num_markers); +#endif +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = section_objs(hdr, sechdrs, secstrings, + "__tracepoints", + sizeof(*mod->tracepoints), + &mod->num_tracepoints); #endif #ifdef CONFIG_MODVERSIONS - if ((mod->num_syms && !crcindex) - || (mod->num_gpl_syms && !gplcrcindex) - || (mod->num_gpl_future_syms && !gplfuturecrcindex) + if ((mod->num_syms && !mod->crcs) + || (mod->num_gpl_syms && !mod->gpl_crcs) + || (mod->num_gpl_future_syms && !mod->gpl_future_crcs) #ifdef CONFIG_UNUSED_SYMBOLS - || (mod->num_unused_syms && !unusedcrcindex) - || (mod->num_unused_gpl_syms && !unusedgplcrcindex) + || (mod->num_unused_syms && !mod->unused_crcs) + || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name); @@ -2161,16 +2141,6 @@ static noinline struct module *load_module(void __user *umod, goto cleanup; } #endif - markersindex = find_sec(hdr, sechdrs, secstrings, "__markers"); - markersstringsindex = find_sec(hdr, sechdrs, secstrings, - "__markers_strings"); - verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose"); - tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints"); - tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings, - "__tracepoints_strings"); - - mcountindex = find_sec(hdr, sechdrs, secstrings, - "__mcount_loc"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -2193,28 +2163,16 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto cleanup; } -#ifdef CONFIG_MARKERS - mod->markers = (void *)sechdrs[markersindex].sh_addr; - mod->num_markers = - sechdrs[markersindex].sh_size / sizeof(*mod->markers); -#endif -#ifdef CONFIG_TRACEPOINTS - mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr; - mod->num_tracepoints = - sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints); -#endif - /* Find duplicate symbols */ err = verify_export_symbols(mod); - if (err < 0) goto cleanup; /* Set up and sort exception table */ - mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable); - mod->extable = extable = (void *)sechdrs[exindex].sh_addr; - sort_extable(extable, extable + mod->num_exentries); + mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + sort_extable(mod->extable, mod->extable + mod->num_exentries); /* Finally, copy percpu area over. */ percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, @@ -2223,11 +2181,17 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); if (!mod->taints) { + struct mod_debug *debug; + unsigned int num_debug; + #ifdef CONFIG_MARKERS marker_update_probe_range(mod->markers, mod->markers + mod->num_markers); #endif - dynamic_printk_setup(sechdrs, verboseindex); + debug = section_objs(hdr, sechdrs, secstrings, "__verbose", + sizeof(*debug), &num_debug); + dynamic_printk_setup(debug, num_debug); + #ifdef CONFIG_TRACEPOINTS tracepoint_update_probe_range(mod->tracepoints, mod->tracepoints + mod->num_tracepoints); @@ -2235,8 +2199,9 @@ static noinline struct module *load_module(void __user *umod, } /* sechdrs[0].sh_size is always zero */ - mseg = (void *)sechdrs[mcountindex].sh_addr; - ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); + mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", + sizeof(*mseg), &num_mcount); + ftrace_init_module(mseg, mseg + num_mcount); err = module_finalize(hdr, sechdrs, mod); if (err < 0) @@ -2261,30 +2226,24 @@ static noinline struct module *load_module(void __user *umod, set_fs(old_fs); mod->args = args; - if (obsparmindex) + if (section_addr(hdr, sechdrs, secstrings, "__obsparm")) printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", mod->name); /* Now sew it into the lists so we can get lockdep and oops - * info during argument parsing. Noone should access us, since - * strong_try_module_get() will fail. */ - stop_machine(__link_module, mod, NULL); - - /* Size of section 0 is 0, so this works well if no params */ - err = parse_args(mod->name, mod->args, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param), - NULL); + * info during argument parsing. Noone should access us, since + * strong_try_module_get() will fail. + * lockdep/oops can run asynchronous, so use the RCU list insertion + * function to insert in a way safe to concurrent readers. + * The mutex protects against concurrent writers. + */ + list_add_rcu(&mod->list, &modules); + + err = parse_args(mod->name, mod->args, kp, num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param)); + err = mod_sysfs_setup(mod, kp, num_kp); if (err < 0) goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); @@ -2473,7 +2432,7 @@ const char *module_address_lookup(unsigned long addr, const char *ret = NULL; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { if (modname) @@ -2496,7 +2455,7 @@ int lookup_module_symbol_name(unsigned long addr, char *symname) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { const char *sym; @@ -2520,7 +2479,7 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { const char *sym; @@ -2547,7 +2506,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; @@ -2590,7 +2549,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) ret = mod_find_symname(mod, colon+1); *colon = ':'; } else { - list_for_each_entry(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) if ((ret = mod_find_symname(mod, name)) != 0) break; } @@ -2599,23 +2558,6 @@ unsigned long module_kallsyms_lookup_name(const char *name) } #endif /* CONFIG_KALLSYMS */ -/* Called by the /proc file system to return a list of modules. */ -static void *m_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&module_mutex); - return seq_list_start(&modules, *pos); -} - -static void *m_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &modules, pos); -} - -static void m_stop(struct seq_file *m, void *p) -{ - mutex_unlock(&module_mutex); -} - static char *module_flags(struct module *mod, char *buf) { int bx = 0; @@ -2649,6 +2591,24 @@ static char *module_flags(struct module *mod, char *buf) return buf; } +#ifdef CONFIG_PROC_FS +/* Called by the /proc file system to return a list of modules. */ +static void *m_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&module_mutex); + return seq_list_start(&modules, *pos); +} + +static void *m_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &modules, pos); +} + +static void m_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&module_mutex); +} + static int m_show(struct seq_file *m, void *p) { struct module *mod = list_entry(p, struct module, list); @@ -2679,13 +2639,33 @@ static int m_show(struct seq_file *m, void *p) Where refcount is a number or -, and deps is a comma-separated list of depends or -. */ -const struct seq_operations modules_op = { +static const struct seq_operations modules_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show }; +static int modules_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &modules_op); +} + +static const struct file_operations proc_modules_operations = { + .open = modules_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_modules_init(void) +{ + proc_create("modules", 0, NULL, &proc_modules_operations); + return 0; +} +module_init(proc_modules_init); +#endif + /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_extables(unsigned long addr) { @@ -2693,7 +2673,7 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (mod->num_exentries == 0) continue; @@ -2719,7 +2699,7 @@ int is_module_address(unsigned long addr) preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_core, mod->core_size)) { preempt_enable(); return 1; @@ -2740,7 +2720,7 @@ struct module *__module_text_address(unsigned long addr) if (addr < module_addr_min || addr > module_addr_max) return NULL; - list_for_each_entry(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) if (within(addr, mod->module_init, mod->init_text_size) || within(addr, mod->module_core, mod->core_text_size)) return mod; @@ -2765,8 +2745,11 @@ void print_modules(void) char buf[8]; printk("Modules linked in:"); - list_for_each_entry(mod, &modules, list) + /* Most callers should already have preempt disabled, but make sure */ + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) printk(" %s%s", mod->name, module_flags(mod, buf)); + preempt_enable(); if (last_unloaded_module[0]) printk(" [last unloaded: %s]", last_unloaded_module); printk("\n"); diff --git a/kernel/panic.c b/kernel/panic.c index bda561ef3cd..4d5088355bf 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -34,13 +34,6 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); -static int __init panic_setup(char *str) -{ - panic_timeout = simple_strtoul(str, NULL, 0); - return 1; -} -__setup("panic=", panic_setup); - static long no_blink(long time) { return 0; @@ -174,6 +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. @@ -218,13 +212,6 @@ void add_taint(unsigned flag) } EXPORT_SYMBOL(add_taint); -static int __init pause_on_oops_setup(char *str) -{ - pause_on_oops = simple_strtoul(str, NULL, 0); - return 1; -} -__setup("pause_on_oops=", pause_on_oops_setup); - static void spin_msec(int msecs) { int i; @@ -384,3 +371,6 @@ void __stack_chk_fail(void) } EXPORT_SYMBOL(__stack_chk_fail); #endif + +core_param(panic, panic_timeout, int, 0644); +core_param(pause_on_oops, pause_on_oops, int, 0644); diff --git a/kernel/params.c b/kernel/params.c index afc46a23eb6..a1e3025b19a 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -373,6 +373,8 @@ int param_get_string(char *buffer, struct kernel_param *kp) } /* sysfs output in /sys/modules/XYZ/parameters/ */ +#define to_module_attr(n) container_of(n, struct module_attribute, attr); +#define to_module_kobject(n) container_of(n, struct module_kobject, kobj); extern struct kernel_param __start___param[], __stop___param[]; @@ -384,6 +386,7 @@ struct param_attribute struct module_param_attrs { + unsigned int num; struct attribute_group grp; struct param_attribute attrs[0]; }; @@ -434,93 +437,120 @@ static ssize_t param_attr_store(struct module_attribute *mattr, #ifdef CONFIG_SYSFS /* - * param_sysfs_setup - setup sysfs support for one module or KBUILD_MODNAME - * @mk: struct module_kobject (contains parent kobject) - * @kparam: array of struct kernel_param, the actual parameter definitions - * @num_params: number of entries in array - * @name_skip: offset where the parameter name start in kparam[].name. Needed for built-in "modules" + * add_sysfs_param - add a parameter to sysfs + * @mk: struct module_kobject + * @kparam: the actual parameter definition to add to sysfs + * @name: name of parameter * - * Create a kobject for a (per-module) group of parameters, and create files - * in sysfs. A pointer to the param_kobject is returned on success, - * NULL if there's no parameter to export, or other ERR_PTR(err). + * Create a kobject if for a (per-module) parameter if mp NULL, and + * create file in sysfs. Returns an error on out of memory. Always cleans up + * if there's an error. */ -static __modinit struct module_param_attrs * -param_sysfs_setup(struct module_kobject *mk, - struct kernel_param *kparam, - unsigned int num_params, - unsigned int name_skip) +static __modinit int add_sysfs_param(struct module_kobject *mk, + struct kernel_param *kp, + const char *name) { - struct module_param_attrs *mp; - unsigned int valid_attrs = 0; - unsigned int i, size[2]; - struct param_attribute *pattr; - struct attribute **gattr; - int err; - - for (i=0; i<num_params; i++) { - if (kparam[i].perm) - valid_attrs++; + struct module_param_attrs *new; + struct attribute **attrs; + int err, num; + + /* We don't bother calling this with invisible parameters. */ + BUG_ON(!kp->perm); + + if (!mk->mp) { + num = 0; + attrs = NULL; + } else { + num = mk->mp->num; + attrs = mk->mp->grp.attrs; } - if (!valid_attrs) - return NULL; - - size[0] = ALIGN(sizeof(*mp) + - valid_attrs * sizeof(mp->attrs[0]), - sizeof(mp->grp.attrs[0])); - size[1] = (valid_attrs + 1) * sizeof(mp->grp.attrs[0]); - - mp = kzalloc(size[0] + size[1], GFP_KERNEL); - if (!mp) - return ERR_PTR(-ENOMEM); - - mp->grp.name = "parameters"; - mp->grp.attrs = (void *)mp + size[0]; - - pattr = &mp->attrs[0]; - gattr = &mp->grp.attrs[0]; - for (i = 0; i < num_params; i++) { - struct kernel_param *kp = &kparam[i]; - if (kp->perm) { - pattr->param = kp; - pattr->mattr.show = param_attr_show; - pattr->mattr.store = param_attr_store; - pattr->mattr.attr.name = (char *)&kp->name[name_skip]; - pattr->mattr.attr.mode = kp->perm; - *(gattr++) = &(pattr++)->mattr.attr; - } + /* Enlarge. */ + new = krealloc(mk->mp, + sizeof(*mk->mp) + sizeof(mk->mp->attrs[0]) * (num+1), + GFP_KERNEL); + if (!new) { + kfree(mk->mp); + err = -ENOMEM; + goto fail; } - *gattr = NULL; - - if ((err = sysfs_create_group(&mk->kobj, &mp->grp))) { - kfree(mp); - return ERR_PTR(err); + attrs = krealloc(attrs, sizeof(new->grp.attrs[0])*(num+2), GFP_KERNEL); + if (!attrs) { + err = -ENOMEM; + goto fail_free_new; } - return mp; + + /* Sysfs wants everything zeroed. */ + memset(new, 0, sizeof(*new)); + memset(&new->attrs[num], 0, sizeof(new->attrs[num])); + memset(&attrs[num], 0, sizeof(attrs[num])); + new->grp.name = "parameters"; + new->grp.attrs = attrs; + + /* Tack new one on the end. */ + new->attrs[num].param = kp; + new->attrs[num].mattr.show = param_attr_show; + new->attrs[num].mattr.store = param_attr_store; + new->attrs[num].mattr.attr.name = (char *)name; + new->attrs[num].mattr.attr.mode = kp->perm; + new->num = num+1; + + /* Fix up all the pointers, since krealloc can move us */ + for (num = 0; num < new->num; num++) + new->grp.attrs[num] = &new->attrs[num].mattr.attr; + new->grp.attrs[num] = NULL; + + mk->mp = new; + return 0; + +fail_free_new: + kfree(new); +fail: + mk->mp = NULL; + return err; } #ifdef CONFIG_MODULES +static void free_module_param_attrs(struct module_kobject *mk) +{ + kfree(mk->mp->grp.attrs); + kfree(mk->mp); + mk->mp = NULL; +} + /* * module_param_sysfs_setup - setup sysfs support for one module * @mod: module * @kparam: module parameters (array) * @num_params: number of module parameters * - * Adds sysfs entries for module parameters, and creates a link from - * /sys/module/[mod->name]/parameters to /sys/parameters/[mod->name]/ + * Adds sysfs entries for module parameters under + * /sys/module/[mod->name]/parameters/ */ int module_param_sysfs_setup(struct module *mod, struct kernel_param *kparam, unsigned int num_params) { - struct module_param_attrs *mp; + int i, err; + bool params = false; + + for (i = 0; i < num_params; i++) { + if (kparam[i].perm == 0) + continue; + err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name); + if (err) + return err; + params = true; + } - mp = param_sysfs_setup(&mod->mkobj, kparam, num_params, 0); - if (IS_ERR(mp)) - return PTR_ERR(mp); + if (!params) + return 0; - mod->param_attrs = mp; - return 0; + /* Create the param group. */ + err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); + if (err) + free_module_param_attrs(&mod->mkobj); + return err; } /* @@ -532,43 +562,55 @@ int module_param_sysfs_setup(struct module *mod, */ void module_param_sysfs_remove(struct module *mod) { - if (mod->param_attrs) { - sysfs_remove_group(&mod->mkobj.kobj, - &mod->param_attrs->grp); + if (mod->mkobj.mp) { + sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); /* We are positive that no one is using any param * attrs at this point. Deallocate immediately. */ - kfree(mod->param_attrs); - mod->param_attrs = NULL; + free_module_param_attrs(&mod->mkobj); } } #endif -/* - * kernel_param_sysfs_setup - wrapper for built-in params support - */ -static void __init kernel_param_sysfs_setup(const char *name, - struct kernel_param *kparam, - unsigned int num_params, - unsigned int name_skip) +static void __init kernel_add_sysfs_param(const char *name, + struct kernel_param *kparam, + unsigned int name_skip) { struct module_kobject *mk; - int ret; + struct kobject *kobj; + int err; - mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL); - BUG_ON(!mk); - - mk->mod = THIS_MODULE; - mk->kobj.kset = module_kset; - ret = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name); - if (ret) { - kobject_put(&mk->kobj); - printk(KERN_ERR "Module '%s' failed to be added to sysfs, " - "error number %d\n", name, ret); - printk(KERN_ERR "The system will be unstable now.\n"); - return; + kobj = kset_find_obj(module_kset, name); + if (kobj) { + /* We already have one. Remove params so we can add more. */ + mk = to_module_kobject(kobj); + /* We need to remove it before adding parameters. */ + sysfs_remove_group(&mk->kobj, &mk->mp->grp); + } else { + mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL); + BUG_ON(!mk); + + mk->mod = THIS_MODULE; + mk->kobj.kset = module_kset; + err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, + "%s", name); + if (err) { + kobject_put(&mk->kobj); + printk(KERN_ERR "Module '%s' failed add to sysfs, " + "error number %d\n", name, err); + printk(KERN_ERR "The system will be unstable now.\n"); + return; + } + /* So that exit path is even. */ + kobject_get(&mk->kobj); } - param_sysfs_setup(mk, kparam, num_params, name_skip); + + /* These should not fail at boot. */ + err = add_sysfs_param(mk, kparam, kparam->name + name_skip); + BUG_ON(err); + err = sysfs_create_group(&mk->kobj, &mk->mp->grp); + BUG_ON(err); kobject_uevent(&mk->kobj, KOBJ_ADD); + kobject_put(&mk->kobj); } /* @@ -579,60 +621,36 @@ static void __init kernel_param_sysfs_setup(const char *name, * The "module" name (KBUILD_MODNAME) is stored before a dot, the * "parameter" name is stored behind a dot in kernel_param->name. So, * extract the "module" name for all built-in kernel_param-eters, - * and for all who have the same, call kernel_param_sysfs_setup. + * and for all who have the same, call kernel_add_sysfs_param. */ static void __init param_sysfs_builtin(void) { - struct kernel_param *kp, *kp_begin = NULL; - unsigned int i, name_len, count = 0; - char modname[MODULE_NAME_LEN + 1] = ""; + struct kernel_param *kp; + unsigned int name_len; + char modname[MODULE_NAME_LEN]; - for (i=0; i < __stop___param - __start___param; i++) { + for (kp = __start___param; kp < __stop___param; kp++) { char *dot; - size_t max_name_len; - kp = &__start___param[i]; - max_name_len = - min_t(size_t, MODULE_NAME_LEN, strlen(kp->name)); + if (kp->perm == 0) + continue; - dot = memchr(kp->name, '.', max_name_len); + dot = strchr(kp->name, '.'); if (!dot) { - DEBUGP("couldn't find period in first %d characters " - "of %s\n", MODULE_NAME_LEN, kp->name); - continue; - } - name_len = dot - kp->name; - - /* new kbuild_modname? */ - if (strlen(modname) != name_len - || strncmp(modname, kp->name, name_len) != 0) { - /* add a new kobject for previous kernel_params. */ - if (count) - kernel_param_sysfs_setup(modname, - kp_begin, - count, - strlen(modname)+1); - - strncpy(modname, kp->name, name_len); - modname[name_len] = '\0'; - count = 0; - kp_begin = kp; + /* This happens for core_param() */ + strcpy(modname, "kernel"); + name_len = 0; + } else { + name_len = dot - kp->name + 1; + strlcpy(modname, kp->name, name_len); } - count++; + kernel_add_sysfs_param(modname, kp, name_len); } - - /* last kernel_params need to be registered as well */ - if (count) - kernel_param_sysfs_setup(modname, kp_begin, count, - strlen(modname)+1); } /* module-related sysfs stuff */ -#define to_module_attr(n) container_of(n, struct module_attribute, attr); -#define to_module_kobject(n) container_of(n, struct module_kobject, kobj); - static ssize_t module_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 153dcb2639c..4e5288a831d 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/posix-timers.c b/kernel/posix-timers.c index b931d7cedbf..a140e44eebb 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -197,6 +197,11 @@ static int common_timer_create(struct k_itimer *new_timer) return 0; } +static int no_timer_create(struct k_itimer *new_timer) +{ + return -EOPNOTSUPP; +} + /* * Return nonzero if we know a priori this clockid_t value is bogus. */ @@ -248,6 +253,7 @@ static __init int init_posix_timers(void) .clock_getres = hrtimer_get_res, .clock_get = posix_get_monotonic_raw, .clock_set = do_posix_clock_nosettime, + .timer_create = no_timer_create, }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); @@ -639,7 +645,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(timer->expires, now); + remaining = ktime_sub(hrtimer_get_expires(timer), now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* @@ -733,7 +739,7 @@ common_timer_set(struct k_itimer *timr, int flags, hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); timr->it.real.timer.function = posix_timer_fn; - timer->expires = timespec_to_ktime(new_setting->it_value); + hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value)); /* Convert interval */ timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); @@ -742,14 +748,12 @@ common_timer_set(struct k_itimer *timr, int flags, if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { /* Setup correct expiry time for relative timers */ if (mode == HRTIMER_MODE_REL) { - timer->expires = - ktime_add_safe(timer->expires, - timer->base->get_time()); + hrtimer_add_expires(timer, timer->base->get_time()); } return 0; } - hrtimer_start(timer, timer->expires, mode); + hrtimer_start_expires(timer, mode); return 0; } diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index dcd165f92a8..23bd4daeb96 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -96,7 +96,7 @@ config SUSPEND config PM_TEST_SUSPEND bool "Test suspend/resume and wakealarm during bootup" - depends on SUSPEND && PM_DEBUG && RTC_LIB=y + depends on SUSPEND && PM_DEBUG && RTC_CLASS=y ---help--- This option will let you suspend your machine during bootup, and make it wake up a few seconds later using an RTC wakeup alarm. diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 331f9836383..c9d74083746 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -651,7 +651,7 @@ static int software_resume(void) pr_debug("PM: Preparing processes for restore.