diff options
Diffstat (limited to 'kernel')
33 files changed, 378 insertions, 330 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 21c7fa615bd3..91e53d04b6a9 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1056,7 +1056,7 @@ static inline void audit_get_stamp(struct audit_context *ctx, static void wait_for_auditd(unsigned long sleep_time) { DECLARE_WAITQUEUE(wait, current); - set_current_state(TASK_INTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); add_wait_queue(&audit_backlog_wait, &wait); if (audit_backlog_limit && diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index a291aa23fb3f..43c307dc9453 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -658,6 +658,7 @@ int audit_add_tree_rule(struct audit_krule *rule) struct vfsmount *mnt; int err; + rule->tree = NULL; list_for_each_entry(tree, &tree_list, list) { if (!strcmp(seed->pathname, tree->pathname)) { put_tree(seed); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 83a2970295d1..6bd4a90d1991 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1021,9 +1021,6 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data - * @loginuid: loginuid of sender - * @sessionid: sessionid for netlink audit message - * @sid: SE Linux Security ID of sender */ int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2a9926275f80..a7c9e6ddb979 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1686,11 +1686,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, */ cgroup_drop_root(opts.new_root); - if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) && - root->flags != opts.flags) { - pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n"); - ret = -EINVAL; - goto drop_new_super; + if (root->flags != opts.flags) { + if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) { + pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n"); + ret = -EINVAL; + goto drop_new_super; + } else { + pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n"); + } } /* no subsys rebinding, so refcounts don't change */ @@ -2699,13 +2702,14 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, goto out; } + cfe->type = (void *)cft; + cfe->dentry = dentry; + dentry->d_fsdata = cfe; + simple_xattrs_init(&cfe->xattrs); + mode = cgroup_file_mode(cft); error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); if (!error) { - cfe->type = (void *)cft; - cfe->dentry = dentry; - dentry->d_fsdata = cfe; - simple_xattrs_init(&cfe->xattrs); list_add_tail(&cfe->node, &parent->files); cfe = NULL; } @@ -2953,11 +2957,8 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, WARN_ON_ONCE(!rcu_read_lock_held()); /* if first iteration, pretend we just visited @cgroup */ - if (!pos) { - if (list_empty(&cgroup->children)) - return NULL; + if (!pos) pos = cgroup; - } /* visit the first child if exists */ next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling); @@ -2965,14 +2966,14 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, return next; /* no child, visit my or the closest ancestor's next sibling */ - do { + while (pos != cgroup) { next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling); if (&next->sibling != &pos->parent->children) return next; pos = pos->parent; - } while (pos != cgroup); + } return NULL; } diff --git a/kernel/cpu.c b/kernel/cpu.c index b5e4ab2d427e..198a38883e64 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -133,6 +133,27 @@ static void cpu_hotplug_done(void) mutex_unlock(&cpu_hotplug.lock); } +/* + * Wait for currently running CPU hotplug operations to complete (if any) and + * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects + * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the + * hotplug path before performing hotplug operations. So acquiring that lock + * guarantees mutual exclusion from any currently running hotplug operations. + */ +void cpu_hotplug_disable(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 1; + cpu_maps_update_done(); +} + +void cpu_hotplug_enable(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 0; + cpu_maps_update_done(); +} + #else /* #if CONFIG_HOTPLUG_CPU */ static void cpu_hotplug_begin(void) {} static void cpu_hotplug_done(void) {} @@ -541,36 +562,6 @@ static int __init alloc_frozen_cpus(void) core_initcall(alloc_frozen_cpus); /* - * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU - * hotplug when tasks are about to be frozen. Also, don't allow the freezer - * to continue until any currently running CPU hotplug operation gets - * completed. - * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the - * 'cpu_add_remove_lock'. And this same lock is also taken by the regular - * CPU hotplug path and released only after it is complete. Thus, we - * (and hence the freezer) will block here until any currently running CPU - * hotplug operation gets completed. - */ -void cpu_hotplug_disable_before_freeze(void) -{ - cpu_maps_update_begin(); - cpu_hotplug_disabled = 1; - cpu_maps_update_done(); -} - - -/* - * When tasks have been thawed, re-enable regular CPU hotplug (which had been - * disabled while beginning to freeze tasks). - */ -void cpu_hotplug_enable_after_thaw(void) -{ - cpu_maps_update_begin(); - cpu_hotplug_disabled = 