diff options
Diffstat (limited to 'kernel')
38 files changed, 332 insertions, 152 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 34c5a2310fbf..95a20f3f52f1 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -182,7 +182,7 @@ struct audit_buffer { struct audit_reply { __u32 portid; - pid_t pid; + struct net *net; struct sk_buff *skb; }; @@ -500,7 +500,7 @@ int audit_send_list(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; - struct net *net = get_net_ns_by_pid(dest->pid); + struct net *net = dest->net; struct audit_net *aunet = net_generic(net, audit_net_id); /* wait for parent to finish and send an ACK */ @@ -510,6 +510,7 @@ int audit_send_list(void *_dest) while ((skb = __skb_dequeue(&dest->q)) != NULL) netlink_unicast(aunet->nlsk, skb, dest->portid, 0); + put_net(net); kfree(dest); return 0; @@ -543,7 +544,7 @@ out_kfree_skb: static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; - struct net *net = get_net_ns_by_pid(reply->pid); + struct net *net = reply->net; struct audit_net *aunet = net_generic(net, audit_net_id); mutex_lock(&audit_cmd_mutex); @@ -552,12 +553,13 @@ static int audit_send_reply_thread(void *arg) /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0); + put_net(net); kfree(reply); return 0; } /** * audit_send_reply - send an audit reply message via netlink - * @portid: netlink port to which to send reply + * @request_skb: skb of request we are replying to (used to target the reply) * @seq: sequence number * @type: audit message type * @done: done (last) flag @@ -568,9 +570,11 @@ static int audit_send_reply_thread(void *arg) * Allocates an skb, builds the netlink message, and sends it to the port id. * No failure notifications. */ -static void audit_send_reply(__u32 portid, int seq, int type, int done, +static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { + u32 portid = NETLINK_CB(request_skb).portid; + struct net *net = sock_net(NETLINK_CB(request_skb).sk); struct sk_buff *skb; struct task_struct *tsk; struct audit_reply *reply = kmalloc(sizeof(struct audit_reply), @@ -583,8 +587,8 @@ static void audit_send_reply(__u32 portid, int seq, int type, int done, if (!skb) goto out; + reply->net = get_net(net); reply->portid = portid; - reply->pid = task_pid_vnr(current); reply->skb = skb; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); @@ -604,9 +608,19 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) int err = 0; /* Only support the initial namespaces for now. */ + /* + * We return ECONNREFUSED because it tricks userspace into thinking + * that audit was not configured into the kernel. Lots of users + * configure their PAM stack (because that's what the distro does) + * to reject login if unable to send messages to audit. If we return + * ECONNREFUSED the PAM stack thinks the kernel does not have audit + * configured in and will let login proceed. If we return EPERM + * userspace will reject all logins. This should be removed when we + * support non init namespaces!! + */ if ((current_user_ns() != &init_user_ns) || (task_active_pid_ns(current) != &init_pid_ns)) - return -EPERM; + return -ECONNREFUSED; switch (msg_type) { case AUDIT_LIST: @@ -673,8 +687,7 @@ static int audit_get_feature(struct sk_buff *skb) seq = nlmsg_hdr(skb)->nlmsg_seq; - audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, - &af, sizeof(af)); + audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af)); return 0; } @@ -794,8 +807,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) s.backlog = skb_queue_len(&audit_skb_queue); s.version = AUDIT_VERSION_LATEST; s.backlog_wait_time = audit_backlog_wait_time; - audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, - &s, sizeof(s)); + audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_SET: { @@ -905,7 +917,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq, data, nlmsg_len(nlh)); break; case AUDIT_LIST_RULES: - err = audit_list_rules_send(NETLINK_CB(skb).portid, seq); + err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: audit_trim_trees(); @@ -970,8 +982,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } - audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO, - 0, 0, sig_data, sizeof(*sig_data) + len); + audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, + sig_data, sizeof(*sig_data) + len); kfree(sig_data); break; case AUDIT_TTY_GET: { @@ -983,8 +995,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) s.log_passwd = tsk->signal->audit_tty_log_passwd; spin_unlock(&tsk->sighand->siglock); - audit_send_reply(NETLINK_CB(skb).portid, seq, - AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); + audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { diff --git a/kernel/audit.h b/kernel/audit.h index 57cc64d67718..8df132214606 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -247,7 +247,7 @@ extern void audit_panic(const char *message); struct audit_netlink_list { __u32 portid; - pid_t pid; + struct net *net; struct sk_buff_head q; }; diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 