diff options
Diffstat (limited to 'kernel')
42 files changed, 1035 insertions, 651 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 470839d1a30e..35ef1185e359 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -obj-y = fork.o exec_domain.o panic.o printk.o \ +obj-y = fork.o exec_domain.o panic.o \ cpu.o exit.o itimer.o time.o softirq.o resource.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ @@ -24,6 +24,7 @@ endif obj-y += sched/ obj-y += power/ +obj-y += printk/ obj-y += cpu/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0e0b20b8c5db..e91963302c0d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1845,36 +1845,43 @@ out: EXPORT_SYMBOL_GPL(cgroup_path); /** - * task_cgroup_path_from_hierarchy - cgroup path of a task on a hierarchy + * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task - * @hierarchy_id: the hierarchy to look up @task's cgroup from * @buf: the buffer to write the path into * @buflen: the length of the buffer * - * Determine @task's cgroup on the hierarchy specified by @hierarchy_id and - * copy its path into @buf. This function grabs cgroup_mutex and shouldn't - * be used inside locks used by cgroup controller callbacks. + * Determine @task's cgroup on the first (the one with the lowest non-zero + * hierarchy_id) cgroup hierarchy and copy its path into @buf. This + * function grabs cgroup_mutex and shouldn't be used inside locks used by + * cgroup controller callbacks. + * + * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short. */ -int task_cgroup_path_from_hierarchy(struct task_struct *task, int hierarchy_id, - char *buf, size_t buflen) +int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroupfs_root *root; - struct cgroup *cgrp = NULL; - int ret = -ENOENT; + struct cgroup *cgrp; + int hierarchy_id = 1, ret = 0; + + if (buflen < 2) + return -ENAMETOOLONG; mutex_lock(&cgroup_mutex); - root = idr_find(&cgroup_hierarchy_idr, hierarchy_id); + root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); + if (root) { cgrp = task_cgroup_from_root(task, root); ret = cgroup_path(cgrp, buf, buflen); + } else { + /* if no hierarchy exists, everyone is in "/" */ + memcpy(buf, "/", 2); } mutex_unlock(&cgroup_mutex); - return ret; } -EXPORT_SYMBOL_GPL(task_cgroup_path_from_hierarchy); +EXPORT_SYMBOL_GPL(task_cgroup_path); /* * Control Group taskset @@ -4328,8 +4335,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, } err = percpu_ref_init(&css->refcnt, css_release); - if (err) + if (err) { + ss->css_free(cgrp); goto err_free_all; + } init_cgroup_css(css, ss, cgrp); @@ -4471,6 +4480,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) struct dentry *d = cgrp->dentry; struct cgroup_event *event, *tmp; struct cgroup_subsys *ss; + struct cgroup *child; bool empty; lockdep_assert_held(&d->d_inode->i_mutex); @@ -4481,12 +4491,28 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * @cgrp from being removed while __put_css_set() is in progress. */ read_lock(&css_set_lock); - empty = list_empty(&cgrp->cset_links) && list_empty(&cgrp->children); + empty = list_empty(&cgrp->cset_links); read_unlock(&css_set_lock); if (!empty) return -EBUSY; /* + * Make sure there's no live children. We can't test ->children + * emptiness as dead children linger on it while being destroyed; + * otherwise, "rmdir parent/child parent" may fail with -EBUSY. + */ + empty = true; + rcu_read_lock(); + list_for_each_entry_rcu(child, &cgrp->children, sibling) { + empty = cgroup_is_dead(child); + if (!empty) + break; + } + rcu_read_unlock(); + if (!empty) + return -EBUSY; + + /* * Block new css_tryget() by killing css refcnts. cgroup core * guarantees that, by the time ->css_offline() is invoked, no new * css reference will be given out via css_tryget(). We can't diff --git a/kernel/cpu.c b/kernel/cpu.c index b2b227b82123..d7f07a2da5a6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -113,7 +113,7 @@ EXPORT_SYMBOL_GPL(put_online_cpus); * get_online_cpus() not an api which is called all that often. * */ -static void cpu_hotplug_begin(void) +void cpu_hotplug_begin(void) { cpu_hotplug.active_writer = current; @@ -127,7 +127,7 @@ static void cpu_hotplug_begin(void) } } -static void cpu_hotplug_done(void) +void cpu_hotplug_done(void) { cpu_hotplug.active_writer = NULL; mutex_unlock(&cpu_hotplug.lock); @@ -154,10 +154,7 @@ void cpu_hotplug_enable(void) cpu_maps_update_done(); } -#else /* #if CONFIG_HOTPLUG_CPU */ -static void cpu_hotplug_begin(void) {} -static void cpu_hotplug_done(void) {} -#endif /* #else #if CONFIG_HOTPLUG_CPU */ +#endif /* CONFIG_HOTPLUG_CPU */ /* Need to know about CPUs going up/down? */ int __ref register_cpu_notifier(struct notifier_block *nb) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e5657788fedd..ea1966db34f2 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -475,13 +475,17 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) /* * Cpusets with tasks - existing or newly being attached - can't - * have empty cpus_allowed or mems_allowed. + * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; - if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress) && - (cpumask_empty(trial->cpus_allowed) && - nodes_empty(trial->mems_allowed))) - goto out; + if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress)) { + if (!cpumask_empty(cur->cpus_allowed) && + cpumask_empty(trial->cpus_allowed)) + goto out; + if (!nodes_empty(cur->mems_allowed) && + nodes_empty(trial->mems_allowed)) + goto out; + } ret = 0; out: @@ -1608,11 +1612,13 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val) { struct cpuset *cs = cgroup_cs(cgrp); cpuset_filetype_t type = cft->private; - int retval = -ENODEV; + int retval = 0; mutex_lock(&cpuset_mutex); - if (!is_cpuset_online(cs)) + if (!is_cpuset_online(cs)) { + retval = -ENODEV; goto out_unlock; + } switch (type) { case FILE_CPU_EXCLUSIVE: diff --git a/kernel/fork.c b/kernel/fork.c index 403d2bb8a968..bf46287c91a4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1177,7 +1177,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, * don't allow the creation of threads. */ if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) && - (task_active_pid_ns(current) != current->nsproxy->pid_ns)) + (task_active_pid_ns(current) != + current->nsproxy->pid_ns_for_children)) return ERR_PTR(-EINVAL); retval = security_task_create(clone_flags); @@ -1351,7 +1352,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (pid != &init_struct_pid) { retval = -ENOMEM; - pid = alloc_pid(p->nsproxy->pid_ns); + pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (!pid) goto bad_fork_cleanup_io; } @@ -1679,6 +1680,12 @@ SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val) +#elif defined(CONFIG_CLONE_BACKWARDS3) +SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, + int, stack_size, + int __user *, parent_tidptr, + int __user *, child_tidptr, + int, tls_val) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, diff --git a/kernel/freezer.c b/kernel/freezer.c index 8b2afc1c9df0..b462fa197517 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -33,7 +33,7 @@ static DEFINE_SPINLOCK(freezer_lock); */ bool freezing_slow_path(struct task_struct *p) { - if (p->flags & PF_NOFREEZE) + if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; if (pm_nosig_freezing || cgroup_freezing(p)) diff --git a/kernel/mutex.c b/kernel/mutex.c index ff05f4bd86eb..a52ee7bb830d 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -686,7 +686,7 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) might_sleep(); ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, &ctx->dep_map, _RET_IP_, ctx); - if (!ret && ctx->acquired > 0) + if (!ret && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); return ret; @@ -702,7 +702,7 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, &ctx->dep_map, _RET_IP_, ctx); - if (!ret && ctx->acquired > 0) + if (!ret && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); return ret; diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 364ceab15f0c..997cbb951a3b 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -29,15 +29,15 @@ static struct kmem_cache *nsproxy_cachep; struct nsproxy init_nsproxy = { - .count = ATOMIC_INIT(1), - .uts_ns = &init_uts_ns, + .count = ATOMIC_INIT(1), + .uts_ns = &init_uts_ns, #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) - .ipc_ns = &init_ipc_ns, + .ipc_ns = &init_ipc_ns, #endif - .mnt_ns = NULL, - .pid_ns = &init_pid_ns, + .mnt_ns = NULL, + .pid_ns_for_children = &init_pid_ns, #ifdef CONFIG_NET - .net_ns = &init_net, + .net_ns = &init_net, #endif }; @@ -85,9 +85,10 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_ipc; } - new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns); - if (IS_ERR(new_nsp->pid_ns)) { - err = PTR_ERR(new_nsp->pid_ns); + new_nsp->pid_ns_for_children = + copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children); + if (IS_ERR(new_nsp->pid_ns_for_children)) { + err = PTR_ERR(new_nsp->pid_ns_for_children); goto out_pid; } @@ -100,8 +101,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, return new_nsp; out_net: - if (new_nsp->pid_ns) - put_pid_ns(new_nsp->pid_ns); + if (new_nsp->pid_ns_for_children) + put_pid_ns(new_nsp->pid_ns_for_children); out_pid: if (new_nsp->ipc_ns) put_ipc_ns(new_nsp->ipc_ns); @@ -174,8 +175,8 @@ void free_nsproxy(struct nsproxy *ns) put_uts_ns(ns->uts_ns); if (ns->ipc_ns) put_ipc_ns(ns->ipc_ns); - if (ns->pid_ns) - put_pid_ns(ns->pid_ns); + if (ns->pid_ns_for_children) + put_pid_ns(ns->pid_ns_for_children); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 6917e8edb48e..601bb361c235 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -349,8 +349,8 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns) if (ancestor != active) return -EINVAL; - put_pid_ns(nsproxy->pid_ns); - nsproxy->pid_ns = get_pid_ns(new); + put_pid_ns(nsproxy->pid_ns_for_children); + nsproxy->pid_ns_for_children = get_pid_ns(new); return 0; } diff --git a/kernel/power/process.c b/kernel/power/process.c index fc0df8486449..06ec8869dbf1 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -109,6 +109,8 @@ static int try_to_freeze_tasks(bool user_only) /** * freeze_processes - Signal user space processes to enter the refrigerator. + * The current thread will not be frozen. The same process that calls + * freeze_processes must later call thaw_processes. * * On success, returns 0. On failure, -errno and system is fully thawed. */ @@ -120,6 +122,9 @@ int freeze_processes(void) if (error) return error; + /* Make sure this task doesn't get frozen */ + current->flags |= PF_SUSPEND_TASK; + if (!pm_freezing) atomic_inc(&system_freezing_cnt); @@ -168,6 +173,7 @@ int freeze_kernel_threads(void) void thaw_processes(void) { struct task_struct *g, *p; + struct task_struct *curr = current; if (pm_freezing) atomic_dec(&system_freezing_cnt); @@ -182,10 +188,15 @@ void thaw_processes(void) read_lock(&tasklist_lock); do_each_thread(g, p) { + /* No other threads should have PF_SUSPEND_TASK set */ + WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK)); __thaw_task(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); + WARN_ON(!(curr->flags & PF_SUSPEND_TASK)); + curr->flags &= ~PF_SUSPEND_TASK; + usermodehelper_enable(); schedule(); diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 06fe28589e9c..a394297f8b2f 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -296,6 +296,17 @@ int pm_qos_request_active(struct pm_qos_request *req) } EXPORT_SYMBOL_GPL(pm_qos_request_active); +static void __pm_qos_update_request(struct pm_qos_request *req, + s32 new_value) +{ + trace_pm_qos_update_request(req->pm_qos_class, new_value); + + if (new_value != req->node.prio) + pm_qos_update_target( + pm_qos_array[req->pm_qos_class]->constraints, + &req->node, PM_QOS_UPDATE_REQ, new_value); +} + /** * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout * @work: work struct for the delayed work (timeout) @@ -308,7 +319,7 @@ static void pm_qos_work_fn(struct work_struct *work) struct pm_qos_request, work); - pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE); + __pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE); } /** @@ -364,12 +375,7 @@ void pm_qos_update_request(struct pm_qos_request *req, } cancel_delayed_work_sync(&req->work); - - trace_pm_qos_update_request(req->pm_qos_class, new_value); - if (new_value != req->node.prio) - pm_qos_update_target( - pm_qos_array[req->pm_qos_class]->constraints, - &req->node, PM_QOS_UPDATE_REQ, new_value); + __pm_qos_update_request(req, new_value); } EXPORT_SYMBOL_GPL(pm_qos_update_request); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index ece04223bb1e..62ee437b5c7e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -210,6 +210,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) goto Platform_wake; } + ftrace_stop(); error = disable_nonboot_cpus(); if (error || suspend_test(TEST_CPUS)) goto Enable_cpus; @@ -232,6 +233,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) Enable_cpus: enable_nonboot_cpus(); + ftrace_start(); Platform_wake: if (need_suspend_ops(state) && suspend_ops->wake) @@ -265,7 +267,6 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); - ftrace_stop(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -285,7 +286,6 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); - ftrace_start(); resume_console(); Close: if (need_suspend_ops(state) && suspend_ops->end) diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile new file mode 100644 index 000000000000..85405bdcf2b3 --- /dev/null +++ b/kernel/printk/Makefile @@ -0,0 +1,2 @@ +obj-y = printk.o +obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c new file mode 100644 index 000000000000..276762f3a460 --- /dev/null +++ b/kernel/printk/braille.c @@ -0,0 +1,49 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/console.h> +#include <linux/string.h> + +#include "console_cmdline.h" +#include "braille.h" + +char *_braille_console_setup(char **str, char **brl_options) +{ + if (!memcmp(*str, "brl,", 4)) { + *brl_options = ""; + *str += 4; + } else if (!memcmp(str, "brl=", 4)) { + *brl_options = *str + 4; + *str = strchr(*brl_options, ','); + if (!