0; - cpu_maps_update_done(); -} - -/* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the @@ -589,12 +580,12 @@ cpu_hotplug_pm_callback(struct notifier_block *nb, case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: - cpu_hotplug_disable_before_freeze(); + cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: - cpu_hotplug_enable_after_thaw(); + cpu_hotplug_enable(); break; default: diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c index 8b86c0c68edf..d5585f5e038e 100644 --- a/kernel/cpu/idle.c +++ b/kernel/cpu/idle.c @@ -40,11 +40,13 @@ __setup("hlt", cpu_idle_nopoll_setup); static inline int cpu_idle_poll(void) { + rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); return 1; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6b41c1899a8b..9dc297faf7c0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4394,6 +4394,64 @@ perf_event_read_event(struct perf_event *event, perf_output_end(&handle); } +typedef int (perf_event_aux_match_cb)(struct perf_event *event, void *data); +typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data); + +static void +perf_event_aux_ctx(struct perf_event_context *ctx, + perf_event_aux_match_cb match, + perf_event_aux_output_cb output, + void *data) +{ + struct perf_event *event; + + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->state < PERF_EVENT_STATE_INACTIVE) + continue; + if (!event_filter_match(event)) + continue; + if (match(event, data)) + output(event, data); + } +} + +static void +perf_event_aux(perf_event_aux_match_cb match, + perf_event_aux_output_cb output, + void *data, + struct perf_event_context *task_ctx) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int ctxn; + + rcu_read_lock(); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->unique_pmu != pmu) + goto next; + perf_event_aux_ctx(&cpuctx->ctx, match, output, data); + if (task_ctx) + goto next; + ctxn = pmu->task_ctx_nr; + if (ctxn < 0) + goto next; + ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); + if (ctx) + perf_event_aux_ctx(ctx, match, output, data); +next: + put_cpu_ptr(pmu->pmu_cpu_context); + } + + if (task_ctx) { + preempt_disable(); + perf_event_aux_ctx(task_ctx, match, output, data); + preempt_enable(); + } + rcu_read_unlock(); +} + /* * task tracking -- fork/exit * @@ -4416,8 +4474,9 @@ struct perf_task_event { }; static void perf_event_task_output(struct perf_event *event, - struct perf_task_event *task_event) + void *data) { + struct perf_task_event *task_event = data; struct perf_output_handle handle; struct perf_sample_data sample; struct task_struct *task = task_event->task; @@ -4445,62 +4504,11 @@ out: task_event->event_id.header.size = size; } -static int perf_event_task_match(struct perf_event *event) -{ - if (event->state < PERF_EVENT_STATE_INACTIVE) - return 0; - - if (!event_filter_match(event)) - return 0; - - if (event->attr.comm || event->attr.mmap || - event->attr.mmap_data || event->attr.task) - return 1; - - return 0; -} - -static void perf_event_task_ctx(struct perf_event_context *ctx, - struct perf_task_event *task_event) +static int perf_event_task_match(struct perf_event *event, + void *data __maybe_unused) { - struct perf_event *event; - - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_task_match(event)) - perf_event_task_output(event, task_event); - } -} - -static void perf_event_task_event(struct perf_task_event *task_event) -{ - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; - struct pmu *pmu; - int ctxn; - - rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_task_ctx(&cpuctx->ctx, task_event); - - ctx = task_event->task_ctx; - if (!ctx) { - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; - ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); - if (ctx) - perf_event_task_ctx(ctx, task_event); - } -next: - put_cpu_ptr(pmu->pmu_cpu_context); - } - if (task_event->task_ctx) - perf_event_task_ctx(task_event->task_ctx, task_event); - - rcu_read_unlock(); + return event->attr.comm || event->attr.mmap || + event->attr.mmap_data || event->attr.task; } static void perf_event_task(struct task_struct *task, @@ -4531,7 +4539,10 @@ static void perf_event_task(struct task_struct *task, }, }; - perf_event_task_event(&task_event); + perf_event_aux(perf_event_task_match, + perf_event_task_output, + &task_event, + task_ctx); } void perf_event_fork(struct task_struct *task) @@ -4557,8 +4568,9 @@ struct perf_comm_event { }; static void perf_event_comm_output(struct perf_event *event, - struct perf_comm_event *comm_event) + void *data) { + struct perf_comm_event *comm_event = data; struct perf_output_handle handle; struct perf_sample_data sample; int size = comm_event->event_id.header.size; @@ -4585,39 +4597,16 @@ out: comm_event->event_id.header.size = size; } -static int perf_event_comm_match(struct perf_event *event) -{ - if (event->state < PERF_EVENT_STATE_INACTIVE) - return 0; - - if (!event_filter_match(event)) - return 0; - - if (event->attr.comm) - return 1; - - return 0; -} - -static void perf_event_comm_ctx(struct perf_event_context *ctx, - struct perf_comm_event *comm_event) +static int perf_event_comm_match(struct perf_event *event, + void *data __maybe_unused) { - struct perf_event *event; - - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_comm_match(event)) - perf_event_comm_output(event, comm_event); - } + return event->attr.comm; } static void perf_event_comm_event(struct perf_comm_event *comm_event) { - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; char comm[TASK_COMM_LEN]; unsigned int size; - struct pmu *pmu; - int ctxn; memset(comm, 0, sizeof(comm)); strlcpy(comm, comm_event->task->comm, sizeof(comm)); @@ -4627,24 +4616,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) comm_event->comm_size = size; comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; - rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_comm_ctx(&cpuctx->ctx, comm_event); - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; - - ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); - if (ctx) - perf_event_comm_ctx(ctx, comm_event); -next: - put_cpu_ptr(pmu->pmu_cpu_context); - } - rcu_read_unlock(); + perf_event_aux(perf_event_comm_match, + perf_event_comm_output, + comm_event, + NULL); } void perf_event_comm(struct task_struct *task) @@ -4706,8 +4682,9 @@ struct perf_mmap_event { }; static void perf_event_mmap_output(struct perf_event *event, - struct perf_mmap_event *mmap_event) + void *data) { + struct perf_mmap_event *mmap_event = data; struct perf_output_handle handle; struct perf_sample_data sample; int size = mmap_event->event_id.header.size; @@ -4734,46 +4711,24 @@ out: } static int perf_event_mmap_match(struct perf_event *event, - struct perf_mmap_event *mmap_event, - int executable) -{ - if (event->state < PERF_EVENT_STATE_INACTIVE) - return 0; - - if (!event_filter_match(event)) - return 0; - - if ((!executable && event->attr.mmap_data) || - (executable && event->attr.mmap)) - return 1; - - return 0; -} - -static void perf_event_mmap_ctx(struct perf_event_context *ctx, - struct perf_mmap_event *mmap_event, - int executable) + void *data) { - struct perf_event *event; + struct perf_mmap_event *mmap_event = data; + struct vm_area_struct *vma = mmap_event->vma; + int executable = vma->vm_flags & VM_EXEC; - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_mmap_match(event, mmap_event, executable)) - perf_event_mmap_output(event, mmap_event); - } + return (!executable && event->attr.mmap_data) || + (executable && event->attr.mmap); } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) { - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; struct vm_area_struct *vma = mmap_event->vma; struct file *file = vma->vm_file; unsigned int size; char tmp[16]; char *buf = NULL; const char *name; - struct pmu *pmu; - int ctxn; memset(tmp, 0, sizeof(tmp)); @@ -4829,27 +4784,10 @@ got_name: mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; - rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, - vma->vm_flags & VM_EXEC); - - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; - - ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); - if (ctx) { - perf_event_mmap_ctx(ctx, mmap_event, - vma->vm_flags & VM_EXEC); - } -next: - put_cpu_ptr(pmu->pmu_cpu_context); - } - rcu_read_unlock(); + perf_event_aux(perf_event_mmap_match, + perf_event_mmap_output, + mmap_event, + NULL); kfree(buf); } diff --git a/kernel/exit.c b/kernel/exit.c index af2eb3cbd499..7bb73f9d09db 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -649,7 +649,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead) * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ forget_original_parent(tsk); - exit_task_namespaces(tsk); write_lock_irq(&tasklist_lock); if (group_dead) @@ -795,6 +794,7 @@ void do_exit(long code) exit_shm(tsk); exit_files(tsk); exit_fs(tsk); + exit_task_namespaces(tsk); exit_task_work(tsk); check_stack_usage(); exit_thread(); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 5a83dde8ca0c..54a4d5223238 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -143,7 +143,10 @@ static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain, * irq_domain_add_simple() - Allocate and register a simple irq_domain. * @of_node: pointer to interrupt controller's device tree node. * @size: total number of irqs in mapping - * @first_irq: first number of irq block assigned to the domain + * @first_irq: first number of irq block assigned to the domain, + * pass zero to assign irqs on-the-fly. This will result in a + * linear IRQ domain so it is important to use irq_create_mapping() + * for each used IRQ, especially when SPARSE_IRQ is enabled. * @ops: map/unmap domain callbacks * @host_data: Controller private data pointer * @@ -191,6 +194,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, /* A linear domain is the default */ return irq_domain_add_linear(of_node, size, ops, host_data); } +EXPORT_SYMBOL_GPL(irq_domain_add_simple); /** * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. @@ -397,11 +401,12 @@ static void irq_domain_disassociate_many(struct irq_domain *domain, while (count--) { int irq = irq_base + count; struct irq_data *irq_data = irq_get_irq_data(irq); - irq_hw_number_t hwirq = irq_data->hwirq; + irq_hw_number_t hwirq; if (WARN_ON(!irq_data || irq_data->domain != domain)) continue; + hwirq = irq_data->hwirq; irq_set_status_flags(irq, IRQ_NOREQUEST); /* remove chip and handler */ diff --git a/kernel/kmod.c b/kernel/kmod.c index 1296e72e4161..8241906c4b61 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -569,6 +569,11 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) int retval = 0; helper_lock(); + if (!sub_info->path) { + retval = -EINVAL; + goto out; + } + if (sub_info->path[0] == '\0') goto out; diff --git a/kernel/module.c b/kernel/module.c index b049939177f6..cab4bce49c23 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2431,10 +2431,10 @@ static void kmemleak_load_module(const struct module *mod, kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); for (i = 1; i < info->hdr->e_shnum; i++) { - const char *name = info->secstrings + info->sechdrs[i].sh_name; - if (!