diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/exit.c | 4 | ||||
| -rw-r--r-- | kernel/fork.c | 2 | ||||
| -rw-r--r-- | kernel/kthread.c | 3 | ||||
| -rw-r--r-- | kernel/marker.c | 114 | ||||
| -rw-r--r-- | kernel/module.c | 11 | ||||
| -rw-r--r-- | kernel/sched.c | 6 | ||||
| -rw-r--r-- | kernel/signal.c | 2 | ||||
| -rw-r--r-- | kernel/trace/Kconfig | 1 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 304 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 23 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_boot.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_branch.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_functions.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_functions_return.c | 16 | ||||
| -rw-r--r-- | kernel/trace/trace_irqsoff.c | 9 | ||||
| -rw-r--r-- | kernel/trace/trace_mmiotrace.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_nop.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_switch.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 3 | ||||
| -rw-r--r-- | kernel/trace/trace_selftest.c | 70 | ||||
| -rw-r--r-- | kernel/trace/trace_sysprof.c | 3 | ||||
| -rw-r--r-- | kernel/tracepoint.c | 34 |
23 files changed, 427 insertions, 199 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index ae2b92b..f995d24 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -54,6 +54,10 @@ #include <asm/pgtable.h> #include <asm/mmu_context.h> +DEFINE_TRACE(sched_process_free); +DEFINE_TRACE(sched_process_exit); +DEFINE_TRACE(sched_process_wait); + static void exit_mm(struct task_struct * tsk); static inline int task_detached(struct task_struct *p) diff --git a/kernel/fork.c b/kernel/fork.c index f608356..0837d0d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -79,6 +79,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ +DEFINE_TRACE(sched_process_fork); + int nr_processes(void) { int cpu; diff --git a/kernel/kthread.c b/kernel/kthread.c index 8e7a7ce..4fbc456 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; +DEFINE_TRACE(sched_kthread_stop); +DEFINE_TRACE(sched_kthread_stop_ret); + struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ diff --git a/kernel/marker.c b/kernel/marker.c index 2898b64..ea54f26 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -81,7 +81,7 @@ struct marker_entry { * though the function pointer change and the marker enabling are two distinct * operations that modifies the execution flow of preemptible code. */ -void __mark_empty_function(void *probe_private, void *call_private, +notrace void __mark_empty_function(void *probe_private, void *call_private, const char *fmt, va_list *args) { } @@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function); * need to put a full smp_rmb() in this branch. This is why we do not use * rcu_dereference() for the pointer read. */ -void marker_probe_cb(const struct marker *mdata, void *call_private, ...) +notrace void marker_probe_cb(const struct marker *mdata, + void *call_private, ...) { va_list args; char ptype; @@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) * sure the teardown of the callbacks can be done correctly when they * are in modules and they insure RCU read coherency. */ - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) va_end(args); } } - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); } EXPORT_SYMBOL_GPL(marker_probe_cb); @@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb); * * Should be connected to markers "MARK_NOARGS". */ -static void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) +static notrace void marker_probe_cb_noarg(const struct marker *mdata, + void *call_private, ...) { va_list args; /* not initialized */ char ptype; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -195,7 +197,7 @@ static void marker_probe_cb_noarg(const struct marker *mdata, void *call_private multi[i].func(multi[i].probe_private, call_private, mdata->format, &args); } - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); } static void free_old_closure(struct rcu_head *head) @@ -477,7 +479,7 @@ static int marker_set_format(struct marker_entry *entry, const char *format) static int set_marker(struct marker_entry *entry, struct marker *elem, int active) { - int ret; + int ret = 0; WARN_ON(strcmp(entry->name, elem->name) != 0); if (entry->format) { @@ -529,9 +531,40 @@ static int set_marker(struct marker_entry *entry, struct marker *elem, */ smp_wmb(); elem->ptype = entry->ptype; + + if (elem->tp_name && (active ^ elem->state)) { + WARN_ON(!elem->tp_cb); + /* + * It is ok to directly call the probe registration because type + * checking has been done in the __trace_mark_tp() macro. + */ + + if (active) { + /* + * try_module_get should always succeed because we hold + * lock_module() to get the tp_cb address. + */ + ret = try_module_get(__module_text_address( + (unsigned long)elem->tp_cb)); + BUG_ON(!ret); + ret = tracepoint_probe_register_noupdate( + elem->tp_name, + elem->tp_cb); + } else { + ret = tracepoint_probe_unregister_noupdate( + elem->tp_name, + elem->tp_cb); + /* + * tracepoint_probe_update_all() must be called + * before the module containing tp_cb is unloaded. + */ + module_put(__module_text_address( + (unsigned long)elem->tp_cb)); + } + } elem->state = active; - return 0; + return ret; } /* @@ -542,7 +575,24 @@ static int set_marker(struct marker_entry *entry, struct marker *elem, */ static void disable_marker(struct marker *elem) { + int ret; + /* leave "call" as is. It is known statically. */ + if (elem->tp_name && elem->state) { + WARN_ON(!elem->tp_cb); + /* + * It is ok to directly call the probe registration because type + * checking has been done in the __trace_mark_tp() macro. + */ + ret = tracepoint_probe_unregister_noupdate(elem->tp_name, + elem->tp_cb); + WARN_ON(ret); + /* + * tracepoint_probe_update_all() must be called + * before the module containing tp_cb is unloaded. + */ + module_put(__module_text_address((unsigned long)elem->tp_cb)); + } elem->state = 0; elem->single.func = __mark_empty_function; /* Update the function before setting the ptype */ @@ -606,6 +656,7 @@ static void marker_update_probes(void) marker_update_probe_range(__start___markers, __stop___markers); /* Markers in modules. */ module_update_markers(); + tracepoint_probe_update_all(); } /** @@ -653,10 +704,11 @@ int marker_probe_register(const char *name, const char *format, goto end; } mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker(name); - WARN_ON(!entry); + if (!entry) + goto end; if (entry->rcu_pending) rcu_barrier_sched(); entry->oldptr = old; @@ -697,7 +749,7 @@ int marker_probe_unregister(const char *name, rcu_barrier_sched(); old = marker_entry_remove_probe(entry, probe, probe_private); mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker(name); if (!entry) @@ -778,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe, rcu_barrier_sched(); old = marker_entry_remove_probe(entry, NULL, probe_private); mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker_from_private_data(probe, probe_private); - WARN_ON(!entry); + if (!entry) + goto end; if (entry->rcu_pending) rcu_barrier_sched(); entry->oldptr = old; @@ -842,3 +895,36 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe, return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(marker_get_private_data); + +#ifdef CONFIG_MODULES + +int marker_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + marker_update_probe_range(mod->markers, + mod->markers + mod->num_markers); + break; + case MODULE_STATE_GOING: + marker_update_probe_range(mod->markers, + mod->markers + mod->num_markers); + break; + } + return 0; +} + +struct notifier_block marker_module_nb = { + .notifier_call = marker_module_notify, + .priority = 0, +}; + +static int init_markers(void) +{ + return register_module_notifier(&marker_module_nb); +} +__initcall(init_markers); + +#endif /* CONFIG_MODULES */ diff --git a/kernel/module.c b/kernel/module.c index 1f4cc00..89bcf7c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2184,24 +2184,15 @@ static noinline struct module *load_module(void __user *umod, struct mod_debug *debug; unsigned int num_debug; -#ifdef CONFIG_MARKERS - marker_update_probe_range(mod->markers, - mod->markers + mod->num_markers); -#endif debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); dynamic_printk_setup(debug, num_debug); - -#ifdef CONFIG_TRACEPOINTS - tracepoint_update_probe_range(mod->tracepoints, - mod->tracepoints + mod->num_tracepoints); -#endif } /* sechdrs[0].sh_size is always zero */ mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", sizeof(*mseg), &num_mcount); - ftrace_init_module(mseg, mseg + num_mcount); + ftrace_init_module(mod, mseg, mseg + num_mcount); err = module_finalize(hdr, sechdrs, mod); if (err < 0) diff --git a/kernel/sched.c b/kernel/sched.c index 50a21f9..327f91c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -118,6 +118,12 @@ */ #define RUNTIME_INF ((u64)~0ULL) +DEFINE_TRACE(sched_wait_task); +DEFINE_TRACE(sched_wakeup); +DEFINE_TRACE(sched_wakeup_new); +DEFINE_TRACE(sched_switch); +DEFINE_TRACE(sched_migrate_task); + #ifdef CONFIG_SMP /* * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) diff --git a/kernel/signal.c b/kernel/signal.c index 4530fc6..e9afe63 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -41,6 +41,8 @@ static struct kmem_cache *sigqueue_cachep; +DEFINE_TRACE(sched_signal_send); + static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9c89526..b8378fa 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -59,7 +59,6 @@ config FUNCTION_TRACER config FUNCTION_RET_TRACER bool "Kernel Function return Tracer" - depends on !DYNAMIC_FTRACE depends on HAVE_FUNCTION_RET_TRACER depends on FUNCTION_TRACER help diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 54cb9a7..f212da4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -50,6 +50,9 @@ static int last_ftrace_enabled; /* Quick disabling of function tracer. */ int function_trace_stop; +/* By default, current tracing type is normal tracing. */ +enum ftrace_tracing_type_t ftrace_tracing_type = FTRACE_TYPE_ENTER; + /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. @@ -334,7 +337,7 @@ ftrace_record_ip(unsigned long ip) { struct dyn_ftrace *rec; - if (!ftrace_enabled || ftrace_disabled) + if (ftrace_disabled) return NULL; rec = ftrace_alloc_dyn_node(ip); @@ -348,107 +351,138 @@ ftrace_record_ip(unsigned long ip) return rec; } -#define FTRACE_ADDR ((long)(ftrace_caller)) +static void print_ip_ins(const char *fmt, unsigned char *p) +{ + int i; + + printk(KERN_CONT "%s", fmt); + + for (i = 0; i < MCOUNT_INSN_SIZE; i++) + printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); +} + +static void ftrace_bug(int failed, unsigned long ip) +{ + switch (failed) { + case -EFAULT: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on modifying "); + print_ip_sym(ip); + break; + case -EINVAL: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace failed to modify "); + print_ip_sym(ip); + print_ip_ins(" actual: ", (unsigned char *)ip); + printk(KERN_CONT "\n"); + break; + case -EPERM: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on writing "); + print_ip_sym(ip); + break; + default: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on unknown error "); + print_ip_sym(ip); + } +} + static int -__ftrace_replace_code(struct dyn_ftrace *rec, - unsigned char *old, unsigned char *new, int enable) +__ftrace_replace_code(struct dyn_ftrace *rec, int enable) { unsigned long ip, fl; + unsigned long ftrace_addr; + +#ifdef CONFIG_FUNCTION_RET_TRACER + if (ftrace_tracing_type == FTRACE_TYPE_ENTER) + ftrace_addr = (unsigned long)ftrace_caller; + else + ftrace_addr = (unsigned long)ftrace_return_caller; +#else + ftrace_addr = (unsigned long)ftrace_caller; +#endif ip = rec->ip; - if (ftrace_filtered && enable) { + /* + * If this record is not to be traced and + * it is not enabled then do nothing. + * + * If this record is not to be traced and + * it is enabled then disabled it. + * + */ + if (rec->flags & FTRACE_FL_NOTRACE) { + if (rec->flags & FTRACE_FL_ENABLED) + rec->flags &= ~FTRACE_FL_ENABLED; + else + return 0; + + } else if (ftrace_filtered && enable) { /* - * If filtering is on: - * - * If this record is set to be filtered and - * is enabled then do nothing. - * - * If this record is set to be filtered and - * it is not enabled, enable it. - * - * If this