\n"); error = prepare_processes(); if (error) { - swsusp_close(); + swsusp_close(FMODE_READ); goto Done; } diff --git a/kernel/power/main.c b/kernel/power/main.c index 19122cf6d82..b8f7ce9473e 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/power.h b/kernel/power/power.h index acc0c101dbd..46b5ec7a3af 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -153,7 +153,7 @@ extern int swsusp_shrink_memory(void); extern void swsusp_free(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); -extern void swsusp_close(void); +extern void swsusp_close(fmode_t); struct timeval; /* kernel/power/swsusp.c */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 80ccac849e4..6da14358537 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -172,13 +172,13 @@ static int swsusp_swap_check(void) /* This is called before saving image */ return res; root_swap = res; - res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR); + res = blkdev_get(resume_bdev, FMODE_WRITE); if (res) return res; res = set_blocksize(resume_bdev, PAGE_SIZE); if (res < 0) - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, FMODE_WRITE); return res; } @@ -426,7 +426,7 @@ int swsusp_write(unsigned int flags) release_swap_writer(&handle); out: - swsusp_close(); + swsusp_close(FMODE_WRITE); return error; } @@ -574,7 +574,7 @@ int swsusp_read(unsigned int *flags_p) error = load_image(&handle, &snapshot, header->pages - 1); release_swap_reader(&handle); - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, FMODE_READ); if (!error) pr_debug("PM: Image successfully loaded\n"); @@ -609,7 +609,7 @@ int swsusp_check(void) return -EINVAL; } if (error) - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, FMODE_READ); else pr_debug("PM: Signature found, resuming\n"); } else { @@ -626,14 +626,14 @@ int swsusp_check(void) * swsusp_close - close swap device. */ -void swsusp_close(void) +void swsusp_close(fmode_t mode) { if (IS_ERR(resume_bdev)) { pr_debug("PM: Image device not initialised\n"); return; } - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, mode); } static int swsusp_header_init(void) diff --git a/kernel/printk.c b/kernel/printk.c index 6341af77eb6..f492f1583d7 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -233,45 +233,6 @@ static inline void boot_delay_msec(void) #endif /* - * Return the number of unread characters in the log buffer. - */ -static int log_buf_get_len(void) -{ - return logged_chars; -} - -/* - * Copy a range of characters from the log buffer. - */ -int log_buf_copy(char *dest, int idx, int len) -{ - int ret, max; - bool took_lock = false; - - if (!oops_in_progress) { - spin_lock_irq(&logbuf_lock); - took_lock = true; - } - - max = log_buf_get_len(); - if (idx < 0 || idx >= max) { - ret = -1; - } else { - if (len > max) - len = max; - ret = len; - idx += (log_end - max); - while (len-- > 0) - dest[len] = LOG_BUF(idx + len); - } - - if (took_lock) - spin_unlock_irq(&logbuf_lock); - - return ret; -} - -/* * Commands to do_syslog: * * 0 -- Close the log. Currently a NOP. diff --git a/kernel/profile.c b/kernel/profile.c index a9e422df6bf..dc41827fbfe 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -102,7 +102,7 @@ int profile_setup(char *str) __setup("profile=", profile_setup); -int profile_init(void) +int __ref profile_init(void) { int buffer_bytes; if (!prof_on) @@ -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 1e68e4c39e2..4c8bcd7dd8e 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/rcupdate.c b/kernel/rcupdate.c index 467d5940f62..ad63af8b252 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -119,18 +119,19 @@ static void _rcu_barrier(enum rcu_barrier type) /* Take cpucontrol mutex to protect against CPU hotplug */ mutex_lock(&rcu_barrier_mutex); init_completion(&rcu_barrier_completion); - atomic_set(&rcu_barrier_cpu_count, 0); /* - * The queueing of callbacks in all CPUs must be atomic with - * respect to RCU, otherwise one CPU may queue a callback, - * wait for a grace period, decrement barrier count and call - * complete(), while other CPUs have not yet queued anything. - * So, we need to make sure that grace periods cannot complete - * until all the callbacks are queued. + * Initialize rcu_barrier_cpu_count to 1, then invoke + * rcu_barrier_func() on each CPU, so that each CPU also has + * incremented rcu_barrier_cpu_count. Only then is it safe to + * decrement rcu_barrier_cpu_count -- otherwise the first CPU + * might complete its grace period before all of the other CPUs + * did their increment, causing this function to return too + * early. */ - rcu_read_lock(); + atomic_set(&rcu_barrier_cpu_count, 1); on_each_cpu(rcu_barrier_func, (void *)type, 1); - rcu_read_unlock(); + if (atomic_dec_and_test(&rcu_barrier_cpu_count)) + complete(&rcu_barrier_completion); wait_for_completion(&rcu_barrier_completion); mutex_unlock(&rcu_barrier_mutex); } diff --git a/kernel/relay.c b/kernel/relay.c index 8d13a7855c0..09ac2008f77 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/resource.c b/kernel/resource.c index 4089d12af6e..4337063663e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -17,6 +17,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/device.h> +#include <linux/pfn.h> #include <asm/io.h> @@ -522,7 +523,7 @@ static void __init __reserve_region_with_split(struct resource *root, { struct resource *parent = root; struct resource *conflict; - struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); + struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC); if (!res) return; @@ -571,7 +572,7 @@ static void __init __reserve_region_with_split(struct resource *root, } -void reserve_region_with_split(struct resource *root, +void __init reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name) { @@ -849,7 +850,8 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) continue; if (p->end < addr) continue; - if (p->start <= addr && (p->end >= addr + size - 1)) + if (PFN_DOWN(p->start) <= PFN_DOWN(addr) && + PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1)) continue; printk(KERN_WARNING "resource map sanity check conflict: " "0x%llx 0x%llx 0x%llx 0x%llx %s\n", diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index 6522ae5b14a..69d9cb921ff 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -631,8 +631,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, /* Setup the timer, when timeout != NULL */ if (unlikely(timeout)) { - hrtimer_start(&timeout->timer, timeout->timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); if (!hrtimer_active(&timeout->timer)) timeout->task = NULL; } diff --git a/kernel/sched.c b/kernel/sched.c index d906f72b42d..e4bb1dd7b30 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -55,6 +55,7 @@ #include <linux/cpuset.h> #include <linux/percpu.h> #include <linux/kthread.h> +#include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/syscalls.h> @@ -227,9 +228,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) now = hrtimer_cb_get_time(&rt_b->rt_period_timer); hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); - hrtimer_start(&rt_b->rt_period_timer, - rt_b->rt_period_timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&rt_b->rt_period_timer, + HRTIMER_MODE_ABS); } spin_unlock(&rt_b->rt_runtime_lock); } @@ -386,7 +386,6 @@ struct cfs_rq { u64 exec_clock; u64 min_vruntime; - u64 pair_start; struct rb_root tasks_timeline; struct rb_node *rb_leftmost; @@ -398,9 +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 */ @@ -819,6 +818,13 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; unsigned int sysctl_sched_shares_ratelimit = 250000; /* + * Inject some fuzzyness into changing the per-cpu group shares + * this avoids remote rq-locks at the expense of fairness. + * default: 4 + */ +unsigned int sysctl_sched_shares_thresh = 4; + +/* * period over which we measure -rt task cpu usage in us. * default: 1s */ @@ -963,6 +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) { @@ -1064,7 +1078,7 @@ static void hrtick_start(struct rq *rq, u64 delay) struct hrtimer *timer = &rq->hrtick_timer; ktime_t time = ktime_add_ns(timer->base->get_time(), delay); - timer->expires = time; + hrtimer_set_expires(timer, time); if (rq == this_rq()) { hrtimer_restart(timer); @@ -1439,9 +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; } @@ -1454,8 +1471,8 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares); * Calculate and set the cpu's group shares. */ static void -__update_group_shares_cpu(struct task_group *tg, int cpu, - unsigned long sd_shares, unsigned long sd_rq_weight) +update_group_shares_cpu(struct task_group *tg, int cpu, + unsigned long sd_shares, unsigned long sd_rq_weight) { int boost = 0; unsigned long shares; @@ -1486,19 +1503,23 @@ __update_group_shares_cpu(struct task_group *tg, int cpu, * */ shares = (sd_shares * rq_weight) / (sd_rq_weight + 1); + shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); - /* - * record the actual number of shares, not the boosted amount. - */ - tg->cfs_rq[cpu]->shares = boost ? 0 : shares; - tg->cfs_rq[cpu]->rq_weight = rq_weight; + if (abs(shares - tg->se[cpu]->load.weight) > + sysctl_sched_shares_thresh) { + struct rq *rq = cpu_rq(cpu); + unsigned long flags; - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; + spin_lock_irqsave(&rq->lock, flags); + /* + * record the actual number of shares, not the boosted amount. + */ + tg->cfs_rq[cpu]->shares = boost ? 0 : shares; + tg->cfs_rq[cpu]->rq_weight = rq_weight; - __set_se_shares(tg->se[cpu], shares); + __set_se_shares(tg->se[cpu], shares); + spin_unlock_irqrestore(&rq->lock, flags); + } } /* @@ -1527,14 +1548,8 @@ static int tg_shares_up(struct task_group *tg, void *data) if (!rq_weight) rq_weight = cpus_weight(sd->span) * NICE_0_LOAD; - for_each_cpu_mask(i, sd->span) { - struct rq *rq = cpu_rq(i); - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __update_group_shares_cpu(tg, i, shares, rq_weight); - spin_unlock_irqrestore(&rq->lock, flags); - } + for_each_cpu_mask(i, sd->span) + update_group_shares_cpu(tg, i, shares, rq_weight); return 0; } @@ -1801,7 +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) @@ -3339,7 +3356,7 @@ small_imbalance: } else this_load_per_task = cpu_avg_load_per_task(this_cpu); - if (max_load - this_load + 2*busiest_load_per_task >= + if (max_load - this_load + busiest_load_per_task >= busiest_load_per_task * imbn) { *imbalance = busiest_load_per_task; return busiest; @@ -4443,12 +4460,8 @@ need_resched_nonpreemptible: if (sched_feat(HRTICK)) hrtick_clear(rq); - /* - * Do the rq-clock update outside the rq lock: - */ - local_irq_disable(); + spin_lock_irq(&rq->lock); update_rq_clock(rq); - spin_lock(&rq->lock); clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { @@ -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 81787248b60..e8ab096ddfe 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 ad958c1ec70..26ed8e3d1c1 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); @@ -319,7 +320,7 @@ static int __init init_sched_debug_procfs(void) { struct proc_dir_entry *pe; - pe = proc_create("sched_debug", 0644, NULL, &sched_debug_fops); + pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops); if (!pe) return -ENOMEM; return 0; @@ -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 f604dae7131..98345e45b05 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -73,6 +73,8 @@ unsigned int sysctl_sched_wakeup_granularity = 5000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +static const struct sched_class fair_sched_class; + /************************************************************** * CFS operations on generic schedulable entities: */ @@ -141,6 +143,49 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se) return se->parent; } +/* return depth at which a sched entity is present in the hierarchy */ +static inline int depth_se(struct sched_entity *se) +{ + int depth = 0; + + for_each_sched_entity(se) + depth++; + + return depth; +} + +static void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ + int se_depth, pse_depth; + + /* + * preemption test can be made between sibling entities who are in the + * same cfs_rq i.e who have a common parent. Walk up the hierarchy of + * both tasks until we find their ancestors who are siblings of common + * parent. + */ + + /* First walk up until both entities are at same depth */ + se_depth = depth_se(*se); + pse_depth = depth_se(*pse); + + while (se_depth > pse_depth) { + se_depth--; + *se = parent_entity(*se); + } + + while (pse_depth > se_depth) { + pse_depth--; + *pse = parent_entity(*pse); + } + + while (!is_same_group(*se, *pse)) { + *se = parent_entity(*se); + *pse = parent_entity(*pse); + } +} + #else /* CONFIG_FAIR_GROUP_SCHED */ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) @@ -191,6 +236,11 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se) return NULL; } +static inline void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ +} + #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -221,6 +271,27 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) return se->vruntime - cfs_rq->min_vruntime; } +static void update_min_vruntime(struct cfs_rq *cfs_rq) +{ + u64 vruntime = cfs_rq->min_vruntime; + + if (cfs_rq->curr) + vruntime = cfs_rq->curr->vruntime; + + if (cfs_rq->rb_leftmost) { + struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost, + struct sched_entity, + run_node); + + if (vruntime == cfs_rq->min_vruntime) + vruntime = se->vruntime; + else + vruntime = min_vruntime(vruntime, se->vruntime); + } + + cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); +} + /* * Enqueue an entity into the rb-tree: */ @@ -254,15 +325,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * Maintain a cache of leftmost tree entries (it is frequently * used): */ - if (leftmost) { + if (leftmost) cfs_rq->rb_leftmost = &se->run_node; - /* - * maintain cfs_rq->min_vruntime to be a monotonic increasing - * value tracking the leftmost vruntime in the tree. - */ - cfs_rq->min_vruntime = - max_vruntime(cfs_rq->min_vruntime, se->vruntime); - } rb_link_node(&se->run_node, parent, link); rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline); @@ -272,37 +336,25 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { if (cfs_rq->rb_leftmost == &se->run_node) { struct rb_node *next_node; - struct sched_entity *next; next_node = rb_next(&se->run_node); cfs_rq->rb_leftmost = next_node; - - if (next_node) { - next = rb_entry(next_node, - struct sched_entity, run_node); - cfs_rq->min_vruntime = - max_vruntime(cfs_rq->min_vruntime, - next->vruntime); - } } - 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); @@ -334,7 +386,7 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, #endif /* - * delta *= w / rw + * delta *= P[w / rw] */ static inline unsigned long calc_delta_weight(unsigned long delta, struct sched_entity *se) @@ -348,15 +400,13 @@ calc_delta_weight(unsigned long delta, struct sched_entity *se) } /* - * delta *= rw / w + * delta /= w */ static inline unsigned long calc_delta_fair(unsigned long delta, struct sched_entity *se) { - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - cfs_rq_of(se)->load.weight, &se->load); - } + if (unlikely(se->load.weight != NICE_0_LOAD)) + delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load); return delta; } @@ -386,26 +436,26 @@ static u64 __sched_period(unsigned long nr_running) * We calculate the wall-time slice from the period by taking a part * proportional to the weight. * - * s = p*w/rw + * s = p*P[w/rw] */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - return calc_delta_weight(__sched_period(cfs_rq->nr_running), se); + unsigned long nr_running = cfs_rq->nr_running; + + if (unlikely(!se->on_rq)) + nr_running++; + + return calc_delta_weight(__sched_period(nr_running), se); } /* * We calculate the vruntime slice of a to be inserted task * - * vs = s*rw/w = p + * vs = s/w */ -static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se) +static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - unsigned long nr_running = cfs_rq->nr_running; - - if (!se->on_rq) - nr_running++; - - return __sched_period(nr_running); + return calc_delta_fair(sched_slice(cfs_rq, se), se); } /* @@ -424,6 +474,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, schedstat_add(cfs_rq, exec_clock, delta_exec); delta_exec_weighted = calc_delta_fair(delta_exec, curr); curr->vruntime += delta_exec_weighted; + update_min_vruntime(cfs_rq); } static void update_curr(struct cfs_rq *cfs_rq) @@ -613,13 +664,7 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) { - u64 vruntime; - - if (first_fair(cfs_rq)) { - vruntime = min_vruntime(cfs_rq->min_vruntime, - __pick_next_entity(cfs_rq)->vruntime); - } else - vruntime = cfs_rq->min_vruntime; + u64 vruntime = cfs_rq->min_vruntime; /* * The 'current' period is already promised to the current tasks, @@ -628,7 +673,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) * stays open at the end. */ if (initial && sched_feat(START_DEBIT)) - vruntime += sched_vslice_add(cfs_rq, se); + vruntime += sched_vslice(cfs_rq, se); if (!initial) { /* sleeps upto a single latency don't count. */ @@ -671,6 +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) { @@ -693,9 +747,12 @@ 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); + update_min_vruntime(cfs_rq); } /* @@ -742,29 +799,18 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) se->prev_sum_exec_runtime = se->sum_exec_runtime; } -static struct sched_entity * -pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - struct rq *rq = rq_of(cfs_rq); - u64 pair_slice = rq->clock - cfs_rq->pair_start; - - if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) { - cfs_rq->pair_start = rq->clock; - return se; - } - - return cfs_rq->next; -} +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); 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; } @@ -849,11 +895,31 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) hrtick_start(rq, delta); } } + +/* + * called from enqueue/dequeue and updates the hrtick when the + * current task is from our class and nr_running is low enough + * to matter. + */ +static void hrtick_update(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + + if (curr->sched_class != &fair_sched_class) + return; + + if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) + hrtick_start_fair(rq, curr); +} #else /* !CONFIG_SCHED_HRTICK */ static inline void hrtick_start_fair(struct rq *rq, struct task_struct *p) { } + +static inline void hrtick_update(struct rq *rq) +{ +} #endif /* @@ -874,7 +940,7 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup) wakeup = 1; } - hrtick_start_fair(rq, rq->curr); + hrtick_update(rq); } /* @@ -896,7 +962,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) sleep = 1; } - hrtick_start_fair(rq, rq->curr); + hrtick_update(rq); } /* @@ -916,6 +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); /* @@ -1002,8 +1070,6 @@ static inline int wake_idle(int cpu, struct task_struct *p) #ifdef CONFIG_SMP -static const struct sched_class fair_sched_class; - #ifdef CONFIG_FAIR_GROUP_SCHED /* * effective_load() calculates the load change as seen from the root_task_group @@ -1104,10 +1170,9 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) return 0; - if (!sync && sched_feat(SYNC_WAKEUPS) && - curr->se.avg_overlap < sysctl_sched_migration_cost && - p->se.avg_overlap < sysctl_sched_migration_cost) - sync = 1; + if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost || + p->se.avg_overlap > sysctl_sched_migration_cost)) + sync = 0; /* * If sync wakeup then subtract the (maximum possible) @@ -1226,33 +1291,88 @@ static unsigned long wakeup_gran(struct sched_entity *se) * More easily preempt - nice tasks, while not making it harder for * + nice tasks. */ - if (sched_feat(ASYM_GRAN)) - gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load); + if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD) + gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se); return gran; } /* + * Should 'se' preempt 'curr'. + * + * |s1 + * |s2 + * |s3 + * g + * |<--->|c + * + * w(c, s1) = -1 + * w(c, s2) = 0 + * w(c, s3) = 1 + * + */ +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) +{ + s64 gran, vdiff = curr->vruntime - se->vruntime; + + if (vdiff <= 0) + return -1; + + gran = wakeup_gran(curr); + if (vdiff > gran) + return 1; + + 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; - s64 delta_exec; 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 @@ -1278,9 +1398,19 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) return; } - delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime; - if (delta_exec > wakeup_gran(pse)) - resched_task(curr); + find_matching_se(&se, &pse); + + while (se) { + BUG_ON(!pse); + + if (wakeup_preempt_entity(se, pse) == 1) { + resched_task(curr); + break; + } + + se = parent_entity(se); + pse = parent_entity(pse); + } } static struct task_struct *pick_next_task_fair(struct rq *rq) @@ -1294,6 +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); @@ -1576,9 +1707,6 @@ static const struct sched_class fair_sched_class = { .enqueue_task = enqueue_task_fair, .dequeue_task = dequeue_task_fair, .yield_task = yield_task_fair, -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_fair, -#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_wakeup, @@ -1586,6 +1714,8 @@ static const struct sched_class fair_sched_class = { .put_prev_task = put_prev_task_fair, #ifdef CONFIG_SMP + .select_task_rq = select_task_rq_fair, + .load_balance = load_balance_fair, .move_one_task = move_one_task_fair, #endif diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 7c9e8f4a049..da5d93b5d2c 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -5,10 +5,11 @@ SCHED_FEAT(START_DEBIT, 1) SCHED_FEAT(AFFINE_WAKEUPS, 1) SCHED_FEAT(CACHE_HOT_BUDDY, 1) SCHED_FEAT(SYNC_WAKEUPS, 1) -SCHED_FEAT(HRTICK, 1) +SCHED_FEAT(HRTICK, 0) SCHED_FEAT(DOUBLE_TICK, 0) SCHED_FEAT(ASYM_GRAN, 1) 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_idletask.c b/kernel/sched_idletask.c index dec4ccabe2f..8a21a2e28c1 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -105,9 +105,6 @@ static const struct sched_class idle_sched_class = { /* dequeue is not valid, we print a debug message there: */ .dequeue_task = dequeue_task_idle, -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_idle, -#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_curr_idle, @@ -115,6 +112,8 @@ static const struct sched_class idle_sched_class = { .put_prev_task = put_prev_task_idle, #ifdef CONFIG_SMP + .select_task_rq = select_task_rq_idle, + .load_balance = load_balance_idle, .move_one_task = move_one_task_idle, #endif diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index b446dc87494..d9ba9d5f99d 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1504,9 +1504,6 @@ static const struct sched_class rt_sched_class = { .enqueue_task = enqueue_task_rt, .dequeue_task = dequeue_task_rt, .yield_task = yield_task_rt, -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_rt, -#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_curr_rt, @@ -1514,6 +1511,8 @@ static const struct sched_class rt_sched_class = { .put_prev_task = put_prev_task_rt, #ifdef CONFIG_SMP + .select_task_rq = select_task_rq_rt, + .load_balance = load_balance_rt, .move_one_task = move_one_task_rt, .set_cpus_allowed = set_cpus_allowed_rt, diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index b8c156979cf..7dbf72a2b02 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -9,7 +9,7 @@ static int show_schedstat(struct seq_file *seq, void *v) { int cpu; - int mask_len = NR_CPUS/32 * 9; + int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9; char *mask_str = kmalloc(mask_len, GFP_KERNEL); if (mask_str == NULL) @@ -90,13 +90,20 @@ static int schedstat_open(struct inode *inode, struct file *file) return res; } -const struct file_operations proc_schedstat_operations = { +static const struct file_operations proc_schedstat_operations = { .open = schedstat_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; +static int __init proc_schedstat_init(void) +{ + proc_create("schedstat", 0, NULL, &proc_schedstat_operations); + return 0; +} +module_init(proc_schedstat_init); + /* * Expects runqueue lock to be held for atomicity of update */ @@ -291,9 +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; @@ -318,9 +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; @@ -346,8 +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/signal.c b/kernel/signal.c index 105217da5c8..4530fc65445 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1144,7 +1144,8 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) struct task_struct * p; for_each_process(p) { - if (p->pid > 1 && !same_thread_group(p, current)) { + if (task_pid_vnr(p) > 1 && + !same_thread_group(p, current)) { int err = group_send_sig_info(sig, info, p); ++count; if (err != -EPERM) diff --git a/kernel/smp.c b/kernel/smp.c index f362a855377..75c8dde58c5 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 7110daeb9a9..e7c69a720d6 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 3953e4aed73..dc0b3be6b7d 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 af3c7cea258..24e8ceacc38 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -37,9 +37,13 @@ struct stop_machine_data { /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ static unsigned int num_threads; static atomic_t thread_ack; -static struct completion finished; static DEFINE_MUTEX(lock); +static struct workqueue_struct *stop_machine_wq; +static struct stop_machine_data active, idle; +static const cpumask_t *active_cpus; +static void *stop_machine_work; + static void set_state(enum stopmachine_state newstate) { /* Reset ack counter. */ @@ -51,21 +55,26 @@ static void set_state(enum stopmachine_state newstate) /* Last one to ack a state moves to the next state. */ static void ack_state(void) { - if (atomic_dec_and_test(&thread_ack)) { - /* If we're the last one to ack the EXIT, we're finished. */ - if (state == STOPMACHINE_EXIT) - complete(&finished); - else - set_state(state + 1); - } + if (atomic_dec_and_test(&thread_ack)) + set_state(state + 1); } -/* This is the actual thread which stops the CPU. It exits by itself rather - * than waiting for kthread_stop(), because it's easier for hotplug CPU. */ -static int stop_cpu(struct stop_machine_data *smdata) +/* This is the actual function which stops the CPU. It runs + * in the context of a dedicated stopmachine workqueue. */ +static void stop_cpu(struct work_struct *unused) { enum stopmachine_state curstate = STOPMACHINE_NONE; - + struct stop_machine_data *smdata = &idle; + int cpu = smp_processor_id(); + int err; + + if (!active_cpus) { + if (cpu == first_cpu(cpu_online_map)) + smdata = &active; + } else { + if (cpu_isset(cpu, *active_cpus)) + smdata = &active; + } /* Simple state machine */ do { /* Chill out and ensure we re-read stopmachine_state. */ @@ -78,9 +87,11 @@ static int stop_cpu(struct stop_machine_data *smdata) hard_irq_disable(); break; case STOPMACHINE_RUN: - /* |= allows error detection if functions on - * multiple CPUs. */ - smdata->fnret |= smdata->fn(smdata->data); + /* On multiple CPUs only a single error code + * is needed to tell that something failed. */ + err = smdata->fn(smdata->data); + if (err) + smdata->fnret = err; break; default: break; @@ -90,7 +101,6 @@ static int stop_cpu(struct stop_machine_data *smdata) } while (curstate != STOPMACHINE_EXIT); local_irq_enable(); - do_exit(0); } /* Callback for CPUs which aren't supposed to do anything. */ @@ -101,78 +111,35 @@ static int chill(void *unused) int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) { - int i, err; - struct stop_machine_data active, idle; - struct task_struct **threads; + struct work_struct *sm_work; + int i, ret; + /* Set up initial state. */ + mutex_lock(&lock); + num_threads = num_online_cpus(); + active_cpus = cpus; active.fn = fn; active.data = data; active.fnret = 0; idle.fn = chill; idle.data = NULL; - /* This could be too big for stack on large machines. */ - threads = kcalloc(NR_CPUS, sizeof(threads[0]), GFP_KERNEL); - if (!threads) - return -ENOMEM; - - /* Set up initial state. */ - mutex_lock(&lock); - init_completion(&finished); - num_threads = num_online_cpus(); set_state(STOPMACHINE_PREPARE); - for_each_online_cpu(i) { - struct stop_machine_data *smdata = &idle; - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - - if (!cpus) { - if (i == first_cpu(cpu_online_map)) - smdata = &active; - } else { - if (cpu_isset(i, *cpus)) - smdata = &active; - } - - threads[i] = kthread_create((void *)stop_cpu, smdata, "kstop%u", - i); - if (IS_ERR(threads[i])) { - err = PTR_ERR(threads[i]); - threads[i] = NULL; - goto kill_threads; - } - - /* Place it onto correct cpu. */ - kthread_bind(threads[i], i); - - /* Make it highest prio. */ - if (sched_setscheduler_nocheck(threads[i], SCHED_FIFO, ¶m)) - BUG(); - } - - /* We've created all the threads. Wake them all: hold this CPU so one + /* Schedule the stop_cpu work on all cpus: hold this CPU so one * doesn't hit this CPU until we're ready. */ get_cpu(); - for_each_online_cpu(i) - wake_up_process(threads[i]); - + for_each_online_cpu(i) { + sm_work = percpu_ptr(stop_machine_work, i); + INIT_WORK(sm_work, stop_cpu); + queue_work_on(i, stop_machine_wq, sm_work); + } /* This will release the thread on our CPU. */ put_cpu(); - wait_for_completion(&finished); - mutex_unlock(&lock); - - kfree(threads); - - return active.fnret; - -kill_threads: - for_each_online_cpu(i) - if (threads[i]) - kthread_stop(threads[i]); + flush_workqueue(stop_machine_wq); + ret = active.fnret; mutex_unlock(&lock); - - kfree(threads); - return err; + return ret; } int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) @@ -187,3 +154,11 @@ int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) return ret; } EXPORT_SYMBOL_GPL(stop_machine); + +static int __init stop_machine_init(void) +{ + stop_machine_wq = create_rt_workqueue("kstop"); + stop_machine_work = alloc_percpu(struct work_struct); + return 0; +} +core_initcall(stop_machine_init); diff --git a/kernel/sys.c b/kernel/sys.c index 53879cdae48..31deba8f7d1 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1716,6 +1716,16 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; + case PR_GET_TIMERSLACK: + error = current->timer_slack_ns; + break; + case PR_SET_TIMERSLACK: + if (arg2 <= 0) + current->timer_slack_ns = + current->default_timer_slack_ns; + else + current->timer_slack_ns = arg2; + break; default: error = -EINVAL; break; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a77b27b11b0..e14a2328170 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 b3cc73931d1..3d56fe7570d 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; @@ -276,6 +279,16 @@ static struct ctl_table kern_table[] = { }, { .ctl_name = CTL_UNNUMBERED, + .procname = "sched_shares_thresh", + .data = &sysctl_sched_shares_thresh, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, + { + .ctl_name = CTL_UNNUMBERED, .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, .maxlen = sizeof(unsigned int), @@ -464,7 +477,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER { .ctl_name = CTL_UNNUMBERED, .procname = "ftrace_enabled", @@ -1315,6 +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.c b/kernel/time.c index 6a08660b4fa..d63a4336fad 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -669,3 +669,21 @@ EXPORT_SYMBOL(get_jiffies_64); #endif EXPORT_SYMBOL(jiffies); + +/* + * Add two timespec values and do a safety check for overflow. + * It's assumed that both values are valid (>= 0) + */ +struct timespec timespec_add_safe(const struct timespec lhs, + const struct timespec rhs) +{ + struct timespec res; + + set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + + if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec) + res.tv_sec = TIME_T_MAX; + + return res; +} diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 1a20715bfd6..8ff15e5d486 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -142,8 +142,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) time_state = TIME_OOP; printk(KERN_NOTICE "Clock: " "inserting leap second 23:59:60 UTC\n"); - leap_timer.expires = ktime_add_ns(leap_timer.expires, - NSEC_PER_SEC); + hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); res = HRTIMER_RESTART; break; case TIME_DEL: diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0581c11fe6c..342fc9ccab4 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -300,7 +300,7 @@ void tick_nohz_stop_sched_tick(int inidle) goto out; } - ts->idle_tick = ts->sched_timer.expires; + ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; rcu_enter_nohz(); @@ -380,21 +380,21 @@ ktime_t tick_nohz_get_sleep_length(void) static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); - ts->sched_timer.expires = ts->idle_tick; + hrtimer_set_expires(&ts->sched_timer, ts->idle_tick); while (1) { /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, tick_period); if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, - ts->sched_timer.expires, + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS); /* Check, if the timer was already in the past */ if (hrtimer_active(&ts->sched_timer)) break; } else { - if (!tick_program_event(ts->sched_timer.expires, 0)) + if (!tick_program_event( + hrtimer_get_expires(&ts->sched_timer), 0)) break; } /* Update jiffies and reread time */ @@ -456,14 +456,16 @@ void tick_nohz_restart_sched_tick(void) */ ts->tick_stopped = 0; ts->idle_exittime = now; + tick_nohz_restart(ts, now); + local_irq_enable(); } static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) { hrtimer_forward(&ts->sched_timer, now, tick_period); - return tick_program_event(ts->sched_timer.expires, 0); + return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0); } /* @@ -542,7 +544,7 @@ static void tick_nohz_switch_to_nohz(void) next = tick_init_jiffy_update(); for (;;) { - ts->sched_timer.expires = next; + hrtimer_set_expires(&ts->sched_timer, next); if (!tick_program_event(next, 0)) break; next = ktime_add(next, tick_period); @@ -566,12 +568,26 @@ 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; if (!ts->tick_stopped) return; - tick_nohz_restart(ts, ktime_get()); + /* + * Do not touch the tick device, when the next expiry is either + * already reached or less/equal than the tick period. + */ + now = ktime_get(); + delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now); + if (delta.tv64 <= tick_period.tv64) + return; + + tick_nohz_restart(ts, now); +#endif } #else @@ -668,16 +684,15 @@ void tick_setup_sched_timer(void) ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; /* Get the next period (per cpu) */ - ts->sched_timer.expires = tick_init_jiffy_update(); + hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); offset = ktime_to_ns(tick_period) >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); - ts->sched_timer.expires = ktime_add_ns(ts->sched_timer.expires, offset); + hrtimer_add_expires_ns(&ts->sched_timer, offset); for (;;) { hrtimer_forward(&ts->sched_timer, now, tick_period); - hrtimer_start(&ts->sched_timer, ts->sched_timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS); /* Check, if the timer was already in the past */ if (hrtimer_active(&ts->sched_timer)) break; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e7acfb482a6..fa05e88aa76 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/time/timer_list.c b/kernel/time/timer_list.c index f6426911e35..a999b92a127 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -66,9 +66,11 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, SEQ_printf(m, ", %s/%d", tmp, timer->start_pid); #endif SEQ_printf(m, "\n"); - SEQ_printf(m, " # expires at %Lu nsecs [in %Ld nsecs]\n", - (unsigned long long)ktime_to_ns(timer->expires), - (long long)(ktime_to_ns(timer->expires) - now)); + SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", + (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)), + (unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)), + (long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now), + (long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now)); } static void diff --git a/kernel/timer.c b/kernel/timer.c index 56becf373c5..dbd50fabe4c 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 1cb3e1f616a..33dbefd471e 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -1,13 +1,13 @@ # -# Architectures that offer an FTRACE implementation should select HAVE_FTRACE: +# Architectures that offer an FUNCTION_TRACER implementation should +# select HAVE_FUNCTION_TRACER: # config NOP_TRACER bool -config HAVE_FTRACE +config HAVE_FUNCTION_TRACER bool - select NOP_TRACER config HAVE_DYNAMIC_FTRACE bool @@ -25,12 +25,15 @@ config TRACING bool select DEBUG_FS select RING_BUFFER - select STACKTRACE + select STACKTRACE if STACKTRACE_SUPPORT select TRACEPOINTS + select NOP_TRACER -config FTRACE +menu "Tracers" + +config FUNCTION_TRACER bool "Kernel Function Tracer" - depends on HAVE_FTRACE + depends