diff options
Diffstat (limited to 'kernel/trace')
| -rw-r--r-- | kernel/trace/Kconfig | 56 | ||||
| -rw-r--r-- | kernel/trace/blktrace.c | 4 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 228 | ||||
| -rw-r--r-- | kernel/trace/power-traces.c | 3 | ||||
| -rw-r--r-- | kernel/trace/ring_buffer.c | 179 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 814 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 158 | ||||
| -rw-r--r-- | kernel/trace/trace_branch.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace_clock.c | 5 | ||||
| -rw-r--r-- | kernel/trace/trace_events.c | 52 | ||||
| -rw-r--r-- | kernel/trace/trace_events_filter.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace_functions.c | 68 | ||||
| -rw-r--r-- | kernel/trace/trace_functions_graph.c | 74 | ||||
| -rw-r--r-- | kernel/trace/trace_irqsoff.c | 35 | ||||
| -rw-r--r-- | kernel/trace/trace_kprobe.c | 10 | ||||
| -rw-r--r-- | kernel/trace/trace_output.c | 81 | ||||
| -rw-r--r-- | kernel/trace/trace_probe.c | 14 | ||||
| -rw-r--r-- | kernel/trace/trace_probe.h | 1 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_switch.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace_sched_wakeup.c | 32 | ||||
| -rw-r--r-- | kernel/trace/trace_selftest.c | 34 | ||||
| -rw-r--r-- | kernel/trace/trace_stack.c | 6 | ||||
| -rw-r--r-- | kernel/trace/trace_syscalls.c | 122 | ||||
| -rw-r--r-- | kernel/trace/trace_uprobe.c | 229 |
24 files changed, 1442 insertions, 775 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 4cea4f41c1d9..fc382d6e2765 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -39,6 +39,9 @@ config HAVE_DYNAMIC_FTRACE help See Documentation/trace/ftrace-design.txt +config HAVE_DYNAMIC_FTRACE_WITH_REGS + bool + config HAVE_FTRACE_MCOUNT_RECORD bool help @@ -78,21 +81,6 @@ config EVENT_TRACING select CONTEXT_SWITCH_TRACER bool -config EVENT_POWER_TRACING_DEPRECATED - depends on EVENT_TRACING - bool "Deprecated power event trace API, to be removed" - default y - help - Provides old power event types: - C-state/idle accounting events: - power:power_start - power:power_end - and old cpufreq accounting event: - power:power_frequency - This is for userspace compatibility - and will vanish after 5 kernel iterations, - namely 3.1. - config CONTEXT_SWITCH_TRACER bool @@ -119,6 +107,7 @@ config TRACING select BINARY_PRINTF select EVENT_TRACING select TRACE_CLOCK + select IRQ_WORK config GENERIC_TRACER bool @@ -249,6 +238,16 @@ config FTRACE_SYSCALLS help Basic tracer to catch the syscall entry and exit events. +config TRACER_SNAPSHOT + bool "Create a snapshot trace buffer" + select TRACER_MAX_TRACE + help + Allow tracing users to take snapshot of the current buffer using the + ftrace interface, e.g.: + + echo 1 > /sys/kernel/debug/tracing/snapshot + cat snapshot + config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER @@ -415,23 +414,32 @@ config PROBE_EVENTS def_bool n config DYNAMIC_FTRACE - bool "enable/disable ftrace tracepoints dynamically" + bool "enable/disable function tracing dynamically" depends on FUNCTION_TRACER depends on HAVE_DYNAMIC_FTRACE default y help - This option will modify all the calls to ftrace dynamically - (will patch them out of the binary image and replace them - with a No-Op instruction) as they are called. A table is - created to dynamically enable them again. + This option will modify all the calls to function tracing + dynamically (will patch them out of the binary image and + replace them with a No-Op instruction) on boot up. During + compile time, a table is made of all the locations that ftrace + can function trace, and this table is linked into the kernel + image. When this is enabled, functions can be individually + enabled, and the functions not enabled will not affect + performance of the system. + + See the files in /sys/kernel/debug/tracing: + available_filter_functions + set_ftrace_filter + set_ftrace_notrace This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise has native performance as long as no tracing is active. - The changes to the code are done by a kernel thread that - wakes up once a second and checks to see if any ftrace calls - were made. If so, it runs stop_machine (stops all CPUS) - and modifies the code to jump over the call to ftrace. +config DYNAMIC_FTRACE_WITH_REGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_REGS config FUNCTION_PROFILER bool "Kernel function profiler" diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index c0bd0308741c..5a0f781cd729 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -147,7 +147,7 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) return; local_irq_save(flags); - buf = per_cpu_ptr(bt->msg_data, smp_processor_id()); + buf = this_cpu_ptr(bt->msg_data); va_start(args, fmt); n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); @@ -783,6 +783,7 @@ static void blk_add_trace_bio_complete(void *ignore, static void blk_add_trace_bio_backmerge(void *ignore, struct request_queue *q, + struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); @@ -790,6 +791,7 @@ static void blk_add_trace_bio_backmerge(void *ignore, static void blk_add_trace_bio_frontmerge(void *ignore, struct request_queue *q, + struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9dcf15d38380..b3fde6d7b7fc 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -10,7 +10,7 @@ * Based on code in the latency_tracer, that is: * * Copyright (C) 2004-2006 Ingo Molnar - * Copyright (C) 2004 William Lee Irwin III + * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/stop_machine.h> @@ -66,7 +66,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, }; /* ftrace_enabled is a method to turn ftrace on or off */ @@ -111,6 +111,26 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) #endif +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /** * ftrace_nr_registered_ops - return number of ops registered * @@ -132,29 +152,21 @@ int ftrace_nr_registered_ops(void) return cnt; } -/* - * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw() is that elements removed from this list - * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw() calls are needed to handle - * concurrent insertions into the ftrace_global_list. - * - * Silly Alpha and silly pointer-speculation compiler optimizations! - */ static void ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs) { - if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) + int bit; + + bit = trace_test_and_set_recursion(TRACE_GLOBAL_START, TRACE_GLOBAL_MAX); + if (bit < 0) return; - trace_recursion_set(TRACE_GLOBAL_BIT); - op = rcu_dereference_raw(ftrace_global_list); /*see above*/ - while (op != &ftrace_list_end) { + do_for_each_ftrace_op(op, ftrace_global_list) { op->func(ip, parent_ip, op, regs); - op = rcu_dereference_raw(op->next); /*see above*/ - }; - trace_recursion_clear(TRACE_GLOBAL_BIT); + } while_for_each_ftrace_op(op); + + trace_clear_recursion(bit); } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, @@ -221,10 +233,24 @@ static void update_global_ops(void) * registered callers. */ if (ftrace_global_list == &ftrace_list_end || - ftrace_global_list->next == &ftrace_list_end) + ftrace_global_list->next == &ftrace_list_end) { func = ftrace_global_list->func; - else + /* + * As we are calling the function directly. + * If it does not have recursion protection, + * the function_trace_op needs to be updated + * accordingly. + */ + if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) + global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; + else + global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE; + } else { func = ftrace_global_list_func; + /* The list has its own recursion protection. */ + global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; + } + /* If we filter on pids, update to use the pid function */ if (!list_empty(&ftrace_pids)) { @@ -337,7 +363,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) return -EINVAL; -#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS /* * If the ftrace_ops specifies SAVE_REGS, then it only can be used * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. @@ -668,7 +694,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) free_page(tmp); } - free_page((unsigned long)stat->pages); stat->pages = NULL; stat->start = NULL; @@ -736,7 +761,6 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) { struct ftrace_profile *rec; struct hlist_head *hhd; - struct hlist_node *n; unsigned long key; key = hash_long(ip, ftrace_profile_bits); @@ -745,7 +769,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) if (hlist_empty(hhd)) return NULL; - hlist_for_each_entry_rcu(rec, n, hhd, node) { + hlist_for_each_entry_rcu(rec, hhd, node) { if (rec->ip == ip) return rec; } @@ -1028,6 +1052,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) static struct pid * const ftrace_swapper_pid = &init_struct_pid; +loff_t +ftrace_filter_lseek(struct file *file, loff_t offset, int whence) +{ + loff_t ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, whence); + else + file->f_pos = ret = 1; + + return ret; +} + #ifdef CONFIG_DYNAMIC_FTRACE #ifndef CONFIG_FTRACE_MCOUNT_RECORD @@ -1107,7 +1144,6 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) unsigned long key; struct ftrace_func_entry *entry; struct hlist_head *hhd; - struct hlist_node *n; if (ftrace_hash_empty(hash)) return NULL; @@ -1119,7 +1155,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) hhd = &hash->buckets[key]; - hlist_for_each_entry_rcu(entry, n, hhd, hlist) { + hlist_for_each_entry_rcu(entry, hhd, hlist) { if (entry->ip == ip) return entry; } @@ -1176,7 +1212,7 @@ remove_hash_entry(struct ftrace_hash *hash, static void ftrace_hash_clear(struct ftrace_hash *hash) { struct hlist_head *hhd; - struct hlist_node *tp, *tn; + struct hlist_node *tn; struct ftrace_func_entry *entry; int size = 1 << hash->size_bits; int i; @@ -1186,7 +1222,7 @@ static void ftrace_hash_clear(struct ftrace_hash *hash) for (i = 0; i < size; i++) { hhd = &hash->buckets[i]; - hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) + hlist_for_each_entry_safe(entry, tn, hhd, hlist) free_hash_entry(hash, entry); } FTRACE_WARN_ON(hash->count); @@ -1249,7 +1285,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) { struct ftrace_func_entry *entry; struct ftrace_hash *new_hash; - struct hlist_node *tp; int size; int ret; int i; @@ -1264,7 +1299,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) size = 1 << hash->size_bits; for (i = 0; i < size; i++) { - hlist_for_each_entry(entry, tp, &hash->buckets[i], hlist) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { ret = add_hash_entry(new_hash, entry->ip); if (ret < 0) goto free_hash; @@ -1290,7 +1325,7 