record is not set to be filtered - * and it is not enabled do nothing. - * - * If this record is set not to trace then - * do nothing. - * - * If this record is set not to trace and - * it is enabled then disable it. - * - * If this record is not set to be filtered and - * it is enabled, disable it. + * Filtering is on: */ - fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE | - FTRACE_FL_ENABLED); + fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED); - if ((fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) || - (fl == (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) || - !fl || (fl == FTRACE_FL_NOTRACE)) + /* Record is filtered and enabled, do nothing */ + if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) return 0; - /* - * If it is enabled disable it, - * otherwise enable it! - */ - if (fl & FTRACE_FL_ENABLED) { - /* swap new and old */ - new = old; - old = ftrace_call_replace(ip, FTRACE_ADDR); + /* Record is not filtered and is not enabled do nothing */ + if (!fl) + return 0; + + /* Record is not filtered but enabled, disable it */ + if (fl == FTRACE_FL_ENABLED) rec->flags &= ~FTRACE_FL_ENABLED; - } else { - new = ftrace_call_replace(ip, FTRACE_ADDR); + else + /* Otherwise record is filtered but not enabled, enable it */ rec->flags |= FTRACE_FL_ENABLED; - } } else { + /* Disable or not filtered */ if (enable) { - /* - * If this record is set not to trace and is - * not enabled, do nothing. - */ - fl = rec->flags & (FTRACE_FL_NOTRACE | FTRACE_FL_ENABLED); - if (fl == FTRACE_FL_NOTRACE) - return 0; - - new = ftrace_call_replace(ip, FTRACE_ADDR); - } else - old = ftrace_call_replace(ip, FTRACE_ADDR); - - if (enable) { + /* if record is enabled, do nothing */ if (rec->flags & FTRACE_FL_ENABLED) return 0; + rec->flags |= FTRACE_FL_ENABLED; + } else { + + /* if record is not enabled do nothing */ if (!(rec->flags & FTRACE_FL_ENABLED)) return 0; + rec->flags &= ~FTRACE_FL_ENABLED; } } - return ftrace_modify_code(ip, old, new); + if (rec->flags & FTRACE_FL_ENABLED) + return ftrace_make_call(rec, ftrace_addr); + else + return ftrace_make_nop(NULL, rec, ftrace_addr); } static void ftrace_replace_code(int enable) { int i, failed; - unsigned char *new = NULL, *old = NULL; struct dyn_ftrace *rec; struct ftrace_page *pg; - if (enable) - old = ftrace_nop_replace(); - else - new = ftrace_nop_replace(); - for (pg = ftrace_pages_start; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { rec = &pg->records[i]; - /* don't modify code that has already faulted */ - if (rec->flags & FTRACE_FL_FAILED) + /* + * Skip over free records and records that have + * failed. + */ + if (rec->flags & FTRACE_FL_FREE || + rec->flags & FTRACE_FL_FAILED) continue; /* ignore updates to this record's mcount site */ @@ -459,68 +493,30 @@ static void ftrace_replace_code(int enable) unfreeze_record(rec); } - failed = __ftrace_replace_code(rec, old, new, enable); + failed = __ftrace_replace_code(rec, enable); if (failed && (rec->flags & FTRACE_FL_CONVERTED)) { rec->flags |= FTRACE_FL_FAILED; if ((system_state == SYSTEM_BOOTING) || !core_kernel_text(rec->ip)) { ftrace_free_rec(rec); - } + } else + ftrace_bug(failed, rec->ip); } } } } -static void print_ip_ins(const char *fmt, unsigned char *p) -{ - int i; - - printk(KERN_CONT "%s", fmt); - - for (i = 0; i < MCOUNT_INSN_SIZE; i++) - printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); -} - static int -ftrace_code_disable(struct dyn_ftrace *rec) +ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) { unsigned long ip; - unsigned char *nop, *call; int ret; ip = rec->ip; - nop = ftrace_nop_replace(); - call = ftrace_call_replace(ip, mcount_addr); - - ret = ftrace_modify_code(ip, call, nop); + ret = ftrace_make_nop(mod, rec, mcount_addr); if (ret) { - switch (ret) { - case -EFAULT: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace faulted on modifying "); - print_ip_sym(ip); - break; - case -EINVAL: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace failed to modify "); - print_ip_sym(ip); - print_ip_ins(" expected: ", call); - print_ip_ins(" actual: ", (unsigned char *)ip); - print_ip_ins(" replace: ", nop); - printk(KERN_CONT "\n"); - break; - case -EPERM: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace faulted on writing "); - print_ip_sym(ip); - break; - default: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace faulted on unknown error "); - print_ip_sym(ip); - } - + ftrace_bug(ret, ip); rec->flags |= FTRACE_FL_FAILED; return 0; } @@ -560,8 +556,7 @@ static void ftrace_startup(void) mutex_lock(&ftrace_start_lock); ftrace_start_up++; - if (ftrace_start_up == 1) - command |= FTRACE_ENABLE_CALLS; + command |= FTRACE_ENABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; @@ -639,7 +634,7 @@ static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; -static int ftrace_update_code(void) +static int ftrace_update_code(struct module *mod) { struct dyn_ftrace *p, *t; cycle_t start, stop; @@ -656,7 +651,7 @@ static int ftrace_update_code(void) list_del_init(&p->list); /* convert record (i.e, patch mcount-call with NOP) */ - if (ftrace_code_disable(p)) { + if (ftrace_code_disable(mod, p)) { p->flags |= FTRACE_FL_CONVERTED; ftrace_update_cnt++; } else @@ -699,7 +694,7 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) cnt = num_to_init / ENTRIES_PER_PAGE; pr_info("ftrace: allocating %ld entries in %d pages\n", - num_to_init, cnt); + num_to_init, cnt + 1); for (i = 0; i < cnt; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); @@ -782,13 +777,11 @@ static void *t_start(struct seq_file *m, loff_t *pos) void *p = NULL; loff_t l = -1; - if (*pos != iter->pos) { - for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) - ; - } else { - l = *pos; - p = t_next(m, p, &l); - } + if (*pos > iter->pos) + *pos = iter->pos; + + l = *pos; + p = t_next(m, p, &l); return p; } @@ -799,15 +792,21 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; if (!rec) return 0; kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - seq_printf(m, "%s\n", str); + ret = seq_printf(m, "%s\n", str); + if (ret < 0) { + iter->pos--; + iter->idx--; + } return 0; } @@ -833,7 +832,7 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -920,7 +919,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->pos = -1; + iter->pos = 0; iter->flags = enable ? FTRACE_ITER_FILTER : FTRACE_ITER_NOTRACE; @@ -1211,7 +1210,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) mutex_lock(&ftrace_sysctl_lock); mutex_lock(&ftrace_start_lock); - if (iter->filtered && ftrace_start_up && ftrace_enabled) + if (ftrace_start_up && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); mutex_unlock(&ftrace_start_lock); mutex_unlock(&ftrace_sysctl_lock); @@ -1298,7 +1297,8 @@ static __init int ftrace_init_debugfs(void) fs_initcall(ftrace_init_debugfs); -static int ftrace_convert_nops(unsigned long *start, +static int ftrace_convert_nops(struct module *mod, + unsigned long *start, unsigned long *end) { unsigned long *p; @@ -1309,23 +1309,32 @@ static int ftrace_convert_nops(unsigned long *start, p = start; while (p < end) { addr = ftrace_call_adjust(*p++); + /* + * Some architecture linkers will pad between + * the different mcount_loc sections of different + * object files to satisfy alignments. + * Skip any NULL pointers. + */ + if (!addr) + continue; ftrace_record_ip(addr); } /* disable interrupts to prevent kstop machine */ local_irq_save(flags); - ftrace_update_code(); + ftrace_update_code(mod); local_irq_restore(flags); mutex_unlock(&ftrace_start_lock); return 0; } -void ftrace_init_module(unsigned long *start, unsigned long *end) +void ftrace_init_module(struct module *mod, + unsigned long *start, unsigned long *end) { if (ftrace_disabled || start == end) return; - ftrace_convert_nops(start, end); + ftrace_convert_nops(mod, start, end); } extern unsigned long __start_mcount_loc[]; @@ -1355,7 +1364,8 @@ void __init ftrace_init(void) last_ftrace_enabled = ftrace_enabled = 1; - ret = ftrace_convert_nops(__start_mcount_loc, + ret = ftrace_convert_nops(NULL, + __start_mcount_loc, __stop_mcount_loc); return; @@ -1411,10 +1421,17 @@ int register_ftrace_function(struct ftrace_ops *ops) return -1; mutex_lock(&ftrace_sysctl_lock); + + if (ftrace_tracing_type == FTRACE_TYPE_RETURN) { + ret = -EBUSY; + goto out; + } + ret = __register_ftrace_function(ops); ftrace_startup(); - mutex_unlock(&ftrace_sysctl_lock); +out: + mutex_unlock(&ftrace_sysctl_lock); return ret; } @@ -1480,16 +1497,45 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, } #ifdef CONFIG_FUNCTION_RET_TRACER + +/* The callback that hooks the return of a function */ trace_function_return_t ftrace_function_return = (trace_function_return_t)ftrace_stub; -void register_ftrace_return(trace_function_return_t func) + +int register_ftrace_return(trace_function_return_t func) { + int ret = 0; + + mutex_lock(&ftrace_sysctl_lock); + + /* + * Don't launch return tracing if normal function + * tracing is already running. + */ + if (ftrace_trace_function != ftrace_stub) { + ret = -EBUSY; + goto out; + } + + ftrace_tracing_type = FTRACE_TYPE_RETURN; ftrace_function_return = func; + ftrace_startup(); + +out: + mutex_unlock(&ftrace_sysctl_lock); + return ret; } void unregister_ftrace_return(void) { + mutex_lock(&ftrace_sysctl_lock); + ftrace_function_return = (trace_function_return_t)ftrace_stub; + ftrace_shutdown(); + /* Restore normal tracing type */ + ftrace_tracing_type = FTRACE_TYPE_ENTER; + + mutex_unlock(&ftrace_sysctl_lock); } #endif diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4a90462..396fda0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1051,7 +1051,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) * Need to use raw, since this must be called before the * recursive protection is performed. */ - raw_local_irq_save(flags); + local_irq_save(flags); cpu = raw_smp_processor_id(); data = tr->data[cpu]; disabled = atomic_inc_return(&data->disabled); @@ -1062,7 +1062,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) } atomic_dec(&data->disabled); - raw_local_irq_restore(flags); + local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_RET_TRACER @@ -2638,8 +2638,11 @@ static int tracing_set_tracer(char *buf) current_trace->reset(tr); current_trace = t; - if (t->init) - t->init(tr); + if (t->init) { + ret = t->init(tr); + if (ret) + goto out; + } trace_branch_enable(tr); out: @@ -2655,6 +2658,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, char buf[max_tracer_type_len+1]; int i; size_t ret; + int err; + + ret = cnt; if (cnt > max_tracer_type_len) cnt = max_tracer_type_len; @@ -2668,12 +2674,11 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) buf[i] = 0; - ret = tracing_set_tracer(buf); - if (!ret) - ret = cnt; + err = tracing_set_tracer(buf); + if (err) + return err; - if (ret > 0) - filp->f_pos += ret; + filp->f_pos += ret; return ret; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 790ea8c..cdbd5cc 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -264,7 +264,8 @@ enum print_line_t { */ struct tracer { const char *name; - void (*init)(struct trace_array *tr); + /* Your tracer should raise a warning if init fails */ + int (*init)(struct trace_array *tr); void (*reset)(struct trace_array *tr); void (*start)(struct trace_array *tr); void (*stop)(struct trace_array *tr); diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index cb333b7..a4fa2c5 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -47,7 +47,7 @@ static void reset_boot_trace(struct trace_array *tr) tracing_reset(tr, cpu); } -static void boot_trace_init(struct trace_array *tr) +static int boot_trace_init(struct trace_array *tr) { int cpu; boot_trace = tr; @@ -56,6 +56,7 @@ static void boot_trace_init(struct trace_array *tr) tracing_reset(tr, cpu); tracing_sched_switch_assign_trace(tr); + return 0; } static enum print_line_t diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 2511e32..23f9b02 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -125,7 +125,7 @@ static void stop_branch_trace(struct trace_array *tr) disable_branch_tracing(); } -static void branch_trace_init(struct trace_array *tr) +static int branch_trace_init(struct trace_array *tr) { int cpu; @@ -133,6 +133,7 @@ static void branch_trace_init(struct trace_array *tr) tracing_reset(tr, cpu); start_branch_trace(tr); + return 0; } static void branch_trace_reset(struct