(info->sechdrs[i].sh_flags & SHF_ALLOC)) - continue; - if (!strstarts(name, ".data") && !strstarts(name, ".bss")) + /* Scan all writable sections that's not executable */ + if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || + !(info->sechdrs[i].sh_flags & SHF_WRITE) || + (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) continue; kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, @@ -2769,24 +2769,11 @@ static void find_module_sections(struct module *mod, struct load_info *info) mod->trace_events = section_objs(info, "_ftrace_events", sizeof(*mod->trace_events), &mod->num_trace_events); - /* - * This section contains pointers to allocated objects in the trace - * code and not scanning it leads to false positives. - */ - kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * - mod->num_trace_events, GFP_KERNEL); #endif #ifdef CONFIG_TRACING mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt", sizeof(*mod->trace_bprintk_fmt_start), &mod->num_trace_bprintk_fmt); - /* - * This section contains pointers to allocated objects in the trace - * code and not scanning it leads to false positives. - */ - kmemleak_scan_area(mod->trace_bprintk_fmt_start, - sizeof(*mod->trace_bprintk_fmt_start) * - mod->num_trace_bprintk_fmt, GFP_KERNEL); #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* sechdrs[0].sh_size is always zero */ diff --git a/kernel/printk.c b/kernel/printk.c index fa36e1494420..8212c1aef125 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -363,6 +363,53 @@ static void log_store(int facility, int level, log_next_seq++; } +#ifdef CONFIG_SECURITY_DMESG_RESTRICT +int dmesg_restrict = 1; +#else +int dmesg_restrict; +#endif + +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* + * Unless restricted, we allow "read all" and "get buffer size" + * for everybody. + */ + return type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER; +} + +static int check_syslog_permissions(int type, bool from_file) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (from_file && type != SYSLOG_ACTION_OPEN) + return 0; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + return 0; + /* + * For historical reasons, accept CAP_SYS_ADMIN too, with + * a warning. + */ + if (capable(CAP_SYS_ADMIN)) { + pr_warn_once("%s (%d): Attempt to access syslog with " + "CAP_SYS_ADMIN but no CAP_SYSLOG " + "(deprecated).\n", + current->comm, task_pid_nr(current)); + return 0; + } + return -EPERM; + } + return security_syslog(type); +} + + /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { u64 seq; @@ -620,7 +667,8 @@ static int devkmsg_open(struct inode *inode, struct file *file) if ((file->f_flags & O_ACCMODE) == O_WRONLY) return 0; - err = security_syslog(SYSLOG_ACTION_READ_ALL); + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); if (err) return err; @@ -813,45 +861,6 @@ static inline void boot_delay_msec(int level) } #endif -#ifdef CONFIG_SECURITY_DMESG_RESTRICT -int dmesg_restrict = 1; -#else -int dmesg_restrict; -#endif - -static int syslog_action_restricted(int type) -{ - if (dmesg_restrict) - return 1; - /* Unless restricted, we allow "read all" and "get buffer size" for everybody */ - return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; -} - -static int check_syslog_permissions(int type, bool from_file) -{ - /* - * If this is from /proc/kmsg and we've already opened it, then we've - * already done the capabilities checks at open time. - */ - if (from_file && type != SYSLOG_ACTION_OPEN) - return 0; - - if (syslog_action_restricted(type)) { - if (capable(CAP_SYSLOG)) - return 0; - /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */ - if (capable(CAP_SYS_ADMIN)) { - printk_once(KERN_WARNING "%s (%d): " - "Attempt to access syslog with CAP_SYS_ADMIN " - "but no CAP_SYSLOG (deprecated).\n", - current->comm, task_pid_nr(current)); - return 0; - } - return -EPERM; - } - return 0; -} - #if defined(CONFIG_PRINTK_TIME) static bool printk_time = 1; #else @@ -1249,7 +1258,7 @@ out: SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { - return do_syslog(type, buf, len, SYSLOG_FROM_CALL); + return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* diff --git a/kernel/range.c b/kernel/range.c index 071b0ab455cb..eb911dbce267 100644 --- a/kernel/range.c +++ b/kernel/range.c @@ -48,9 +48,11 @@ int add_range_with_merge(struct range *range, int az, int nr_range, final_start = min(range[i].start, start); final_end = max(range[i].end, end); - range[i].start = final_start; - range[i].end = final_end; - return nr_range; + /* clear it and add it back for further merge */ + range[i].start = 0; + range[i].end = 0; + return add_range_with_merge(range, az, nr_range, + final_start, final_end); } /* Need to add it: */ diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 16ea67925015..35380019f0fc 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1451,9 +1451,9 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); #ifdef CONFIG_PROVE_RCU_DELAY - if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 && + if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 && system_state == SYSTEM_RUNNING) - schedule_timeout_uninterruptible(2); + udelay(200); #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ cond_resched(); } @@ -1613,6 +1613,14 @@ static int __noreturn rcu_gp_kthread(void *arg) } } +static void rsp_wakeup(struct irq_work *work) +{ + struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); + + /* Wake up rcu_gp_kthread() to start the grace period. */ + wake_up(&rsp->gp_wq); +} + /* * Start a new RCU grace period if warranted, re-initializing the hierarchy * in preparation for detecting the next grace period. The caller must hold @@ -1637,8 +1645,12 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, } rsp->gp_flags = RCU_GP_FLAG_INIT; - /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + /* + * We can't do wakeups while holding the rnp->lock, as that + * could cause possible deadlocks with the rq->lock. Deter + * the wakeup to interrupt context. + */ + irq_work_queue(&rsp->wakeup_work); } /* @@ -3235,6 +3247,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, rsp->rda = rda; init_waitqueue_head(&rsp->gp_wq); + init_irq_work(&rsp->wakeup_work, rsp_wakeup); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcutree.h b/kernel/rcutree.h index da77a8f57ff9..4df503470e42 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -27,6 +27,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/seqlock.h> +#include <linux/irq_work.h> /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -442,6 +443,7 @@ struct rcu_state { char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ + struct irq_work wakeup_work; /* Postponed wakeups */ }; /* Values for rcu_state structure's gp_flags field. */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 170814dc418f..3db5a375d8dd 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -88,7 +88,7 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_RCU_NOCB_CPU #ifndef CONFIG_RCU_NOCB_CPU_NONE if (!have_rcu_nocb_mask) { - alloc_bootmem_cpumask_var(&rcu_nocb_mask); + zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); have_rcu_nocb_mask = true; } #ifdef CONFIG_RCU_NOCB_CPU_ZERO @@ -1667,7 +1667,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) rdtp->last_accelerate = jiffies; /* Request timer delay depending on laziness, and round. */ - if (rdtp->all_lazy) { + if (!rdtp->all_lazy) { *dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; } else { diff --git a/kernel/softirq.c b/kernel/softirq.c index b5197dcb0dad..3d6833f125d3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -195,8 +195,12 @@ void local_bh_enable_ip(unsigned long ip) EXPORT_SYMBOL(local_bh_enable_ip); /* - * We restart softirq processing for at most 2 ms, - * and if need_resched() is not set. + * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times, + * but break the loop if need_resched() is set or after 2 ms. + * The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in + * certain cases, such as stop_machine(), jiffies may cease to + * increment and so we need the MAX_SOFTIRQ_RESTART limit as + * well to make sure we eventually return from this method. * * These limits have been established via experimentation. * The two things to balance is latency against fairness - @@ -204,6 +208,7 @@ EXPORT_SYMBOL(local_bh_enable_ip); * should not be able to lock up the box. */ #define MAX_SOFTIRQ_TIME msecs_to_jiffies(2) +#define MAX_SOFTIRQ_RESTART 10 asmlinkage void __do_softirq(void) { @@ -212,6 +217,7 @@ asmlinkage void __do_softirq(void) unsigned long end = jiffies + MAX_SOFTIRQ_TIME; int cpu; unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; /* * Mask out PF_MEMALLOC s current task context is borrowed for the @@ -265,7 +271,8 @@ restart: pending = local_softirq_pending(); if (pending) { - if (time_before(jiffies, end) && !need_resched()) + if (time_before(jiffies, end) && !need_resched() && + --max_restart) goto restart; wakeup_softirqd(); diff --git a/kernel/sys.c b/kernel/sys.c index b95d3c72ba21..2bbd9a73b54c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -362,6 +362,29 @@ int unregister_reboot_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_reboot_notifier); +/* Add backwards compatibility for stable trees. */ +#ifndef PF_NO_SETAFFINITY +#define PF_NO_SETAFFINITY PF_THREAD_BOUND +#endif + +static void migrate_to_reboot_cpu(void) +{ + /* The boot cpu is always logical cpu 0 */ + int cpu = 0; + + cpu_hotplug_disable(); + + /* Make certain the cpu I'm about to reboot on is online */ + if (!cpu_online(cpu)) + cpu = cpumask_first(cpu_online_mask); + + /* Prevent races with other tasks migrating this task */ + current->flags |= PF_NO_SETAFFINITY; + + /* Make certain I only run on the appropriate processor */ + set_cpus_allowed_ptr(current, cpumask_of(cpu)); +} + /** * kernel_restart - reboot the system * @cmd: pointer to buffer containing command to execute for restart @@ -373,7 +396,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier); void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); - disable_nonboot_cpus(); + migrate_to_reboot_cpu(); syscore_shutdown(); if (!cmd) printk(KERN_EMERG "Restarting system.