on HAVE_FUNCTION_TRACER depends on DEBUG_KERNEL select FRAME_POINTER select TRACING @@ -49,7 +52,6 @@ config IRQSOFF_TRACER default n depends on TRACE_IRQFLAGS_SUPPORT depends on GENERIC_TIME - depends on HAVE_FTRACE depends on DEBUG_KERNEL select TRACE_IRQFLAGS select TRACING @@ -73,7 +75,6 @@ config PREEMPT_TRACER default n depends on GENERIC_TIME depends on PREEMPT - depends on HAVE_FTRACE depends on DEBUG_KERNEL select TRACING select TRACER_MAX_TRACE @@ -101,7 +102,6 @@ config SYSPROF_TRACER config SCHED_TRACER bool "Scheduling Latency Tracer" - depends on HAVE_FTRACE depends on DEBUG_KERNEL select TRACING select CONTEXT_SWITCH_TRACER @@ -112,7 +112,6 @@ config SCHED_TRACER config CONTEXT_SWITCH_TRACER bool "Trace process context switches" - depends on HAVE_FTRACE depends on DEBUG_KERNEL select TRACING select MARKERS @@ -122,9 +121,9 @@ config CONTEXT_SWITCH_TRACER config BOOT_TRACER bool "Trace boot initcalls" - depends on HAVE_FTRACE depends on DEBUG_KERNEL select TRACING + select CONTEXT_SWITCH_TRACER help This tracer helps developers to optimize boot times: it records the timings of the initcalls and traces key events and the identity @@ -141,9 +140,9 @@ config BOOT_TRACER config STACK_TRACER bool "Trace max stack" - depends on HAVE_FTRACE + depends on HAVE_FUNCTION_TRACER depends on DEBUG_KERNEL - select FTRACE + select FUNCTION_TRACER select STACKTRACE help This special tracer records the maximum stack footprint of the @@ -160,7 +159,7 @@ config STACK_TRACER config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" - depends on FTRACE + depends on FUNCTION_TRACER depends on HAVE_DYNAMIC_FTRACE depends on DEBUG_KERNEL default y @@ -170,7 +169,7 @@ config DYNAMIC_FTRACE with a No-Op instruction) as they are called. A table is created to dynamically enable them again. - This way a CONFIG_FTRACE kernel is slightly larger, but otherwise + This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise has native performance as long as no tracing is active. The changes to the code are done by a kernel thread that @@ -195,3 +194,5 @@ config FTRACE_STARTUP_TEST a series of tests are made to verify that the tracer is functioning properly. It will do tests on all the configured tracers of ftrace. + +endmenu diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index a85dfba88ba..c8228b1a49e 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -1,7 +1,7 @@ # Do not instrument the tracer itself: -ifdef CONFIG_FTRACE +ifdef CONFIG_FUNCTION_TRACER ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) @@ -10,13 +10,13 @@ CFLAGS_trace_selftest_dynamic.o = -pg obj-y += trace_selftest_dynamic.o endif -obj-$(CONFIG_FTRACE) += libftrace.o +obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o obj-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o -obj-$(CONFIG_FTRACE) += trace_functions.o +obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4dda4f60a2a..78db083390f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -25,13 +25,24 @@ #include <linux/ftrace.h> #include <linux/sysctl.h> #include <linux/ctype.h> -#include <linux/hash.h> #include <linux/list.h> #include <asm/ftrace.h> #include "trace.h" +#define FTRACE_WARN_ON(cond) \ + do { \ + if (WARN_ON(cond)) \ + ftrace_kill(); \ + } while (0) + +#define FTRACE_WARN_ON_ONCE(cond) \ + do { \ + if (WARN_ON_ONCE(cond)) \ + ftrace_kill(); \ + } while (0) + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; @@ -153,21 +164,8 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) } #ifdef CONFIG_DYNAMIC_FTRACE - #ifndef CONFIG_FTRACE_MCOUNT_RECORD -/* - * The hash lock is only needed when the recording of the mcount - * callers are dynamic. That is, by the caller themselves and - * not recorded via the compilation. - */ -static DEFINE_SPINLOCK(ftrace_hash_lock); -#define ftrace_hash_lock(flags) spin_lock_irqsave(&ftrace_hash_lock, flags) -#define ftrace_hash_unlock(flags) \ - spin_unlock_irqrestore(&ftrace_hash_lock, flags) -#else -/* This is protected via the ftrace_lock with MCOUNT_RECORD. */ -#define ftrace_hash_lock(flags) do { (void)(flags); } while (0) -#define ftrace_hash_unlock(flags) do { } while(0) +# error Dynamic ftrace depends on MCOUNT_RECORD #endif /* @@ -178,8 +176,6 @@ static DEFINE_SPINLOCK(ftrace_hash_lock); */ static unsigned long mcount_addr = MCOUNT_ADDR; -static struct task_struct *ftraced_task; - enum { FTRACE_ENABLE_CALLS = (1 << 0), FTRACE_DISABLE_CALLS = (1 << 1), @@ -189,14 +185,9 @@ enum { }; static int ftrace_filtered; -static int tracing_on; -static int frozen_record_count; - -static struct hlist_head ftrace_hash[FTRACE_HASHSIZE]; -static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu); +static LIST_HEAD(ftrace_new_addrs); -static DEFINE_MUTEX(ftraced_lock); static DEFINE_MUTEX(ftrace_regex_lock); struct ftrace_page { @@ -214,16 +205,13 @@ struct ftrace_page { static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; -static int ftraced_trigger; -static int ftraced_suspend; -static int ftraced_stop; - -static int ftrace_record_suspend; - static struct dyn_ftrace *ftrace_free_records; #ifdef CONFIG_KPROBES + +static int frozen_record_count; + static inline void freeze_record(struct dyn_ftrace *rec) { if (!(rec->flags & FTRACE_FL_FROZEN)) { @@ -250,72 +238,6 @@ static inline int record_frozen(struct dyn_ftrace *rec) # define record_frozen(rec) ({ 0; }) #endif /* CONFIG_KPROBES */ -int skip_trace(unsigned long ip) -{ - unsigned long fl; - struct dyn_ftrace *rec; - struct hlist_node *t; - struct hlist_head *head; - - if (frozen_record_count == 0) - return 0; - - head = &ftrace_hash[hash_long(ip, FTRACE_HASHBITS)]; - hlist_for_each_entry_rcu(rec, t, head, node) { - if (rec->ip == ip) { - if (record_frozen(rec)) { - if (rec->flags & FTRACE_FL_FAILED) - return 1; - - if (!(rec->flags & FTRACE_FL_CONVERTED)) - return 1; - - if (!tracing_on || !ftrace_enabled) - return 1; - - if (ftrace_filtered) { - fl = rec->flags & (FTRACE_FL_FILTER | - FTRACE_FL_NOTRACE); - if (!fl || (fl & FTRACE_FL_NOTRACE)) - return 1; - } - } - break; - } - } - - return 0; -} - -static inline int -ftrace_ip_in_hash(unsigned long ip, unsigned long key) -{ - struct dyn_ftrace *p; - struct hlist_node *t; - int found = 0; - - hlist_for_each_entry_rcu(p, t, &ftrace_hash[key], node) { - if (p->ip == ip) { - found = 1; - break; - } - } - - return found; -} - -static inline void -ftrace_add_hash(struct dyn_ftrace *node, unsigned long key) -{ - hlist_add_head_rcu(&node->node, &ftrace_hash[key]); -} - -/* called from kstop_machine */ -static inline void ftrace_del_hash(struct dyn_ftrace *node) -{ - hlist_del(&node->node); -} - static void ftrace_free_rec(struct dyn_ftrace *rec) { rec->ip = (unsigned long)ftrace_free_records; @@ -346,7 +268,6 @@ void ftrace_release(void *start, unsigned long size) } } spin_unlock(&ftrace_lock); - } static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) @@ -358,10 +279,8 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) rec = ftrace_free_records; if (unlikely(!(rec->flags & FTRACE_FL_FREE))) { - WARN_ON_ONCE(1); + FTRACE_WARN_ON_ONCE(1); ftrace_free_records = NULL; - ftrace_disabled = 1; - ftrace_enabled = 0; return NULL; } @@ -371,172 +290,125 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) } if (ftrace_pages->index == ENTRIES_PER_PAGE) { - if (!ftrace_pages->next) - return NULL; + if (!ftrace_pages->next) { + /* allocate another page */ + ftrace_pages->next = + (void *)get_zeroed_page(GFP_KERNEL); + if (!ftrace_pages->next) + return NULL; + } ftrace_pages = ftrace_pages->next; } return &ftrace_pages->records[ftrace_pages->index++]; } -static void +static struct dyn_ftrace * ftrace_record_ip(unsigned long ip) { - struct dyn_ftrace *node; - unsigned long flags; - unsigned long key; - int resched; - int cpu; + struct dyn_ftrace *rec; if (!ftrace_enabled || ftrace_disabled) - return; - - resched = need_resched(); - preempt_disable_notrace(); - - /* - * We simply need to protect against recursion. - * Use the the raw version of smp_processor_id and not - * __get_cpu_var which can call debug hooks that can - * cause a recursive crash here. - */ - cpu = raw_smp_processor_id(); - per_cpu(ftrace_shutdown_disable_cpu, cpu)++; - if (per_cpu(ftrace_shutdown_disable_cpu, cpu) != 1) - goto out; - - if (unlikely(ftrace_record_suspend)) - goto out; - - key = hash_long(ip, FTRACE_HASHBITS); - - WARN_ON_ONCE(key >= FTRACE_HASHSIZE); - - if (ftrace_ip_in_hash(ip, key)) - goto out; - - ftrace_hash_lock(flags); - - /* This ip may have hit the hash before the lock */ - if (ftrace_ip_in_hash(ip, key)) - goto out_unlock; - - node = ftrace_alloc_dyn_node(ip); - if (!node) - goto out_unlock; + return NULL; - node->ip = ip; - - ftrace_add_hash(node, key); + rec = ftrace_alloc_dyn_node(ip); + if (!rec) + return NULL; - ftraced_trigger = 1; + rec->ip = ip; - out_unlock: - ftrace_hash_unlock(flags); - out: - per_cpu(ftrace_shutdown_disable_cpu, cpu)--; + list_add(&rec->list, &ftrace_new_addrs); - /* prevent recursion with scheduler */ - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + return rec; } #define FTRACE_ADDR ((long)(ftrace_caller)) 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++) { @@ -554,12 +426,11 @@ 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) || !core_kernel_text(rec->ip)) { - ftrace_del_hash(rec); ftrace_free_rec(rec); } } @@ -567,15 +438,6 @@ static void ftrace_replace_code(int enable) } } -static void ftrace_shutdown_replenish(void) -{ - if (ftrace_pages->next) - return; - - /* allocate another page */ - ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL); -} - static void print_ip_ins(const char *fmt, unsigned char *p) { int i; @@ -591,23 +453,23 @@ ftrace_code_disable(struct dyn_ftrace *rec) { unsigned long ip; unsigned char *nop, *call; - int failed; + int ret; ip = rec->ip; nop = ftrace_nop_replace(); call = ftrace_call_replace(ip, mcount_addr); - failed = ftrace_modify_code(ip, call, nop); - if (failed) { - switch (failed) { - case 1: - WARN_ON_ONCE(1); + ret = ftrace_modify_code(ip, call, nop); + if (ret) { + switch (ret) { + case -EFAULT: + FTRACE_WARN_ON_ONCE(1); pr_info("ftrace faulted on modifying "); print_ip_sym(ip); break; - case 2: - WARN_ON_ONCE(1); + case -EINVAL: + FTRACE_WARN_ON_ONCE(1); pr_info("ftrace failed to modify "); print_ip_sym(ip); print_ip_ins(" expected: ", call); @@ -615,6 +477,15 @@ ftrace_code_disable(struct dyn_ftrace *rec) print_ip_ins(" replace: ", nop); printk(KERN_CONT "\n"); break; + case -EPERM: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on writing "); + print_ip_sym(ip); + break; + default: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on unknown error "); + print_ip_sym(ip); } rec->flags |= FTRACE_FL_FAILED; @@ -623,37 +494,18 @@ ftrace_code_disable(struct dyn_ftrace *rec) return 1; } -static int __ftrace_update_code(void *ignore); - static int __ftrace_modify_code(void *data) { - unsigned long addr; int *command = data; - if (*command & FTRACE_ENABLE_CALLS) { - /* - * Update any recorded ips now that we have the - * machine stopped - */ - __ftrace_update_code(NULL); + 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); - if (*command & FTRACE_ENABLE_MCOUNT) { - addr = (unsigned long)ftrace_record_ip; - ftrace_mcount_set(&addr); - } else if (*command & FTRACE_DISABLE_MCOUNT) { - addr = (unsigned long)ftrace_stub; - ftrace_mcount_set(&addr); - } - return 0; } @@ -662,26 +514,9 @@ static void ftrace_run_update_code(int command) stop_machine(__ftrace_modify_code, &command, NULL); } -void ftrace_disable_daemon(void) -{ - /* Stop the daemon from calling kstop_machine */ - mutex_lock(&ftraced_lock); - ftraced_stop = 1; - mutex_unlock(&ftraced_lock); - - ftrace_force_update(); -} - -void ftrace_enable_daemon(void) -{ - mutex_lock(&ftraced_lock); - ftraced_stop = 