*str) + pr_err("need port name after brl=\n"); + else + *((*str)++) = 0; + } else + return NULL; + + return *str; +} + +int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + int rtn = 0; + + if (c->brl_options) { + console->flags |= CON_BRL; + rtn = braille_register_console(console, c->index, c->options, + c->brl_options); + } + + return rtn; +} + +int +_braille_unregister_console(struct console *console) +{ + if (console->flags & CON_BRL) + return braille_unregister_console(console); + + return 0; +} diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h new file mode 100644 index 000000000000..769d771145c8 --- /dev/null +++ b/kernel/printk/braille.h @@ -0,0 +1,48 @@ +#ifndef _PRINTK_BRAILLE_H +#define _PRINTK_BRAILLE_H + +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ + c->brl_options = brl_options; +} + +char * +_braille_console_setup(char **str, char **brl_options); + +int +_braille_register_console(struct console *console, struct console_cmdline *c); + +int +_braille_unregister_console(struct console *console); + +#else + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ +} + +static inline char * +_braille_console_setup(char **str, char **brl_options) +{ + return NULL; +} + +static inline int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + return 0; +} + +static inline int +_braille_unregister_console(struct console *console) +{ + return 0; +} + +#endif + +#endif diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h new file mode 100644 index 000000000000..cbd69d842341 --- /dev/null +++ b/kernel/printk/console_cmdline.h @@ -0,0 +1,14 @@ +#ifndef _CONSOLE_CMDLINE_H +#define _CONSOLE_CMDLINE_H + +struct console_cmdline +{ + char name[8]; /* Name of the driver */ + int index; /* Minor dev. to use */ + char *options; /* Options for the driver */ +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + char *brl_options; /* Options for braille driver */ +#endif +}; + +#endif diff --git a/kernel/printk.c b/kernel/printk/printk.c index 69b0890ed7e5..b4e8500afdb3 100644 --- a/kernel/printk.c +++ b/kernel/printk/printk.c @@ -51,6 +51,9 @@ #define CREATE_TRACE_POINTS #include <trace/events/printk.h> +#include "console_cmdline.h" +#include "braille.h" + /* printk's without a loglevel use this.. */ #define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL @@ -105,19 +108,11 @@ static struct console *exclusive_console; /* * Array of consoles built from command line options (console=) */ -struct console_cmdline -{ - char name[8]; /* Name of the driver */ - int index; /* Minor dev. to use */ - char *options; /* Options for the driver */ -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - char *brl_options; /* Options for braille driver */ -#endif -}; #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; + static int selected_console = -1; static int preferred_console = -1; int console_set_on_cmdline; @@ -178,7 +173,7 @@ static int console_may_schedule; * 67 "g" * 0032 00 00 00 padding to next message header * - * The 'struct log' buffer header must never be directly exported to + * The 'struct printk_log' buffer header must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * @@ -200,7 +195,7 @@ enum log_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; -struct log { +struct printk_log { u64 ts_nsec; /* timestamp in nanoseconds */ u16 len; /* length of entire record */ u16 text_len; /* length of text buffer */ @@ -248,7 +243,7 @@ static u32 clear_idx; #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) #define LOG_ALIGN 4 #else -#define LOG_ALIGN __alignof__(struct log) +#define LOG_ALIGN __alignof__(struct printk_log) #endif #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); @@ -259,35 +254,35 @@ static u32 log_buf_len = __LOG_BUF_LEN; static volatile unsigned int logbuf_cpu = UINT_MAX; /* human readable text of the record */ -static char *log_text(const struct log *msg) +static char *log_text(const struct printk_log *msg) { - return (char *)msg + sizeof(struct log); + return (char *)msg + sizeof(struct printk_log); } /* optional key/value pair dictionary attached to the record */ -static char *log_dict(const struct log *msg) +static char *log_dict(const struct printk_log *msg) { - return (char *)msg + sizeof(struct log) + msg->text_len; + return (char *)msg + sizeof(struct printk_log) + msg->text_len; } /* get record by index; idx must point to valid msg */ -static struct log *log_from_idx(u32 idx) +static struct printk_log *log_from_idx(u32 idx) { - struct log *msg = (struct log *)(log_buf + idx); + struct printk_log *msg = (struct printk_log *)(log_buf + idx); /* * A length == 0 record is the end of buffer marker. Wrap around and * read the message at the start of the buffer. */ if (!msg->len) - return (struct log *)log_buf; + return (struct printk_log *)log_buf; return msg; } /* get next record; idx must point to valid msg */ static u32 log_next(u32 idx) { - struct log *msg = (struct log *)(log_buf + idx); + struct printk_log *msg = (struct printk_log *)(log_buf + idx); /* length == 0 indicates the end of the buffer; wrap */ /* @@ -296,7 +291,7 @@ static u32 log_next(u32 idx) * return the one after that. */ if (!msg->len) { - msg = (struct log *)log_buf; + msg = (struct printk_log *)log_buf; return msg->len; } return idx + msg->len; @@ -308,11 +303,11 @@ static void log_store(int facility, int level, const char *dict, u16 dict_len, const char *text, u16 text_len) { - struct log *msg; + struct printk_log *msg; u32 size, pad_len; /* number of '\0' padding bytes to next message */ - size = sizeof(struct log) + text_len + dict_len; + size = sizeof(struct printk_log) + text_len + dict_len; pad_len = (-size) & (LOG_ALIGN - 1); size += pad_len; @@ -324,7 +319,7 @@ static void log_store(int facility, int level, else free = log_first_idx - log_next_idx; - if (free > size + sizeof(struct log)) + if (free > size + sizeof(struct printk_log)) break; /* drop old messages until we have enough contiuous space */ @@ -332,18 +327,18 @@ static void log_store(int facility, int level, log_first_seq++; } - if (log_next_idx + size + sizeof(struct log) >= log_buf_len) { + if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) { /* * This message + an additional empty header does not fit * at the end of the buffer. Add an empty header with len == 0 * to signify a wrap around. */ - memset(log_buf + log_next_idx, 0, sizeof(struct log)); + memset(log_buf + log_next_idx, 0, sizeof(struct printk_log)); log_next_idx = 0; } /* fill message */ - msg = (struct log *)(log_buf + log_next_idx); + msg = (struct printk_log *)(log_buf + log_next_idx); memcpy(log_text(msg), text, text_len); msg->text_len = text_len; memcpy(log_dict(msg), dict, dict_len); @@ -356,7 +351,7 @@ static void log_store(int facility, int level, else msg->ts_nsec = local_clock(); memset(log_dict(msg) + dict_len, 0, pad_len); - msg->len = sizeof(struct log) + text_len + dict_len + pad_len; + msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len; /* insert message */ log_next_idx += msg->len; @@ -479,7 +474,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; - struct log *msg; + struct printk_log *msg; u64 ts_usec; size_t i; char cont = '-'; @@ -724,14 +719,14 @@ void log_buf_kexec_setup(void) VMCOREINFO_SYMBOL(log_first_idx); VMCOREINFO_SYMBOL(log_next_idx); /* - * Export struct log size and field offsets. User space tools can + * Export struct printk_log size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ - VMCOREINFO_STRUCT_SIZE(log); - VMCOREINFO_OFFSET(log, ts_nsec); - VMCOREINFO_OFFSET(log, len); - VMCOREINFO_OFFSET(log, text_len); - VMCOREINFO_OFFSET(log, dict_len); + VMCOREINFO_STRUCT_SIZE(printk_log); + VMCOREINFO_OFFSET(printk_log, ts_nsec); + VMCOREINFO_OFFSET(printk_log, len); + VMCOREINFO_OFFSET(printk_log, text_len); + VMCOREINFO_OFFSET(printk_log, dict_len); } #endif @@ -884,7 +879,7 @@ static size_t print_time(u64 ts, char *buf) (unsigned long)ts, rem_nsec / 1000); } -static size_t print_prefix(const struct log *msg, bool syslog, char *buf) +static size_t print_prefix(const struct printk_log *msg, bool syslog, char *buf) { size_t len = 0; unsigned int prefix = (msg->facility << 3) | msg->level; @@ -907,7 +902,7 @@ static size_t print_prefix(const struct log *msg, bool syslog, char *buf) return len; } -static size_t msg_print_text(const struct log *msg, enum log_flags prev, +static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, bool syslog, char *buf, size_t size) { const char *text = log_text(msg); @@ -969,7 +964,7 @@ static size_t msg_print_text(const struct log *msg, enum log_flags prev, static int syslog_print(char __user *buf, int size) { char *text; - struct log *msg; + struct printk_log *msg; int len = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); @@ -1060,7 +1055,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) idx = clear_idx; prev = 0; while (seq < log_next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); len += msg_print_text(msg, prev, true, NULL, 0); prev = msg->flags; @@ -1073,7 +1068,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) idx = clear_idx; prev = 0; while (len > size && seq < log_next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); len -= msg_print_text(msg, prev, true, NULL, 0); prev = msg->flags; @@ -1087,7 +1082,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) len = 0; prev = 0; while (len >= 0 && seq < next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); int textlen; textlen = msg_print_text(msg, prev, true, text, @@ -1233,7 +1228,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) error = 0; while (seq < log_next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); error += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); @@ -1719,10 +1714,10 @@ static struct cont { u8 level; bool flushed:1; } cont; -static struct log *log_from_idx(u32 idx) { return NULL; } +static struct printk_log *log_from_idx(u32 idx) { return NULL; } static u32 log_next(u32 idx) { return 0; } static void call_console_drivers(int level, const char *text, size_t len) {} -static size_t msg_print_text(const struct log *msg, enum log_flags prev, +static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, bool syslog, char *buf, size_t size) { return 0; } static size_t cont_print_text(char *text, size_t size) { return 0; } @@ -1761,23 +1756,23 @@ static int __add_preferred_console(char *name, int idx, char *options, * See if this tty is not yet registered, and * if we have a slot free. */ - for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++) - if (strcmp(console_cmdline[i].name, name) == 0 && - console_cmdline[i].index == idx) { - if (!brl_options) - selected_console = i; - return 0; + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (strcmp(c->name, name) == 0 && c->index == idx) { + if (!brl_options) + selected_console = i; + return 0; } + } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) selected_console = i; - c = &console_cmdline[i]; strlcpy(c->name, name, sizeof(c->name)); c->options = options; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - c->brl_options = brl_options; -#endif + braille_set_options(c, brl_options); + c->index = idx; return 0; } @@ -1790,20 +1785,8 @@ static int __init console_setup(char *str) char *s, *options, *brl_options = NULL; int idx; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - if (!memcmp(str, "brl,", 4)) { - brl_options = ""; - str += 4; - } else if (!memcmp(str, "brl=", 4)) { - brl_options = str + 4; - str = strchr(brl_options, ','); - if (!str) { - printk(KERN_ERR "need port name after brl=\n"); - return 1; - } - *(str++) = 0; - } -#endif + if (_braille_console_setup(&str, &brl_options)) + return 1; /* * Decode str into name, index, options. @@ -1858,15 +1841,15 @@ int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, cha struct console_cmdline *c; int i; - for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++) - if (strcmp(console_cmdline[i].name, name) == 0 && - console_cmdline[i].index == idx) { - c = &console_cmdline[i]; - strlcpy(c->name, name_new, sizeof(c->name)); - c->name[sizeof(c->name) - 1] = 0; - c->options = options; - c->index = idx_new; - return i; + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) + if (strcmp(c->name, name) == 0 && c->index == idx) { + strlcpy(c->name, name_new, sizeof(c->name)); + c->name[sizeof(c->name) - 1] = 0; + c->options = options; + c->index = idx_new; + return i; } /* not found */ return -1; @@ -2046,7 +2029,7 @@ void console_unlock(void) console_cont_flush(text, sizeof(text)); again: for (;;) { - struct log *msg; + struct printk_log *msg; size_t len; int level; @@ -2241,6 +2224,14 @@ void register_console(struct console *newcon) int i; unsigned long flags; struct console *bcon = NULL; + struct console_cmdline *c; + + if (console_drivers) + for_each_console(bcon) + if (WARN(bcon == newcon, + "console '%s%d' already registered\n", + bcon->name, bcon->index)) + return; /* * before we register a new CON_BOOT console, make sure we don't @@ -2288,30 +2279,25 @@ void register_console(struct console *newcon) * See if this console matches one we selected on * the command line. */ - for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; - i++) { - if (strcmp(console_cmdline[i].name, newcon->name) != 0) + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && - newcon->index != console_cmdline[i].index) + newcon->index != c->index) continue; if (newcon->index < 0) - newcon->index = console_cmdline[i].index; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - if (console_cmdline[i].brl_options) { - newcon->flags |= CON_BRL; - braille_register_console(newcon, - console_cmdline[i].index, - console_cmdline[i].options, - console_cmdline[i].brl_options); + newcon->index = c->index; + + if (_braille_register_console(newcon, c)) return; - } -#endif + if (newcon->setup && newcon->setup(newcon, console_cmdline[i].options) != 0) break; newcon->flags |= CON_ENABLED; - newcon->index = console_cmdline[i].index; + newcon->index = c->index; if (i == selected_console) { newcon->flags |= CON_CONSDEV; preferred_console = selected_console; @@ -2394,13 +2380,13 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { struct console *a, *b; - int res = 1; + int res; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - if (console->flags & CON_BRL) - return braille_unregister_console(console); -#endif + res = _braille_unregister_console(console); + if (res) + return res; + res = 1; console_lock(); if (console_drivers == console) { console_drivers=console->next; @@ -2666,7 +2652,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { - struct log *msg; + struct printk_log *msg; size_t l = 0; bool ret = false; @@ -2778,7 +2764,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, idx = dumper->cur_idx; prev = 0; while (seq < dumper->next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); l += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); @@ -2791,7 +2777,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, idx = dumper->cur_idx; prev = 0; while (l > size && seq < dumper->next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); l -= msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); @@ -2806,7 +2792,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, l = 0; prev = 0; while (seq < dumper->next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); l += msg_print_text(msg, prev, syslog, buf + l, size - l); idx = log_next(idx); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 4041f5747e73..a146ee327f6a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -469,7 +469,6 @@ static int ptrace_detach(struct task_struct *child, unsigned int data) /* Architecture-specific hardware disable .. */ ptrace_disable(child); clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - flush_ptrace_hw_breakpoint(child); write_lock_irq(&tasklist_lock); /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7c32cb7bfeb..05c39f030314 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -933,6 +933,8 @@ static int effective_prio(struct task_struct *p) /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. */ inline int task_curr(const struct task_struct *p) { @@ -1482,7 +1484,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * Returns %true if @p was woken up, %false if it was already running + * Return: %true if @p was woken up, %false if it was already running. * or @state didn't match @p's state. */ static int @@ -1491,7 +1493,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; - smp_wmb(); + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); raw_spin_lock_irqsave(&p->pi_lock, flags); if (!(p->state & state)) goto out; @@ -1577,8 +1585,9 @@ out: * @p: The process to be woken up. * * Attempt to wake up the nominated process and move it to the set of runnable - * processes. Returns 1 if the process was woken up, 0 if it was already - * running. + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. * * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. @@ -2191,6 +2200,8 @@ void scheduler_tick(void) * This makes sure that uptime, CFS vruntime, load * balancing, etc... continue to move forward, even * with a very low granularity. + * + * Return: Maximum deferment in nanoseconds. */ u64 scheduler_tick_max_deferment(void) { @@ -2394,6 +2405,12 @@ need_resched: if (sched_feat(HRTICK)) hrtick_clear(rq); + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); switch_count = &prev->nivcsw; @@ -2796,8 +2813,8 @@ EXPORT_SYMBOL(wait_for_completion); * specified timeout to expire. The timeout is in jiffies. It is not * interruptible. * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. */ unsigned long __sched wait_for_completion_timeout(struct completion *x, unsigned long timeout) @@ -2829,8 +2846,8 @@ EXPORT_SYMBOL(wait_for_completion_io); * specified timeout to expire. The timeout is in jiffies. It is not * interruptible. The caller is accounted as waiting for IO. * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. */ unsigned long __sched wait_for_completion_io_timeout(struct completion *x, unsigned long timeout) @@ -2846,7 +2863,7 @@ EXPORT_SYMBOL(wait_for_completion_io_timeout); * This waits for completion of a specific task to be signaled. It is * interruptible. * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. + * Return: -ERESTARTSYS if interrupted, 0 if completed. */ int __sched wait_for_completion_interruptible(struct completion *x) { @@ -2865,8 +2882,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible); * This waits for either a completion of a specific task to be signaled or for a * specified timeout to expire. It is interruptible. The timeout is in jiffies. * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. */ long __sched wait_for_completion_interruptible_timeout(struct completion *x, @@ -2883,7 +2900,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); * This waits to be signaled for completion of a specific task. It can be * interrupted by a kill signal. * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. + * Return: -ERESTARTSYS if interrupted, 0 if completed. */ int __sched wait_for_completion_killable(struct completion *x) { @@ -2903,8 +2920,8 @@ EXPORT_SYMBOL(wait_for_completion_killable); * signaled or for a specified timeout to expire. It can be * interrupted by a kill signal. The timeout is in jiffies. * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. */ long __sched wait_for_completion_killable_timeout(struct completion *x, @@ -2918,7 +2935,7 @@ EXPORT_SYMBOL(wait_for_completion_killable_timeout); * try_wait_for_completion - try to decrement a completion without blocking * @x: completion structure * - * Returns: 0 if a decrement cannot be done without blocking + * Return: 0 if a decrement cannot be done without blocking * 1 if a decrement succeeded. * * If a completion is being used as a counting completion, @@ -2945,7 +2962,7 @@ EXPORT_SYMBOL(try_wait_for_completion); * completion_done - Test to see if a completion has any waiters * @x: completion structure * - * Returns: 0 if there are waiters (wait_for_completion() in progress) + * Return: 0 if there are waiters (wait_for_completion() in progress) * 1 if there are no waiters. * */ @@ -3182,7 +3199,7 @@ SYSCALL_DEFINE1(nice, int, increment) * task_prio - return the priority value of a given task. * @p: the task in question. * - * This is the priority value as seen by users in /proc. + * Return: The priority value as seen by users in /proc. * RT tasks are offset by -200. Normal tasks are centered * around 0, value goes from -16 to +15. */ @@ -3194,6 +3211,8 @@ int task_prio(const struct task_struct *p) /** * task_nice - return the nice value of a given task. * @p: the task in question. + * + * Return: The nice value [ -20 ... 0 ... 19 ]. */ int task_nice(const struct task_struct *p) { @@ -3204,6 +3223,8 @@ EXPORT_SYMBOL(task_nice); /** * idle_cpu - is a given cpu idle currently? * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. */ int idle_cpu(int cpu) { @@ -3226,6 +3247,8 @@ int idle_cpu(int cpu) /** * idle_task - return the idle task for a given cpu. * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. */ struct task_struct *idle_task(int cpu) { @@ -3235,6 +3258,8 @@ struct task_struct *idle_task(int cpu) /** * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. */ static struct task_struct *find_process_by_pid(pid_t pid) { @@ -3432,6 +3457,8 @@ recheck: * @policy: new policy. * @param: structure containing the new RT priority. * + * Return: 0 on success. An error code otherwise. + * * NOTE that the task may be already dead. */ int sched_setscheduler(struct task_struct *p, int policy, @@ -3451,6 +3478,8 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * current context has permission. For example, this is needed in * stop_machine(): we create temporary high priority worker threads, * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. */ int sched_setscheduler_nocheck(struct task_struct *p, int policy, const struct sched_param *param) @@ -3485,6 +3514,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) * @pid: the pid in question. * @policy: new policy. * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) @@ -3500,6 +3531,8 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, * sys_sched_setparam - set/change the RT priority of a thread * @pid: the pid in question. * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) { @@ -3509,6 +3542,9 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) /** * sys_sched_getscheduler - get the policy (scheduling class) of a thread * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. */ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) { @@ -3535,6 +3571,9 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) * sys_sched_getparam - get the RT priority of a thread * @pid: the pid in question. * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. */ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) { @@ -3659,6 +3698,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr * @user_mask_ptr: user-space pointer to the new cpu mask + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, unsigned long __user *, user_mask_ptr) @@ -3710,6 +3751,8 @@ out_unlock: * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr * @user_mask_ptr: user-space pointer to hold the current cpu mask + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, unsigned long __user *, user_mask_ptr) @@ -3744,6 +3787,8 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, * * This function yields the current CPU to other tasks. If there are no * other threads running on this CPU then this function will return. + * + * Return: 0. */ SYSCALL_DEFINE0(sched_yield) { @@ -3869,7 +3914,7 @@ EXPORT_SYMBOL(yield); * It's the caller's job to ensure that the target task struct * can't go away on us before we can do any checks. * - * Returns: + * Return: * true (>0) if we indeed boosted the target task. * false (0) if we failed to boost the target. * -ESRCH if there's no task to yield to. @@ -3972,8 +4017,9 @@ long __sched io_schedule_timeout(long timeout) * sys_sched_get_priority_max - return maximum RT priority. * @policy: scheduling class. * - * this syscall returns the maximum rt_priority that can be used - * by a given scheduling class. + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. */ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) { @@ -3997,8 +4043,9 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) * sys_sched_get_priority_min - return minimum RT priority. * @policy: scheduling class. * - * this syscall returns the minimum rt_priority that can be used - * by a given scheduling class. + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. */ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) { @@ -4024,6 +4071,9 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) * * this syscall writes the default timeslice value of a given process * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, struct timespec __user *, interval) @@ -6632,6 +6682,8 @@ void normalize_rt_tasks(void) * @cpu: the processor in question. * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. */ struct task_struct *curr_task(int cpu) { diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 1095e878a46f..8b836b376d91 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -62,7 +62,7 @@ static int convert_prio(int prio) * any discrepancies created by racing against the uncertainty of the current * priority configuration. * - * Returns: (int)bool - CPUs were found + * Return: (int)bool - CPUs were found */ int cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask) @@ -203,7 +203,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * cpupri_init - initialize the cpupri structure * @cp: The cpupri context * - * Returns: -ENOMEM if memory fails. + * Return: -ENOMEM on memory allocation failure. */ int cpupri_init(struct cpupri *cp) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bb456f44b7b1..68f1609ca149 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -851,7 +851,7 @@ void task_numa_fault(int node, int pages, bool migrated) { struct task_struct *p = current; - if (!sched_feat_numa(NUMA)) + if (!numabalancing_enabled) return; /* FIXME: Allocate task-specific structure for placement policy here */ @@ -2032,6 +2032,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) */ update_entity_load_avg(curr, 1); update_cfs_rq_blocked_load(cfs_rq, 1); + update_cfs_shares(cfs_rq); #ifdef CONFIG_SCHED_HRTICK /* @@ -4280,6 +4281,8 @@ struct sg_lb_stats { * get_sd_load_idx - Obtain the load index for a given sched domain. * @sd: The sched_domain whose load_idx is to be obtained. * @idle: The Idle status of the CPU for whose sd load_icx is obtained. + * + * Return: The load index. */ static inline int get_sd_load_idx(struct sched_domain *sd, enum cpu_idle_type idle) @@ -4574,6 +4577,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, * * Determine if @sg is a busier group than the previously selected * busiest group. + * + * Return: %true if @sg is a busier group than the previously selected + * busiest group. %false otherwise. */ static bool update_sd_pick_busiest(struct lb_env *env, struct sd_lb_stats *sds, @@ -4691,7 +4697,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, * assuming lower CPU number will be equivalent to lower a SMT thread * number. * - * Returns 1 when packing is required and a task should be moved to + * Return: 1 when packing is required and a task should be moved to * this CPU. The amount of the imbalance is returned in *imbalance. * * @env: The load balancing environment. @@ -4869,7 +4875,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * @balance: Pointer to a variable indicating if this_cpu * is the appropriate cpu to perform load balancing at this_level. * - * Returns: - the busiest group if imbalance exists. + * Return: - The busiest group if imbalance exists. * - If no imbalance and user has opted for power-savings balance, * return the least loaded group whose CPUs can be * put to idle by rebalancing its tasks onto our group. @@ -5786,7 +5792,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) entity_tick(cfs_rq, se, queued); } - if (sched_feat_numa(NUMA)) + if (numabalancing_enabled) task_tick_numa(rq, curr); update_rq_runnable_avg(rq, 1); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ac09d98490aa..07f6fc468e17 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2346,7 +2346,11 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp, int write, void *data) { if (write) { - *valp = msecs_to_jiffies(*negp ? -*lvalp : *lvalp); + unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp); + + if (jif > INT_MAX) + return 1; + *valp = (int)jif; } else { int val = *valp; unsigned long lval; diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index a326f27d7f09..0b479a6a22bb 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -121,7 +121,7 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate) BUG_ON(bits > 32); WARN_ON(!irqs_disabled()); read_sched_clock = read; - sched_clock_mask = (1 << bits) - 1; + sched_clock_mask = (1ULL << bits) - 1; cd.rate = rate; /* calculate the mult/shift to convert counter ticks to ns. */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index e80183f4a6c4..e8a1516cc0a3 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -182,7 +182,8 @@ static bool can_stop_full_tick(void) * Don't allow the user to think they can get * full NO_HZ with this machine. */ - WARN_ONCE(1, "NO_HZ FULL will not work with unstable sched clock"); + WARN_ONCE(have_nohz_full_mask, + "NO_HZ FULL will not work with unstable sched clock"); return false; } #endif @@ -343,8 +344,6 @@ static int tick_nohz_init_all(void) void __init tick_nohz_init(void) { - int cpu; - if (!have_nohz_full_mask) { if (tick_nohz_init_all() < 0) return; @@ -827,13 +826,10 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); - if (ts->inidle) { - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); + if (ts->inidle) __tick_nohz_idle_enter(ts); - } else { + else tick_nohz_full_stop_tick(ts); - } } /** @@ -931,8 +927,6 @@ void tick_nohz_idle_exit(void) ts->inidle = 0; - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); if (ts->idle_active || ts->tick_stopped) now = ktime_get(); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 3bdf28323012..61ed862cdd37 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -265,10 +265,9 @@ static inline void timer_list_header(struct seq_file *m, u64 now) static int timer_list_show(struct seq_file *m, void *v) { struct timer_list_iter *iter = v; - u64 now = ktime_to_ns(ktime_get()); if (iter->cpu == -1 && !iter->second_pass) - timer_list_header(m, now); + timer_list_header(m, iter->now); else if (!iter->second_pass) print_cpu(m, iter->cpu, iter->now); #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -298,33 +297,41 @@ void sysrq_timer_list_show(void) return; } -static void *timer_list_start(struct seq_file *file, loff_t *offset) +static void *move_iter(struct timer_list_iter *iter, loff_t offset) { - struct timer_list_iter *iter = file->private; - - if (!*offset) { - iter->cpu = -1; - iter->now = ktime_to_ns(ktime_get()); - } else if (iter->cpu >= nr_cpu_ids) { + for (; offset; offset--) { + iter->cpu = cpumask_next(iter->cpu, cpu_online_mask); + if (iter->cpu >= nr_cpu_ids) { #ifdef CONFIG_GENERIC_CLOCKEVENTS - if (!iter->second_pass) { - iter->cpu = -1; - iter->second_pass = true; - } else - return NULL; + if (!iter->second_pass) { + iter->cpu = -1; + iter->second_pass = true; + } else + return NULL; #else - return NULL; + return NULL; #endif + } } return iter; } +static void *timer_list_start(struct seq_file *file, loff_t *offset) +{ + struct timer_list_iter *iter = file->private; + + if (!*offset) + iter->now = ktime_to_ns(ktime_get()); + iter->cpu = -1; + iter->second_pass = false; + return move_iter(iter, *offset); +} + static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset) { struct timer_list_iter *iter = file->private; - iter->cpu = cpumask_next(iter->cpu, cpu_online_mask); ++*offset; - return timer_list_start(file, offset); + return move_iter(iter, 1); } static void timer_list_stop(struct seq_file *seq, void *v) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 67708f46baae..a6d098c6df3f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1441,12 +1441,22 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, * the hashes are freed with call_rcu_sched(). */ static int -ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { struct ftrace_hash *filter_hash; struct ftrace_hash *notrace_hash; int ret; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* + * There's a small race when adding ops that the ftrace handler + * that wants regs, may be called without them. We can not + * allow that handler to be called if regs is NULL. + */ + if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS)) + return 0; +#endif + filter_hash = rcu_dereference_raw_notrace(ops->filter_hash); notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash); @@ -2159,12 +2169,57 @@ static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; -static int ops_traces_mod(struct ftrace_ops *ops) +static inline int ops_traces_mod(struct ftrace_ops *ops) { - struct ftrace_hash *hash; + /* + * Filter_hash being empty will default to trace module. + * But notrace hash requires a test of individual module functions. + */ + return ftrace_hash_empty(ops->filter_hash) && + ftrace_hash_empty(ops->notrace_hash); +} + +/* + * Check if the current ops references the record. + * + * If the ops traces all functions, then it was already accounted for. + * If the ops does not trace the current record function, skip it. + * If the ops ignores the function via notrace filter, skip it. + */ +static inline bool +ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + /* If ops isn't enabled, ignore it */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return 0; + + /* If ops traces all mods, we already accounted for it */ + if (ops_traces_mod(ops)) + return 0; + + /* The function must be in the filter */ + if (!ftrace_hash_empty(ops->filter_hash) && + !ftrace_lookup_ip(ops->filter_hash, rec->ip)) + return 0; + + /* If in notrace hash, we ignore it too */ + if (ftrace_lookup_ip(ops->notrace_hash, rec->ip)) + return 0; - hash = ops->filter_hash; - return ftrace_hash_empty(hash); + return 1; +} + +static int referenced_filters(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + int cnt = 0; + + for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { + if (ops_references_rec(ops, rec)) + cnt++; + } + + return cnt; } static int ftrace_update_code(struct module *mod) @@ -2173,6 +2228,7 @@ static int ftrace_update_code(struct module *mod) struct dyn_ftrace *p; cycle_t start, stop; unsigned long ref = 0; + bool test = false; int i; /* @@ -2186,9 +2242,12 @@ static int ftrace_update_code(struct module *mod) for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { - if (ops->flags & FTRACE_OPS_FL_ENABLED && - ops_traces_mod(ops)) - ref++; + if (ops->flags & FTRACE_OPS_FL_ENABLED) { + if (ops_traces_mod(ops)) + ref++; + else + test = true; + } } } @@ -2198,12 +2257,16 @@ static int ftrace_update_code(struct module *mod) for (pg = ftrace_new_pgs; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { + int cnt = ref; + /* If something went wrong, bail without enabling anything */ if (unlikely(ftrace_disabled)) return -1; p = &pg->records[i]; - p->flags = ref; + if (test) + cnt += referenced_filters(p); + p->flags = cnt; /* * Do the initial record conversion from mcount jump @@ -2223,7 +2286,7 @@ static int ftrace_update_code(struct module *mod) * conversion puts the module to the correct state, thus * passing the ftrace_make_call check. */ - if (ftrace_start_up && ref) { + if (ftrace_start_up && cnt) { int failed = __ftrace_replace_code(p, 1); if (failed) ftrace_bug(failed, p->ip); @@ -3374,6 +3437,12 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return add_hash_entry(hash, ip); } +static void ftrace_ops_update_code(struct ftrace_ops *ops) +{ + if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled) + ftrace_run_update_code(FTRACE_UPDATE_CALLS); +} + static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long ip, int remove, int reset, int enable) @@ -3416,9 +3485,8 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); - if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED - && ftrace_enabled) - ftrace_run_update_code(FTRACE_UPDATE_CALLS); + if (!ret) + ftrace_ops_update_code(ops); mutex_unlock(&ftrace_lock); @@ -3645,9 +3713,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file) mutex_lock(&ftrace_lock); ret = ftrace_hash_move(iter->ops, filter_hash, orig_hash, iter->hash); - if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED) - && ftrace_enabled) - ftrace_run_update_code(FTRACE_UPDATE_CALLS); + if (!ret) + ftrace_ops_update_code(iter->ops); mutex_unlock(&ftrace_lock); } @@ -4218,7 +4285,7 @@ static inline void ftrace_startup_enable(int command) { } # define ftrace_shutdown_sysctl() do { } while (0) static inline int -ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { return 1; } @@ -4241,7 +4308,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, do_for_each_ftrace_op(op, ftrace_control_list) { if (!(op->flags & FTRACE_OPS_FL_STUB) && !ftrace_function_local_disabled(op) && - ftrace_ops_test(op, ip)) + ftrace_ops_test(op, ip, regs)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); trace_recursion_clear(TRACE_CONTROL_BIT); @@ -4274,7 +4341,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, */ preempt_disable_notrace(); do_for_each_ftrace_op(op, ftrace_ops_list) { - if (ftrace_ops_test(op, ip)) + if (ftrace_ops_test(op, ip, regs)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); preempt_enable_notrace(); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e444ff88f0a4..cc2f66f68dc5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -36,11 +36,11 @@ int ring_buffer_print_entry_header(struct trace_seq *s) { int ret; - ret = trace_seq_printf(s, "# compressed entry header\n"); - ret = trace_seq_printf(s, "\ttype_len : 5 bits\n"); - ret = trace_seq_printf(s, "\ttime_delta : 27 bits\n"); - ret = trace_seq_printf(s, "\tarray : 32 bits\n"); - ret = trace_seq_printf(s, "\n"); + ret = trace_seq_puts(s, "# compressed entry header\n"); + ret = trace_seq_puts(s, "\ttype_len : 5 bits\n"); + ret = trace_seq_puts(s, "\ttime_delta : 27 bits\n"); + ret = trace_seq_puts(s, "\tarray : 32 bits\n"); + ret = trace_seq_putc(s, '\n'); ret = trace_seq_printf(s, "\tpadding : type == %d\n", RINGBUF_TYPE_PADDING); ret = trace_seq_printf(s, "\ttime_extend : type == %d\n", @@ -1066,7 +1066,7 @@ static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, } /** - * check_pages - integrity check of buffer pages + * rb_check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test * * As a safety measure we check to make sure the data pages have not @@ -1258,7 +1258,7 @@ static int rb_cpu_notify(struct notifier_block *self, #endif /** - * ring_buffer_alloc - allocate a new ring_buffer + * __ring_buffer_alloc - allocate a new ring_buffer * @size: the size in bytes per cpu that is needed. * @flags: attributes to set for the ring buffer. * @@ -1607,6 +1607,7 @@ static void update_pages_handler(struct work_struct *work) * ring_buffer_resize - resize the ring buffer * @buffer: the buffer to resize. * @size: the new size. + * @cpu_id: the cpu buffer to resize * * Minimum size is 2 * BUF_PAGE_SIZE. * @@ -3956,11 +3957,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * expected. * * After a sequence of ring_buffer_read_prepare calls, the user is - * expected to make at least one call to ring_buffer_prepare_sync. + * expected to make at least one call to ring_buffer_read_prepare_sync. * Afterwards, ring_buffer_read_start is invoked to get things going * for real. * - * This overall must be paired with ring_buffer_finish. + * This overall must be paired with ring_buffer_read_finish. */ struct ring_buffer_iter * ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu) @@ -4009,7 +4010,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync); * an intervening ring_buffer_read_prepare_sync must have been * performed. * - * Must be paired with ring_buffer_finish. + * Must be paired with ring_buffer_read_finish. */ void ring_buffer_read_start(struct ring_buffer_iter *iter) @@ -4031,7 +4032,7 @@ ring_buffer_read_start(struct ring_buffer_iter *iter) EXPORT_SYMBOL_GPL(ring_buffer_read_start); /** - * ring_buffer_finish - finish reading the iterator of the buffer + * ring_buffer_read_finish - finish reading the iterator of the buffer * @iter: The iterator retrieved by ring_buffer_start * * This re-enables the recording to the buffer, and frees the @@ -4346,6 +4347,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); /** * ring_buffer_alloc_read_page - allocate a page to read from buffer * @buffer: the buffer to allocate for. + * @cpu: the cpu buffer to allocate. * * This function is used in conjunction with ring_buffer_read_page. * When reading a full page from the ring buffer, these functions @@ -4403,7 +4405,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * to swap with a page in the ring buffer. * * for example: - * rpage = ring_buffer_alloc_read_page(buffer); + * rpage = ring_buffer_alloc_read_page(buffer, cpu); * if (!rpage) * return error; * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0cd500bffd9b..496f94d57698 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -243,20 +243,25 @@ int filter_current_check_discard(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(filter_current_check_discard); -cycle_t ftrace_now(int cpu) +cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu) { u64 ts; /* Early boot up does not have a buffer yet */ - if (!global_trace.trace_buffer.buffer) + if (!buf->buffer) return trace_clock_local(); - ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu); - ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts); + ts = ring_buffer_time_stamp(buf->buffer, cpu); + ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); return ts; } +cycle_t ftrace_now(int cpu) +{ + return buffer_ftrace_now(&global_trace.trace_buffer, cpu); +} + /** * tracing_is_enabled - Show if global_trace has been disabled * @@ -1211,7 +1216,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) /* Make sure all commits have finished */ synchronize_sched(); - buf->time_start = ftrace_now(buf->cpu); + buf->time_start = buffer_ftrace_now(buf, buf->cpu); for_each_online_cpu(cpu) ring_buffer_reset_cpu(buffer, cpu); @@ -1219,23 +1224,17 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) ring_buffer_record_enable(buffer); } -void tracing_reset_current(int cpu) -{ - tracing_reset(&global_trace.trace_buffer, cpu); -} - +/* Must have trace_types_lock held */ void tracing_reset_all_online_cpus(void) { struct trace_array *tr; - mutex_lock(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE tracing_reset_online_cpus(&tr->max_buffer); #endif } - mutex_unlock(&trace_types_lock); } #define SAVED_CMDLINES 128 @@ -2843,6 +2842,17 @@ static int s_show(struct seq_file *m, void *v) return 0; } +/* + * Should be used after trace_array_get(), trace_types_lock + * ensures that i_cdev was already initialized. + */ +static inline int tracing_get_cpu(struct inode *inode) +{ + if (inode->i_cdev) /* See trace_create_cpu_file() */ + return (long)inode->i_cdev - 1; + return RING_BUFFER_ALL_CPUS; +} + static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, @@ -2851,9 +2861,9 @@ static const struct seq_operations tracer_seq_ops = { }; static struct trace_iterator * -__tracing_open(struct trace_array *tr, struct trace_cpu *tc, - struct inode *inode, struct file *file, bool snapshot) +__tracing_open(struct inode *inode, struct file *file, bool snapshot) { + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int cpu; @@ -2894,8 +2904,8 @@ __tracing_open(struct trace_array *tr, struct trace_cpu *tc, iter->trace_buffer = &tr->trace_buffer; iter->snapshot = snapshot; iter->pos = -1; + iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); - iter->cpu_file = tc->cpu; /* Notify the tracer early; before we stop tracing. */ if (iter->trace && iter->trace->open) @@ -2971,45 +2981,22 @@ static int tracing_open_generic_tr(struct inode *inode, struct file *filp) filp->private_data = inode->i_private; return 0; - -} - -static int tracing_open_generic_tc(struct inode *inode, struct file *filp) -{ - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; - - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; - - filp->private_data = inode->i_private; - - return 0; - } static int tracing_release(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; struct seq_file *m = file->private_data; struct trace_iterator *iter; - struct trace_array *tr; int cpu; - /* Writes do not use seq_file, need to grab tr from inode */ if (!(file->f_mode & FMODE_READ)) { - struct trace_cpu *tc = inode->i_private; - - trace_array_put(tc->tr); + trace_array_put(tr); return 0; } + /* Writes do not use seq_file */ iter = m->private; - tr = iter->tr; - trace_array_put(tr); - mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { @@ -3023,6 +3010,9 @@ static int tracing_release(struct inode *inode, struct file *file) if (!iter->snapshot) /* reenable tracing if it was previously enabled */ tracing_start_tr(tr); + + __trace_array_put(tr); + mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); @@ -3042,15 +3032,6 @@ static int tracing_release_generic_tr(struct inode *inode, struct file *file) return 0; } -static int tracing_release_generic_tc(struct inode *inode, struct file *file) -{ - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; - - trace_array_put(tr); - return 0; -} - static int tracing_single_release_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -3062,8 +3043,7 @@ static int tracing_single_release_tr(struct inode *inode, struct file *file) static int tracing_open(struct inode *inode, struct file *file) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int ret = 0; @@ -3071,16 +3051,17 @@ static int tracing_open(struct inode *inode, struct file *file) return -ENODEV; /* If this file was open for write, then erase contents */ - if ((file->f_mode & FMODE_WRITE) && - (file->f_flags & O_TRUNC)) { - if (tc->cpu == RING_BUFFER_ALL_CPUS) + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + int cpu = tracing_get_cpu(inode); + + if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&tr->trace_buffer); else - tracing_reset(&tr->trace_buffer, tc->cpu); + tracing_reset(&tr->trace_buffer, cpu); } if (file->f_mode & FMODE_READ) { - iter = __tracing_open(tr, tc, inode, file, false); + iter = __tracing_open(inode, file, false); if (IS_ERR(iter)) ret = PTR_ERR(iter); else if (trace_flags & TRACE_ITER_LATENCY_FMT) @@ -3447,6 +3428,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, static int tracing_trace_options_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; + int ret; if (tracing_disabled) return -ENODEV; @@ -3454,7 +3436,11 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file) if (trace_array_get(tr) < 0) return -ENODEV; - return single_open(file, tracing_trace_options_show, inode->i_private); + ret = single_open(file, tracing_trace_options_show, inode->i_private); + if (ret < 0) + trace_array_put(tr); + + return ret; } static const struct file_operations tracing_iter_fops = { @@ -3537,14 +3523,14 @@ static const char readme_msg[] = "\n snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n" "\t\t\t Read the contents for more information\n" #endif -#ifdef CONFIG_STACKTRACE +#ifdef CONFIG_STACK_TRACER " stack_trace\t\t- Shows the max stack trace when active\n" " stack_max_size\t- Shows current max stack size that was traced\n" "\t\t\t Write into this file to reset the max size (trigger a new trace)\n" #ifdef CONFIG_DYNAMIC_FTRACE " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n" #endif -#endif /* CONFIG_STACKTRACE */ +#endif /* CONFIG_STACK_TRACER */ ; static ssize_t @@ -3941,8 +3927,7 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, static int tracing_open_pipe(struct inode *inode, struct file *filp) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int ret = 0; @@ -3958,6 +3943,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; + __trace_array_put(tr); goto out; } @@ -3987,9 +3973,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - iter->cpu_file = tc->cpu; - iter->tr = tc->tr; - iter->trace_buffer = &tc->tr->trace_buffer; + iter->tr = tr; + iter->trace_buffer = &tr->trace_buffer; + iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); filp->private_data = iter; @@ -4012,8 +3998,7 @@ fail: static int tracing_release_pipe(struct inode *inode, struct file *file) { struct trace_iterator *iter = file->private_data; - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; mutex_lock(&trace_types_lock); @@ -4166,6 +4151,7 @@ waitagain: memset(&iter->seq, 0, sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); + cpumask_clear(iter->started); iter->pos = -1; trace_event_read_lock(); @@ -4366,15 +4352,16 @@ static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct trace_cpu *tc = filp->private_data; - struct trace_array *tr = tc->tr; + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + int cpu = tracing_get_cpu(inode); char buf[64]; int r = 0; ssize_t ret; mutex_lock(&trace_types_lock); - if (tc->cpu == RING_BUFFER_ALL_CPUS) { + if (cpu == RING_BUFFER_ALL_CPUS) { int cpu, buf_size_same; unsigned long size; @@ -4401,7 +4388,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -4413,7 +4400,8 @@ static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct trace_cpu *tc = filp->private_data; + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; unsigned long val; int ret; @@ -4427,8 +4415,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, /* value is in KB */ val <<= 10; - - ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu); + ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode)); if (ret < 0) return ret; @@ -4482,7 +4469,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) /* disable tracing ? */ if (trace_flags & TRACE_ITER_STOP_ON_FREE) - tracing_off(); + tracer_tracing_off(tr); /* resize the ring buffer to 0 */ tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); @@ -4647,12 +4634,12 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ - tracing_reset_online_cpus(&global_trace.trace_buffer); + tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); - tracing_reset_online_cpus(&global_trace.max_buffer); + tracing_reset_online_cpus(&tr->max_buffer); #endif mutex_unlock(&trace_types_lock); @@ -4689,8 +4676,7 @@ struct ftrace_buffer_info { #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; struct seq_file *m; int ret = 0; @@ -4699,26 +4685,29 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) return -ENODEV; if (file->f_mode & FMODE_READ) { - iter = __tracing_open(tr, tc, inode, file, true); + iter = __tracing_open(inode, file, true); if (IS_ERR(iter)) ret = PTR_ERR(iter); } else { /* Writes still need the seq_file to hold the private data */ + ret = -ENOMEM; m = kzalloc(sizeof(*m), GFP_KERNEL); if (!m) - return -ENOMEM; + goto out; iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { kfree(m); - return -ENOMEM; + goto out; } + ret = 0; + iter->tr = tr; - iter->trace_buffer = &tc->tr->max_buffer; - iter->cpu_file = tc->cpu; + iter->trace_buffer = &tr->max_buffer; + iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; } - +out: if (ret < 0) trace_array_put(tr); @@ -4873,11 +4862,11 @@ static const struct file_operations tracing_pipe_fops = { }; static const struct file_operations tracing_entries_fops = { - .open = tracing_open_generic_tc, + .open = tracing_open_generic_tr, .read = tracing_entries_read, .write = tracing_entries_write, .llseek = generic_file_llseek, - .release = tracing_release_generic_tc, + .release = tracing_release_generic_tr, }; static const struct file_operations tracing_total_entries_fops = { @@ -4929,8 +4918,7 @@ static const struct file_operations snapshot_raw_fops = { static int tracing_buffers_open(struct inode *inode, struct file *filp) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct ftrace_buffer_info *info; int ret; @@ -4948,10 +4936,8 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) mutex_lock(&trace_types_lock); - tr->ref++; - info->iter.tr = tr; - info->iter.cpu_file = tc->cpu; + info->iter.cpu_file = tracing_get_cpu(inode); info->iter.trace = tr->current_trace; info->iter.trace_buffer = &tr->trace_buffer; info->spare = NULL; @@ -5268,14 +5254,14 @@ static ssize_t tracing_stats_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - struct trace_cpu *tc = filp->private_data; - struct trace_array *tr = tc->tr; + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; struct trace_buffer *trace_buf = &tr->trace_buffer; + int cpu = tracing_get_cpu(inode); struct trace_seq *s; unsigned long cnt; unsigned long long t; unsigned long usec_rem; - int cpu = tc->cpu; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) @@ -5328,9 +5314,10 @@ tracing_stats_read(struct file *filp, char __user *ubuf, } static const struct file_operations tracing_stats_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_stats_read, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -5519,10 +5506,20 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) return tr->percpu_dir; } +static struct dentry * +trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent, + void *data, long cpu, const struct file_operations *fops) +{ + struct dentry *ret = trace_create_file(name, mode, parent, data, fops); + + if (ret) /* See tracing_get_cpu() */ + ret->d_inode->i_cdev = (void *)(cpu + 1); + return ret; +} + static void tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) { - struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu); struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ @@ -5538,28 +5535,28 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) } /* per cpu trace_pipe */ - trace_create_file("trace_pipe", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_pipe_fops); + trace_create_cpu_file("trace_pipe", 0444, d_cpu, + tr, cpu, &tracing_pipe_fops); /* per cpu trace */ - trace_create_file("trace", 0644, d_cpu, - (void *)&data->trace_cpu, &tracing_fops); + trace_create_cpu_file("trace", 0644, d_cpu, + tr, cpu, &tracing_fops); - trace_create_file("trace_pipe_raw", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_buffers_fops); + trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu, + tr, cpu, &tracing_buffers_fops); - trace_create_file("stats", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_stats_fops); + trace_create_cpu_file("stats", 0444, d_cpu, + tr, cpu, &tracing_stats_fops); - trace_create_file("buffer_size_kb", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_entries_fops); + trace_create_cpu_file("buffer_size_kb", 0444, d_cpu, + tr, cpu, &tracing_entries_fops); #ifdef