diff options
Diffstat (limited to 'kernel')
53 files changed, 1072 insertions, 307 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index baa55e50a315..f0c40bf49d9f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -18,6 +18,17 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE) endif +# Prevents flicker of uninteresting __do_softirq()/__local_bh_disable_ip() +# in coverage traces. +KCOV_INSTRUMENT_softirq.o := n +# These are called from save_stack_trace() on slub debug path, +# and produce insane amounts of uninteresting coverage. +KCOV_INSTRUMENT_module.o := n +KCOV_INSTRUMENT_extable.o := n +# Don't self-instrument. +KCOV_INSTRUMENT_kcov.o := n +KASAN_SANITIZE_kcov.o := n + # cond_syscall is currently not LTO compatible CFLAGS_sys_ni.o = $(DISABLE_LTO) @@ -68,6 +79,7 @@ obj-$(CONFIG_AUDITSYSCALL) += auditsc.o obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o audit_fsnotify.o obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_GCOV_KERNEL) += gcov/ +obj-$(CONFIG_KCOV) += kcov.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 195ffaee50b9..7d0e3cf8abe1 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2412,8 +2412,8 @@ void __audit_seccomp(unsigned long syscall, long signr, int code) return; audit_log_task(ab); audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x", - signr, syscall_get_arch(), syscall, is_compat_task(), - KSTK_EIP(current), code); + signr, syscall_get_arch(), syscall, + in_compat_syscall(), KSTK_EIP(current), code); audit_log_end(ab); } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 972d9a8e4ac4..be0abf669ced 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -27,6 +27,7 @@ #include <linux/random.h> #include <linux/moduleloader.h> #include <linux/bpf.h> +#include <linux/frame.h> #include <asm/unaligned.h> @@ -649,6 +650,7 @@ load_byte: WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); return 0; } +STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3fe02c152799..671dc05c0b0f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -59,6 +59,9 @@ #include <linux/delay.h> #include <linux/atomic.h> #include <linux/cpuset.h> +#include <linux/proc_ns.h> +#include <linux/nsproxy.h> +#include <linux/proc_ns.h> #include <net/sock.h> /* @@ -215,6 +218,15 @@ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_free_callback __read_mostly; +/* cgroup namespace for init task */ +struct cgroup_namespace init_cgroup_ns = { + .count = { .counter = 2, }, + .user_ns = &init_user_ns, + .ns.ops = &cgroupns_operations, + .ns.inum = PROC_CGROUP_INIT_INO, + .root_cset = &init_css_set, +}; + /* Ditto for the can_fork callback. */ static u16 have_canfork_callback __read_mostly; @@ -2002,6 +2014,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, { bool is_v2 = fs_type == &cgroup2_fs_type; struct super_block *pinned_sb = NULL; + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup_subsys *ss; struct cgroup_root *root; struct cgroup_sb_opts opts; @@ -2010,6 +2023,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, int i; bool new_sb; + get_cgroup_ns(ns); + + /* Check if the caller has permission to mount. */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { + put_cgroup_ns(ns); + return ERR_PTR(-EPERM); + } + /* * The first time anyone tries to mount a cgroup, enable the list * linking each css_set to its tasks and fix up all existing tasks. @@ -2020,6 +2041,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, if (is_v2) { if (data) { pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); + put_cgroup_ns(ns); return ERR_PTR(-EINVAL); } cgrp_dfl_visible = true; @@ -2125,6 +2147,16 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, goto out_unlock; } + /* + * We know this subsystem has not yet been bound. Users in a non-init + * user namespace may only mount hierarchies with no bound subsystems, + * i.e. 'none,name=user1' + */ + if (!opts.none && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_unlock; + } + root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) { ret = -ENOMEM; @@ -2143,12 +2175,37 @@ out_free: kfree(opts.release_agent); kfree(opts.name); - if (ret) + if (ret) { + put_cgroup_ns(ns); return ERR_PTR(ret); + } out_mount: dentry = kernfs_mount(fs_type, flags, root->kf_root, is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC, &new_sb); + + /* + * In non-init cgroup namespace, instead of root cgroup's + * dentry, we return the dentry corresponding to the + * cgroupns->root_cgrp. + */ + if (!IS_ERR(dentry) && ns != &init_cgroup_ns) { + struct dentry *nsdentry; + struct cgroup *cgrp; + + mutex_lock(&cgroup_mutex); + spin_lock_bh(&css_set_lock); + + cgrp = cset_cgroup_from_root(ns->root_cset, root); + + spin_unlock_bh(&css_set_lock); + mutex_unlock(&cgroup_mutex); + + nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb); + dput(dentry); + dentry = nsdentry; + } + if (IS_ERR(dentry) || !new_sb) cgroup_put(&root->cgrp); @@ -2161,6 +2218,7 @@ out_mount: deactivate_super(pinned_sb); } + put_cgroup_ns(ns); return dentry; } @@ -2189,14 +2247,45 @@ static struct file_system_type cgroup_fs_type = { .name = "cgroup", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; +static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) +{ + struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); + int ret; + + ret = kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); + if (ret < 0 || ret >= buflen) + return NULL; + return buf; +} + +char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) +{ + char *ret; + + mutex_lock(&cgroup_mutex); + spin_lock_bh(&css_set_lock); + + ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); + + spin_unlock_bh(&css_set_lock); + mutex_unlock(&cgroup_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(cgroup_path_ns); + /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task @@ -2224,7 +2313,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) if (root) { cgrp = task_cgroup_from_root(task, root); - path = cgroup_path(cgrp, buf, buflen); + path = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); } else { /* if no hierarchy exists, everyone is in "/" */ if (strlcpy(buf, "/", buflen) < buflen) @@ -5450,6 +5539,8 @@ int __init cgroup_init(void) BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); + get_user_ns(init_cgroup_ns.user_ns); + mutex_lock(&cgroup_mutex); /* @@ -5601,7 +5692,8 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { - path = cgroup_path(cgrp, buf, PATH_MAX); + path = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, + current->nsproxy->cgroup_ns); if (!path) { retval = -ENAMETOOLONG; goto out_unlock; @@ -5886,7 +5978,9 @@ static void cgroup_release_agent(struct work_struct *work) if (!pathbuf || !agentbuf) goto out; - path = cgroup_path(cgrp, pathbuf, PATH_MAX); + spin_lock_bh(&css_set_lock); + path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); + spin_unlock_bh(&css_set_lock); if (!path) goto out; @@ -6098,6 +6192,133 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ +/* cgroup namespaces */ + +static struct cgroup_namespace *alloc_cgroup_ns(void) +{ + struct cgroup_namespace *new_ns; + int ret; + + new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL); + if (!new_ns) + return ERR_PTR(-ENOMEM); + ret = ns_alloc_inum(&new_ns->ns); + if (ret) { + kfree(new_ns); + return ERR_PTR(ret); + } + atomic_set(&new_ns->count, 1); + new_ns->ns.ops = &cgroupns_operations; + return new_ns; +} + +void free_cgroup_ns(struct cgroup_namespace *ns) +{ + put_css_set(ns->root_cset); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + kfree(ns); +} +EXPORT_SYMBOL(free_cgroup_ns); + +struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + struct cgroup_namespace *new_ns; + struct css_set *cset; + + BUG_ON(!old_ns); + + if (!(flags & CLONE_NEWCGROUP)) { + get_cgroup_ns(old_ns); + return old_ns; + } + + /* Allow only sysadmin to create cgroup namespace. */ + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + mutex_lock(&cgroup_mutex); + spin_lock_bh(&css_set_lock); + + cset = task_css_set(current); + get_css_set(cset); + + spin_unlock_bh(&css_set_lock); + mutex_unlock(&cgroup_mutex); + + new_ns = alloc_cgroup_ns(); + if (IS_ERR(new_ns)) { + put_css_set(cset); + return new_ns; + } + + new_ns->user_ns = get_user_ns(user_ns); + new_ns->root_cset = cset; + + return new_ns; +} + +static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) +{ + return container_of(ns, struct cgroup_namespace, ns); +} + +static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns) +{ + struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); + + if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) || + !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Don't need to do anything if we are attaching to our own cgroupns. */ + if (cgroup_ns == nsproxy->cgroup_ns) + return 0; + + get_cgroup_ns(cgroup_ns); + put_cgroup_ns(nsproxy->cgroup_ns); + nsproxy->cgroup_ns = cgroup_ns; + + return 0; +} + +static struct ns_common *cgroupns_get(struct task_struct *task) +{ + struct cgroup_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->cgroup_ns; + get_cgroup_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void cgroupns_put(struct ns_common *ns) +{ + put_cgroup_ns(to_cg_ns(ns)); +} + +const struct proc_ns_operations cgroupns_operations = { + .name = "cgroup", + .type = CLONE_NEWCGROUP, + .get = cgroupns_get, + .put = cgroupns_put, + .install = cgroupns_install, +}; + +static __init int cgroup_namespaces_init(void) +{ + return 0; +} +subsys_initcall(cgroup_namespaces_init); + #ifdef CONFIG_CGROUP_DEBUG static struct cgroup_subsys_state * debug_css_alloc(struct cgroup_subsys_state *parent_css) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 90899837ea78..00ab5c2b7c5b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2714,10 +2714,10 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, goto out; retval = -ENAMETOOLONG; - rcu_read_lock(); - css = task_css(tsk, cpuset_cgrp_id); - p = cgroup_path(css->cgroup, buf, PATH_MAX); - rcu_read_unlock(); + css = task_get_css(tsk, cpuset_cgrp_id); + p = cgroup_path_ns(css->cgroup, buf, PATH_MAX, + current->nsproxy->cgroup_ns); + css_put(css); if (!p) goto out_free; seq_puts(m, p); diff --git a/kernel/events/core.c b/kernel/events/core.c index 712570dddacd..de24fbce5277 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -376,8 +376,11 @@ static void update_perf_cpu_limits(void) u64 tmp = perf_sample_period_ns; tmp *= sysctl_perf_cpu_time_max_percent; - do_div(tmp, 100); - ACCESS_ONCE(perf_sample_allowed_ns) = tmp; + tmp = div_u64(tmp, 100); + if (!tmp) + tmp = 1; + + WRITE_ONCE(perf_sample_allowed_ns, tmp); } static int perf_rotate_context(struct perf_cpu_context *cpuctx); @@ -409,7 +412,13 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, if (ret || !write) return ret; - update_perf_cpu_limits(); + if (sysctl_perf_cpu_time_max_percent == 100) { + printk(KERN_WARNING + "perf: Dynamic interrupt throttling disabled, can hang your system!