0; - mutex_unlock(&ftraced_lock); - - ftrace_force_update(); -} - static ftrace_func_t saved_ftrace_func; +static int ftrace_start; +static DEFINE_MUTEX(ftrace_start_lock); static void ftrace_startup(void) { @@ -690,10 +525,9 @@ static void ftrace_startup(void) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftraced_lock); - ftraced_suspend++; - if (ftraced_suspend == 1) - command |= FTRACE_ENABLE_CALLS; + mutex_lock(&ftrace_start_lock); + ftrace_start++; + command |= FTRACE_ENABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -705,7 +539,7 @@ static void ftrace_startup(void) ftrace_run_update_code(command); out: - mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_start_lock); } static void ftrace_shutdown(void) @@ -715,9 +549,9 @@ static void ftrace_shutdown(void) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftraced_lock); - ftraced_suspend--; - if (!ftraced_suspend) + mutex_lock(&ftrace_start_lock); + ftrace_start--; + if (!ftrace_start) command |= FTRACE_DISABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { @@ -730,7 +564,7 @@ static void ftrace_shutdown(void) ftrace_run_update_code(command); out: - mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_start_lock); } static void ftrace_startup_sysctl(void) @@ -740,15 +574,15 @@ static void ftrace_startup_sysctl(void) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftraced_lock); + mutex_lock(&ftrace_start_lock); /* Force update next time */ saved_ftrace_func = NULL; - /* ftraced_suspend is true if we want ftrace running */ - if (ftraced_suspend) + /* ftrace_start is true if we want ftrace running */ + if (ftrace_start) command |= FTRACE_ENABLE_CALLS; ftrace_run_update_code(command); - mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_start_lock); } static void ftrace_shutdown_sysctl(void) @@ -758,112 +592,50 @@ static void ftrace_shutdown_sysctl(void) if (unlikely(ftrace_disabled)) return; - mutex_lock(&ftraced_lock); - /* ftraced_suspend is true if ftrace is running */ - if (ftraced_suspend) + mutex_lock(&ftrace_start_lock); + /* ftrace_start is true if ftrace is running */ + if (ftrace_start) command |= FTRACE_DISABLE_CALLS; ftrace_run_update_code(command); - mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_start_lock); } static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; -static int __ftrace_update_code(void *ignore) +static int ftrace_update_code(void) { - int i, save_ftrace_enabled; + struct dyn_ftrace *p, *t; cycle_t start, stop; - struct dyn_ftrace *p; - struct hlist_node *t, *n; - struct hlist_head *head, temp_list; - - /* Don't be recording funcs now */ - ftrace_record_suspend++; - save_ftrace_enabled = ftrace_enabled; - ftrace_enabled = 0; start = ftrace_now(raw_smp_processor_id()); ftrace_update_cnt = 0; - /* No locks needed, the machine is stopped! */ - for (i = 0; i < FTRACE_HASHSIZE; i++) { - INIT_HLIST_HEAD(&temp_list); - head = &ftrace_hash[i]; - - /* all CPUS are stopped, we are safe to modify code */ - hlist_for_each_entry_safe(p, t, n, head, node) { - /* Skip over failed records which have not been - * freed. */ - if (p->flags & FTRACE_FL_FAILED) - continue; + list_for_each_entry_safe(p, t, &ftrace_new_addrs, list) { - /* Unconverted records are always at the head of the - * hash bucket. Once we encounter a converted record, - * simply skip over to the next bucket. Saves ftraced - * some processor cycles (ftrace does its bid for - * global warming :-p ). */ - if (p->flags & (FTRACE_FL_CONVERTED)) - break; + /* If something went wrong, bail without enabling anything */ + if (unlikely(ftrace_disabled)) + return -1; - /* Ignore updates to this record's mcount site. - * Reintroduce this record at the head of this - * bucket to attempt to "convert" it again if - * the kprobe on it is unregistered before the - * next run. */ - if (get_kprobe((void *)p->ip)) { - ftrace_del_hash(p); - INIT_HLIST_NODE(&p->node); - hlist_add_head(&p->node, &temp_list); - freeze_record(p); - continue; - } else { - unfreeze_record(p); - } + list_del_init(&p->list); - /* convert record (i.e, patch mcount-call with NOP) */ - if (ftrace_code_disable(p)) { - p->flags |= FTRACE_FL_CONVERTED; - ftrace_update_cnt++; - } else { - if ((system_state == SYSTEM_BOOTING) || - !core_kernel_text(p->ip)) { - ftrace_del_hash(p); - ftrace_free_rec(p); - } - } - } - - hlist_for_each_entry_safe(p, t, n, &temp_list, node) { - hlist_del(&p->node); - INIT_HLIST_NODE(&p->node); - hlist_add_head(&p->node, head); - } + /* convert record (i.e, patch mcount-call with NOP) */ + if (ftrace_code_disable(p)) { + p->flags |= FTRACE_FL_CONVERTED; + ftrace_update_cnt++; + } else + ftrace_free_rec(p); } stop = ftrace_now(raw_smp_processor_id()); ftrace_update_time = stop - start; ftrace_update_tot_cnt += ftrace_update_cnt; - ftraced_trigger = 0; - - ftrace_enabled = save_ftrace_enabled; - ftrace_record_suspend--; return 0; } -static int ftrace_update_code(void) -{ - if (unlikely(ftrace_disabled) || - !ftrace_enabled || !ftraced_trigger) - return 0; - - stop_machine(__ftrace_update_code, NULL, NULL); - - return 1; -} - static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) { struct ftrace_page *pg; @@ -892,8 +664,8 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) pg = ftrace_pages = ftrace_pages_start; cnt = num_to_init / ENTRIES_PER_PAGE; - pr_info("ftrace: allocating %ld hash entries in %d pages\n", - num_to_init, cnt); + pr_info("ftrace: allocating %ld entries in %d pages\n", + num_to_init, cnt + 1); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -954,6 +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; @@ -973,13 +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; } @@ -990,15 +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; } @@ -1024,7 +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) { @@ -1111,7 +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; @@ -1401,10 +1180,10 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) } mutex_lock(&ftrace_sysctl_lock); - mutex_lock(&ftraced_lock); - if (iter->filtered && ftraced_suspend && ftrace_enabled) + mutex_lock(&ftrace_start_lock); + if (ftrace_start && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); - mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_start_lock); mutex_unlock(&ftrace_sysctl_lock); kfree(iter); @@ -1424,55 +1203,6 @@ ftrace_notrace_release(struct inode *inode, struct file *file) return ftrace_regex_release(inode, file, 0); } -static ssize_t -ftraced_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - /* don't worry about races */ - char *buf = ftraced_stop ? "disabled\n" : "enabled\n"; - int r = strlen(buf); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static ssize_t -ftraced_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - long val; - int ret; - - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - if (strncmp(buf, "enable", 6) == 0) - val = 1; - else if (strncmp(buf, "disable", 7) == 0) - val = 0; - else { - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) - return ret; - - val = !!val; - } - - if (val) - ftrace_enable_daemon(); - else - ftrace_disable_daemon(); - - filp->f_pos += cnt; - - return cnt; -} - static struct file_operations ftrace_avail_fops = { .open = ftrace_avail_open, .read = seq_read, @@ -1503,54 +1233,6 @@ static struct file_operations ftrace_notrace_fops = { .release = ftrace_notrace_release, }; -static struct file_operations ftraced_fops = { - .open = tracing_open_generic, - .read = ftraced_read, - .write = ftraced_write, -}; - -/** - * ftrace_force_update - force an update to all recording ftrace functions - */ -int ftrace_force_update(void) -{ - int ret = 0; - - if (unlikely(ftrace_disabled)) - return -ENODEV; - - mutex_lock(&ftrace_sysctl_lock); - mutex_lock(&ftraced_lock); - - /* - * If ftraced_trigger is not set, then there is nothing - * to update. - */ - if (ftraced_trigger && !ftrace_update_code()) - ret = -EBUSY; - - mutex_unlock(&ftraced_lock); - mutex_unlock(&ftrace_sysctl_lock); - - return ret; -} - -static void ftrace_force_shutdown(void) -{ - struct task_struct *task; - int command = FTRACE_DISABLE_CALLS | FTRACE_UPDATE_TRACE_FUNC; - - mutex_lock(&ftraced_lock); - task = ftraced_task; - ftraced_task = NULL; - ftraced_suspend = -1; - ftrace_run_update_code(command); - mutex_unlock(&ftraced_lock); - - if (task) - kthread_stop(task); -} - static __init int ftrace_init_debugfs(void) { struct dentry *d_tracer; @@ -1581,17 +1263,11 @@ static __init int ftrace_init_debugfs(void) pr_warning("Could not create debugfs " "'set_ftrace_notrace' entry\n"); - entry = debugfs_create_file("ftraced_enabled", 0644, d_tracer, - NULL, &ftraced_fops); - if (!entry) - pr_warning("Could not create debugfs " - "'ftraced_enabled' entry\n"); return 0; } fs_initcall(ftrace_init_debugfs); -#ifdef CONFIG_FTRACE_MCOUNT_RECORD static int ftrace_convert_nops(unsigned long *start, unsigned long *end) { @@ -1599,20 +1275,18 @@ static int ftrace_convert_nops(unsigned long *start, unsigned long addr; unsigned long flags; + mutex_lock(&ftrace_start_lock); p = start; while (p < end) { addr = ftrace_call_adjust(*p++); - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); ftrace_record_ip(addr); - spin_unlock(&ftrace_lock); - ftrace_shutdown_replenish(); } - /* p is ignored */ + /* disable interrupts to prevent kstop machine */ local_irq_save(flags); - __ftrace_update_code(p); + ftrace_update_code(); local_irq_restore(flags); + mutex_unlock(&ftrace_start_lock); return 0; } @@ -1658,130 +1332,34 @@ void __init ftrace_init(void) failed: ftrace_disabled = 1; } -#else /* CONFIG_FTRACE_MCOUNT_RECORD */ -static int ftraced(void *ignore) -{ - unsigned long usecs; - - while (!kthread_should_stop()) { - - set_current_state(TASK_INTERRUPTIBLE); - - /* check once a second */ - schedule_timeout(HZ); - if (unlikely(ftrace_disabled)) - continue; - - mutex_lock(&ftrace_sysctl_lock); - mutex_lock(&ftraced_lock); - if (!ftraced_suspend && !ftraced_stop && - ftrace_update_code()) { - usecs = nsecs_to_usecs(ftrace_update_time); - if (ftrace_update_tot_cnt > 100000) { - ftrace_update_tot_cnt = 0; - pr_info("hm, dftrace overflow: %lu change%s" - " (%lu total) in %lu usec%s\n", - ftrace_update_cnt, - ftrace_update_cnt != 1 ? "s" : "", - ftrace_update_tot_cnt, - usecs, usecs != 1 ? "s" : ""); - ftrace_disabled = 1; - WARN_ON_ONCE(1); - } - } - mutex_unlock(&ftraced_lock); - mutex_unlock(&ftrace_sysctl_lock); - - ftrace_shutdown_replenish(); - } - __set_current_state(TASK_RUNNING); - return 0; -} +#else -static int __init ftrace_dynamic_init(void) +static int __init ftrace_nodyn_init(void) { - struct task_struct *p; - unsigned long addr; - int ret; - - addr = (unsigned long)ftrace_record_ip; - - stop_machine(ftrace_dyn_arch_init, &addr, NULL); - - /* ftrace_dyn_arch_init places the return code in addr */ - if (addr) { - ret = (int)addr; - goto failed; - } - - ret = ftrace_dyn_table_alloc(NR_TO_INIT); - if (ret) - goto failed; - - p = kthread_run(ftraced, NULL, "ftraced"); - if (IS_ERR(p)) { - ret = -1; - goto failed; - } - - last_ftrace_enabled = ftrace_enabled = 1; - ftraced_task = p; - + ftrace_enabled = 1; return 0; - - failed: - ftrace_disabled = 1; - return ret; } +device_initcall(ftrace_nodyn_init); -core_initcall(ftrace_dynamic_init); -#endif /* CONFIG_FTRACE_MCOUNT_RECORD */ - -#else # define ftrace_startup() do { } while (0) # define ftrace_shutdown() do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) -# define ftrace_force_shutdown() do { } while (0) #endif /* CONFIG_DYNAMIC_FTRACE */ /** - * ftrace_kill_atomic - kill ftrace from critical sections + * ftrace_kill - kill ftrace * * This function should be used by panic code. It stops ftrace * but in a not so nice way. If you need to simply kill ftrace * from a non-atomic section, use ftrace_kill. */ -void ftrace_kill_atomic(void) -{ - ftrace_disabled = 1; - ftrace_enabled = 0; -#ifdef CONFIG_DYNAMIC_FTRACE - ftraced_suspend = -1; -#endif - clear_ftrace_function(); -} - -/** - * ftrace_kill - totally shutdown ftrace - * - * This is a safety measure. If something was detected that seems - * wrong, calling this function will keep ftrace from doing - * any more modifications, and updates. - * used when something went wrong. - */ void ftrace_kill(void) { - mutex_lock(&ftrace_sysctl_lock); ftrace_disabled = 1; ftrace_enabled = 0; - clear_ftrace_function(); - mutex_unlock(&ftrace_sysctl_lock); - - /* Try to totally disable ftrace */ - ftrace_force_shutdown(); } /** @@ -1870,3 +1448,4 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, mutex_unlock(&ftrace_sysctl_lock); return ret; } + diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 94af1fe56bb..668bbb5ef2b 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) @@ -130,7 +165,7 @@ struct buffer_page { static inline void free_buffer_page(struct buffer_page *bpage) { if (bpage->page) - __free_page(bpage->page); + free_page((unsigned long)bpage->page); kfree(bpage); } @@ -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; } @@ -966,7 +1008,9 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, if (unlikely(*delta > (1ULL << 59) && !once++)) { printk(KERN_WARNING "Delta way too big! %llu" " ts=%llu write stamp = %llu\n", - *delta, *ts, cpu_buffer->write_stamp); + (unsigned long long)*delta, + (unsigned long long)*ts, + (unsigned long long)cpu_buffer->write_stamp); WARN_ON(1); } @@ -1020,8 +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); /* @@ -1043,7 +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)) { @@ -1116,6 +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; @@ -1153,7 +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; @@ -1232,6 +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; @@ -1530,10 +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 */ @@ -1663,6 +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; @@ -1670,6 +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; @@ -1720,6 +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; @@ -1728,6 +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; @@ -2012,3 +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 d345d649d07..d86e3252f30 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -34,6 +34,7 @@ #include <linux/stacktrace.h> #include <linux/ring_buffer.h> +#include <linux/irqflags.h> #include "trace.h" @@ -655,7 +656,11 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; entry->flags = +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | +#else + TRACE_FLAG_IRQS_NOSUPPORT | +#endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); @@ -700,6 +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; @@ -725,6 +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, @@ -851,7 +858,7 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) preempt_enable_notrace(); } -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER static void function_trace_call(unsigned long ip, unsigned long parent_ip) { @@ -865,9 +872,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) if (unlikely(!ftrace_function_enabled)) return; - if (skip_trace(ip)) - return; - pc = preempt_count(); resched = need_resched(); preempt_disable_notrace(); @@ -1084,17 +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 */ @@ -1103,10 +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; } @@ -1117,9 +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; } @@ -1246,7 +1259,8 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid); trace_seq_printf(s, "%3d", cpu); trace_seq_printf(s, "%c%c", - (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.', + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.', ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.')); hardirq = entry->flags & TRACE_FLAG_HARDIRQ; @@ -1372,10 +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; } @@ -1491,12 +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; } @@ -1747,7 +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) { @@ -1928,6 +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); } @@ -2379,9 +2388,10 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, int i; size_t ret; + ret = cnt; + if (cnt > max_tracer_type_len) cnt = max_tracer_type_len; - ret = cnt; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; @@ -2414,8 +2424,8 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, out: mutex_unlock(&trace_types_lock); - if (ret == cnt) - filp->f_pos += cnt; + if (ret > 0) + filp->f_pos += ret; return ret; } @@ -2667,7 +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)) @@ -2695,6 +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) { @@ -2726,6 +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); @@ -3097,7 +3122,7 @@ void ftrace_dump(void) dump_ran = 1; /* No turning back! */ - ftrace_kill_atomic(); + ftrace_kill(); for_each_tracing_cpu(cpu) { atomic_inc(&global_trace.data[cpu]->disabled); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f1f99572cde..8465ad05270 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -120,18 +120,20 @@ struct trace_boot { /* * trace_flag_type is an enumeration that holds different * states when a trace occurs. These are: - * IRQS_OFF - interrupts were disabled - * NEED_RESCED - reschedule is requested - * HARDIRQ - inside an interrupt handler - * SOFTIRQ - inside a softirq handler - * CONT - multiple entries hold the trace item + * IRQS_OFF - interrupts were disabled + * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags + * NEED_RESCED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler + * CONT - multiple entries hold the trace item */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_NEED_RESCHED = 0x02, - TRACE_FLAG_HARDIRQ = 0x04, - TRACE_FLAG_SOFTIRQ = 0x08, - TRACE_FLAG_CONT = 0x10, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_CONT = 0x20, }; #define TRACE_BUF_SIZE 1024 @@ -335,7 +337,7 @@ void update_max_tr_single(struct trace_array *tr, extern cycle_t ftrace_now(int cpu); -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER void tracing_start_function_trace(void); void tracing_stop_function_trace(void); #else diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index e90eb0c2c56..0f85a64003d 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -64,7 +64,7 @@ static void function_trace_ctrl_update(struct trace_array *tr) static struct tracer function_trace __read_mostly = { - .name = "ftrace", + .name = "function", .init = function_trace_init, .reset = function_trace_reset, .ctrl_update = function_trace_ctrl_update, diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index a7db7f040ae..9c74071c10e 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -63,7 +63,7 @@ irq_trace(void) */ static __cacheline_aligned_in_smp unsigned long max_sequence; -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER /* * irqsoff uses its own tracer function to keep the overhead down: */ @@ -104,7 +104,7 @@ static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, }; -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ /* * Should this new latency be reported/recorded? diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index f28484618ff..e62cbf78eab 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_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index fe4a252c236..3ae93f16b56 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -31,7 +31,7 @@ static raw_spinlock_t wakeup_lock = static void __wakeup_reset(struct trace_array *tr); -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER /* * irqsoff uses its own tracer function to keep the overhead down: */ @@ -96,7 +96,7 @@ static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, }; -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ /* * Should this new latency be reported/recorded? diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 09cf230d7ec..90bc752a758 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -70,7 +70,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) return ret; } -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE @@ -99,13 +99,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, /* passed in by parameter to fool gcc from optimizing */ func(); - /* update the records */ - ret = ftrace_force_update(); - if (ret) { - printk(KERN_CONT ".. ftraced failed .. "); - return ret; - } - /* * Some archs *cough*PowerPC*cough* add charachters to the * start of the function names. We simply put a '*' to @@ -183,13 +176,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* make sure msleep has been recorded */ msleep(1); - /* force the recorded functions to be traced */ - ret = ftrace_force_update(); - if (ret) { - printk(KERN_CONT ".. ftraced failed .. "); - return ret; - } - /* start the tracing */ ftrace_enabled = 1; tracer_enabled = 1; @@ -226,7 +212,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) return ret; } -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_IRQSOFF_TRACER int diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 74c5d9a3afa..3bdb44bde4b 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -44,6 +44,10 @@ static inline void check_stack(void) if (this_size <= max_stack_size) return; + /* we do not handle interrupt stacks yet */ + if (!object_is_on_stack(&this_size)) + return; + raw_local_irq_save(flags); __raw_spin_lock(&max_stack_lock); @@ -180,11 +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) @@ -197,12 +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)) ; @@ -231,10 +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", @@ -242,6 +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; @@ -271,10 +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/tracepoint.c b/kernel/tracepoint.c index f2b7c28a470..af8c8566488 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -131,6 +131,9 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe) old = entry->funcs; + if (!old) + return NULL; + debug_print_probes(entry); /* (N -> M), (N > 1, M >= 0) probes */ for (nr_probes = 0; old[nr_probes]; nr_probes++) { @@ -388,6 +391,11 @@ int tracepoint_probe_unregister(const char *name, void *probe) if (entry->rcu_pending) rcu_barrier_sched(); old = tracepoint_entry_remove_probe(entry, probe); + if (!old) { + printk(KERN_WARNING "Warning: Trying to unregister a probe" + "that doesn't exist\n"); + goto end; + } mutex_unlock(&tracepoints_mutex); tracepoint_update_probes(); /* may update entry */ mutex_lock(&tracepoints_mutex); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 714afad4653..d4dc69ddebd 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -62,6 +62,7 @@ struct workqueue_struct { const char *name; int singlethread; int freezeable; /* Freeze threads during suspend */ + int rt; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -766,6 +767,7 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct workqueue_struct *wq = cwq->wq; const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d"; struct task_struct *p; @@ -781,7 +783,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) */ if (IS_ERR(p)) return PTR_ERR(p); - + if (cwq->wq->rt) + sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; return 0; @@ -801,6 +804,7 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) struct workqueue_struct *__create_workqueue_key(const char *name, int singlethread, int freezeable, + int rt, struct lock_class_key *key, const char *lock_name) { @@ -822,6 +826,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); wq->singlethread = singlethread; wq->freezeable = freezeable; + wq->rt = rt; INIT_LIST_HEAD(&wq->list); if (singlethread) { @@ -965,6 +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; |