CONFIG_TRACER_SNAPSHOT - trace_create_file("snapshot", 0644, d_cpu, - (void *)&data->trace_cpu, &snapshot_fops); + trace_create_cpu_file("snapshot", 0644, d_cpu, + tr, cpu, &snapshot_fops); - trace_create_file("snapshot_raw", 0444, d_cpu, - (void *)&data->trace_cpu, &snapshot_raw_fops); + trace_create_cpu_file("snapshot_raw", 0444, d_cpu, + tr, cpu, &snapshot_raw_fops); #endif } @@ -5868,17 +5865,6 @@ struct dentry *trace_instance_dir; static void init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer); -static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf) -{ - int cpu; - - for_each_tracing_cpu(cpu) { - memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu)); - per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu; - per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr; - } -} - static int allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) { @@ -5896,8 +5882,6 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size return -ENOMEM; } - init_trace_buffers(tr, buf); - /* Allocate the first page for all buffers */ set_buffer_entries(&tr->trace_buffer, ring_buffer_size(tr->trace_buffer.buffer, 0)); @@ -5964,17 +5948,15 @@ static int new_instance_create(const char *name) if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; - /* Holder for file callbacks */ - tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS; - tr->trace_cpu.tr = tr; - tr->dir = debugfs_create_dir(name, trace_instance_dir); if (!tr->dir) goto out_free_tr; ret = event_trace_add_tracer(tr->dir, tr); - if (ret) + if (ret) { + debugfs_remove_recursive(tr->dir); goto out_free_tr; + } init_tracer_debugfs(tr, tr->dir); @@ -6120,13 +6102,13 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) tr, &tracing_iter_fops); trace_create_file("trace", 0644, d_tracer, - (void *)&tr->trace_cpu, &tracing_fops); + tr, &tracing_fops); trace_create_file("trace_pipe", 0444, d_tracer, - (void *)&tr->trace_cpu, &tracing_pipe_fops); + tr, &tracing_pipe_fops); trace_create_file("buffer_size_kb", 0644, d_tracer, - (void *)&tr->trace_cpu, &tracing_entries_fops); + tr, &tracing_entries_fops); trace_create_file("buffer_total_size_kb", 0444, d_tracer, tr, &tracing_total_entries_fops); @@ -6141,11 +6123,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) &trace_clock_fops); trace_create_file("tracing_on", 0644, d_tracer, - tr, &rb_simple_fops); + tr, &rb_simple_fops); #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, - (void *)&tr->trace_cpu, &snapshot_fops); + tr, &snapshot_fops); #endif for_each_tracing_cpu(cpu) @@ -6439,10 +6421,6 @@ __init static int tracer_alloc_buffers(void) global_trace.flags = TRACE_ARRAY_FL_GLOBAL; - /* Holder for file callbacks */ - global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS; - global_trace.trace_cpu.tr = &global_trace; - INIT_LIST_HEAD(&global_trace.systems); INIT_LIST_HEAD(&global_trace.events); list_add(&global_trace.list, &ftrace_trace_arrays); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4a4f6e1828b6..afaae41b0a02 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -130,19 +130,12 @@ enum trace_flag_type { struct trace_array; -struct trace_cpu { - struct trace_array *tr; - struct dentry *dir; - int cpu; -}; - /* * The CPU trace array - it consists of thousands of trace entries * plus some other descriptor data: (for example which task started * the trace, etc.) */ struct trace_array_cpu { - struct trace_cpu trace_cpu; atomic_t disabled; void *buffer_page; /* ring buffer spare */ @@ -196,7 +189,6 @@ struct trace_array { bool allocated_snapshot; #endif int buffer_disabled; - struct trace_cpu trace_cpu; /* place holder */ #ifdef CONFIG_FTRACE_SYSCALLS int sys_refcount_enter; int sys_refcount_exit; @@ -214,7 +206,6 @@ struct trace_array { struct dentry *event_dir; struct list_head systems; struct list_head events; - struct task_struct *waiter; int ref; }; @@ -680,6 +671,15 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); +/* + * Tracer data references selftest functions that only occur + * on boot up. These can be __init functions. Thus, when selftests + * are enabled, then the tracers need to reference __init functions. + */ +#define __tracer_data __refdata +#else +/* Tracers are seldom changed. Optimize when selftests are disabled. */ +#define __tracer_data __read_mostly #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 84b1e045faba..80c36bcf66e8 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -236,6 +236,10 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, + "perf buffer not large enough")) + return NULL; + pc = preempt_count(); *rctxp = perf_swevent_get_recursion_context(); @@ -266,6 +270,10 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, struct pt_regs regs; int rctx; + head = this_cpu_ptr(event_function.perf_events); + if (hlist_empty(head)) + return; + #define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \ sizeof(u64)) - sizeof(u32)) @@ -279,8 +287,6 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, entry->ip = ip; entry->parent_ip = parent_ip; - - head = this_cpu_ptr(event_function.perf_events); perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, 1, ®s, head, NULL); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7d854290bf81..29a7ebcfb426 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -409,33 +409,42 @@ static void put_system(struct ftrace_subsystem_dir *dir) mutex_unlock(&event_mutex); } -/* - * Open and update trace_array ref count. - * Must have the current trace_array passed to it. - */ -static int tracing_open_generic_file(struct inode *inode, struct file *filp) +static void remove_subsystem(struct ftrace_subsystem_dir *dir) { - struct ftrace_event_file *file = inode->i_private; - struct trace_array *tr = file->tr; - int ret; + if (!dir) + return; - if (trace_array_get(tr) < 0) - return -ENODEV; + if (!--dir->nr_events) { + debugfs_remove_recursive(dir->entry); + list_del(&dir->list); + __put_system_dir(dir); + } +} - ret = tracing_open_generic(inode, filp); - if (ret < 0) - trace_array_put(tr); - return ret; +static void *event_file_data(struct file *filp) +{ + return ACCESS_ONCE(file_inode(filp)->i_private); } -static int tracing_release_generic_file(struct inode *inode, struct file *filp) +static void remove_event_file_dir(struct ftrace_event_file *file) { - struct ftrace_event_file *file = inode->i_private; - struct trace_array *tr = file->tr; + struct dentry *dir = file->dir; + struct dentry *child; - trace_array_put(tr); + if (dir) { + spin_lock(&dir->d_lock); /* probably unneeded */ + list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) { + if (child->d_inode) /* probably unneeded */ + child->d_inode->i_private = NULL; + } + spin_unlock(&dir->d_lock); - return 0; + debugfs_remove_recursive(dir); + } + + list_del(&file->list); + remove_subsystem(file->system); + kmem_cache_free(file_cachep, file); } /* @@ -679,15 +688,25 @@ static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_file *file = filp->private_data; + struct ftrace_event_file *file; + unsigned long flags; char buf[4] = "0"; - if (file->flags & FTRACE_EVENT_FL_ENABLED && - !(file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)) + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (likely(file)) + flags = file->flags; + mutex_unlock(&event_mutex); + + if (!file) + return -ENODEV; + + if (flags & FTRACE_EVENT_FL_ENABLED && + !(flags & FTRACE_EVENT_FL_SOFT_DISABLED)) strcpy(buf, "1"); - if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED || - file->flags & FTRACE_EVENT_FL_SOFT_MODE) + if (flags & FTRACE_EVENT_FL_SOFT_DISABLED || + flags & FTRACE_EVENT_FL_SOFT_MODE) strcat(buf, "*"); strcat(buf, "\n"); @@ -699,13 +718,10 @@ static ssize_t event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_file *file = filp->private_data; + struct ftrace_event_file *file; unsigned long val; int ret; - if (!file) - return -EINVAL; - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; @@ -717,8 +733,11 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, switch (val) { case 0: case 1: + ret = -ENODEV; mutex_lock(&event_mutex); - ret = ftrace_event_enable_disable(file, val); + file = event_file_data(filp); + if (likely(file)) + ret = ftrace_event_enable_disable(file, val); mutex_unlock(&event_mutex); break; @@ -825,65 +844,39 @@ enum { static void *f_next(struct seq_file *m, void *v, loff_t *pos) { - struct ftrace_event_call *call = m->private; - struct ftrace_event_field *field; + struct ftrace_event_call *call = event_file_data(m->private); struct list_head *common_head = &ftrace_common_fields; struct list_head *head = trace_get_fields(call); + struct list_head *node = v; (*pos)++; switch ((unsigned long)v) { case FORMAT_HEADER: - if (unlikely(list_empty(common_head))) - return NULL; - - field = list_entry(common_head->prev, - struct ftrace_event_field, link); - return field; + node = common_head; + break; case FORMAT_FIELD_SEPERATOR: - if (unlikely(list_empty(head))) - return NULL; - - field = list_entry(head->prev, struct ftrace_event_field, link); - return field; + node = head; + break; case FORMAT_PRINTFMT: /* all done */ return NULL; } - field = v; - if (field->link.prev == common_head) + node = node->prev; + if (node == common_head) return (void *)FORMAT_FIELD_SEPERATOR; - else if (field->link.prev == head) + else if (node == head) return (void *)FORMAT_PRINTFMT; - - field = list_entry(field->link.prev, struct ftrace_event_field, link); - - return field; -} - -static void *f_start(struct seq_file *m, loff_t *pos) -{ - loff_t l = 0; - void *p; - - /* Start by showing the header */ - if (!*pos) - return (void *)FORMAT_HEADER; - - p = (void *)FORMAT_HEADER; - do { - p = f_next(m, p, &l); - } while (p && l < *pos); - - return p; + else + return node; } static int f_show(struct seq_file *m, void *v) { - struct ftrace_event_call *call = m->private; + struct ftrace_event_call *call = event_file_data(m->private); struct ftrace_event_field *field; const char *array_descriptor; @@ -904,8 +897,7 @@ static int f_show(struct seq_file *m, void *v) return 0; } - field = v; - + field = list_entry(v, struct ftrace_event_field, link); /* * Smartly shows the array type(except dynamic array). * Normal: @@ -932,8 +924,25 @@ static int f_show(struct seq_file *m, void *v) return 0; } +static void *f_start(struct seq_file *m, loff_t *pos) +{ + void *p = (void *)FORMAT_HEADER; + loff_t l = 0; + + /* ->stop() is called even if ->start() fails */ + mutex_lock(&event_mutex); + if (!event_file_data(m->private)) + return ERR_PTR(-ENODEV); + + while (l < *pos && p) + p = f_next(m, p, &l); + + return p; +} + static void f_stop(struct seq_file *m, void *p) { + mutex_unlock(&event_mutex); } static const struct seq_operations trace_format_seq_ops = { @@ -945,7 +954,6 @@ static const struct seq_operations trace_format_seq_ops = { static int trace_format_open(struct inode *inode, struct file *file) { - struct ftrace_event_call *call = inode->i_private; struct seq_file *m; int ret; @@ -954,7 +962,7 @@ static int trace_format_open(struct inode *inode, struct file *file) return ret; m = file->private_data; - m->private = call; + m->private = file; return 0; } @@ -962,45 +970,47 @@ static int trace_format_open(struct inode *inode, struct file *file) static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; - struct trace_seq *s; - int r; + int id = (long)event_file_data(filp); + char buf[32]; + int len; if (*ppos) return 0; - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; + if (unlikely(!id)) + return -ENODEV; - trace_seq_init(s); - trace_seq_printf(s, "%d\n", call->event.type); + len = sprintf(buf, "%d\n", id); - r = simple_read_from_buffer(ubuf, cnt, ppos, - s->buffer, s->len); - kfree(s); - return r; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; + struct ftrace_event_call *call; struct trace_seq *s; - int r; + int r = -ENODEV; if (*ppos) return 0; s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) return -ENOMEM; trace_seq_init(s); - print_event_filter(call, s); - r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); + mutex_lock(&event_mutex); + call = event_file_data(filp); + if (call) + print_event_filter(call, s); + mutex_unlock(&event_mutex); + + if (call) + r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); kfree(s); @@ -1011,9 +1021,9 @@ static ssize_t event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; + struct ftrace_event_call *call; char *buf; - int err; + int err = -ENODEV; if (cnt >= PAGE_SIZE) return -EINVAL; @@ -1028,7 +1038,12 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, } buf[cnt] = '\0'; - err = apply_event_filter(call, buf); + mutex_lock(&event_mutex); + call = event_file_data(filp); + if (call) + err = apply_event_filter(call, buf); + mutex_unlock(&event_mutex); + free_page((unsigned long) buf); if (err < 0) return err; @@ -1218,6 +1233,7 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) static int ftrace_event_avail_open(struct inode *inode, struct file *file); static int ftrace_event_set_open(struct inode *inode, struct file *file); +static int ftrace_event_release(struct inode *inode, struct file *file); static const struct seq_operations show_event_seq_ops = { .start = t_start, @@ -1245,14 +1261,13 @@ static const struct file_operations ftrace_set_event_fops = { .read = seq_read, .write = ftrace_event_write, .llseek = seq_lseek, - .release = seq_release, + .release = ftrace_event_release, }; static const struct file_operations ftrace_enable_fops = { - .open = tracing_open_generic_file, + .open = tracing_open_generic, .read = event_enable_read, .write = event_enable_write, - .release = tracing_release_generic_file, .llseek = default_llseek, }; @@ -1264,7 +1279,6 @@ static const struct file_operations ftrace_event_format_fops = { }; static const struct file_operations ftrace_event_id_fops = { - .open = tracing_open_generic, .read = event_id_read, .llseek = default_llseek, }; @@ -1323,6 +1337,15 @@ ftrace_event_open(struct inode *inode, struct file *file, return ret; } +static int ftrace_event_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + + return seq_release(inode, file); +} + static int ftrace_event_avail_open(struct inode *inode, struct file *file) { @@ -1336,12 +1359,19 @@ ftrace_event_set_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_set_event_seq_ops; struct trace_array *tr = inode->i_private; + int ret; + + if (trace_array_get(tr) < 0) + return -ENODEV; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) ftrace_clear_events(tr); - return ftrace_event_open(inode, file, seq_ops); + ret = ftrace_event_open(inode, file, seq_ops); + if (ret < 0) + trace_array_put(tr); + return ret; } static struct event_subsystem * @@ -1496,8 +1526,8 @@ event_create_dir(struct dentry *parent, #ifdef CONFIG_PERF_EVENTS if (call->event.type && call->class->reg) - trace_create_file("id", 0444, file->dir, call, - id); + trace_create_file("id", 0444, file->dir, + (void *)(long)call->event.type, id); #endif /* @@ -1522,33 +1552,16 @@ event_create_dir(struct dentry *parent, return 0; } -static void remove_subsystem(struct ftrace_subsystem_dir *dir) -{ - if (!dir) - return; - - if (!