67ccf0e7cca9..135944a7b28a 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -916,7 +916,7 @@ static int audit_tree_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { return 0; } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2596fac5dcb4..70b4554d2fbe 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -471,7 +471,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *dname) + const unsigned char *dname, u32 cookie) { struct inode *inode; struct audit_parent *parent; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 14a78cca384e..92062fd6cc8c 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -29,6 +29,8 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> +#include <net/net_namespace.h> +#include <net/sock.h> #include "audit.h" /* @@ -1065,11 +1067,13 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data, /** * audit_list_rules_send - list the audit rules - * @portid: target portid for netlink audit messages + * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ -int audit_list_rules_send(__u32 portid, int seq) +int audit_list_rules_send(struct sk_buff *request_skb, int seq) { + u32 portid = NETLINK_CB(request_skb).portid; + struct net *net = sock_net(NETLINK_CB(request_skb).sk); struct task_struct *tsk; struct audit_netlink_list *dest; int err = 0; @@ -1083,8 +1087,8 @@ int audit_list_rules_send(__u32 portid, int seq) dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL); if (!dest) return -ENOMEM; + dest->net = get_net(net); dest->portid = portid; - dest->pid = task_pid_vnr(current); skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 10176cd5956a..7aef2f4b6c64 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1719,7 +1719,7 @@ void audit_putname(struct filename *name) struct audit_context *context = current->audit_context; BUG_ON(!context); - if (!context->in_syscall) { + if (!name->aname || !context->in_syscall) { #if AUDIT_DEBUG == 2 printk(KERN_ERR "%s:%d(:%d): final_putname(%p)\n", __FILE__, __LINE__, context->serial, name); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e2f46ba37f72..0c753ddd223b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -886,7 +886,9 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) * per-subsystem and moved to css->id so that lookups are * successful until the target css is released. */ + mutex_lock(&cgroup_mutex); idr_remove(&cgrp->root->cgroup_idr, cgrp->id); + mutex_unlock(&cgroup_mutex); cgrp->id = -1; call_rcu(&cgrp->rcu_head, cgroup_free_rcu); @@ -1566,10 +1568,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, mutex_lock(&cgroup_mutex); mutex_lock(&cgroup_root_mutex); - root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp, - 0, 1, GFP_KERNEL); - if (root_cgrp->id < 0) + ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL); + if (ret < 0) goto unlock_drop; + root_cgrp->id = ret; /* Check for name clashes with existing mounts */ ret = -EBUSY; @@ -2763,10 +2765,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) */ update_before = cgroup_serial_nr_next; - mutex_unlock(&cgroup_mutex); - /* add/rm files for all cgroups created before */ - rcu_read_lock(); css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; @@ -2775,23 +2774,19 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) inode = cgrp->dentry->d_inode; dget(cgrp->dentry); - rcu_read_unlock(); - dput(prev); prev = cgrp->dentry; + mutex_unlock(&cgroup_mutex); mutex_lock(&inode->i_mutex); mutex_lock(&cgroup_mutex); if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp)) ret = cgroup_addrm_files(cgrp, cfts, is_add); - mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); - - rcu_read_lock(); if (ret) break; } - rcu_read_unlock(); + mutex_unlock(&cgroup_mutex); dput(prev); deactivate_super(sb); return ret; @@ -2910,9 +2905,14 @@ static void cgroup_enable_task_cg_lists(void) * We should check if the process is exiting, otherwise * it will race with cgroup_exit() in that the list * entry won't be deleted though the process has exited. + * Do it while holding siglock so that we don't end up + * racing against cgroup_exit(). */ + spin_lock_irq(&p->sighand->siglock); if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list)) list_add(&p->cg_list, &task_css_set(p)->tasks); + spin_unlock_irq(&p->sighand->siglock); + task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); @@ -4112,17 +4112,17 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) err = percpu_ref_init(&css->refcnt, css_release); if (err) - goto err_free; + goto err_free_css; init_css(css, ss, cgrp); err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id); if (err) - goto err_free; + goto err_free_percpu_ref; err = online_css(css); if (err) - goto err_free; + goto err_clear_dir; dget(cgrp->dentry); css_get(css->parent); @@ -4138,8 +4138,11 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss) return 0; -err_free: +err_clear_dir: + cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id); +err_free_percpu_ref: percpu_ref_cancel_init(&css->refcnt); +err_free_css: ss->css_free(css); return err; } @@ -4158,7 +4161,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, struct cgroup *cgrp; struct cgroup_name *name; struct cgroupfs_root *root = parent->root; - int ssid, err = 0; + int ssid, err; struct cgroup_subsys *ss; struct super_block *sb = root->sb; @@ -4168,19 +4171,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, return -ENOMEM; name = cgroup_alloc_name(dentry); - if (!name) + if (!name) { + err = -ENOMEM; goto err_free_cgrp; + } rcu_assign_pointer(cgrp->name, name); /* - * Temporarily set the pointer to NULL, so idr_find() won't return - * a half-baked cgroup. - */ - cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL); - if (cgrp->id < 0) - goto err_free_name; - - /* * Only live parents can have children. Note that the liveliness * check isn't strictly necessary because cgroup_mkdir() and * cgroup_rmdir() are fully synchronized by i_mutex; however, do it @@ -4189,7 +4186,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, */ if (!cgroup_lock_live_group(parent)) { err = -ENODEV; - goto err_free_id; + goto err_free_name; + } + + /* + * Temporarily set the pointer to NULL, so idr_find() won't return + * a half-baked cgroup. + */ + cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL); + if (cgrp->id < 0) { + err = -ENOMEM; + goto err_unlock; } /* Grab a reference on the superblock so the hierarchy doesn't @@ -4221,7 +4228,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, */ err = cgroup_create_file(dentry, S_IFDIR | mode, sb); if (err < 0) - goto err_unlock; + goto err_free_id; lockdep_assert_held(&dentry->d_inode->i_mutex); cgrp->serial_nr = cgroup_serial_nr_next++; @@ -4257,12 +4264,12 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, return 0; -err_unlock: - mutex_unlock(&cgroup_mutex); - /* Release the reference count that we took on the superblock */ - deactivate_super(sb); err_free_id: idr_remove(&root->cgroup_idr, cgrp->id); + /* Release the reference count that we took on the superblock */ + deactivate_super(sb); +err_unlock: + mutex_unlock(&cgroup_mutex); err_free_name: kfree(rcu_dereference_raw(cgrp->name)); err_free_cgrp: diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4410ac6a55f1..e6b1b66afe52 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -974,12 +974,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Temporarilly set tasks mems_allowed to target nodes of migration, * so that the migration code can allocate pages on these nodes. * - * Call holding cpuset_mutex, so current's cpuset won't change - * during this call, as manage_mutex holds off any cpuset_attach() - * calls. Therefore we don't need to take task_lock around the - * call to guarantee_online_mems(), as we know no one is changing - * our task's cpuset. - * * While the mm_struct we are migrating is typically from some * other task, the task_struct mems_allowed that we are hacking * is for our current task, which must allocate new pages for that @@ -996,8 +990,10 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + rcu_read_lock(); mems_cs = effective_nodemask_cpuset(task_cs(tsk)); guarantee_online_mems(mems_cs, &tsk->mems_allowed); + rcu_read_unlock(); } /* @@ -2486,9 +2482,9 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) task_lock(current); cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); task_unlock(current); - allowed = node_isset(node, cs->mems_allowed); mutex_unlock(&callback_mutex); return allowed; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 56003c6edfd3..fa0b2d4ad83c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7856,14 +7856,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu) static void __perf_event_exit_context(void *__info) { struct perf_event_context *ctx = __info; - struct perf_event *event, *tmp; + struct perf_event *event; perf_pmu_rotate_stop(ctx->pmu); - list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry) - __perf_remove_from_context(event); - list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry) + rcu_read_lock(); + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) __perf_remove_from_context(event); + rcu_read_unlock(); } static void perf_event_exit_cpu_context(int cpu) @@ -7887,11 +7887,11 @@ static void perf_event_exit_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); + perf_event_exit_cpu_context(cpu); + mutex_lock(&swhash->hlist_mutex); swevent_hlist_release(swhash); mutex_unlock(&swhash->hlist_mutex); - - perf_event_exit_cpu_context(cpu); } #else static inline void perf_event_exit_cpu(int cpu) { } diff --git a/kernel/futex.c b/kernel/futex.c index 5d17e3a83f8c..67dacaf93e56 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -236,6 +236,7 @@ static const struct futex_q futex_q_init = { * waiting on a futex. */ struct futex_hash_bucket { + atomic_t waiters; spinlock_t lock; struct plist_head chain; } ____cacheline_aligned_in_smp; @@ -255,22 +256,37 @@ static inline void futex_get_mm(union futex_key *key) smp_mb__after_atomic_inc(); } -static inline bool hb_waiters_pending(struct futex_hash_bucket *hb) +/* + * Reflects a new waiter being added to the waitqueue. + */ +static inline void hb_waiters_inc(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP + atomic_inc(&hb->waiters); /* - * Tasks trying to enter the critical region are most likely - * potential waiters that will be added to the plist. Ensure - * that wakers won't miss to-be-slept tasks in the window between - * the wait call and the actual plist_add. + * Full barrier (A), see the ordering comment above. */ - if (spin_is_locked(&hb->lock)) - return true; - smp_rmb(); /* Make sure we check the lock state first */ + smp_mb__after_atomic_inc(); +#endif +} + +/* + * Reflects a waiter being removed from the waitqueue by wakeup + * paths. + */ +static inline void hb_waiters_dec(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + atomic_dec(&hb->waiters); +#endif +} - return !plist_head_empty(&hb->chain); +static inline int hb_waiters_pending(struct futex_hash_bucket *hb) +{ +#ifdef CONFIG_SMP + return atomic_read(&hb->waiters); #else - return true; + return 1; #endif } @@ -956,6 +972,7 @@ static void __unqueue_futex(struct futex_q *q) hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); } /* @@ -1259,7 +1276,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, */ if (likely(&hb1->chain != &hb2->chain)) { plist_del(&q->list, &hb1->chain); + hb_waiters_dec(hb1); plist_add(&q->list, &hb2->chain); + hb_waiters_inc(hb2); q->lock_ptr = &hb2->lock; } get_futex_key_refs(key2); @@ -1602,6 +1621,17 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) struct futex_hash_bucket *hb; hb = hash_futex(&q->key); + + /* + * Increment the counter before taking the lock so that + * a potential waker won't miss a to-be-slept task that is + * waiting for the spinlock. This is safe as all queue_lock() + * users end up calling queue_me(). Similarly, for housekeeping, + * decrement the counter at queue_unlock() when some error has + * occurred and we don't end up adding the task to the list. + */ + hb_waiters_inc(hb); + q->lock_ptr = &hb->lock; spin_lock(&hb->lock); /* implies MB (A) */ @@ -1613,6 +1643,7 @@ queue_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); + hb_waiters_dec(hb); } /** @@ -2344,6 +2375,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * Unqueue the futex_q and determine which it was. */ plist_del(&q->list, &hb->chain); + hb_waiters_dec(hb); /* Handle spurious wakeups gracefully */ ret = -EWOULDBLOCK; @@ -2886,6 +2918,7 @@ static int __init futex_init(void) futex_detect_cmpxchg(); for (i = 0; i < futex_hashsize; i++) { + atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 4a1fef09f658..07cbdfea9ae2 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -40,6 +40,7 @@ config IRQ_EDGE_EOI_HANDLER # Generic configurable interrupt chip implementation config GENERIC_IRQ_CHIP bool + select IRQ_DOMAIN # Generic irq_domain hw <--> linux irq number translation config IRQ_DOMAIN diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index bd8e788d71e0..1ef0606797c9 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -73,6 +73,51 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq, EXPORT_SYMBOL(devm_request_threaded_irq); /** + * devm_request_any_context_irq - allocate an interrupt line for a managed device + * @dev: device to request interrupt for + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @thread_fn: function to be called in a threaded interrupt context. NULL + * for devices which handle everything in @handler + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * Except for the extra @dev argument, this function takes the + * same arguments and performs the same function as + * request_any_context_irq(). IRQs requested with this function will be + * automatically freed on driver detach. + * + * If an IRQ allocated with this function needs to be freed + * separately, devm_free_irq() must be used. + */ +int devm_request_any_context_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id) +{ + struct irq_devres *dr; + int rc; + + dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres), + GFP_KERNEL); + if (!dr) + return -ENOMEM; + + rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id); + if (rc) { + devres_free(dr); + return rc; + } + + dr->irq = irq; + dr->dev_id = dev_id; + devres_add(dev, dr); + + return 0; +} +EXPORT_SYMBOL(devm_request_any_context_irq); + +/** * devm_free_irq - free an interrupt * @dev: device to free interrupt for * @irq: Interrupt line to free diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 192a302d6cfd..8ab8e9390297 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -274,6 +274,7 @@ struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } +EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index cf68bb36fe58..f14033700c25 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -10,6 +10,7 @@ #include <linux/mutex.