\n"); + WRITE_ONCE(perf_sample_allowed_ns, 0); + } else { + update_perf_cpu_limits(); + } return 0; } @@ -423,62 +432,68 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, #define NR_ACCUMULATED_SAMPLES 128 static DEFINE_PER_CPU(u64, running_sample_length); +static u64 __report_avg; +static u64 __report_allowed; + static void perf_duration_warn(struct irq_work *w) { - u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns); - u64 avg_local_sample_len; - u64 local_samples_len; - - local_samples_len = __this_cpu_read(running_sample_length); - avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES; - printk_ratelimited(KERN_WARNING - "perf interrupt took too long (%lld > %lld), lowering " - "kernel.perf_event_max_sample_rate to %d\n", - avg_local_sample_len, allowed_ns >> 1, - sysctl_perf_event_sample_rate); + "perf: interrupt took too long (%lld > %lld), lowering " + "kernel.perf_event_max_sample_rate to %d\n", + __report_avg, __report_allowed, + sysctl_perf_event_sample_rate); } static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn); void perf_sample_event_took(u64 sample_len_ns) { - u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns); - u64 avg_local_sample_len; - u64 local_samples_len; + u64 max_len = READ_ONCE(perf_sample_allowed_ns); + u64 running_len; + u64 avg_len; + u32 max; - if (allowed_ns == 0) + if (max_len == 0) return; - /* decay the counter by 1 average sample */ - local_samples_len = __this_cpu_read(running_sample_length); - local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES; - local_samples_len += sample_len_ns; - __this_cpu_write(running_sample_length, local_samples_len); + /* Decay the counter by 1 average sample. */ + running_len = __this_cpu_read(running_sample_length); + running_len -= running_len/NR_ACCUMULATED_SAMPLES; + running_len += sample_len_ns; + __this_cpu_write(running_sample_length, running_len); /* - * note: this will be biased artifically low until we have - * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us + * Note: this will be biased artifically low until we have + * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us * from having to maintain a count. */ - avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES; - - if (avg_local_sample_len <= allowed_ns) + avg_len = running_len/NR_ACCUMULATED_SAMPLES; + if (avg_len <= max_len) return; - if (max_samples_per_tick <= 1) - return; + __report_avg = avg_len; + __report_allowed = max_len; - max_samples_per_tick = DIV_ROUND_UP(max_samples_per_tick, 2); - sysctl_perf_event_sample_rate = max_samples_per_tick * HZ; - perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; + /* + * Compute a throttle threshold 25% below the current duration. + */ + avg_len += avg_len / 4; + max = (TICK_NSEC / 100) * sysctl_perf_cpu_time_max_percent; + if (avg_len < max) + max /= (u32)avg_len; + else + max = 1; - update_perf_cpu_limits(); + WRITE_ONCE(perf_sample_allowed_ns, avg_len); + WRITE_ONCE(max_samples_per_tick, max); + + sysctl_perf_event_sample_rate = max * HZ; + perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; if (!irq_work_queue(&perf_duration_work)) { - early_printk("perf interrupt took too long (%lld > %lld), lowering " + early_printk("perf: interrupt took too long (%lld > %lld), lowering " "kernel.perf_event_max_sample_rate to %d\n", - avg_local_sample_len, allowed_ns >> 1, + __report_avg, __report_allowed, sysctl_perf_event_sample_rate); } } @@ -4210,6 +4225,14 @@ static void __perf_event_period(struct perf_event *event, active = (event->state == PERF_EVENT_STATE_ACTIVE); if (active) { perf_pmu_disable(ctx->pmu); + /* + * We could be throttled; unthrottle now to avoid the tick + * trying to unthrottle while we already re-started the event. + */ + if (event->hw.interrupts == MAX_INTERRUPTS) { + event->hw.interrupts = 0; + perf_log_throttle(event, 1); + } event->pmu->stop(event, PERF_EF_UPDATE); } @@ -9426,10 +9449,29 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: + /* + * This must be done before the CPU comes alive, because the + * moment we can run tasks we can encounter (software) events. + * + * Specifically, someone can have inherited events on kthreadd + * or a pre-existing worker thread that gets re-bound. + */ perf_event_init_cpu(cpu); break; case CPU_DOWN_PREPARE: + /* + * This must be done before the CPU dies because after that an + * active event might want to IPI the CPU and that'll not work + * so great for dead CPUs. + * + * XXX smp_call_function_single() return -ENXIO without a warn + * so we could possibly deal with this. + * + * This is safe against new events arriving because + * sys_perf_event_open() serializes against hotplug using + * get_online_cpus(). + */ perf_event_exit_cpu(cpu); break; default: diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 1faad2cfdb9e..c61f0cbd308b 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -746,8 +746,10 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) rb->user_page = all_buf; rb->data_pages[0] = all_buf + PAGE_SIZE; - rb->page_order = ilog2(nr_pages); - rb->nr_pages = !!nr_pages; + if (nr_pages) { + rb->nr_pages = 1; + rb->page_order = ilog2(nr_pages); + } ring_buffer_init(rb, watermark, flags); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 5f6ce931f1ea..220fc17b9718 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -299,7 +299,7 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, retry: /* Read the page with vaddr into memory */ - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); if (ret <= 0) return ret; @@ -1701,7 +1701,13 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) if (likely(result == 0)) goto out; - result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); + /* + * The NULL 'tsk' here ensures that any faults that occur here + * will not be accounted to the task. 'mm' *is* current->mm, + * but we treat this as a 'remote' access since it is + * essentially a kernel access to the memory. + */ + result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (result < 0) return result; diff --git a/kernel/exit.c b/kernel/exit.c index 10e088237fed..fd90195667e1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -53,6 +53,7 @@ #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> +#include <linux/kcov.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -434,7 +435,7 @@ static void exit_mm(struct task_struct *tsk) mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) - exit_oom_victim(); + exit_oom_victim(tsk); } static struct task_struct *find_alive_thread(struct task_struct *p) @@ -655,6 +656,7 @@ void do_exit(long code) TASKS_RCU(int tasks_rcu_i); profile_task_exit(tsk); + kcov_task_exit(tsk); WARN_ON(blk_needs_flush_plug(tsk)); diff --git a/kernel/fork.c b/kernel/fork.c index accb7221d547..d277e83ed3e0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -75,6 +75,7 @@ #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> +#include <linux/kcov.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -392,6 +393,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) account_kernel_stack(ti, 1); + kcov_task_init(tsk); + return tsk; free_ti: @@ -1892,7 +1895,7 @@ static int check_unshare_flags(unsigned long unshare_flags) if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| - CLONE_NEWUSER|CLONE_NEWPID)) + CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing diff --git a/kernel/hung_task.c b/kernel/hung_task.c index e0f90c2b57aa..d234022805dc 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -185,10 +185,12 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) rcu_read_unlock(); } -static unsigned long timeout_jiffies(unsigned long timeout) +static long hung_timeout_jiffies(unsigned long last_checked, + unsigned long timeout) { /* timeout of 0 will disable the watchdog */ - return timeout ? timeout * HZ : MAX_SCHEDULE_TIMEOUT; + return timeout ? last_checked - jiffies + timeout * HZ : + MAX_SCHEDULE_TIMEOUT; } /* @@ -224,18 +226,21 @@ EXPORT_SYMBOL_GPL(reset_hung_task_detector); */ static int watchdog(void *dummy) { + unsigned long hung_last_checked = jiffies; + set_user_nice(current, 0); for ( ; ; ) { unsigned long timeout = sysctl_hung_task_timeout_secs; + long t = hung_timeout_jiffies(hung_last_checked, timeout); - while (schedule_timeout_interruptible(timeout_jiffies(timeout))) - timeout = sysctl_hung_task_timeout_secs; - - if (atomic_xchg(&reset_hung_task, 0)) + if (t <= 0) { + if (!atomic_xchg(&reset_hung_task, 0)) + check_hung_uninterruptible_tasks(timeout); + hung_last_checked = jiffies; continue; - - check_hung_uninterruptible_tasks(timeout); + } + schedule_timeout_interruptible(t); } return 0; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 64731e84c982..cc1cc641d653 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1322,8 +1322,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (nmsk != omsk) /* hope the handler works with current trigger mode */ - pr_warning("irq %d uses trigger mode %u; requested %u\n", - irq, nmsk, omsk); + pr_warn("irq %d uses trigger mode %u; requested %u\n", + irq, nmsk, omsk); } *old_ptr = new; diff --git a/kernel/kcov.c b/kernel/kcov.c new file mode 100644 index 000000000000..3efbee0834a8 --- /dev/null +++ b/kernel/kcov.c @@ -0,0 +1,273 @@ +#define pr_fmt(fmt) "kcov: " fmt + +#include <linux/compiler.h> +#include <linux/types.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/vmalloc.