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, struct ftrace_hash **dst, struct ftrace_hash *src) { struct ftrace_func_entry *entry; - struct hlist_node *tp, *tn; + struct hlist_node *tn; struct hlist_head *hhd; struct ftrace_hash *old_hash; struct ftrace_hash *new_hash; @@ -1336,7 +1371,7 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, size = 1 << src->size_bits; for (i = 0; i < size; i++) { hhd = &src->buckets[i]; - hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) { + hlist_for_each_entry_safe(entry, tn, hhd, hlist) { if (bits > 0) key = hash_long(entry->ip, bits); else @@ -2437,7 +2472,7 @@ static void reset_iter_read(struct ftrace_iterator *iter) { iter->pos = 0; iter->func_pos = 0; - iter->flags &= ~(FTRACE_ITER_PRINTALL & FTRACE_ITER_HASH); + iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_HASH); } static void *t_start(struct seq_file *m, loff_t *pos) @@ -2590,7 +2625,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash) * routine, you can use ftrace_filter_write() for the write * routine if @flag has FTRACE_ITER_FILTER set, or * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set. - * ftrace_regex_lseek() should be used as the lseek routine, and + * ftrace_filter_lseek() should be used as the lseek routine, and * release must call ftrace_regex_release(). */ int @@ -2674,19 +2709,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file) inode, file); } -loff_t -ftrace_regex_lseek(struct file *file, loff_t offset, int origin) -{ - loff_t ret; - - if (file->f_mode & FMODE_READ) - ret = seq_lseek(file, offset, origin); - else - file->f_pos = ret = 1; - - return ret; -} - static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; @@ -2868,14 +2890,13 @@ static int __init ftrace_mod_cmd_init(void) { return register_ftrace_command(&ftrace_mod_cmd); } -device_initcall(ftrace_mod_cmd_init); +core_initcall(ftrace_mod_cmd_init); static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ftrace_func_probe *entry; struct hlist_head *hhd; - struct hlist_node *n; unsigned long key; key = hash_long(ip, FTRACE_HASH_BITS); @@ -2891,7 +2912,7 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, * on the hash. rcu_read_lock is too dangerous here. */ preempt_disable_notrace(); - hlist_for_each_entry_rcu(entry, n, hhd, node) { + hlist_for_each_entry_rcu(entry, hhd, node) { if (entry->ip == ip) entry->ops->func(ip, parent_ip, &entry->data); } @@ -3042,7 +3063,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { struct ftrace_func_probe *entry; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; char str[KSYM_SYMBOL_LEN]; int type = MATCH_FULL; int i, len = 0; @@ -3065,7 +3086,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; - hlist_for_each_entry_safe(entry, n, tmp, hhd, node) { + hlist_for_each_entry_safe(entry, tmp, hhd, node) { /* break up if statements for readability */ if ((flags & PROBE_TEST_FUNC) && entry->ops != ops) @@ -3082,8 +3103,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, continue; } - hlist_del(&entry->node); - call_rcu(&entry->rcu, ftrace_free_entry_rcu); + hlist_del_rcu(&entry->node); + call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu); } } __disable_ftrace_function_probe(); @@ -3419,14 +3440,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata; static int __init set_ftrace_notrace(char *str) { - strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_notrace=", set_ftrace_notrace); static int __init set_ftrace_filter(char *str) { - strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_filter=", set_ftrace_filter); @@ -3549,7 +3570,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3557,7 +3578,7 @@ static const struct file_operations ftrace_notrace_fops = { .open = ftrace_notrace_open, .read = seq_read, .write = ftrace_notrace_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3762,8 +3783,8 @@ static const struct file_operations ftrace_graph_fops = { .open = ftrace_graph_open, .read = seq_read, .write = ftrace_graph_write, + .llseek = ftrace_filter_lseek, .release = ftrace_graph_release, - .llseek = seq_lseek, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -3970,35 +3991,49 @@ static void ftrace_init_module(struct module *mod, ftrace_process_locs(mod, start, end); } -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) +static int ftrace_module_notify_enter(struct notifier_block *self, + unsigned long val, void *data) { struct module *mod = data; - switch (val) { - case MODULE_STATE_COMING: + if (val == MODULE_STATE_COMING) ftrace_init_module(mod, mod->ftrace_callsites, mod->ftrace_callsites + mod->num_ftrace_callsites); - break; - case MODULE_STATE_GOING: + return 0; +} + +static int ftrace_module_notify_exit(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + if (val == MODULE_STATE_GOING) ftrace_release_mod(mod); - break; - } return 0; } #else -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) +static int ftrace_module_notify_enter(struct notifier_block *self, + unsigned long val, void *data) +{ + return 0; +} +static int ftrace_module_notify_exit(struct notifier_block *self, + unsigned long val, void *data) { return 0; } #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_nb = { - .notifier_call = ftrace_module_notify, - .priority = 0, +struct notifier_block ftrace_module_enter_nb = { + .notifier_call = ftrace_module_notify_enter, + .priority = INT_MAX, /* Run before anything that can use kprobes */ +}; + +struct notifier_block ftrace_module_exit_nb = { + .notifier_call = ftrace_module_notify_exit, + .priority = INT_MIN, /* Run after anything that can remove kprobes */ }; extern unsigned long __start_mcount_loc[]; @@ -4032,9 +4067,13 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_nb); + ret = register_module_notifier(&ftrace_module_enter_nb); if (ret) - pr_warning("Failed to register trace ftrace module notifier\n"); + pr_warning("Failed to register trace ftrace module enter notifier\n"); + + ret = register_module_notifier(&ftrace_module_exit_nb); + if (ret) + pr_warning("Failed to register trace ftrace module exit notifier\n"); set_ftrace_early_filters(); @@ -4055,7 +4094,7 @@ static int __init ftrace_nodyn_init(void) ftrace_enabled = 1; return 0; } -device_initcall(ftrace_nodyn_init); +core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } @@ -4090,14 +4129,12 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, */ preempt_disable_notrace(); trace_recursion_set(TRACE_CONTROL_BIT); - op = rcu_dereference_raw(ftrace_control_list); - while (op != &ftrace_list_end) { - if (!ftrace_function_local_disabled(op) && + 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)) op->func(ip, parent_ip, op, regs); - - op = rcu_dereference_raw(op->next); - }; + } while_for_each_ftrace_op(op); trace_recursion_clear(TRACE_CONTROL_BIT); preempt_enable_notrace(); } @@ -4112,27 +4149,26 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { struct ftrace_ops *op; + int bit; if (function_trace_stop) return; - if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) + bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + if (bit < 0) return; - trace_recursion_set(TRACE_INTERNAL_BIT); /* * Some of the ops may be dynamically allocated, * they must be freed after a synchronize_sched(). */ preempt_disable_notrace(); - op = rcu_dereference_raw(ftrace_ops_list); - while (op != &ftrace_list_end) { + do_for_each_ftrace_op(op, ftrace_ops_list) { if (ftrace_ops_test(op, ip)) op->func(ip, parent_ip, op, regs); - op = rcu_dereference_raw(op->next); - }; + } while_for_each_ftrace_op(op); preempt_enable_notrace(); - trace_recursion_clear(TRACE_INTERNAL_BIT); + trace_clear_recursion(bit); } /* @@ -4143,8 +4179,8 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, * Archs are to support both the regs and ftrace_ops at the same time. * If they support ftrace_ops, it is assumed they support regs. * If call backs want to use regs, they must either check for regs - * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS. - * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved. + * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS. + * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved. * An architecture can pass partial regs with ftrace_ops and still * set the ARCH_SUPPORT_FTARCE_OPS. */ @@ -4381,7 +4417,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, if (strlen(tmp) == 0) return 1; - ret = strict_strtol(tmp, 10, &val); + ret = kstrtol(tmp, 10, &val); if (ret < 0) return ret; @@ -4403,7 +4439,7 @@ static const struct file_operations ftrace_pid_fops = { .open = ftrace_pid_open, .write = ftrace_pid_write, .read = seq_read, - .llseek = seq_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_pid_release, }; @@ -4519,12 +4555,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); /* we are starting ftrace again */ - if (ftrace_ops_list != &ftrace_list_end) { - if (ftrace_ops_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_ops_list->func; - else - ftrace_trace_function = ftrace_ops_list_func; - } + if (ftrace_ops_list != &ftrace_list_end) + update_ftrace_function(); } else { /* stopping ftrace calls (just send to ftrace_stub) */ diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c index f55fcf61b223..1c71382b283d 100644 --- a/kernel/trace/power-traces.c +++ b/kernel/trace/power-traces.c @@ -13,8 +13,5 @@ #define CREATE_TRACE_POINTS #include <trace/events/power.h> -#ifdef EVENT_POWER_TRACING_DEPRECATED -EXPORT_TRACEPOINT_SYMBOL_GPL(power_start); -#endif EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b979426d16c6..6989df2ba194 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3,8 +3,10 @@ * * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> */ +#include <linux/ftrace_event.h> #include <linux/ring_buffer.h> #include <linux/trace_clock.h> +#include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/debugfs.h> #include <linux/uaccess.h> @@ -21,7 +23,6 @@ #include <linux/fs.h> #include <asm/local.h> -#include "trace.h" static void update_pages_handler(struct work_struct *work); @@ -177,7 +178,7 @@ void tracing_off_permanent(void) #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) #define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ -#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS # define RB_FORCE_8BYTE_ALIGNMENT 0 # define RB_ARCH_ALIGNMENT RB_ALIGNMENT #else @@ -185,6 +186,8 @@ void tracing_off_permanent(void) # define RB_ARCH_ALIGNMENT 8U #endif +#define RB_ALIGN_DATA __aligned(RB_ARCH_ALIGNMENT) + /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX @@ -333,7 +336,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ - unsigned char data[]; /* data of buffer page */ + unsigned char data[] RB_ALIGN_DATA; /* data of buffer page */ }; /* @@ -460,9 +463,10 @@ struct ring_buffer_per_cpu { unsigned long lost_events; unsigned long last_overrun; local_t entries_bytes; - local_t commit_overrun; - local_t overrun; local_t entries; + local_t overrun; + local_t commit_overrun; + local_t dropped_events; local_t committing; local_t commits; unsigned long read; @@ -1396,6 +1400,8 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head_page_with_bit; head_page = &rb_set_head_page(cpu_buffer)->list; + if (!head_page) + break; prev_page = head_page->prev; first_page = pages->next; @@ -1820,7 +1826,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta) } /** - * ring_buffer_update_event - update event type and data + * rb_update_event - update event type and data * @event: the even to update * @type: the type of event * @length: the size of the event field in the ring buffer @@ -2155,8 +2161,10 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, * If we are not in overwrite mode, * this is easy, just stop here. */ - if (!(buffer->flags & RB_FL_OVERWRITE)) + if (!(buffer->flags & RB_FL_OVERWRITE)) { + local_inc(&cpu_buffer->dropped_events); goto out_reset; + } ret = rb_handle_head_page(cpu_buffer, tail_page, @@ -2427,41 +2435,76 @@ rb_reserve_next_event(struct ring_buffer *buffer, #ifdef CONFIG_TRACING -#define TRACE_RECURSIVE_DEPTH 16 +/* + * The lock and unlock are done within a preempt disable section. + * The current_context per_cpu variable can only be modified + * by the current task between lock and unlock. But it can + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. + * + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. + * + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. + */ +static DEFINE_PER_CPU(unsigned int, current_context); -/* Keep this code out of the fast path cache */ -static noinline void trace_recursive_fail(void) +static __always_inline int trace_recursive_lock(void) { - /* Disable all tracing before we do anything else */ - tracing_off_permanent(); + unsigned int val = this_cpu_read(current_context); + int bit; - printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:" - "HC[%lu]:SC[%lu]:NMI[%lu]\n", - trace_recursion_buffer(), - hardirq_count() >> HARDIRQ_SHIFT, - softirq_count() >> SOFTIRQ_SHIFT, - in_nmi()); - - WARN_ON_ONCE(1); -} - -static inline int trace_recursive_lock(void) -{ - trace_recursion_inc(); + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; - if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH)) - return 0; + if (unlikely(val & (1 << bit))) + return 1; - trace_recursive_fail(); + val |= (1 << bit); + this_cpu_write(current_context, val); - return -1; + return 0; } -static inline void trace_recursive_unlock(void) +static __always_inline void trace_recursive_unlock(void) { - WARN_ON_ONCE(!trace_recursion_buffer()); + unsigned int val = this_cpu_read(current_context); - trace_recursion_dec(); + val--; + val &= this_cpu_read(current_context); + this_cpu_write(current_context, val); } #else @@ -2720,8 +2763,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_discard_commit); * and not the length of the event which would hold the header. */ int ring_buffer_write(struct ring_buffer *buffer, - unsigned long length, - void *data) + unsigned long length, + void *data) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; @@ -2929,12 +2972,12 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ -unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) +u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) { unsigned long flags; struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; - unsigned long ret; + u64 ret = 0; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; @@ -2949,7 +2992,8 @@ unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) bpage = cpu_buffer->reader_page; else bpage = rb_set_head_page(cpu_buffer); - ret = bpage->page->time_stamp; + if (bpage) + ret = bpage->page->time_stamp; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return ret; @@ -2995,7 +3039,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); /** - * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer + * ring_buffer_overrun_cpu - get the number of overruns caused by the ring + * buffer wrapping around (only if RB_FL_OVERWRITE is on). * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ @@ -3015,7 +3060,9 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); /** - * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits + * ring_buffer_commit_overrun_cpu - get the number of overruns caused by + * commits failing due to the buffer wrapping around while there are uncommitted + * events, such as during an interrupt storm. * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ @@ -3036,6 +3083,46 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu); /** + * ring_buffer_dropped_events_cpu - get the number of dropped events caused by + * the ring buffer filling up (only if RB_FL_OVERWRITE is off). + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of overruns from + */ +unsigned long +ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->dropped_events); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu); + +/** + * ring_buffer_read_events_cpu - get the number of events successfully read + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of events read + */ +unsigned long +ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + return cpu_buffer->read; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu); + +/** * ring_buffer_entries - get the number of entries in a buffer * @buffer: The ring buffer * @@ -3260,6 +3347,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) * Splice the empty reader page into the list around the head. */ reader = rb_set_head_page(cpu_buffer); + if (!reader) + goto out; cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next); cpu_buffer->reader_page->list.prev = reader->list.prev; @@ -3392,7 +3481,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) /* check for end of page padding */ if ((iter->head >= rb_page_size(iter->head_page)) && (iter->head_page != cpu_buffer->commit_page)) - rb_advance_iter(iter); + rb_inc_iter(iter); } static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer) @@ -3778,12 +3867,17 @@ void ring_buffer_read_finish(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + unsigned long flags; /* * Ring buffer is disabled from recording, here's a good place - * to check the integrity of the ring buffer. + * to check the integrity of the ring buffer. + * Must prevent readers from trying to read, as the check + * clears the HEAD page and readers require it. */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_check_pages(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->buffer->resize_disabled); @@ -3864,9 +3958,10 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) local_set(&cpu_buffer->reader_page->page->commit, 0); cpu_buffer->reader_page->read = 0; - local_set(&cpu_buffer->commit_overrun, 0); local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0); + local_set(&cpu_buffer->commit_overrun, 0); + local_set(&cpu_buffer->dropped_events, 0); local_set(&cpu_buffer->entries, 0); local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 31e4f55773f1..66338c4f7f4b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9,7 +9,7 @@ * * Based on code from the latency_tracer, that is: * Copyright (C) 2004-2006 Ingo Molnar - * Copyright (C) 2004 William Lee Irwin III + * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/ring_buffer.h> #include <generated/utsrelease.h> @@ -19,6 +19,7 @@ #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/irqflags.h> +#include <linux/irq_work.h> #include <linux/debugfs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> @@ -38,6 +39,7 @@ #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> +#include <linux/sched/rt.h> #include "trace.h" #include "trace_output.h" @@ -78,6 +80,21 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set) } /* + * To prevent the comm cache from being overwritten when no + * tracing is active, only save the comm when a trace event + * occurred. + */ +static DEFINE_PER_CPU(bool, trace_cmdline_save); + +/* + * When a reader is waiting for data, then this variable is + * set to true. + */ +static bool trace_wakeup_needed; + +static struct irq_work trace_work_wakeup; + +/* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization * of the tracer is successful. But that is the only place that sets @@ -115,7 +132,7 @@ static char *default_bootup_tracer; static int __init set_cmdline_ftrace(char *str) { - strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); + strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ ring_buffer_expanded = 1; @@ -139,6 +156,18 @@ static int __init set_ftrace_dump_on_oops(char *str) } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); + +static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; +static char *trace_boot_options __initdata; + +static int __init set_trace_boot_options(char *str) +{ + strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + trace_boot_options = trace_boot_options_buf; + return 0; +} +__setup("trace_options=", set_trace_boot_options); + unsigned long long ns2usecs(cycle_t nsec) { nsec += 500; @@ -198,20 +227,9 @@ static struct trace_array max_tr; static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data); -/* tracer_enabled is used to toggle activation of a tracer */ -static int tracer_enabled = 1; - -/** - * tracing_is_enabled - return tracer_enabled status - * - * This function is used by other tracers to know the status - * of the tracer_enabled flag. Tracers may use this function - * to know if it should enable their features when starting - * up. See irqsoff tracer for an example (start_irqsoff_tracer). - */ int tracing_is_enabled(void) { - return tracer_enabled; + return tracing_is_on(); } /* @@ -232,7 +250,7 @@ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; static struct tracer *trace_types __read_mostly; /* current_trace points to the tracer that is currently active */ -static struct tracer *current_trace __read_mostly; +static struct tracer *current_trace __read_mostly = &nop_trace; /* * trace_types_lock is used to protect the trace_types list. @@ -333,12 +351,18 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); -static void wakeup_work_handler(struct work_struct *work) +/** + * trace_wake_up - wake up tasks waiting for trace input + * + * Schedules a delayed work to wake up any task that is blocked on the + * trace_wait queue. These is used with trace_poll for tasks polling the + * trace. + */ +static void trace_wake_up(struct irq_work *work) { - wake_up(&trace_wait); -} + wake_up_all(&trace_wait); -static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); +} /** * tracing_on - enable tracing buffers @@ -393,22 +417,6 @@ int tracing_is_on(void) } EXPORT_SYMBOL_GPL(tracing_is_on); -/** - * trace_wake_up - wake up tasks waiting for trace input - * - * Schedules a delayed work to wake up any task that is blocked on the - * trace_wait queue. These is used with trace_poll for tasks polling the - * trace. - */ -void trace_wake_up(void) -{ - const unsigned long delay = msecs_to_jiffies(2); - - if (trace_flags & TRACE_ITER_BLOCK) - return; - schedule_delayed_work(&wakeup_work, delay); -} - static int __init set_buf_size(char *str) { unsigned long buf_size; @@ -431,7 +439,7 @@ static int __init set_tracing_thresh(char *str) if (!str) return 0; - ret = strict_strtoul(str, 0, &threshold); + ret = kstrtoul(str, 0, &threshold); if (ret < 0) return 0; tracing_thresh = threshold * 1000; @@ -477,10 +485,12 @@ static const char *trace_options[] = { static struct { u64 (*func)(void); const char *name; + int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { - { trace_clock_local, "local" }, - { trace_clock_global, "global" }, - { trace_clock_counter, "counter" }, + { trace_clock_local, "local", 1 }, + { trace_clock_global, "global", 1 }, + { trace_clock_counter, "counter", 0 }, + ARCH_TRACE_CLOCKS }; int trace_clock_id; @@ -694,18 +704,22 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct ring_buffer *buf = tr->buffer; + struct ring_buffer *buf; if (trace_stop_count) return; WARN_ON_ONCE(!irqs_disabled()); - if (!current_trace->use_max_tr) { - WARN_ON_ONCE(1); + + if (!current_trace->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(current_trace != &nop_trace); return; } + arch_spin_lock(&ftrace_max_lock); + buf = tr->buffer; tr->buffer = max_tr.buffer; max_tr.buffer = buf; @@ -730,8 +744,9 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); - if (!current_trace->use_max_tr) { - WARN_ON_ONCE(1); + if (!current_trace->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(current_trace != &nop_trace); return; } @@ -757,6 +772,40 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ +static void default_wait_pipe(struct trace_iterator *iter) +{ + DEFINE_WAIT(wait); + + prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + trace_wakeup_needed = true; + + if (trace_empty(iter)) + schedule(); + + finish_wait(&trace_wait, &wait); +} + /** * register_tracer - register a tracer with the ftrace system. * @type - the plugin for the tracer @@ -819,10 +868,13 @@ int register_tracer(struct tracer *type) current_trace = type; - /* If we expanded the buffers, make sure the max is expanded too */ - if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, trace_buf_size, - RING_BUFFER_ALL_CPUS); + if (type->use_max_tr) { + /* If we expanded the buffers, make sure the max is expanded too */ + if (ring_buffer_expanded) + ring_buffer_resize(max_tr.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); + type->allocated_snapshot = true; + } /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); @@ -838,10 +890,14 @@ int register_tracer(struct tracer *type) /* Only reset on passing, to avoid touching corrupted buffers */ tracing_reset_online_cpus(tr); - /* Shrink the max buffer again */ - if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, 1, - RING_BUFFER_ALL_CPUS); + if (type->use_max_tr) { + type->allocated_snapshot = false; + + /* Shrink the max buffer again */ + if (ring_buffer_expanded) + ring_buffer_resize(max_tr.buffer, 1, + RING_BUFFER_ALL_CPUS); + } printk(KERN_CONT "PASSED\n"); } @@ -875,36 +931,13 @@ int register_tracer(struct tracer *type) return ret; } -void unregister_tracer(struct tracer *type) -{ - struct tracer **t; - - mutex_lock(&trace_types_lock); - for (t = &trace_types; *t; t = &(*t)->next) { - if (*t == type) - goto found; - } - pr_info("Tracer %s not registered\n", type->name); - goto out; - - found: - *t = (*t)->next; - - if (type == current_trace && tracer_enabled) { - tracer_enabled = 0; - tracing_stop(); - if (current_trace->stop) - current_trace->stop(&global_trace); - current_trace = &nop_trace; - } -out: - mutex_unlock(&trace_types_lock); -} - void tracing_reset(struct trace_array *tr, int cpu) { struct ring_buffer *buffer = tr->buffer; + if (!buffer) + return; + ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ @@ -919,6 +952,9 @@ void tracing_reset_online_cpus(struct trace_array *tr) struct ring_buffer *buffer = tr->buffer; int cpu; + if (!buffer) + return; + ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ @@ -1131,10 +1167,14 @@ void trace_find_cmdline(int pid, char comm[]) void tracing_record_cmdline(struct task_struct *tsk) { - if (atomic_read(&trace_record_cmdline_disabled) || !tracer_enabled || - !tracing_is_on()) + if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) return; + if (!