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/topology.h> #include <linux/seq_file.h> #include <linux/slab.h> diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 481a13c43b17..d3bf660cb57f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -802,8 +802,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc, static void wake_threads_waitq(struct irq_desc *desc) { - if (atomic_dec_and_test(&desc->threads_active) && - waitqueue_active(&desc->wait_for_threads)) + if (atomic_dec_and_test(&desc->threads_active)) wake_up(&desc->wait_for_threads); } diff --git a/kernel/kmod.c b/kernel/kmod.c index b086006c59e7..6b375af4958d 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -239,7 +239,7 @@ static int ____call_usermodehelper(void *data) commit_creds(new); - retval = do_execve(sub_info->path, + retval = do_execve(getname_kernel(sub_info->path), (const char __user *const __user *)sub_info->argv, (const char __user *const __user *)sub_info->envp); if (!retval) diff --git a/kernel/power/console.c b/kernel/power/console.c index eacb8bd8cab4..aba9c545a0e3 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,6 +9,7 @@ #include <linux/kbd_kern.h> #include <linux/vt.h> #include <linux/module.h> +#include <linux/slab.h> #include "power.h" #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b1d255f04135..4dae9cbe9259 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1076,7 +1076,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) next_seq = log_next_seq; len = 0; - prev = 0; while (len >= 0 && seq < next_seq) { struct printk_log *msg = log_from_idx(idx); int textlen; @@ -2788,7 +2787,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, next_idx = idx; l = 0; - prev = 0; while (seq < dumper->next_seq) { struct printk_log *msg = log_from_idx(idx); diff --git a/kernel/profile.c b/kernel/profile.c index 6631e1ef55ab..ebdd9c1a86b4 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -549,14 +549,14 @@ static int create_hash_tables(void) struct page *page; page = alloc_pages_exact_node(node, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, 0); if (!page) goto out_cleanup; per_cpu(cpu_profile_hits, cpu)[1] = (struct profile_hit *)page_address(page); page = alloc_pages_exact_node(node, - GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, 0); if (!page) goto out_cleanup; diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 43c2bcc35761..b30a2924ef14 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu) if (unlikely(!sched_clock_running)) return 0ull; - preempt_disable(); + preempt_disable_notrace(); scd = cpu_sdc(cpu); if (cpu != smp_processor_id()) clock = sched_clock_remote(scd); else clock = sched_clock_local(scd); - preempt_enable(); + preempt_enable_notrace(); return clock; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b46131ef6aab..f5c6635b806c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1952,7 +1952,7 @@ static int dl_overflow(struct task_struct *p, int policy, { struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - u64 period = attr->sched_period; + u64 period = attr->sched_period ?: attr->sched_deadline; u64 runtime = attr->sched_runtime; u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; int cpus, err = -1; @@ -3338,6 +3338,15 @@ recheck: return -EPERM; } + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + return -EPERM; + /* * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. @@ -3661,13 +3670,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) * @pid: the pid in question. * @uattr: structure containing the extended parameters. */ -SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr) +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) { struct sched_attr attr; struct task_struct *p; int retval; - if (!uattr || pid < 0) + if (!uattr || pid < 0 || flags) return -EINVAL; if (sched_copy_attr(uattr, &attr)) @@ -3786,7 +3796,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, attr->size = usize; } - ret = copy_to_user(uattr, attr, usize); + ret = copy_to_user(uattr, attr, attr->size); if (ret) return -EFAULT; @@ -3804,8 +3814,8 @@ err_size: * @uattr: structure containing the extended parameters. * @size: sizeof(attr) for fwd/bwd comp. */ -SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, size) +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) { struct sched_attr attr = { .size = sizeof(struct sched_attr), @@ -3814,7 +3824,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, int retval; if (!uattr || pid < 0 || size > PAGE_SIZE || - size < SCHED_ATTR_SIZE_VER0) + size < SCHED_ATTR_SIZE_VER0 || flags) return -EINVAL; rcu_read_lock(); @@ -7422,6 +7432,7 @@ static int sched_dl_global_constraints(void) u64 period = global_rt_period(); u64 new_bw = to_ratio(period, runtime); int cpu, ret = 0; + unsigned long flags; /* * Here we want to check the bandwidth not being set to some @@ -7435,10 +7446,10 @@ static int sched_dl_global_constraints(void) for_each_possible_cpu(cpu) { struct dl_bw *dl_b = dl_bw_of(cpu); - raw_spin_lock(&dl_b->lock); + raw_spin_lock_irqsave(&dl_b->lock, flags); if (new_bw < dl_b->total_bw) ret = -EBUSY; - raw_spin_unlock(&dl_b->lock); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); if (ret) break; @@ -7451,6 +7462,7 @@ static void sched_dl_do_global(void) { u64 new_bw = -1; int cpu; + unsigned long flags; def_dl_bandwidth.dl_period = global_rt_period(); def_dl_bandwidth.dl_runtime = global_rt_runtime(); @@ -7464,9 +7476,9 @@ static void sched_dl_do_global(void) for_each_possible_cpu(cpu) { struct dl_bw *dl_b = dl_bw_of(cpu); - raw_spin_lock(&dl_b->lock); + raw_spin_lock_irqsave(&dl_b->lock, flags); dl_b->bw = new_bw; - raw_spin_unlock(&dl_b->lock); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); } } @@ -7475,7 +7487,8 @@ static int sched_rt_global_validate(void) if (sysctl_sched_rt_period <= 0) return -EINVAL; - if (sysctl_sched_rt_runtime > sysctl_sched_rt_period) + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) return -EINVAL; return 0; diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 045fc74e3f09..5b9bb42b2d47 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx) static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl) { - WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID); + WARN_ON(idx == IDX_INVALID || !cpu_present(idx)); if (dl_time_before(new_dl, cp->elements[idx].dl)) { cp->elements[idx].dl = new_dl; @@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, } out: - WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1); + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); return best_cpu; } @@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) int old_idx, new_cpu; unsigned long flags; - WARN_ON(cpu > num_present_cpus()); + WARN_ON(!cpu_present(cpu)); raw_spin_lock_irqsave(&cp->lock, flags); old_idx = cp->cpu_to_idx[cpu]; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 0dd5e0971a07..6e79b3faa4cd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq) static void update_dl_migration(struct dl_rq *dl_rq) { - if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) { + if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) { if (!dl_rq->overloaded) { dl_set_overload(rq_of_dl_rq(dl_rq)); dl_rq->overloaded = 1; @@ -135,9 +135,7 @@ static void update_dl_migration(struct dl_rq *dl_rq) static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - dl_rq = &rq_of_dl_rq(dl_rq)->dl; - dl_rq->dl_nr_total++; if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory++; @@ -147,9 +145,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - dl_rq = &rq_of_dl_rq(dl_rq)->dl; - dl_rq->dl_nr_total--; if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory--; @@ -566,6 +562,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) return 1; } +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); + /* * Update the current task's runtime statistics (provided it is still * a -deadline task and has not been removed from the dl_rq). @@ -629,11 +627,13 @@ static void update_curr_dl(struct rq *rq) struct rt_rq *rt_rq = &rq->rt; raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_time += delta_exec; /* * We'll let actual RT tasks worry about the overflow here, we - * have our own CBS to keep us inline -- see above. + * have our own CBS to keep us inline; only account when RT + * bandwidth is relevant. */ + if (sched_rt_bandwidth_account(rt_rq)) + rt_rq->rt_time += delta_exec; raw_spin_unlock(&rt_rq->rt_runtime_lock); } } @@ -717,6 +717,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); dl_rq->dl_nr_running++; + inc_nr_running(rq_of_dl_rq(dl_rq)); inc_dl_deadline(dl_rq, deadline); inc_dl_migration(dl_se, dl_rq); @@ -730,6 +731,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; + dec_nr_running(rq_of_dl_rq(dl_rq)); dec_dl_deadline(dl_rq, dl_se->deadline); dec_dl_migration(dl_se, dl_rq); @@ -836,8 +838,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); - - inc_nr_running(rq); } static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) @@ -850,8 +850,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); __dequeue_task_dl(rq, p, flags); - - dec_nr_running(rq); } /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 966cc2bfcb77..9b4c4f320130 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1757,6 +1757,8 @@ void task_numa_work(struct callback_head *work) start = end; if (pages <= 0) goto out; + + cond_resched(); } while (end != vma->vm_end); } @@ -6999,15 +7001,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) struct cfs_rq *cfs_rq = cfs_rq_of(se); /* - * Ensure the task's vruntime is normalized, so that when its + * Ensure the task's vruntime is normalized, so that when it's * switched back to the fair class the enqueue_entity(.flags=0) will * do the right thing. * - * If it was on_rq, then the dequeue_entity(.flags=0) will already - * have normalized the vruntime, if it was !on_rq, then only when + * If it's on_rq, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !on_rq, then only when * the task is sleeping will it still have non-normalized vruntime. */ - if (!se->on_rq && p->state != TASK_RUNNING) { + if (!p->on_rq && p->state != TASK_RUNNING) { /* * Fix up our vruntime so that the current sleep doesn't * cause 'unlimited' sleep bonus. diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a2740b775b45..1999021042c7 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -538,6 +538,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) #endif /* CONFIG_RT_GROUP_SCHED */ +bool sched_rt_bandwidth_account(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + return (hrtimer_active(&rt_b->rt_period_timer) || + rt_rq->rt_time < rt_b->rt_runtime); +} + #ifdef CONFIG_SMP /* * We ran out of runtime, see if we can borrow some from our neighbours. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c2119fd20f8b..f964add50f38 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -462,7 +462,6 @@ struct dl_rq { } earliest_dl; unsigned long dl_nr_migratory; - unsigned long dl_nr_total; int overloaded; /* diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 84571e09c907..01fbae5b97b7 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * */ smp_call_function_single(min(cpu1, cpu2), &irq_cpu_stop_queue_work, - &call_args, 0); + &call_args, 1); lg_local_unlock(&stop_cpus_lock); preempt_enable(); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7a925ba456fb..a6a5bf53e86d 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -51,7 +51,13 @@ * HZ shrinks, so values greater than 8 overflow 32bits when * HZ=100. */ +#if HZ < 34 +#define JIFFIES_SHIFT 6 +#elif HZ < 67 +#define JIFFIES_SHIFT 7 +#else #define JIFFIES_SHIFT 8 +#endif static cycle_t jiffies_read(struct clocksource *cs) { diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 0abb36464281..4d23dc4d8139 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -116,20 +116,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) void __init sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { + u64 res, wrap, new_mask, new_epoch, cyc, ns; + u32 new_mult, new_shift; + ktime_t new_wrap_kt; unsigned long r; - u64 res, wrap; char r_unit; if (cd.rate > rate) return; WARN_ON(!irqs_disabled()); - read_sched_clock = read; - sched_clock_mask = CLOCKSOURCE_MASK(bits); - cd.rate = rate; /* calculate the mult/shift to convert counter ticks to ns. */ - clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600); + clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); + + new_mask = CLOCKSOURCE_MASK(bits); + + /* calculate how many ns until we wrap */ + wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask); + new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3)); + + /* update epoch for new counter and update epoch_ns from old counter*/ + new_epoch = read(); + cyc = read_sched_clock(); + ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, + cd.mult, cd.shift); + + raw_write_seqcount_begin(&cd.seq); + read_sched_clock = read; + sched_clock_mask = new_mask; + cd.rate = rate; + cd.wrap_kt = new_wrap_kt; + cd.mult = new_mult; + cd.shift = new_shift; + cd.epoch_cyc = new_epoch; + cd.epoch_ns = ns; + raw_write_seqcount_end(&cd.seq); r = rate; if (r >= 4000000) { @@ -141,22 +163,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits, } else r_unit = ' '; - /* calculate how many ns until we wrap */ - wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask); - cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3)); - /* calculate the ns resolution of this counter */ - res = cyc_to_ns(1ULL, cd.mult, cd.shift); + res = cyc_to_ns(1ULL, new_mult, new_shift); + pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", bits, r, r_unit, res, wrap); - update_sched_clock(); - - /* - * Ensure that sched_clock() starts off at 0ns - */ - cd.epoch_ns = 0; - /* Enable IRQ time accounting if we have a fast enough sched_clock */ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 43780ab5e279..98977a57ac72 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -756,6 +756,7 @@ out: static void tick_broadcast_clear_oneshot(int cpu) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); } static void tick_broadcast_init_next_event(struct cpumask *mask, diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0aa4ce81bc16..5b40279ecd71 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1435,7 +1435,8 @@ void update_wall_time(void) out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) - clock_was_set(); + /* Have to call _delayed version, since in irq context*/ + clock_was_set_delayed(); } /** diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 294b8a271a04..fc4da2d97f9b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2397,6 +2397,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, write &= RB_WRITE_MASK; tail = write - length; + /* + * If this is the first commit on the page, then it has the same + * timestamp as the page itself. + */ + if (!tail) + delta = 0; + /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) return rb_move_tail(cpu_buffer, length, tail, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 