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/kcov.h> + +/* + * kcov descriptor (one per opened debugfs file). + * State transitions of the descriptor: + * - initial state after open() + * - then there must be a single ioctl(KCOV_INIT_TRACE) call + * - then, mmap() call (several calls are allowed but not useful) + * - then, repeated enable/disable for a task (only one task a time allowed) + */ +struct kcov { + /* + * Reference counter. We keep one for: + * - opened file descriptor + * - task with enabled coverage (we can't unwire it from another task) + */ + atomic_t refcount; + /* The lock protects mode, size, area and t. */ + spinlock_t lock; + enum kcov_mode mode; + /* Size of arena (in long's for KCOV_MODE_TRACE). */ + unsigned size; + /* Coverage buffer shared with user space. */ + void *area; + /* Task for which we collect coverage, or NULL. */ + struct task_struct *t; +}; + +/* + * Entry point from instrumented code. + * This is called once per basic-block/edge. + */ +void __sanitizer_cov_trace_pc(void) +{ + struct task_struct *t; + enum kcov_mode mode; + + t = current; + /* + * We are interested in code coverage as a function of a syscall inputs, + * so we ignore code executed in interrupts. + */ + if (!t || in_interrupt()) + return; + mode = READ_ONCE(t->kcov_mode); + if (mode == KCOV_MODE_TRACE) { + unsigned long *area; + unsigned long pos; + + /* + * There is some code that runs in interrupts but for which + * in_interrupt() returns false (e.g. preempt_schedule_irq()). + * READ_ONCE()/barrier() effectively provides load-acquire wrt + * interrupts, there are paired barrier()/WRITE_ONCE() in + * kcov_ioctl_locked(). + */ + barrier(); + area = t->kcov_area; + /* The first word is number of subsequent PCs. */ + pos = READ_ONCE(area[0]) + 1; + if (likely(pos < t->kcov_size)) { + area[pos] = _RET_IP_; + WRITE_ONCE(area[0], pos); + } + } +} +EXPORT_SYMBOL(__sanitizer_cov_trace_pc); + +static void kcov_get(struct kcov *kcov) +{ + atomic_inc(&kcov->refcount); +} + +static void kcov_put(struct kcov *kcov) +{ + if (atomic_dec_and_test(&kcov->refcount)) { + vfree(kcov->area); + kfree(kcov); + } +} + +void kcov_task_init(struct task_struct *t) +{ + t->kcov_mode = KCOV_MODE_DISABLED; + t->kcov_size = 0; + t->kcov_area = NULL; + t->kcov = NULL; +} + +void kcov_task_exit(struct task_struct *t) +{ + struct kcov *kcov; + + kcov = t->kcov; + if (kcov == NULL) + return; + spin_lock(&kcov->lock); + if (WARN_ON(kcov->t != t)) { + spin_unlock(&kcov->lock); + return; + } + /* Just to not leave dangling references behind. */ + kcov_task_init(t); + kcov->t = NULL; + spin_unlock(&kcov->lock); + kcov_put(kcov); +} + +static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) +{ + int res = 0; + void *area; + struct kcov *kcov = vma->vm_file->private_data; + unsigned long size, off; + struct page *page; + + area = vmalloc_user(vma->vm_end - vma->vm_start); + if (!area) + return -ENOMEM; + + spin_lock(&kcov->lock); + size = kcov->size * sizeof(unsigned long); + if (kcov->mode == KCOV_MODE_DISABLED || vma->vm_pgoff != 0 || + vma->vm_end - vma->vm_start != size) { + res = -EINVAL; + goto exit; + } + if (!kcov->area) { + kcov->area = area; + vma->vm_flags |= VM_DONTEXPAND; + spin_unlock(&kcov->lock); + for (off = 0; off < size; off += PAGE_SIZE) { + page = vmalloc_to_page(kcov->area + off); + if (vm_insert_page(vma, vma->vm_start + off, page)) + WARN_ONCE(1, "vm_insert_page() failed"); + } + return 0; + } +exit: + spin_unlock(&kcov->lock); + vfree(area); + return res; +} + +static int kcov_open(struct inode *inode, struct file *filep) +{ + struct kcov *kcov; + + kcov = kzalloc(sizeof(*kcov), GFP_KERNEL); + if (!kcov) + return -ENOMEM; + atomic_set(&kcov->refcount, 1); + spin_lock_init(&kcov->lock); + filep->private_data = kcov; + return nonseekable_open(inode, filep); +} + +static int kcov_close(struct inode *inode, struct file *filep) +{ + kcov_put(filep->private_data); + return 0; +} + +static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, + unsigned long arg) +{ + struct task_struct *t; + unsigned long size, unused; + + switch (cmd) { + case KCOV_INIT_TRACE: + /* + * Enable kcov in trace mode and setup buffer size. + * Must happen before anything else. + */ + if (kcov->mode != KCOV_MODE_DISABLED) + return -EBUSY; + /* + * Size must be at least 2 to hold current position and one PC. + * Later we allocate size * sizeof(unsigned long) memory, + * that must not overflow. + */ + size = arg; + if (size < 2 || size > INT_MAX / sizeof(unsigned long)) + return -EINVAL; + kcov->size = size; + kcov->mode = KCOV_MODE_TRACE; + return 0; + case KCOV_ENABLE: + /* + * Enable coverage for the current task. + * At this point user must have been enabled trace mode, + * and mmapped the file. Coverage collection is disabled only + * at task exit or voluntary by KCOV_DISABLE. After that it can + * be enabled for another task. + */ + unused = arg; + if (unused != 0 || kcov->mode == KCOV_MODE_DISABLED || + kcov->area == NULL) + return -EINVAL; + if (kcov->t != NULL) + return -EBUSY; + t = current; + /* Cache in task struct for performance. */ + t->kcov_size = kcov->size; + t->kcov_area = kcov->area; + /* See comment in __sanitizer_cov_trace_pc(). */ + barrier(); + WRITE_ONCE(t->kcov_mode, kcov->mode); + t->kcov = kcov; + kcov->t = t; + /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */ + kcov_get(kcov); + return 0; + case KCOV_DISABLE: + /* Disable coverage for the current task. */ + unused = arg; + if (unused != 0 || current->kcov != kcov) + return -EINVAL; + t = current; + if (WARN_ON(kcov->t != t)) + return -EINVAL; + kcov_task_init(t); + kcov->t = NULL; + kcov_put(kcov); + return 0; + default: + return -ENOTTY; + } +} + +static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) +{ + struct kcov *kcov; + int res; + + kcov = filep->private_data; + spin_lock(&kcov->lock); + res = kcov_ioctl_locked(kcov, cmd, arg); + spin_unlock(&kcov->lock); + return res; +} + +static const struct file_operations kcov_fops = { + .open = kcov_open, + .unlocked_ioctl = kcov_ioctl, + .mmap = kcov_mmap, + .release = kcov_close, +}; + +static int __init kcov_init(void) +{ + if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) { + pr_err("failed to create kcov in debugfs\n"); + return -ENOMEM; + } + return 0; +} + +device_initcall(kcov_init); diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 8e96f6cc2a4a..31322a4275cd 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,3 +1,6 @@ +# Any varying coverage in these files is non-deterministic +# and is generally not a function of system call inputs. +KCOV_INSTRUMENT := n obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o diff --git a/kernel/memremap.c b/kernel/memremap.c index 584febd13e2e..a6d382312e6f 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -41,11 +41,13 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * memremap() - remap an iomem_resource as cacheable memory * @offset: iomem resource start address * @size: size of remap - * @flags: either MEMREMAP_WB or MEMREMAP_WT + * @flags: any of MEMREMAP_WB, MEMREMAP_WT and MEMREMAP_WC * * memremap() is "ioremap" for cases where it is known that the resource * being mapped does not have i/o side effects and the __iomem - * annotation is not applicable. + * annotation is not applicable. In the case of multiple flags, the different + * mapping types will be attempted in the order listed below until one of + * them succeeds. * * MEMREMAP_WB - matches the default mapping for System RAM on * the architecture. This is usually a read-allocate write-back cache. @@ -57,6 +59,10 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * cache or are written through to memory and never exist in a * cache-dirty state with respect to program visibility. Attempts to * map System RAM with this mapping type will fail. + * + * MEMREMAP_WC - establish a writecombine mapping, whereby writes may + * be coalesced together (e.g. in the CPU's write buffers), but is otherwise + * uncached. Attempts to map System RAM with this mapping type will fail. */ void *memremap(resource_size_t offset, size_t size, unsigned long flags) { @@ -64,6 +70,9 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); void *addr = NULL; + if (!flags) + return NULL; + if (is_ram == REGION_MIXED) { WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n", &offset, (unsigned long) size); @@ -72,7 +81,6 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) /* Try all mapping types requested until one returns non-NULL */ if (flags & MEMREMAP_WB) { - flags &= ~MEMREMAP_WB; /* * MEMREMAP_WB is special in that it can be satisifed * from the direct map. Some archs depend on the @@ -86,21 +94,22 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) } /* - * If we don't have a mapping yet and more request flags are - * pending then we will be attempting to establish a new virtual + * If we don't have a mapping yet and other request flags are + * present then we will be attempting to establish a new virtual * address mapping. Enforce that this mapping is not aliasing * System RAM. */ - if (!addr && is_ram == REGION_INTERSECTS && flags) { + if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) { WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", &offset, (unsigned long) size); return NULL; } - if (!addr && (flags & MEMREMAP_WT)) { - flags &= ~MEMREMAP_WT; + if (!addr && (flags & MEMREMAP_WT)) addr = ioremap_wt(offset, size); - } + + if (!addr && (flags & MEMREMAP_WC)) + addr = ioremap_wc(offset, size); return addr; } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 49746c81ad8d..782102e59eed 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -25,6 +25,7 @@ #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/syscalls.h> +#include <linux/cgroup.h> static struct kmem_cache *nsproxy_cachep; @@ -39,6 +40,9 @@ struct nsproxy init_nsproxy = { #ifdef CONFIG_NET .net_ns = &init_net, #endif +#ifdef CONFIG_CGROUPS + .cgroup_ns = &init_cgroup_ns, +#endif }; static inline struct nsproxy *create_nsproxy(void) @@ -92,6 +96,13 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_pid; } + new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns, + tsk->nsproxy->cgroup_ns); + if (IS_ERR(new_nsp->cgroup_ns)) { + err = PTR_ERR(new_nsp->cgroup_ns); + goto out_cgroup; + } + new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns); if (IS_ERR(new_nsp->net_ns)) { err = PTR_ERR(new_nsp->net_ns); @@ -101,6 +112,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, return new_nsp; out_net: + put_cgroup_ns(new_nsp->cgroup_ns); +out_cgroup: if (new_nsp->pid_ns_for_children) put_pid_ns(new_nsp->pid_ns_for_children); out_pid: @@ -128,7 +141,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) struct nsproxy *new_ns; if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWPID | CLONE_NEWNET)))) { + CLONE_NEWPID | CLONE_NEWNET | + CLONE_NEWCGROUP)))) { get_nsproxy(old_ns); return 0; } @@ -165,6 +179,7 @@ void free_nsproxy(struct nsproxy *ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns_for_children) put_pid_ns(ns->pid_ns_for_children); + put_cgroup_ns(ns->cgroup_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } @@ -180,7 +195,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWNET | CLONE_NEWPID))) + CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP))) return 0; user_ns = new_cred ? new_cred->user_ns : current_user_ns(); diff --git a/kernel/panic.c b/kernel/panic.c index fa400852bf6c..535c96510a44 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -73,6 +73,26 @@ void __weak nmi_panic_self_stop(struct pt_regs *regs) atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); +/* + * A variant of panic() called from NMI context. We return if we've already + * panicked on this CPU. If another CPU already panicked, loop in + * nmi_panic_self_stop() which can provide architecture dependent code such + * as saving register state for crash dump. + */ +void nmi_panic(struct pt_regs *regs, const char *msg) +{ + int old_cpu, cpu; + + cpu = raw_smp_processor_id(); + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); + + if (old_cpu == PANIC_CPU_INVALID) + panic("%s", msg); + else if (old_cpu != cpu) + nmi_panic_self_stop(regs); +} +EXPORT_SYMBOL(nmi_panic); + /** * panic - halt the system * @fmt: The text string to print diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index aa0f26b58426..fca9254280ee 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -339,6 +339,7 @@ int hibernation_snapshot(int platform_mode) pm_message_t msg; int error; + pm_suspend_clear_flags(); error = platform_begin(platform_mode); if (error) goto Close; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 230a77225e2e..5b70d64b871e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -473,8 +473,7 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_FREEZE) { #ifdef CONFIG_PM_DEBUG if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) { - pr_warning("PM: Unsupported test mode for suspend to idle," - "please choose none/freezer/devices/platform.\n"); + pr_warn("PM: Unsupported test mode for suspend to idle, please choose none/freezer/devices/platform.\n"); return -EAGAIN; } #endif diff --git a/kernel/profile.c b/kernel/profile.c index 51369697466e..c2199e9901c9 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -44,7 +44,7 @@ int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); static cpumask_var_t prof_cpu_mask; -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); static DEFINE_PER_CPU(int, cpu_profile_flip); static DEFINE_MUTEX(profile_flip_mutex); @@ -202,7 +202,7 @@ int profile_event_unregister(enum profile_type type, struct notifier_block *n) } EXPORT_SYMBOL_GPL(profile_event_unregister); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending * profile hits. read_profile() IPI's all cpus to request them diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 2341efe7fe02..d49bfa1e53e6 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -73,12 +73,11 @@ void __ptrace_unlink(struct task_struct *child) { BUG_ON(!child->ptrace); - child->ptrace = 0; child->parent = child->real_parent; list_del_init(&child->ptrace_entry); spin_lock(&child->sighand->siglock); - + child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. @@ -681,7 +680,7 @@ static int ptrace_peek_siginfo(struct task_struct *child, break; #ifdef CONFIG_COMPAT - if (unlikely(is_compat_task())) { + if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info) || diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 61a16569ffbf..032b2c015beb 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,3 +1,7 @@ +# Any varying coverage in these files is non-deterministic +# and is generally not a function of system call inputs. +KCOV_INSTRUMENT := n + obj-y += update.o sync.o obj-$(CONFIG_SRCU) += srcu.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 302d6ebd64f7..414d9c16da42 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -2,6 +2,10 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) endif +# These files are disabled because they produce non-interesting flaky coverage +# that is not a function of syscall inputs. E.g. involuntary context switches. +KCOV_INSTRUMENT := n + ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is # needed for x86 only. Why this used to be enabled for all architectures is beyond diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4ee3ce7ec78d..d8465eeab8b3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -73,6 +73,7 @@ #include <linux/init_task.h> #include <linux/context_tracking.h> #include <linux/compiler.h> +#include <linux/frame.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -2689,7 +2690,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) /* * context_switch - switch to the new MM and the new thread's register state. */ -static inline struct rq * +static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { @@ -3204,6 +3205,7 @@ static void __sched notrace __schedule(bool preempt) balance_callback(rq); } +STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */ static inline void sched_submit_work(struct task_struct *tsk) { @@ -5369,6 +5371,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_UP_PREPARE: rq->calc_load_update = calc_load_update; + account_reset_rq(rq); break; case CPU_ONLINE: @@ -7535,7 +7538,7 @@ void set_curr_task(int cpu, struct task_struct *p) /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); -static void free_sched_group(struct task_group *tg) +static void sched_free_group(struct task_group *tg) { free_fair_sched_group(tg); free_rt_sched_group(tg); @@ -7561,7 +7564,7 @@ struct task_group *sched_create_group(struct task_group *parent) return tg; err: - free_sched_group(tg); + sched_free_group(tg); return ERR_PTR(-ENOMEM); } @@ -7581,17 +7584,16 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) } /* rcu callback to free various structures associated with a task group */ -static void free_sched_group_rcu(struct rcu_head *rhp) +static void sched_free_group_rcu(struct rcu_head *rhp) { /* now it should be safe to free those cfs_rqs */ - free_sched_group(container_of(rhp, struct task_group, rcu)); + sched_free_group(container_of(rhp, struct task_group, rcu)); } -/* Destroy runqueue etc associated with a task group */ void sched_destroy_group(struct task_group *tg) { /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&tg->rcu, free_sched_group_rcu); + call_rcu(&tg->rcu, sched_free_group_rcu); } void sched_offline_group(struct task_group *tg) @@ -8050,31 +8052,26 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); + sched_online_group(tg, parent); + return &tg->css; } -static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - struct task_group *parent = css_tg(css->parent); - if (parent) - sched_online_group(tg, parent); - return 0; + sched_offline_group(tg); } static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - sched_destroy_group(tg); -} - -static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) -{ - struct task_group *tg = css_tg(css); - - sched_offline_group(tg); + /* + * Relies on the RCU grace period between css_released() and this. + */ + sched_free_group(tg); } static void cpu_cgroup_fork(struct task_struct *task) @@ -8434,9 +8431,8 @@ static struct cftype cpu_files[] = { struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, + .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, - .css_online = cpu_cgroup_css_online, - .css_offline = cpu_cgroup_css_offline, .fork = cpu_cgroup_fork, .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 2ddaebf7469a..4a811203c04a 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -145,13 +145,16 @@ static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) } static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, - u64 reset) + u64 val) { struct cpuacct *ca = css_ca(css); int err = 0; int i; - if (reset) { + /* + * Only allow '0' here to do a reset. + */ + if (val) { err = -EINVAL; goto out; } @@ -235,23 +238,10 @@ static struct cftype files[] = { void cpuacct_charge(struct task_struct *tsk, u64 cputime) { struct cpuacct *ca; - int cpu; - - cpu = task_cpu(tsk); rcu_read_lock(); - - ca = task_ca(tsk); - - while (true) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - *cpuusage += cputime; - - ca = parent_ca(ca); - if (!ca) - break; - } - + for (ca = task_ca(tsk); ca; ca = parent_ca(ca)) + *this_cpu_ptr(ca->cpuusage) += cputime; rcu_read_unlock(); } @@ -260,18 +250,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime) * * Note: it's the caller that updates the account of the root cgroup. */ -void cpuacct_account_field(struct task_struct *p, int index, u64 val) +void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) { - struct kernel_cpustat *kcpustat; struct cpuacct *ca; rcu_read_lock(); - ca = task_ca(p); - while (ca != &root_cpuacct) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += val; - ca = parent_ca(ca); - } + for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca)) + this_cpu_ptr(ca->cpustat)->cpustat[index] += val; rcu_read_unlock(); } diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index ed605624a5e7..ba72807c73d4 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -1,7 +1,7 @@ #ifdef CONFIG_CGROUP_CPUACCT extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); -extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); +extern void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else @@ -10,7 +10,7 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) } static inline void -cpuacct_account_field(struct task_struct *p, int index, u64 val) +cpuacct_account_field(struct task_struct *tsk, int index, u64 val) { } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 46d64e4ccfde..0fe30e66aff1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3181,17 +3181,25 @@ static inline void check_schedstat_required(void) static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { + bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING); + bool curr = cfs_rq->curr == se; + /* - * Update the normalized vruntime before updating min_vruntime - * through calling update_curr(). + * If we're the current task, we must renormalise before calling + * update_curr(). */ - if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING)) + if (renorm && curr) se->vruntime += cfs_rq->min_vruntime; + update_curr(cfs_rq); + /* - * Update run-time statistics of the 'current'. + * Otherwise, renormalise after, such that we're placed at the current + * moment in time, instead of some random moment in the past. */ - update_curr(cfs_rq); + if (renorm && !curr) + se->vruntime += cfs_rq->min_vruntime; + enqueue_entity_load_avg(cfs_rq, se); account_entity_enqueue(cfs_rq, se); update_cfs_shares(cfs_rq); @@ -3207,7 +3215,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_stats_enqueue(cfs_rq, se); check_spread(cfs_rq, se); } - if (se != cfs_rq->curr) + if (!curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; @@ -5071,7 +5079,19 @@ static int select_idle_sibling(struct task_struct *p, int target) return i; /* - * Otherwise, iterate the domains and find an elegible idle cpu. + * Otherwise, iterate the domains and find an eligible idle cpu. + * + * A completely idle sched group at higher domains is more + * desirable than an idle group at a lower level, because lower + * domains have smaller groups and usually share hardware + * resources which causes tasks to contend on them, e.g. x86 + * hyperthread siblings in the lowest domain (SMT) can contend + * on the shared cpu pipeline. + * + * However, while we prefer idle groups at higher domains + * finding an idle cpu at the lowest domain is still better than + * returning 'target', which we've already established, isn't + * idle. */ sd = rcu_dereference(per_cpu(sd_llc, target)); for_each_lower_domain(sd) { @@ -5081,11 +5101,16 @@ static int select_idle_sibling(struct task_struct *p, int target) tsk_cpus_allowed(p))) goto next; + /* Ensure the entire group is idle */ for_each_cpu(i, sched_group_cpus(sg)) { if (i == target || !idle_cpu(i)) goto next; } + /* + * It doesn't matter which cpu we pick, the + * whole group is idle. + */ target = cpumask_first_and(sched_group_cpus(sg), tsk_cpus_allowed(p)); goto done; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 382848a24ed9..ec2e8d23527e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1841,3 +1841,16 @@ static inline void cpufreq_trigger_update(u64 time) static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {} static inline void cpufreq_trigger_update(u64 time) {} #endif /* CONFIG_CPU_FREQ */ + +static inline void account_reset_rq(struct rq *rq) +{ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + rq->prev_irq_time = 0; +#endif +#ifdef CONFIG_PARAVIRT + rq->prev_steal_time = 0; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + rq->prev_steal_time_rq = 0; +#endif +} diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 15a1795bbba1..e1e5a354854e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -395,7 +395,7 @@ seccomp_prepare_user_filter(const char __user *user_filter) struct seccomp_filter *filter = ERR_PTR(-EFAULT); #ifdef CONFIG_COMPAT - if (is_compat_task()) { + if (in_compat_syscall()) { struct compat_sock_fprog fprog32; if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) goto out; @@ -529,7 +529,7 @@ static void __secure_computing_strict(int this_syscall) { int *syscall_whitelist = mode1_syscalls; #ifdef CONFIG_COMPAT - if (is_compat_task()) + if (in_compat_syscall()) syscall_whitelist = mode1_syscalls_32; #endif do { diff --git a/kernel/signal.c b/kernel/signal.c index 0508544c8ced..aa9bf00749c1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2709,6 +2709,10 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) err |= __put_user(from->si_upper, &to->si_upper); } #endif +#ifdef SEGV_PKUERR + if (from->si_signo == SIGSEGV && from->si_code == SEGV_PKUERR) + err |= __put_user(from->si_pkey, &to->si_pkey); +#endif break; case __SI_CHLD: err |= __put_user(from->si_pid, &to->si_pid); @@ -3581,6 +3585,10 @@ __weak const char *arch_vma_name(struct vm_area_struct *vma) void __init signals_init(void) { + /* If this check fails, the __ARCH_SI_PREAMBLE_SIZE value is wrong! */ + BUILD_BUG_ON(__ARCH_SI_PREAMBLE_SIZE + != offsetof(struct siginfo, _sifields._pad)); + sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 8aae49dd7da8..17caf4b63342 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -227,7 +227,7 @@ static inline bool lockdep_softirq_start(void) { return false; } static inline void lockdep_softirq_end(bool in_hardirq) { } #endif -asmlinkage __visible void __do_softirq(void) +asmlinkage __visible void __softirq_entry __do_softirq(void) { unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 7e7746a42a62..10a1d7dc9313 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1321,7 +1321,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, } mnt = task_active_pid_ns(current)->proc_mnt; - file = file_open_root(mnt->mnt_root, mnt, pathname, flags); + file = file_open_root(mnt->mnt_root, mnt, pathname, flags, 0); result = PTR_ERR(file); if (IS_ERR(file)) goto out_putname; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 195fe7d2caad..084b79f5917e 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -378,7 +378,7 @@ static int __init tick_nohz_full_setup(char *str) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); if (cpulist_parse(str, tick_nohz_full_mask) < 0) { - pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); + pr_warn("NO_HZ: Incorrect nohz_full cpumask\n"); free_bootmem_cpumask_var(tick_nohz_full_mask); return 1; } @@ -446,8 +446,7 @@ void __init tick_nohz_init(void) * interrupts to avoid circular dependency on the tick */ if (!arch_irq_work_has_interrupt()) { - pr_warning("NO_HZ: Can't run full dynticks because arch doesn't " - "support irq work self-IPIs\n"); + pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); cpumask_copy(housekeeping_mask, cpu_possible_mask); tick_nohz_full_running = false; @@ -457,7 +456,8 @@ void __init tick_nohz_init(void) cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { - pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); + pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", + cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index d1798fa0c743..73164c3aa56b 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1566,6 +1566,17 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_uninterruptible); +/* + * Like schedule_timeout_uninterruptible(), except this task will not contribute + * to load average. + */ +signed long __sched schedule_timeout_idle(signed long timeout) +{ + __set_current_state(TASK_IDLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_idle); + #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head) { diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2aeb6ffc0a1e..f94e7a21f52d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1437,12 +1437,12 @@ static struct trace_event trace_blk_event = { static int __init init_blk_tracer(void) { if (!register_trace_event(&trace_blk_event)) { - pr_warning("Warning: could not register block events\n"); + pr_warn("Warning: could not register block events\n"); return 1; } if (register_tracer(&blk_tracer) != 0) { - pr_warning("Warning: could not register the block tracer\n"); + pr_warn("Warning: could not register the block tracer\n"); unregister_trace_event(&trace_blk_event); return 1; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 57a6eea84694..b1870fbd2b67 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1030,8 +1030,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) for_each_possible_cpu(cpu) { stat = &per_cpu(ftrace_profile_stats, cpu); - /* allocate enough for function name + cpu number */ - name = kmalloc(32, GFP_KERNEL); + name = kasprintf(GFP_KERNEL, "function%d", cpu); if (!name) { /* * The files created are permanent, if something happens @@ -1043,7 +1042,6 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) return; } stat->stat = function_stats; - snprintf(name, 32, "function%d", cpu); stat->stat.name = name; ret = register_stat_tracer(&stat->stat); if (ret) { @@ -1058,8 +1056,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) entry = tracefs_create_file("function_profile_enabled", 0644, d_tracer, NULL, &ftrace_profile_fops); if (!entry) - pr_warning("Could not create tracefs " - "'function_profile_enabled' entry\n"); + pr_warn("Could not create tracefs 'function_profile_enabled' entry\n"); } #else /* CONFIG_FUNCTION_PROFILER */ @@ -1610,7 +1607,7 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) return keep_regs; } -static void __ftrace_hash_rec_update(struct ftrace_ops *ops, +static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) { @@ -1618,12 +1615,13 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, struct ftrace_hash *other_hash; struct ftrace_page *pg; struct dyn_ftrace *rec; + bool update = false; int count = 0; int all = 0; /* Only update if the ops has been registered */ if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) - return; + return false; /* * In the filter_hash case: @@ -1650,7 +1648,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, * then there's nothing to do. */ if (ftrace_hash_empty(hash)) - return; + return false; } do_for_each_ftrace_rec(pg, rec) { @@ -1694,7 +1692,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (inc) { rec->flags++; if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) - return; + return false; /* * If there's only a single callback registered to a @@ -1720,7 +1718,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0)) - return; + return false; rec->flags--; /* @@ -1753,22 +1751,28 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, */ } count++; + + /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ + update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE; + /* Shortcut, if we handled all records, we are done. */ if (!all && count == hash->count) - return; + return update; } while_for_each_ftrace_rec(); + + return update; } -static void ftrace_hash_rec_disable(struct ftrace_ops *ops, +static bool ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash) { - __ftrace_hash_rec_update(ops, filter_hash, 0); + return __ftrace_hash_rec_update(ops, filter_hash, 0); } -static void ftrace_hash_rec_enable(struct ftrace_ops *ops, +static bool ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash) { - __ftrace_hash_rec_update(ops, filter_hash, 1); + return __ftrace_hash_rec_update(ops, filter_hash, 1); } static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops, @@ -2314,8 +2318,8 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_curr(rec); if (FTRACE_WARN_ON(!ops)) { - pr_warning("Bad