--dir->nr_events) { - debugfs_remove_recursive(dir->entry); - list_del(&dir->list); - __put_system_dir(dir); - } -} - static void remove_event_from_tracers(struct ftrace_event_call *call) { struct ftrace_event_file *file; struct trace_array *tr; do_for_each_event_file_safe(tr, file) { - if (file->event_call != call) continue; - list_del(&file->list); - debugfs_remove_recursive(file->dir); - remove_subsystem(file->system); - kmem_cache_free(file_cachep, file); - + remove_event_file_dir(file); /* * The do_for_each_event_file_safe() is * a double loop. After finding the call for this @@ -1700,16 +1713,53 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) destroy_preds(call); } +static int probe_remove_event_call(struct ftrace_event_call *call) +{ + struct trace_array *tr; + struct ftrace_event_file *file; + +#ifdef CONFIG_PERF_EVENTS + if (call->perf_refcount) + return -EBUSY; +#endif + do_for_each_event_file(tr, file) { + if (file->event_call != call) + continue; + /* + * We can't rely on ftrace_event_enable_disable(enable => 0) + * we are going to do, FTRACE_EVENT_FL_SOFT_MODE can suppress + * TRACE_REG_UNREGISTER. + */ + if (file->flags & FTRACE_EVENT_FL_ENABLED) + return -EBUSY; + /* + * The do_for_each_event_file_safe() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); + + __trace_remove_event_call(call); + + return 0; +} + /* Remove an event_call */ -void trace_remove_event_call(struct ftrace_event_call *call) +int trace_remove_event_call(struct ftrace_event_call *call) { + int ret; + mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); down_write(&trace_event_sem); - __trace_remove_event_call(call); + ret = probe_remove_event_call(call); up_write(&trace_event_sem); mutex_unlock(&event_mutex); mutex_unlock(&trace_types_lock); + + return ret; } #define for_each_event(event, start, end) \ @@ -2278,12 +2328,8 @@ __trace_remove_event_dirs(struct trace_array *tr) { struct ftrace_event_file *file, *next; - list_for_each_entry_safe(file, next, &tr->events, list) { - list_del(&file->list); - debugfs_remove_recursive(file->dir); - remove_subsystem(file->system); - kmem_cache_free(file_cachep, file); - } + list_for_each_entry_safe(file, next, &tr->events, list) + remove_event_file_dir(file); } static void diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 0d883dc057d6..97daa8cf958d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -637,17 +637,15 @@ static void append_filter_err(struct filter_parse_state *ps, free_page((unsigned long) buf); } +/* caller must hold event_mutex */ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) { - struct event_filter *filter; + struct event_filter *filter = call->filter; - mutex_lock(&event_mutex); - filter = call->filter; if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else - trace_seq_printf(s, "none\n"); - mutex_unlock(&event_mutex); + trace_seq_puts(s, "none\n"); } void print_subsystem_event_filter(struct event_subsystem *system, @@ -660,7 +658,7 @@ void print_subsystem_event_filter(struct event_subsystem *system, if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else - trace_seq_printf(s, DEFAULT_SYS_FILTER_MESSAGE "\n"); + trace_seq_puts(s, DEFAULT_SYS_FILTER_MESSAGE "\n"); mutex_unlock(&event_mutex); } @@ -1841,23 +1839,22 @@ static int create_system_filter(struct event_subsystem *system, return err; } +/* caller must hold event_mutex */ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) { struct event_filter *filter; - int err = 0; - - mutex_lock(&event_mutex); + int err; if (!strcmp(strstrip(filter_string), "0")) { filter_disable(call); filter = call->filter; if (!filter) - goto out_unlock; + return 0; RCU_INIT_POINTER(call->filter, NULL); /* Make sure the filter is not being used */ synchronize_sched(); __free_filter(filter); - goto out_unlock; + return 0; } err = create_filter(call, filter_string, true, &filter); @@ -1884,8 +1881,6 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) __free_filter(tmp); } } -out_unlock: - mutex_unlock(&event_mutex); return err; } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index b863f93b30f3..38fe1483c508 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -199,7 +199,7 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) return 0; } -static struct tracer function_trace __read_mostly = +static struct tracer function_trace __tracer_data = { .name = "function", .init = function_trace_init, diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 8388bc99f2ee..b5c09242683d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -446,7 +446,7 @@ print_graph_proc(struct trace_seq *s, pid_t pid) /* First spaces to align center */ for (i = 0; i < spaces / 2; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -457,7 +457,7 @@ print_graph_proc(struct trace_seq *s, pid_t pid) /* Last spaces to align center */ for (i = 0; i < spaces - (spaces / 2); i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -503,7 +503,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) ------------------------------------------ */ - ret = trace_seq_printf(s, + ret = trace_seq_puts(s, " ------------------------------------------\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -516,7 +516,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " => "); + ret = trace_seq_puts(s, " => "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -524,7 +524,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, + ret = trace_seq_puts(s, "\n ------------------------------------------\n\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -645,7 +645,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, ret = print_graph_proc(s, pid); if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " | "); + ret = trace_seq_puts(s, " | "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -657,9 +657,9 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, return ret; if (type == TRACE_GRAPH_ENT) - ret = trace_seq_printf(s, "==========>"); + ret = trace_seq_puts(s, "==========>"); else - ret = trace_seq_printf(s, "<=========="); + ret = trace_seq_puts(s, "<=========="); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -668,7 +668,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, if (ret != TRACE_TYPE_HANDLED) return ret; - ret = trace_seq_printf(s, "\n"); + ret = trace_seq_putc(s, '\n'); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -705,13 +705,13 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s) len += strlen(nsecs_str); } - ret = trace_seq_printf(s, " us "); + ret = trace_seq_puts(s, " us "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; /* Print remaining spaces to fit the row's width */ for (i = len; i < 7; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -731,13 +731,13 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, /* No real adata, just filling the column with spaces */ switch (duration) { case DURATION_FILL_FULL: - ret = trace_seq_printf(s, " | "); + ret = trace_seq_puts(s, " | "); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; case DURATION_FILL_START: - ret = trace_seq_printf(s, " "); + ret = trace_seq_puts(s, " "); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; case DURATION_FILL_END: - ret = trace_seq_printf(s, " |"); + ret = trace_seq_puts(s, " |"); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; } @@ -745,10 +745,10 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, if (flags & TRACE_GRAPH_PRINT_OVERHEAD) { /* Duration exceeded 100 msecs */ if (duration > 100000ULL) - ret = trace_seq_printf(s, "! "); + ret = trace_seq_puts(s, "! "); /* Duration exceeded 10 msecs */ else if (duration > 10000ULL) - ret = trace_seq_printf(s, "+ "); + ret = trace_seq_puts(s, "+ "); } /* @@ -757,7 +757,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, * to fill out the space. */ if (ret == -1) - ret = trace_seq_printf(s, " "); + ret = trace_seq_puts(s, " "); /* Catching here any failure happenned above */ if (!ret) @@ -767,7 +767,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, if (ret != TRACE_TYPE_HANDLED) return ret; - ret = trace_seq_printf(s, "| "); + ret = trace_seq_puts(s, "| "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -817,7 +817,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -858,7 +858,7 @@ print_graph_entry_nested(struct trace_iterator *iter, /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -917,7 +917,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " | "); + ret = trace_seq_puts(s, " | "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -1117,7 +1117,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, /* Closing brace */ for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -1129,7 +1129,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, * belongs to, write out the function name. */ if (func_match) { - ret = trace_seq_printf(s, "}\n"); + ret = trace_seq_puts(s, "}\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } else { @@ -1179,13 +1179,13 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, /* Indentation */ if (depth > 0) for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } /* The comment */ - ret = trace_seq_printf(s, "/* "); + ret = trace_seq_puts(s, "/* "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -1216,7 +1216,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, s->len--; } - ret = trace_seq_printf(s, " */\n"); + ret = trace_seq_puts(s, " */\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -1448,7 +1448,7 @@ static struct trace_event graph_trace_ret_event = { .funcs = &graph_functions }; -static struct tracer graph_trace __read_mostly = { +static struct tracer graph_trace __tracer_data = { .name = "function_graph", .open = graph_trace_open, .pipe_open = graph_trace_open, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7ed6976493c8..243f6834d026 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -95,7 +95,7 @@ static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp) } static int register_probe_event(struct trace_probe *tp); -static void unregister_probe_event(struct trace_probe *tp); +static int unregister_probe_event(struct trace_probe *tp); static DEFINE_MUTEX(probe_lock); static LIST_HEAD(probe_list); @@ -243,11 +243,11 @@ find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) static int disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) { + struct event_file_link *link = NULL; + int wait = 0; int ret = 0; if (file) { - struct event_file_link *link; - link = find_event_file_link(tp, file); if (!link) { ret = -EINVAL; @@ -255,10 +255,7 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) } list_del_rcu(&link->list); - /* synchronize with kprobe_trace_func/kretprobe_trace_func */ - synchronize_sched(); - kfree(link); - + wait = 1; if (!list_empty(&tp->files)) goto out; @@ -271,8 +268,22 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) disable_kretprobe(&tp->rp); else disable_kprobe(&tp->rp.kp); + wait = 1; } out: + if (wait) { + /* + * Synchronize with kprobe_trace_func/kretprobe_trace_func + * to ensure disabled (all running handlers are finished). + * This is not only for kfree(), but also the caller, + * trace_remove_event_call() supposes it for releasing + * event_call related objects, which will be accessed in + * the kprobe_trace_func/kretprobe_trace_func. + */ + synchronize_sched(); + kfree(link); /* Ignored if link == NULL */ + } + return ret; } @@ -340,9 +351,12 @@ static int unregister_trace_probe(struct trace_probe *tp) if (trace_probe_is_enabled(tp)) return -EBUSY; + /* Will fail if probe is being used by ftrace or perf */ + if (unregister_probe_event(tp)) + return -EBUSY; + __unregister_trace_probe(tp); list_del(&tp->list); - unregister_probe_event(tp); return 0; } @@ -621,7 +635,9 @@ static int release_all_trace_probes(void) /* TODO: Use batch unregistration */ while (!list_empty(&probe_list)) { tp = list_entry(probe_list.next, struct trace_probe, list); - unregister_trace_probe(tp); + ret = unregister_trace_probe(tp); + if (ret) + goto end; free_trace_probe(tp); } @@ -1087,9 +1103,6 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs) __size = sizeof(*entry) + tp->size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "profile buffer not large enough")) - return; entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); if (!entry) @@ -1120,9 +1133,6 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri, __size = sizeof(*entry) + tp->size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "profile buffer not large enough")) - return; entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); if (!entry) @@ -1242,11 +1252,15 @@ static int register_probe_event(struct trace_probe *tp) return ret; } -static void unregister_probe_event(struct trace_probe *tp) +static int unregister_probe_event(struct trace_probe *tp) { + int ret; + /* tp->event is unregistered in trace_remove_event_call() */ - trace_remove_event_call(&tp->call); - kfree(tp->call.print_fmt); + ret = trace_remove_event_call(&tp->call); + if (!ret) + kfree(tp->call.print_fmt); + return ret; } /* Make a debugfs interface for controlling probe points */ diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index a5e8f4878bfa..b3dcfb2f0fef 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -90,7 +90,7 @@ static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) if (drv) ret += trace_seq_printf(s, " %s\n", drv->name); else - ret += trace_seq_printf(s, " \n"); + ret += trace_seq_puts(s, " \n"); return ret; } @@ -107,7 +107,7 @@ static void mmio_pipe_open(struct trace_iterator *iter) struct header_iter *hiter; struct trace_seq *s = &iter->seq; - trace_seq_printf(s, "VERSION 20070824\n"); + trace_seq_puts(s, "VERSION 20070824\n"); hiter = kzalloc(sizeof(*hiter), GFP_KERNEL); if (!hiter) @@ -209,7 +209,7 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter) (rw->value >> 0) & 0xff, rw->pc, 0); break; default: - ret = trace_seq_printf(s, "rw what?