trace_array *tr) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 8693b7a..e74f6d0 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -42,9 +42,10 @@ static void stop_function_trace(struct trace_array *tr) tracing_stop_cmdline_record(); } -static void function_trace_init(struct trace_array *tr) +static int function_trace_init(struct trace_array *tr) { start_function_trace(tr); + return 0; } static void function_trace_reset(struct trace_array *tr) diff --git a/kernel/trace/trace_functions_return.c b/kernel/trace/trace_functions_return.c index 7680b21..a68564a 100644 --- a/kernel/trace/trace_functions_return.c +++ b/kernel/trace/trace_functions_return.c @@ -14,28 +14,18 @@ #include "trace.h" -static void start_return_trace(struct trace_array *tr) -{ - register_ftrace_return(&trace_function_return); -} - -static void stop_return_trace(struct trace_array *tr) -{ - unregister_ftrace_return(); -} - -static void return_trace_init(struct trace_array *tr) +static int return_trace_init(struct trace_array *tr) { int cpu; for_each_online_cpu(cpu) tracing_reset(tr, cpu); - start_return_trace(tr); + return register_ftrace_return(&trace_function_return); } static void return_trace_reset(struct trace_array *tr) { - stop_return_trace(tr); + unregister_ftrace_return(); } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index d919d4e..7c2e326 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -416,11 +416,12 @@ static void irqsoff_tracer_close(struct trace_iterator *iter) } #ifdef CONFIG_IRQSOFF_TRACER -static void irqsoff_tracer_init(struct trace_array *tr) +static int irqsoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_IRQS_OFF; __irqsoff_tracer_init(tr); + return 0; } static struct tracer irqsoff_tracer __read_mostly = { @@ -442,11 +443,12 @@ static struct tracer irqsoff_tracer __read_mostly = #endif #ifdef CONFIG_PREEMPT_TRACER -static void preemptoff_tracer_init(struct trace_array *tr) +static int preemptoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_PREEMPT_OFF; __irqsoff_tracer_init(tr); + return 0; } static struct tracer preemptoff_tracer __read_mostly = @@ -471,11 +473,12 @@ static struct tracer preemptoff_tracer __read_mostly = #if defined(CONFIG_IRQSOFF_TRACER) && \ defined(CONFIG_PREEMPT_TRACER) -static void preemptirqsoff_tracer_init(struct trace_array *tr) +static int preemptirqsoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF; __irqsoff_tracer_init(tr); + return 0; } static struct tracer preemptirqsoff_tracer __read_mostly = diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 51bcf37..433d650 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -30,13 +30,14 @@ static void mmio_reset_data(struct trace_array *tr) tracing_reset(tr, cpu); } -static void mmio_trace_init(struct trace_array *tr) +static int mmio_trace_init(struct trace_array *tr) { pr_debug("in %s\n", __func__); mmio_trace_array = tr; mmio_reset_data(tr); enable_mmiotrace(); + return 0; } static void mmio_trace_reset(struct trace_array *tr) diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 2ef1d22..0e77415c 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -24,7 +24,7 @@ static void stop_nop_trace(struct trace_array *tr) /* Nothing to do! */ } -static void nop_trace_init(struct trace_array *tr) +static int nop_trace_init(struct trace_array *tr) { int cpu; ctx_trace = tr; @@ -33,6 +33,7 @@ static void nop_trace_init(struct trace_array *tr) tracing_reset(tr, cpu); start_nop_trace(tr); + return 0; } static void nop_trace_reset(struct trace_array *tr) diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index be35bdf..8633905 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -206,10 +206,11 @@ static void stop_sched_trace(struct trace_array *tr) tracing_stop_sched_switch_record(); } -static void sched_switch_trace_init(struct trace_array *tr) +static int sched_switch_trace_init(struct trace_array *tr) { ctx_trace = tr; start_sched_trace(tr); + return 0; } static void sched_switch_trace_reset(struct trace_array *tr) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 983f2b1..0067b49 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -331,10 +331,11 @@ static void stop_wakeup_tracer(struct trace_array *tr) unregister_trace_sched_wakeup(probe_wakeup); } -static void wakeup_tracer_init(struct trace_array *tr) +static int wakeup_tracer_init(struct trace_array *tr) { wakeup_trace = tr; start_wakeup_tracer(tr); + return 0; } static void wakeup_tracer_reset(struct trace_array *tr) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 24e6e07..88c8eb7 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -52,7 +52,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) int cpu, ret = 0; /* Don't allow flipping of max traces now */ - raw_local_irq_save(flags); + local_irq_save(flags); __raw_spin_lock(&ftrace_max_lock); cnt = ring_buffer_entries(tr->buffer); @@ -63,7 +63,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) break; } __raw_spin_unlock(&ftrace_max_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); if (count) *count = cnt; @@ -71,6 +71,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) return ret; } +static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) +{ + printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n", + trace->name, init_ret); +} #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE @@ -111,7 +116,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, ftrace_set_filter(func_name, strlen(func_name), 1); /* enable tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } /* Sleep for a 1/10 of a second */ msleep(100); @@ -181,7 +190,12 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ftrace_enabled = 1; tracer_enabled = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ @@ -223,7 +237,12 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* reset the max latency */ tracing_max_latency = 0; /* disable interrupts for a bit */ @@ -272,7 +291,12 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) } /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* reset the max latency */ tracing_max_latency = 0; /* disable preemption for a bit */ @@ -321,7 +345,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * } /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } /* reset the max latency */ tracing_max_latency = 0; @@ -449,7 +477,12 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) wait_for_completion(&isrt); /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* reset the max latency */ tracing_max_latency = 0; @@ -505,7 +538,12 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr int ret; /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ @@ -532,7 +570,12 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return 0; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ @@ -554,7 +597,12 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c index 05f7534..54960ed 100644 --- a/kernel/trace/trace_sysprof.c +++ b/kernel/trace/trace_sysprof.c @@ -261,11 +261,12 @@ static void stop_stack_trace(struct trace_array *tr) mutex_unlock(&sample_timer_lock); } -static void stack_trace_init(struct trace_array *tr) +static int stack_trace_init(struct trace_array *tr) { sysprof_trace = tr; start_stack_trace(tr); + return 0; } static void stack_trace_reset(struct trace_array *tr) diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index e96590f..7960274 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -262,6 +262,7 @@ static void set_tracepoint(struct tracepoint_entry **entry, static void disable_tracepoint(struct tracepoint *elem) { elem->state = 0; + rcu_assign_pointer(elem->funcs, NULL); } /** @@ -540,3 +541,36 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter) iter->tracepoint = NULL; } EXPORT_SYMBOL_GPL(tracepoint_iter_reset); + +#ifdef CONFIG_MODULES + +int tracepoint_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + break; + case MODULE_STATE_GOING: + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + break; + } + return 0; +} + +struct notifier_block tracepoint_module_nb = { + .notifier_call = tracepoint_module_notify, + .priority = 0, +}; + +static int init_tracepoints(void) +{ + return register_module_notifier(&tracepoint_module_nb); +} +__initcall(init_tracepoints); + +#endif /* CONFIG_MODULES */ |