815c878f409b..24c1f2382557 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1600,15 +1600,31 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); +static struct ring_buffer *temp_buffer; + struct ring_buffer_event * trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, struct ftrace_event_file *ftrace_file, int type, unsigned long len, unsigned long flags, int pc) { + struct ring_buffer_event *entry; + *current_rb = ftrace_file->tr->trace_buffer.buffer; - return trace_buffer_lock_reserve(*current_rb, + entry = trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); + /* + * If tracing is off, but we have triggers enabled + * we still need to look at the event data. Use the temp_buffer + * to store the trace event for the tigger to use. It's recusive + * safe and will not be recorded anywhere. + */ + if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) { + *current_rb = temp_buffer; + entry = trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); + } + return entry; } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); @@ -6494,11 +6510,16 @@ __init static int tracer_alloc_buffers(void) raw_spin_lock_init(&global_trace.start_lock); + /* Used for event triggers */ + temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE); + if (!temp_buffer) + goto out_free_cpumask; + /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); - goto out_free_cpumask; + goto out_free_temp_buffer; } if (global_trace.buffer_disabled) @@ -6540,6 +6561,8 @@ __init static int tracer_alloc_buffers(void) return 0; +out_free_temp_buffer: + ring_buffer_free(temp_buffer); out_free_cpumask: free_percpu(global_trace.trace_buffer.data); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e71ffd4eccb5..7b16d40bd64d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -27,12 +27,6 @@ DEFINE_MUTEX(event_mutex); -DEFINE_MUTEX(event_storage_mutex); -EXPORT_SYMBOL_GPL(event_storage_mutex); - -char event_storage[EVENT_STORAGE_SIZE]; -EXPORT_SYMBOL_GPL(event_storage); - LIST_HEAD(ftrace_events); static LIST_HEAD(ftrace_common_fields); @@ -1777,6 +1771,16 @@ static void trace_module_add_events(struct module *mod) { struct ftrace_event_call **call, **start, **end; + if (!mod->num_trace_events) + return; + + /* Don't add infrastructure for mods without tracepoints */ + if (trace_module_has_bad_taint(mod)) { + pr_err("%s: module has bad taint, not creating trace events\n", + mod->name); + return; + } + start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 7c3e3e72e2b6..ee0a5098ac43 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __array #define __array(type, item, len) \ do { \ + char *type_str = #type"["__stringify(len)"]"; \ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - mutex_lock(&event_storage_mutex); \ - snprintf(event_storage, sizeof(event_storage), \ - "%s[%d]", #type, len); \ - ret = trace_define_field(event_call, event_storage, #item, \ + ret = trace_define_field(event_call, type_str, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ is_signed_type(type), filter_type); \ - mutex_unlock(&event_storage_mutex); \ if (ret) \ return ret; \ } while (0); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 29f26540e9c9..031cc5655a51 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -631,6 +631,11 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter) EXPORT_SYMBOL_GPL(tracepoint_iter_reset); #ifdef CONFIG_MODULES +bool trace_module_has_bad_taint(struct module *mod) +{ + return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)); +} + static int tracepoint_module_coming(struct module *mod) { struct tp_module *tp_mod, *iter; @@ -641,7 +646,7 @@ static int tracepoint_module_coming(struct module *mod) * module headers (for forced load), to make sure we don't cause a crash. * Staging and out-of-tree GPL modules are fine. */ - if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP))) + if (trace_module_has_bad_taint(mod)) return 0; mutex_lock(&tracepoints_mutex); tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 240fb62cf394..dd06439b9c84 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -225,7 +225,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id) * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test - * for and handle handle INVALID_UID being returned. INVALID_UID + * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 82ef9f3b7473..193e977a10ea 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1851,6 +1851,12 @@ static void destroy_worker(struct worker *worker) if (worker->flags & WORKER_IDLE) pool->nr_idle--; + /* + * Once WORKER_DIE is set, the kworker may destroy itself at any + * point. Pin to ensure the task stays until we're done with it. + */ + get_task_struct(worker->task); + list_del_init(&worker->entry); worker->flags |= WORKER_DIE; @@ -1859,6 +1865,7 @@ static void destroy_worker(struct worker *worker) spin_unlock_irq(&pool->lock); kthread_stop(worker->task); + put_task_struct(worker->task); kfree(worker); spin_lock_irq(&pool->lock); |