trampoline accounting at: %p (%pS)\n", - (void *)rec->ip, (void *)rec->ip); + pr_warn("Bad trampoline accounting at: %p (%pS)\n", + (void *)rec->ip, (void *)rec->ip); /* Ftrace is shutting down, return anything */ return (unsigned long)FTRACE_ADDR; } @@ -2644,7 +2648,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return ret; ftrace_start_up++; - command |= FTRACE_UPDATE_CALLS; /* * Note that ftrace probes uses this to start up @@ -2665,7 +2668,8 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return ret; } - ftrace_hash_rec_enable(ops, 1); + if (ftrace_hash_rec_enable(ops, 1)) + command |= FTRACE_UPDATE_CALLS; ftrace_startup_enable(command); @@ -2695,11 +2699,11 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) /* Disabling ipmodify never fails */ ftrace_hash_ipmodify_disable(ops); - ftrace_hash_rec_disable(ops, 1); - ops->flags &= ~FTRACE_OPS_FL_ENABLED; + if (ftrace_hash_rec_disable(ops, 1)) + command |= FTRACE_UPDATE_CALLS; - command |= FTRACE_UPDATE_CALLS; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d9293402ee68..a2f0b9f33e9b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -74,11 +74,6 @@ static struct tracer_opt dummy_tracer_opt[] = { { } }; -static struct tracer_flags dummy_tracer_flags = { - .val = 0, - .opts = dummy_tracer_opt -}; - static int dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { @@ -1258,12 +1253,22 @@ int __init register_tracer(struct tracer *type) if (!type->set_flag) type->set_flag = &dummy_set_flag; - if (!type->flags) - type->flags = &dummy_tracer_flags; - else + if (!type->flags) { + /*allocate a dummy tracer_flags*/ + type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); + if (!type->flags) { + ret = -ENOMEM; + goto out; + } + type->flags->val = 0; + type->flags->opts = dummy_tracer_opt; + } else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; + /* store the tracer for __set_tracer_option */ + type->flags->trace = type; + ret = run_tracer_selftest(type); if (ret < 0) goto out; @@ -1659,6 +1664,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, #else TRACE_FLAG_IRQS_NOSUPPORT | #endif + ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | @@ -2071,20 +2077,20 @@ void trace_printk_init_buffers(void) /* trace_printk() is for debug use only. Don't use it in production. */ - pr_warning("\n"); - pr_warning("**********************************************************\n"); - pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); - pr_warning("** **\n"); - pr_warning("** trace_printk() being used. Allocating extra memory. **\n"); - pr_warning("** **\n"); - pr_warning("** This means that this is a DEBUG kernel and it is **\n"); - pr_warning("** unsafe for production use. **\n"); - pr_warning("** **\n"); - pr_warning("** If you see this message and you are not debugging **\n"); - pr_warning("** the kernel, report this immediately to your vendor! **\n"); - pr_warning("** **\n"); - pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); - pr_warning("**********************************************************\n"); + pr_warn("\n"); + pr_warn("**********************************************************\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("** **\n"); + pr_warn("** trace_printk() being used. Allocating extra memory. **\n"); + pr_warn("** **\n"); + pr_warn("** This means that this is a DEBUG kernel and it is **\n"); + pr_warn("** unsafe for production use. **\n"); + pr_warn("** **\n"); + pr_warn("** If you see this message and you are not debugging **\n"); + pr_warn("** the kernel, report this immediately to your vendor! **\n"); + pr_warn("** **\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("**********************************************************\n"); /* Expand the buffers to set size */ tracing_update_buffers(); @@ -3505,7 +3511,7 @@ static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { - struct tracer *trace = tr->current_trace; + struct tracer *trace = tracer_flags->trace; int ret; ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); @@ -4101,7 +4107,7 @@ trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start, */ map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL); if (!map_array) { - pr_warning("Unable to allocate trace enum mapping\n"); + pr_warn("Unable to allocate trace enum mapping\n"); return; } @@ -4949,7 +4955,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, spd.nr_pages = i; - ret = splice_to_pipe(pipe, &spd); + if (i) + ret = splice_to_pipe(pipe, &spd); + else + ret = 0; out: splice_shrink_spd(&spd); return ret; @@ -6131,7 +6140,7 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) snprintf(cpu_dir, 30, "cpu%ld", cpu); d_cpu = tracefs_create_dir(cpu_dir, d_percpu); if (!d_cpu) { - pr_warning("Could not create tracefs '%s' entry\n", cpu_dir); + pr_warn("Could not create tracefs '%s' entry\n", cpu_dir); return; } @@ -6318,7 +6327,7 @@ struct dentry *trace_create_file(const char *name, ret = tracefs_create_file(name, mode, parent, data, fops); if (!ret) - pr_warning("Could not create tracefs '%s' entry\n", name); + pr_warn("Could not create tracefs '%s' entry\n", name); return ret; } @@ -6337,7 +6346,7 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr) tr->options = tracefs_create_dir("options", d_tracer); if (!tr->options) { - pr_warning("Could not create tracefs directory 'options'\n"); + pr_warn("Could not create tracefs directory 'options'\n"); return NULL; } @@ -6391,11 +6400,8 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer) return; for (i = 0; i < tr->nr_topts; i++) { - /* - * Check if these flags have already been added. - * Some tracers share flags. - */ - if (tr->topts[i].tracer->flags == tracer->flags) + /* Make sure there's no duplicate flags. */ + if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags)) return; } @@ -7248,8 +7254,8 @@ __init static int tracer_alloc_buffers(void) if (trace_boot_clock) { ret = tracing_set_clock(&global_trace, trace_boot_clock); if (ret < 0) - pr_warning("Trace clock %s not defined, going back to default\n", - trace_boot_clock); + pr_warn("Trace clock %s not defined, going back to default\n", + trace_boot_clock); } /* diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8414fa40bf27..3fff4adfd431 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -125,6 +125,7 @@ enum trace_flag_type { TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, }; #define TRACE_BUF_SIZE 1024 @@ -345,6 +346,7 @@ struct tracer_opt { struct tracer_flags { u32 val; struct tracer_opt *opts; + struct tracer *trace; }; /* Makes more easy to define a tracer opt */ @@ -1111,6 +1113,18 @@ struct filter_pred { unsigned short right; }; +static inline bool is_string_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_STATIC_STRING || + field->filter_type == FILTER_PTR_STRING; +} + +static inline bool is_function_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_TRACE_FN; +} + extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct trace_event_file *file, @@ -1159,9 +1173,24 @@ struct event_trigger_data { struct event_filter __rcu *filter; char *filter_str; void *private_data; + bool paused; struct list_head list; }; +extern void trigger_data_free(struct event_trigger_data *data); +extern int event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data); +extern int trace_event_trigger_enable_disable(struct trace_event_file *file, + int trigger_enable); +extern void update_cond_flag(struct trace_event_file *file); +extern void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct trace_event_file *file); +extern int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct trace_event_file *file); +extern int register_event_command(struct event_command *cmd); + /** * struct event_trigger_ops - callbacks for trace event triggers * @@ -1174,7 +1203,8 @@ struct event_trigger_data { * @func: The trigger 'probe' function called when the triggering * event occurs. The data passed into this callback is the data * that was supplied to the event_command @reg() function that - * registered the trigger (see struct event_command). + * registered the trigger (see struct event_command) along with + * the trace record, rec. * * @init: An optional initialization function called for the trigger * when the trigger is registered (via the event_command reg() @@ -1199,7 +1229,8 @@ struct event_trigger_data { * (see trace_event_triggers.c). */ struct event_trigger_ops { - void (*func)(struct event_trigger_data *data); + void (*func)(struct event_trigger_data *data, + void *rec); int (*init)(struct event_trigger_ops *ops, struct event_trigger_data *data); void (*free)(struct event_trigger_ops *ops, @@ -1243,27 +1274,10 @@ struct event_trigger_ops { * values are defined by adding new values to the trigger_type * enum in include/linux/trace_events.h. * - * @post_trigger: A flag that says whether or not this command needs - * to have its action delayed until after the current event has - * been closed. Some triggers need to avoid being invoked while - * an event is currently in the process of being logged, since - * the trigger may itself log data into the trace buffer. Thus - * we make sure the current event is committed before invoking - * those triggers. To do that, the trigger invocation is split - * in two - the first part checks the filter using the current - * trace record; if a command has the @post_trigger flag set, it - * sets a bit for itself in the return value, otherwise it - * directly invokes the trigger. Once all commands have been - * either invoked or set their return flag, the current record is - * either committed or discarded. At that point, if any commands - * have deferred their triggers, those commands are finally - * invoked following the close of the current event. In other - * words, if the event_trigger_ops @func() probe implementation - * itself logs to the trace buffer, this flag should be set, - * otherwise it can be left unspecified. + * @flags: See the enum event_command_flags below. * - * All the methods below, except for @set_filter(), must be - * implemented. + * All the methods below, except for @set_filter() and @unreg_all(), + * must be implemented. * * @func: The callback function responsible for parsing and * registering the trigger written to the 'trigger' file by the @@ -1288,6 +1302,10 @@ struct event_trigger_ops { * This is usually implemented by the generic utility function * @unregister_trigger() (see trace_event_triggers.c). * + * @unreg_all: An optional function called to remove all the triggers + * from the list of triggers associated with the event. Called + * when a trigger file is opened in truncate mode. + * * @set_filter: An optional function called to parse and set a filter * for the trigger. If no @set_filter() method is set for the * event command, filters set by the user for the command will be @@ -1301,7 +1319,7 @@ struct event_command { struct list_head list; char *name; enum event_trigger_type trigger_type; - bool post_trigger; + int flags; int (*func)(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, char *cmd, char *params); @@ -1313,12 +1331,56 @@ struct event_command { struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); + void (*unreg_all)(struct trace_event_file *file); int (*set_filter)(char *filter_str, struct event_trigger_data *data, struct trace_event_file *file); struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param); }; +/** + * enum event_command_flags - flags for struct event_command + * + * @POST_TRIGGER: A flag that says whether or not this command needs + * to have its action delayed until after the current event has + * been closed. Some triggers need to avoid being invoked while + * an event is currently in the process of being logged, since + * the trigger may itself log data into the trace buffer. Thus + * we make sure the current event is committed before invoking + * those triggers. To do that, the trigger invocation is split + * in two - the first part checks the filter using the current + * trace record; if a command has the @post_trigger flag set, it + * sets a bit for itself in the return value, otherwise it + * directly invokes the trigger. Once all commands have been + * either invoked or set their return flag, the current record is + * either committed or discarded. At that point, if any commands + * have deferred their triggers, those commands are finally + * invoked following the close of the current event. In other + * words, if the event_trigger_ops @func() probe implementation + * itself logs to the trace buffer, this flag should be set, + * otherwise it can be left unspecified. + * + * @NEEDS_REC: A flag that says whether or not this command needs + * access to the trace record in order to perform its function, + * regardless of whether or not it has a filter associated with + * it (filters make a trigger require access to the trace record + * but are not always present). + */ +enum event_command_flags { + EVENT_CMD_FL_POST_TRIGGER = 1, + EVENT_CMD_FL_NEEDS_REC = 2, +}; + +static inline bool event_command_post_trigger(struct event_command *cmd_ops) +{ + return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER; +} + +static inline bool event_command_needs_rec(struct event_command *cmd_ops) +{ + return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC; +} + extern int trace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable); extern int tracing_alloc_snapshot(void); @@ -1365,8 +1427,13 @@ int perf_ftrace_event_register(struct trace_event_call *call, #ifdef CONFIG_FTRACE_SYSCALLS void init_ftrace_syscalls(void); +const char *get_syscall_name(int syscall); #else static inline void init_ftrace_syscalls(void) { } +static inline const char *get_syscall_name(int syscall) +{ + return NULL; +} #endif #ifdef CONFIG_EVENT_TRACING diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 6816302542b2..b3f5051cd4e9 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -961,18 +961,6 @@ int filter_assign_type(const char *type) return FILTER_OTHER; } -static bool is_function_field(struct ftrace_event_field *field) -{ - return field->filter_type == FILTER_TRACE_FN; -} - -static bool is_string_field(struct ftrace_event_field *field) -{ - return field->filter_type == FILTER_DYN_STRING || - field->filter_type == FILTER_STATIC_STRING || - field->filter_type == FILTER_PTR_STRING; -} - static bool is_legal_op(struct ftrace_event_field *field, int op) { if (is_string_field(field) && diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index b38f617b6181..d67992f3bb0e 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -28,8 +28,7 @@ static LIST_HEAD(trigger_commands); static DEFINE_MUTEX(trigger_cmd_mutex); -static void -trigger_data_free(struct event_trigger_data *data) +void trigger_data_free(struct event_trigger_data *data) { if (data->cmd_ops->set_filter) data->cmd_ops->set_filter(NULL, data, NULL); @@ -73,18 +72,20 @@ event_triggers_call(struct trace_event_file *file, void *rec) return tt; list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->paused) + continue; if (!rec) { - data->ops->func(data); + data->ops->func(data, rec); continue; } filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; - if (data->cmd_ops->post_trigger) { + if (event_command_post_trigger(data->cmd_ops)) { tt |= data->cmd_ops->trigger_type; continue; } - data->ops->func(data); + data->ops->func(data, rec); } return tt; } @@ -94,6 +95,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call); * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event * @tt: enum event_trigger_type containing a set bit for each trigger to invoke + * @rec: The trace entry for the event * * For each trigger associated with an event, invoke the trigger * function registered with the associated trigger command, if the @@ -104,13 +106,16 @@ EXPORT_SYMBOL_GPL(event_triggers_call); */ void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt) + enum event_trigger_type tt, + void *rec) { struct event_trigger_data *data; list_for_each_entry_rcu(data, &file->triggers, list) { + if (data->paused) + continue; if (data->cmd_ops->trigger_type & tt) - data->ops->func(data); + data->ops->func(data, rec); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -188,6 +193,19 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) return -ENODEV; } + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) { + struct trace_event_file *event_file; + struct event_command *p; + + event_file = event_file_data(file); + + list_for_each_entry(p, &trigger_commands, list) { + if (p->unreg_all) + p->unreg_all(event_file); + } + } + if (file->f_mode & FMODE_READ) { ret = seq_open(file, &event_triggers_seq_ops); if (!ret) { @@ -306,7 +324,7 @@ const struct file_operations event_trigger_fops = { * Currently we only register event commands from __init, so mark this * __init too. */ -static __init int register_event_command(struct event_command *cmd) +__init int register_event_command(struct event_command *cmd) { struct event_command *p; int ret = 0; @@ -395,9 +413,8 @@ event_trigger_print(const char *name, struct seq_file *m, * * Return: 0 on success, errno otherwise */ -static int -event_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +int event_trigger_init(struct event_trigger_ops *ops, + struct event_trigger_data *data) { data->ref++; return 0; @@ -425,8 +442,8 @@ event_trigger_free(struct event_trigger_ops *ops, trigger_data_free(data); } -static int trace_event_trigger_enable_disable(struct trace_event_file *file, - int trigger_enable) +int trace_event_trigger_enable_disable(struct trace_event_file *file, + int trigger_enable) { int ret = 0; @@ -483,13 +500,14 @@ clear_event_triggers(struct trace_array *tr) * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be * cleared. */ -static void update_cond_flag(struct trace_event_file *file) +void update_cond_flag(struct trace_event_file *file) { struct event_trigger_data *data; bool set_cond = false; list_for_each_entry_rcu(data, &file->triggers, list) { - if (data->filter || data->cmd_ops->post_trigger) { + if (data->filter || event_command_post_trigger(data->cmd_ops) || + event_command_needs_rec(data->cmd_ops)) { set_cond = true; break; } @@ -560,9 +578,9 @@ out: * Usually used directly as the @unreg method in event command * implementations. */ -static void unregister_trigger(char *glob, struct event_trigger_ops *ops, - struct event_trigger_data *test, - struct trace_event_file *file) +void unregister_trigger(char *glob, struct event_trigger_ops *ops, + struct event_trigger_data *test, + struct trace_event_file *file) { struct event_trigger_data *data; bool unregistered = false; @@ -696,9 +714,9 @@ event_trigger_callback(struct event_command *cmd_ops, * * Return: 0 on success, errno otherwise */ -static int set_trigger_filter(char *filter_str, - struct event_trigger_data *trigger_data, - struct trace_event_file *file) +int set_trigger_filter(char *filter_str, + struct event_trigger_data *trigger_data, + struct trace_event_file *file) { struct event_trigger_data *data = trigger_data; struct event_filter *filter = NULL, *tmp; @@ -747,7 +765,7 @@ static int set_trigger_filter(char *filter_str, } static void -traceon_trigger(struct event_trigger_data *data) +traceon_trigger(struct event_trigger_data *data, void *rec) { if (tracing_is_on()) return; @@ -756,7 +774,7 @@ traceon_trigger(struct event_trigger_data *data) } static void -traceon_count_trigger(struct event_trigger_data *data) +traceon_count_trigger(struct event_trigger_data *data, void *rec) { if (tracing_is_on()) return; @@ -771,7 +789,7 @@ traceon_count_trigger(struct event_trigger_data *data) } static void -traceoff_trigger(struct event_trigger_data *data) +traceoff_trigger(struct event_trigger_data *data, void *rec) { if (!tracing_is_on()) return; @@ -780,7 +798,7 @@ traceoff_trigger(struct event_trigger_data *data) } static void -traceoff_count_trigger(struct event_trigger_data *data) +traceoff_count_trigger(struct event_trigger_data *data, void *rec) { if (!tracing_is_on()) return; @@ -876,13 +894,13 @@ static struct event_command trigger_traceoff_cmd = { #ifdef CONFIG_TRACER_SNAPSHOT static void -snapshot_trigger(struct event_trigger_data *data) +snapshot_trigger(struct event_trigger_data *data, void *rec) { tracing_snapshot(); } static void -snapshot_count_trigger(struct event_trigger_data *data) +snapshot_count_trigger(struct event_trigger_data *data, void *rec) { if (!data->count) return; @@ -890,7 +908,7 @@ snapshot_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - snapshot_trigger(data); + snapshot_trigger(data, rec); } static int @@ -969,13 +987,13 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; } #define STACK_SKIP 3 static void -stacktrace_trigger(struct event_trigger_data *data) +stacktrace_trigger(struct event_trigger_data *data, void *rec) { trace_dump_stack(STACK_SKIP); } static void -stacktrace_count_trigger(struct event_trigger_data *data) +stacktrace_count_trigger(struct event_trigger_data *data, void *rec) { if (!data->count) return; @@ -983,7 +1001,7 @@ stacktrace_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - stacktrace_trigger(data); + stacktrace_trigger(data, rec); } static int @@ -1017,7 +1035,7 @@ stacktrace_get_trigger_ops(char *cmd, char *param) static struct event_command trigger_stacktrace_cmd = { .name = "stacktrace", .trigger_type = ETT_STACKTRACE, - .post_trigger = true, + .flags = EVENT_CMD_FL_POST_TRIGGER, .func = event_trigger_callback, .reg = register_trigger, .unreg = unregister_trigger, @@ -1054,7 +1072,7 @@ struct enable_trigger_data { }; static void -event_enable_trigger(struct event_trigger_data *data) +event_enable_trigger(struct event_trigger_data *data, void *rec) { struct enable_trigger_data *enable_data = data->private_data; @@ -1065,7 +1083,7 @@ event_enable_trigger(struct event_trigger_data *data) } static void -event_enable_count_trigger(struct event_trigger_data *data) +event_enable_count_trigger(struct event_trigger_data *data, void *rec) { struct enable_trigger_data *enable_data = data->private_data; @@ -1079,7 +1097,7 @@ event_enable_count_trigger(struct event_trigger_data *data) if (data->count != -1) (data->count)--; - event_enable_trigger(data); + event_enable_trigger(data, rec); } static int diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index fcd41a166405..5a095c2e4b69 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -219,6 +219,8 @@ static void tracing_stop_function_trace(struct trace_array *tr) unregister_ftrace_function(tr->ops); } +static struct tracer function_trace; + static int func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { @@ -228,6 +230,10 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) break; + /* We can change this flag when not running. */ + if (tr->current_trace != &function_trace) + break; + unregister_ftrace_function(tr->ops); if (set) { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index a663cbb84107..3a0244ff7ea8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -8,6 +8,7 @@ */ #include <linux/uaccess.h> #include <linux/ftrace.h> +#include <linux/interrupt.h> #include <linux/slab.h> #include <linux/fs.h> @@ -1350,7 +1351,7 @@ void graph_trace_open(struct trace_iterator *iter) out_err_free: kfree(data); out_err: - pr_warning("function graph tracer: not enough memory\n"); + pr_warn("function graph tracer: not enough memory\n"); } void graph_trace_close(struct trace_iterator *iter) @@ -1468,12 +1469,12 @@ static __init int init_graph_trace(void) max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); if (!register_trace_event(&graph_trace_entry_event)) { - pr_warning("Warning: could not register graph trace events\n"); + pr_warn("Warning: could not register graph trace events\n"); return 1; } if (!register_trace_event(&graph_trace_ret_event)) { - pr_warning("Warning: could not register graph trace events\n"); + pr_warn("Warning: could not register graph trace events\n"); return 1; } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index e4e56589ec1d..03cdff84d026 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr, return 0; local_save_flags(*flags); - /* slight chance to get a false positive on tracing_cpu */ - if (!irqs_disabled_flags(*flags)) + /* + * Slight chance to get a false positive on tracing_cpu, + * although I'm starting to think there isn't a chance. + * Leave this for now just to be paranoid. + */ + if (!irqs_disabled_flags(*flags) && !preempt_count()) return 0; *data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -622,7 +626,6 @@ static int __irqsoff_tracer_init(struct trace_array *tr) irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); - tracing_reset_online_cpus(&tr->trace_buffer); ftrace_init_array_ops(tr, irqsoff_tracer_call); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 21b81a41dae5..919e0ddd8fcc 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -459,16 +459,14 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) if (ret == 0) tk->tp.flags |= TP_FLAG_REGISTERED; else { - pr_warning("Could not insert probe at %s+%lu: %d\n", - trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); + pr_warn("Could not insert probe at %s+%lu: %d\n", + trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret); if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { - pr_warning("This probe might be able to register after" - "target module is loaded. Continue.\n"); + pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); ret = 0; } else if (ret == -EILSEQ) { - pr_warning("Probing address(0x%p) is not an " - "instruction boundary.\n", - tk->rp.kp.addr); + pr_warn("Probing address(0x%p) is not an instruction boundary.\n", + tk->rp.kp.addr); ret = -EINVAL; } } @@ -529,7 +527,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) /* Register new event */ ret = register_kprobe_event(tk); if (ret) { - pr_warning("Failed to register probe event(%d)\n", ret); + pr_warn("Failed to register probe event(%d)\n", ret); goto end; } @@ -564,10 +562,9 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, __unregister_trace_kprobe(tk); ret = __register_trace_kprobe(tk); if (ret) - pr_warning("Failed to re-register probe %s on" - "%s: %d\n", - trace_event_name(&tk->tp.call), - mod->name, ret); + pr_warn("Failed to re-register probe %s on %s: %d\n", + trace_event_name(&tk->tp.call), + mod->name, ret); } } mutex_unlock(&probe_lock); @@ -1336,16 +1333,14 @@ static __init int init_kprobe_trace(void) /* Event list interface */ if (!entry) - pr_warning("Could not create tracefs " - "'kprobe_events' entry\n"); + pr_warn("Could not create tracefs 'kprobe_events' entry\n"); /* Profile interface */ entry = tracefs_create_file("kprobe_profile", 0444, d_tracer, NULL, &kprobe_profile_ops); if (!entry) - pr_warning("Could not create tracefs " - "'kprobe_profile' entry\n"); + pr_warn("Could not create tracefs 'kprobe_profile' entry\n"); return 0; } fs_initcall(init_kprobe_trace); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 2be8c4f2403d..68f376ca6d3f 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -146,7 +146,7 @@ static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp, /* XXX: This is later than where events were lost. */ trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n); if (!overrun_detected) - pr_warning("mmiotrace has lost events.\n"); + pr_warn("mmiotrace has lost events\n"); overrun_detected = true; goto print_out; } diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 8bb2071474dd..49f61fe96a6b 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -56,7 +56,7 @@ static void nop_trace_reset(struct trace_array *tr) } /* It only serves as a signal handler and a callback to - * accept or refuse tthe setting of a flag. + * accept or refuse the setting of a flag. * If you don't implement it, then the flag setting will be * automatically accepted. */ @@ -75,7 +75,7 @@ static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (bit == TRACE_NOP_OPT_REFUSE) { printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse." - "Now cat trace_options to see the result\n", + " Now cat trace_options to see the result\n", set); return -EINVAL; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 282982195e09..0bb9cf2d53e6 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -389,7 +389,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) char irqs_off; int hardirq; int softirq; + int nmi; + nmi = entry->flags & TRACE_FLAG_NMI; hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; @@ -415,10 +417,12 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) } hardsoft_irq = + (nmi && hardirq) ? 'Z' : + nmi ? 'z' : (hardirq && softirq) ? 'H' : - hardirq ? 'h' : - softirq ? 's' : - '.'; + hardirq ? 'h' : + softirq ? 's' : + '.' ; trace_seq_printf(s, "%c%c%c", irqs_off, need_resched, hardsoft_irq); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 060df67dbdd1..f96f0383f6c6 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, void *v) const char *str = *fmt; int i; + if (!*fmt) + return 0; + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); /* diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 1769a81da8a7..1d372fa6fefb 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -636,8 +636,8 @@ ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer, *tmp = '\0'; size = tmp - kbuf + 1; } else if (done + size < count) { - pr_warning("Line length is too long: " - "Should be less than %d.", WRITE_BUFSIZE); + pr_warn("Line length is too long: Should be less than %d\n", + WRITE_BUFSIZE); ret = -EINVAL; goto out; } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 6cf935316769..413ff108fbd0 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -281,8 +281,7 @@ static int tracing_stat_init(void) stat_dir = tracefs_create_dir("trace_stat", d_tracing); if (!stat_dir) - pr_warning("Could not create tracefs " - "'trace_stat' entry\n"); + pr_warn("Could not create tracefs 'trace_stat' entry\n"); return 0; } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index d1663083d903..e78f364cc192 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -106,6 +106,17 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr) return syscalls_metadata[nr]; } +const char *get_syscall_name(int syscall) +{ + struct syscall_metadata *entry; + + entry = syscall_nr_to_meta(syscall); + if (!entry) + return NULL; + + return entry->name; +} + static enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags, struct trace_event *event) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index d2f6d0be3503..7915142c89e4 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -334,7 +334,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu) ret = register_uprobe_event(tu); if (ret) { - pr_warning("Failed to register probe event(%d)\n", ret); + pr_warn("Failed to register probe event(%d)\n", ret); goto end; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index ecd536de603a..d0639d917899 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -491,7 +491,7 @@ static __init int init_tracepoints(void) ret = register_module_notifier(&tracepoint_module_nb); if (ret) - pr_warning("Failed to register tracepoint module enter notifier\n"); + pr_warn("Failed to register tracepoint module enter notifier\n"); return ret; } |