\n"); + ret = trace_seq_puts(s, "rw what?\n"); break; } if (ret) @@ -245,7 +245,7 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter) secs, usec_rem, m->map_id, 0UL, 0); break; default: - ret = trace_seq_printf(s, "map what?\n"); + ret = trace_seq_puts(s, "map what?\n"); break; } if (ret) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bb922d9ee51b..34e7cbac0c9c 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -78,7 +78,7 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter) trace_assign_type(field, entry); - ret = trace_seq_printf(s, "%s", field->buf); + ret = trace_seq_puts(s, field->buf); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -558,14 +558,14 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, if (ret) ret = trace_seq_puts(s, "??"); if (ret) - ret = trace_seq_puts(s, "\n"); + ret = trace_seq_putc(s, '\n'); continue; } if (!ret) break; if (ret) ret = seq_print_user_ip(s, mm, ip, sym_flags); - ret = trace_seq_puts(s, "\n"); + ret = trace_seq_putc(s, '\n'); } if (mm) @@ -579,7 +579,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) int ret; if (!ip) - return trace_seq_printf(s, "0"); + return trace_seq_putc(s, '0'); if (sym_flags & TRACE_ITER_SYM_OFFSET) ret = seq_print_sym_offset(s, "%s", ip); @@ -964,14 +964,14 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags, goto partial; if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) { - if (!trace_seq_printf(s, " <-")) + if (!trace_seq_puts(s, " <-")) goto partial; if (!seq_print_ip_sym(s, field->parent_ip, flags)) goto partial; } - if (!trace_seq_printf(s, "\n")) + if (!trace_seq_putc(s, '\n')) goto partial; return TRACE_TYPE_HANDLED; @@ -1210,7 +1210,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter, if (!seq_print_ip_sym(s, *p, flags)) goto partial; - if (!trace_seq_puts(s, "\n")) + if (!trace_seq_putc(s, '\n')) goto partial; } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 322e16461072..8fd03657bc7d 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -175,7 +175,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags, entry = syscall_nr_to_meta(syscall); if (!entry) { - trace_seq_printf(s, "\n"); + trace_seq_putc(s, '\n'); return TRACE_TYPE_HANDLED; } @@ -566,15 +566,15 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) if (!sys_data) return; + head = this_cpu_ptr(sys_data->enter_event->perf_events); + if (hlist_empty(head)) + return; + /* get the size after alignment with the u32 buffer size field */ size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec); size = ALIGN(size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "perf buffer not large enough")) - return; - rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, sys_data->enter_event->event.type, regs, &rctx); if (!rec) @@ -583,8 +583,6 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - - head = this_cpu_ptr(sys_data->enter_event->perf_events); perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } @@ -642,18 +640,14 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) if (!sys_data) return; + head = this_cpu_ptr(sys_data->exit_event->perf_events); + if (hlist_empty(head)) + return; + /* We can probably do that at build time */ size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - /* - * Impossible, but be paranoid with the future - * How to put this check outside runtime? - */ - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "exit event has grown above perf buffer size")) - return; - rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, sys_data->exit_event->event.type, regs, &rctx); if (!rec) @@ -661,8 +655,6 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - - head = this_cpu_ptr(sys_data->exit_event->perf_events); perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index d5d0cd368a56..272261b5f94f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -70,7 +70,7 @@ struct trace_uprobe { (sizeof(struct probe_arg) * (n))) static int register_uprobe_event(struct trace_uprobe *tu); -static void unregister_uprobe_event(struct trace_uprobe *tu); +static int unregister_uprobe_event(struct trace_uprobe *tu); static DEFINE_MUTEX(uprobe_lock); static LIST_HEAD(uprobe_list); @@ -164,11 +164,17 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou } /* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ -static void unregister_trace_uprobe(struct trace_uprobe *tu) +static int unregister_trace_uprobe(struct trace_uprobe *tu) { + int ret; + + ret = unregister_uprobe_event(tu); + if (ret) + return ret; + list_del(&tu->list); - unregister_uprobe_event(tu); free_trace_uprobe(tu); + return 0; } /* Register a trace_uprobe and probe_event */ @@ -181,9 +187,12 @@ static int register_trace_uprobe(struct trace_uprobe *tu) /* register as an event */ old_tp = find_probe_event(tu->call.name, tu->call.class->system); - if (old_tp) + if (old_tp) { /* delete old event */ - unregister_trace_uprobe(old_tp); + ret = unregister_trace_uprobe(old_tp); + if (ret) + goto end; + } ret = register_uprobe_event(tu); if (ret) { @@ -256,6 +265,8 @@ static int create_trace_uprobe(int argc, char **argv) group = UPROBE_EVENT_SYSTEM; if (is_delete) { + int ret; + if (!event) { pr_info("Delete command needs an event name.\n"); return -EINVAL; @@ -269,9 +280,9 @@ static int create_trace_uprobe(int argc, char **argv) return -ENOENT; } /* delete an event */ - unregister_trace_uprobe(tu); + ret = unregister_trace_uprobe(tu); mutex_unlock(&uprobe_lock); - return 0; + return ret; } if (argc < 2) { @@ -408,16 +419,20 @@ fail_address_parse: return ret; } -static void cleanup_all_probes(void) +static int cleanup_all_probes(void) { struct trace_uprobe *tu; + int ret = 0; mutex_lock(&uprobe_lock); while (!list_empty(&uprobe_list)) { tu = list_entry(uprobe_list.next, struct trace_uprobe, list); - unregister_trace_uprobe(tu); + ret = unregister_trace_uprobe(tu); + if (ret) + break; } mutex_unlock(&uprobe_lock); + return ret; } /* Probes listing interfaces */ @@ -462,8 +477,13 @@ static const struct seq_operations probes_seq_op = { static int probes_open(struct inode *inode, struct file *file) { - if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - cleanup_all_probes(); + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = cleanup_all_probes(); + if (ret) + return ret; + } return seq_open(file, &probes_seq_op); } @@ -818,8 +838,6 @@ static void uprobe_perf_print(struct trace_uprobe *tu, size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) - return; preempt_disable(); head = this_cpu_ptr(call->perf_events); @@ -970,12 +988,17 @@ static int register_uprobe_event(struct trace_uprobe *tu) return ret; } -static void unregister_uprobe_event(struct trace_uprobe *tu) +static int unregister_uprobe_event(struct trace_uprobe *tu) { + int ret; + /* tu->event is unregistered in trace_remove_event_call() */ - trace_remove_event_call(&tu->call); + ret = trace_remove_event_call(&tu->call); + if (ret) + return ret; kfree(tu->call.print_fmt); tu->call.print_fmt = NULL; + return 0; } /* Make a trace interface for controling probe points */ diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index d8c30db06c5b..9064b919a406 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -62,6 +62,9 @@ int create_user_ns(struct cred *new) kgid_t group = new->egid; int ret; + if (parent_ns->level > 32) + return -EUSERS; + /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, @@ -92,6 +95,7 @@ int create_user_ns(struct cred *new) atomic_set(&ns->count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; + ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; @@ -105,16 +109,21 @@ int create_user_ns(struct cred *new) int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; + int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); - if (!cred) - return -ENOMEM; + if (cred) { + err = create_user_ns(cred); + if (err) + put_cred(cred); + else + *new_cred = cred; + } - *new_cred = cred; - return create_user_ns(cred); + return err; } void free_user_ns(struct user_namespace *ns) diff --git a/kernel/wait.c b/kernel/wait.c index ce0daa320a26..d550920e040c 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -333,7 +333,8 @@ int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait(wq, &q->wait, mode); val = q->key.flags; if (atomic_read(val) == 0) - ret = (*action)(val); + break; + ret = (*action)(val); } while (!ret && atomic_read(val) != 0); finish_wait(wq, &q->wait); return ret; @@ -362,8 +363,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); /** * wake_up_atomic_t - Wake up a waiter on a atomic_t - * @word: The word being waited on, a kernel virtual address - * @bit: The bit of the word being waited on + * @p: The atomic_t being waited on, a kernel virtual address * * Wake up anyone waiting for the atomic_t to go to zero. * diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0b72e816b8d0..5f8ee91abdff 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2201,6 +2201,15 @@ __acquires(&pool->lock) dump_stack(); } + /* + * The following prevents a kworker from hogging CPU on !PREEMPT + * kernels, where a requeueing work item waiting for something to + * happen could deadlock with stop_machine as such work item could + * indefinitely requeue itself while all other CPUs are trapped in + * stop_machine. + */ + cond_resched(); + spin_lock_irq(&pool->lock); /* clear cpu intensive status */ @@ -2817,6 +2826,19 @@ already_gone: return false; } +static bool __flush_work(struct work_struct *work) +{ + struct wq_barrier barr; + + if (start_flush_work(work, &barr)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else { + return false; + } +} + /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush @@ -2830,18 +2852,10 @@ already_gone: */ bool flush_work(struct work_struct *work) { - struct wq_barrier barr; - lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); - if (start_flush_work(work, &barr)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - return true; - } else { - return false; - } + return __flush_work(work); } EXPORT_SYMBOL_GPL(flush_work); @@ -3081,25 +3095,26 @@ static struct workqueue_struct *dev_to_wq(struct device *dev) return wq_dev->wq; } -static ssize_t wq_per_cpu_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } +static DEVICE_ATTR_RO(per_cpu); -static ssize_t wq_max_active_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t max_active_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } -static ssize_t wq_max_active_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t max_active_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; @@ -3110,12 +3125,14 @@ static ssize_t wq_max_active_store(struct device *dev, workqueue_set_max_active(wq, val); return count; } +static DEVICE_ATTR_RW(max_active); -static struct device_attribute wq_sysfs_attrs[] = { - __ATTR(per_cpu, 0444, wq_per_cpu_show, NULL), - __ATTR(max_active, 0644, wq_max_active_show, wq_max_active_store), - __ATTR_NULL, +static struct attribute *wq_sysfs_attrs[] = { + &dev_attr_per_cpu.attr, + &dev_attr_max_active.attr, + NULL, }; +ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_pool_ids_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -3265,7 +3282,7 @@ static struct device_attribute wq_sysfs_unbound_attrs[] = { static struct bus_type wq_subsys = { .name = "workqueue", - .dev_attrs = wq_sysfs_attrs, + .dev_groups = wq_sysfs_groups, }; static int __init wq_sysfs_init(void) @@ -3411,6 +3428,12 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); + /* + * Unlike hash and equality test, this function doesn't ignore + * ->no_numa as it is used for both pool and wq attrs. Instead, + * get_unbound_pool() explicitly clears ->no_numa after copying. + */ + to->no_numa = from->no_numa; } /* hash value of the content of @attr */ @@ -3578,6 +3601,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); + /* + * no_numa isn't a worker_pool attribute, always clear it. See + * 'struct workqueue_attrs' comments for detail. + */ + pool->attrs->no_numa = false; + /* if cpumask is contained inside a NUMA node, we belong to that node */ if (wq_numa_enabled) { for_each_node(node) { @@ -4756,7 +4785,14 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); - flush_work(&wfc.work); + + /* + * The work item is on-stack and can't lead to deadlock through + * flushing. Use __flush_work() to avoid spurious lockdep warnings + * when work_on_cpu()s are nested. + */ + __flush_work(&wfc.work); + return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); |