\n"); @@ -400,7 +423,7 @@ static void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); - disable_nonboot_cpus(); + migrate_to_reboot_cpu(); syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); @@ -419,7 +442,7 @@ void kernel_power_off(void) kernel_shutdown_prepare(SYSTEM_POWER_OFF); if (pm_power_off_prepare) pm_power_off_prepare(); - disable_nonboot_cpus(); + migrate_to_reboot_cpu(); syscore_shutdown(); printk(KERN_EMERG "Power down.\n"); kmsg_dump(KMSG_DUMP_POWEROFF); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index e4c07b0692bb..70f27e89012b 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,11 +12,6 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool -# Platforms has a persistent clock -config ALWAYS_USE_PERSISTENT_CLOCK - bool - default n - # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 12ff13a838c6..8f5b3b98577b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -874,7 +874,6 @@ static void hardpps_update_phase(long error) void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) { struct pps_normtime pts_norm, freq_norm; - unsigned long flags; pts_norm = pps_normalize_ts(*phase_ts); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 206bbfb34e09..0c739423b0f9 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -511,6 +511,12 @@ again: } } + /* + * Remove the current cpu from the pending mask. The event is + * delivered immediately in tick_do_broadcast() ! + */ + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask); + /* Take care of enforced broadcast requests */ cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask); cpumask_clear(tick_broadcast_force_mask); @@ -575,8 +581,8 @@ void tick_broadcast_oneshot_control(unsigned long reason) raw_spin_lock_irqsave(&tick_broadcast_lock, flags); if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { - WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { + WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); /* * We only reprogram the broadcast timer if we @@ -786,11 +792,11 @@ bool tick_broadcast_oneshot_available(void) void __init tick_broadcast_init(void) { - alloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); - alloc_cpumask_var(&tmpmask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); #ifdef CONFIG_TICK_ONESHOT - alloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); - alloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); - alloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); #endif } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index bc67d4245e1d..f4208138fbf4 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -717,6 +717,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) tick_do_timer_cpu = TICK_DO_TIMER_NONE; + return false; } if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) @@ -1168,7 +1169,7 @@ void tick_cancel_sched_timer(int cpu) hrtimer_cancel(&ts->sched_timer); # endif - ts->nohz_mode = NOHZ_MODE_INACTIVE; + memset(ts, 0, sizeof(*ts)); } #endif diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 98cd470bbe49..baeeb5c87cf1 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -975,6 +975,14 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); + /* + * On some systems the persistent_clock can not be detected at + * timekeeping_init by its return value, so if we see a valid + * value returned, update the persistent_clock_exists flag. + */ + if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) + persistent_clock_exist = true; + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); diff --git a/kernel/timer.c b/kernel/timer.c index a860bba34412..15ffdb3f1948 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1539,12 +1539,12 @@ static int __cpuinit init_timers_cpu(int cpu) boot_done = 1; base = &boot_tvec_bases; } + spin_lock_init(&base->lock); tvec_base_done[cpu] = 1; } else { base = per_cpu(tvec_bases, cpu); } - spin_lock_init(&base->lock); for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b549b0f5b977..6c508ff33c62 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -120,22 +120,22 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); /* * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw() is that elements removed from this list + * can use rcu_dereference_raw_notrace() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw() calls are needed to handle + * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ #define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw(list); \ + op = rcu_dereference_raw_notrace(list); \ do /* * Optimized for just a single item in the list (as that is the normal case). */ #define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw((op)->next)) && \ + while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ unlikely((op) != &ftrace_list_end)) static inline void ftrace_ops_init(struct ftrace_ops *ops) @@ -779,7 +779,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) if (hlist_empty(hhd)) return NULL; - hlist_for_each_entry_rcu(rec, hhd, node) { + hlist_for_each_entry_rcu_notrace(rec, hhd, node) { if (rec->ip == ip) return rec; } @@ -1165,7 +1165,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) hhd = &hash->buckets[key]; - hlist_for_each_entry_rcu(entry, hhd, hlist) { + hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) { if (entry->ip == ip) return entry; } @@ -1422,8 +1422,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) struct ftrace_hash *notrace_hash; int ret; - filter_hash = rcu_dereference_raw(ops->filter_hash); - notrace_hash = rcu_dereference_raw(ops->notrace_hash); + filter_hash = rcu_dereference_raw_notrace(ops->filter_hash); + notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash); if ((ftrace_hash_empty(filter_hash) || ftrace_lookup_ip(filter_hash, ip)) && @@ -2920,7 +2920,7 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, * on the hash. rcu_read_lock is too dangerous here. */ preempt_disable_notrace(); - hlist_for_each_entry_rcu(entry, hhd, node) { + hlist_for_each_entry_rcu_notrace(entry, hhd, node) { if (entry->ip == ip) entry->ops->func(ip, parent_ip, &entry->data); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b59aea2c48c2..e444ff88f0a4 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -620,6 +620,9 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, if (cpu == RING_BUFFER_ALL_CPUS) work = &buffer->irq_work; else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ae6fa2d1cdf7..e71a8be4a6ee 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -652,8 +652,6 @@ static struct { ARCH_TRACE_CLOCKS }; -int trace_clock_id; - /* * trace_parser_get_init - gets the buffer for trace parser */ @@ -843,7 +841,15 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN); max_data->pid = tsk->pid; - max_data->uid = task_uid(tsk); + /* + * If tsk == current, then use current_uid(), as that does not use + * RCU. The irq tracer can be called out of RCU scope. + */ + if (tsk == current) + max_data->uid = current_uid(); + else + max_data->uid = task_uid(tsk); + max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; max_data->policy = tsk->policy; max_data->rt_priority = tsk->rt_priority; @@ -2818,7 +2824,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ - if (trace_clocks[trace_clock_id].in_ns) + if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; /* stop the trace while dumping if we are not opening "snapshot" */ @@ -3817,7 +3823,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->iter_flags |= TRACE_FILE_LAT_FMT; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ - if (trace_clocks[trace_clock_id].in_ns) + if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; iter->cpu_file = tc->cpu; @@ -5087,7 +5093,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); - if (trace_clocks[trace_clock_id].in_ns) { + if (trace_clocks[tr->clock_id].in_ns) { /* local or global for trace_clock */ t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); @@ -6216,10 +6222,15 @@ __init static int tracer_alloc_buffers(void) trace_init_cmdlines(); - register_tracer(&nop_trace); - + /* + * register_tracer() might reference current_trace, so it + * needs to be set before we register anything. This is + * just a bootstrap of current_trace anyway. + */ global_trace.current_trace = &nop_trace; + register_tracer(&nop_trace); + /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 711ca7d3e7f1..20572ed88c5c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -700,8 +700,6 @@ enum print_line_t print_trace_line(struct trace_iterator *iter); extern unsigned long trace_flags; -extern int trace_clock_id; - /* Standard output formatting function used for function return traces */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7a0cf68027cc..27963e2bf4bf 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2072,8 +2072,10 @@ event_enable_func(struct ftrace_hash *hash, out_reg: /* Don't let event modules unload while probe registered */ ret = try_module_get(file->event_call->mod); - if (!ret) + if (!ret) { + ret = -EBUSY; goto out_free; + } ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index a6361178de5a..e1b653f7e1ca 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -750,7 +750,11 @@ static int filter_set_pred(struct event_filter *filter, static void __free_preds(struct event_filter *filter) { + int i; + if (filter->preds) { + for (i = 0; i < filter->n_preds; i++) + kfree(filter->preds[i].ops); kfree(filter->preds); filter->preds = NULL; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 636d45fe69b3..9f46e98ba8f2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -35,7 +35,7 @@ struct trace_probe { const char *symbol; /* symbol name */ struct ftrace_event_class class; struct ftrace_event_call call; - struct ftrace_event_file **files; + struct ftrace_event_file * __rcu *files; ssize_t size; /* trace entry size */ unsigned int nr_args; struct probe_arg args[]; @@ -185,9 +185,14 @@ static struct trace_probe *find_trace_probe(const char *event, static int trace_probe_nr_files(struct trace_probe *tp) { - struct ftrace_event_file **file = tp->files; + struct ftrace_event_file **file; int ret = 0; + /* + * Since all tp->files updater is protected by probe_enable_lock, + * we don't need to lock an rcu_read_lock. + */ + file = rcu_dereference_raw(tp->files); if (file) while (*(file++)) ret++; @@ -209,9 +214,10 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) mutex_lock(&probe_enable_lock); if (file) { - struct ftrace_event_file **new, **old = tp->files; + struct ftrace_event_file **new, **old; int n = trace_probe_nr_files(tp); + old = rcu_dereference_raw(tp->files); /* 1 is for new one and 1 is for stopper */ new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *), GFP_KERNEL); @@ -251,11 +257,17 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) static int trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file) { + struct ftrace_event_file **files; int i; - if (tp->files) { - for (i = 0; tp->files[i]; i++) - if (tp->files[i] == file) + /* + * Since all tp->files updater is protected by probe_enable_lock, + * we don't need to lock an rcu_read_lock. + */ + files = rcu_dereference_raw(tp->files); + if (files) { + for (i = 0; files[i]; i++) + if (files[i] == file) return i; } @@ -274,10 +286,11 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) mutex_lock(&probe_enable_lock); if (file) { - struct ftrace_event_file **new, **old = tp->files; + struct ftrace_event_file **new, **old; int n = trace_probe_nr_files(tp); int i, j; + old = rcu_dereference_raw(tp->files); if (n == 0 || trace_probe_file_index(tp, file) < 0) { ret = -EINVAL; goto out_unlock; @@ -872,9 +885,16 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs, static __kprobes void kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs) { - struct ftrace_event_file **file = tp->files; + /* + * Note: preempt is already disabled around the kprobe handler. + * However, we still need an smp_read_barrier_depends() corresponding + * to smp_wmb() in rcu_assign_pointer() to access the pointer. + */ + struct ftrace_event_file **file = rcu_dereference_raw(tp->files); + + if (unlikely(!file)) + return; - /* Note: preempt is already disabled around the kprobe handler */ while (*file) { __kprobe_trace_func(tp, regs, *file); file++; @@ -925,9 +945,16 @@ static __kprobes void kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, struct pt_regs *regs) { - struct ftrace_event_file **file = tp->files; + /* + * Note: preempt is already disabled around the kprobe handler. + * However, we still need an smp_read_barrier_depends() corresponding + * to smp_wmb() in rcu_assign_pointer() to access the pointer. + */ + struct ftrace_event_file **file = rcu_dereference_raw(tp->files); + + if (unlikely(!file)) + return; - /* Note: preempt is already disabled around the kprobe handler */ while (*file) { __kretprobe_trace_func(tp, ri, regs, *file); file++; @@ -935,7 +962,7 @@ kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, } /* Event entry printers */ -enum print_line_t +static enum print_line_t print_kprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { @@ -971,7 +998,7 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -enum print_line_t +static enum print_line_t print_kretprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 55e2cf66967b..2901e3b88590 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1159,7 +1159,7 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4aa9f5bc6b2d..ee8e29a2320c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -296,7 +296,7 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; struct workqueue_struct *system_wq __read_mostly; -EXPORT_SYMBOL_GPL(system_wq); +EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __read_mostly; @@ -1411,7 +1411,7 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(queue_work_on); +EXPORT_SYMBOL(queue_work_on); void delayed_work_timer_fn(unsigned long __data) { @@ -1485,7 +1485,7 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(queue_delayed_work_on); +EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU @@ -2059,6 +2059,7 @@ static bool manage_workers(struct worker *worker) if (unlikely(!mutex_trylock(&pool->manager_mutex))) { spin_unlock_irq(&pool->lock); mutex_lock(&pool->manager_mutex); + spin_lock_irq(&pool->lock); ret = true; } @@ -4311,6 +4312,12 @@ bool current_is_workqueue_rescuer(void) * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * + * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. + * Note that both per-cpu and unbound workqueues may be associated with + * multiple pool_workqueues which have separate congested states. A + * workqueue being congested on one CPU doesn't mean the workqueue is also + * contested on other CPUs / NUMA nodes. + * * RETURNS: * %true if congested, %false otherwise. */ @@ -4321,6 +4328,9 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) rcu_read_lock_sched(); + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); + if (!(wq->flags & WQ_UNBOUND)) pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); else @@ -4895,7 +4905,8 @@ static void __init wq_numa_init(void) BUG_ON(!tbl); for_each_node(node) - BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node)); + BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, + node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); |