__this_cpu_read(trace_cmdline_save)) + return; + + __this_cpu_write(trace_cmdline_save, false); + trace_save_cmdline(tsk); } @@ -1146,7 +1186,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; - entry->padding = 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -1178,27 +1217,36 @@ trace_buffer_lock_reserve(struct ring_buffer *buffer, return event; } +void +__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) +{ + __this_cpu_write(trace_cmdline_save, true); + if (trace_wakeup_needed) { + trace_wakeup_needed = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&trace_work_wakeup); + } + ring_buffer_unlock_commit(buffer, event); +} + static inline void __trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, - unsigned long flags, int pc, - int wake) + unsigned long flags, int pc) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); ftrace_trace_userstack(buffer, flags, pc); - - if (wake) - trace_wake_up(); } void trace_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { - __trace_buffer_unlock_commit(buffer, event, flags, pc, 1); + __trace_buffer_unlock_commit(buffer, event, flags, pc); } +EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, @@ -1215,29 +1263,21 @@ void trace_current_buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { - __trace_buffer_unlock_commit(buffer, event, flags, pc, 1); + __trace_buffer_unlock_commit(buffer, event, flags, pc); } EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit); -void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc) -{ - __trace_buffer_unlock_commit(buffer, event, flags, pc, 0); -} -EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit); - -void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc, - struct pt_regs *regs) +void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc, + struct pt_regs *regs) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack_regs(buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } -EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs); +EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); void trace_current_buffer_discard_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) @@ -1269,7 +1309,7 @@ trace_function(struct trace_array *tr, entry->parent_ip = parent_ip; if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); } void @@ -1313,7 +1353,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ preempt_disable_notrace(); - use_stack = ++__get_cpu_var(ftrace_stack_reserve); + use_stack = __this_cpu_inc_return(ftrace_stack_reserve); /* * We don't need any atomic variables, just a barrier. * If an interrupt comes in, we don't care, because it would @@ -1362,12 +1402,12 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, entry->size = trace.nr_entries; if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out: /* Again, don't let gcc optimize things here */ barrier(); - __get_cpu_var(ftrace_stack_reserve)--; + __this_cpu_dec(ftrace_stack_reserve); preempt_enable_notrace(); } @@ -1458,7 +1498,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) save_stack_trace_user(&trace); if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out_drop_count: __this_cpu_dec(user_stack_count); @@ -1495,7 +1535,6 @@ static struct trace_buffer_struct *trace_percpu_nmi_buffer; static char *get_trace_buf(void) { struct trace_buffer_struct *percpu_buffer; - struct trace_buffer_struct *buffer; /* * If we have allocated per cpu buffers, then we do not @@ -1513,9 +1552,7 @@ static char *get_trace_buf(void) if (!percpu_buffer) return NULL; - buffer = per_cpu_ptr(percpu_buffer, smp_processor_id()); - - return buffer->buffer; + return this_cpu_ptr(&percpu_buffer->buffer[0]); } static int alloc_percpu_trace_buffer(void) @@ -1559,10 +1596,10 @@ static int alloc_percpu_trace_buffer(void) return -ENOMEM; } +static int buffers_allocated; + void trace_printk_init_buffers(void) { - static int buffers_allocated; - if (buffers_allocated) return; @@ -1571,7 +1608,38 @@ void trace_printk_init_buffers(void) pr_info("ftrace: Allocated trace_printk buffers\n"); + /* Expand the buffers to set size */ + tracing_update_buffers(); + buffers_allocated = 1; + + /* + * trace_printk_init_buffers() can be called by modules. + * If that happens, then we need to start cmdline recording + * directly here. If the global_trace.buffer is already + * allocated here, then this was called by module code. + */ + if (global_trace.buffer) + tracing_start_cmdline_record(); +} + +void trace_printk_start_comm(void) +{ + /* Start tracing comms if trace printk is set */ + if (!buffers_allocated) + return; + tracing_start_cmdline_record(); +} + +static void trace_printk_start_stop_comm(int enabled) +{ + if (!buffers_allocated) + return; + + if (enabled) + tracing_start_cmdline_record(); + else + tracing_stop_cmdline_record(); } /** @@ -1622,7 +1690,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) memcpy(entry->buf, tbuffer, sizeof(u32) * len); if (!filter_check_discard(call, entry, buffer, event)) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } @@ -1693,7 +1761,7 @@ int trace_array_vprintk(struct trace_array *tr, memcpy(&entry->buf, tbuffer, len); entry->buf[len] = '\0'; if (!filter_check_discard(call, entry, buffer, event)) { - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } out: @@ -1889,21 +1957,27 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; - static struct tracer *old_tracer; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; int cpu; - /* copy the tracer to avoid using a global lock all around */ + /* + * copy the tracer to avoid using a global lock all around. + * iter->trace is a copy of current_trace, the pointer to the + * name may be used instead of a strcmp(), as iter->trace->name + * will point to the same string as current_trace->name. + */ mutex_lock(&trace_types_lock); - if (unlikely(old_tracer != current_trace && current_trace)) { - old_tracer = current_trace; + if (unlikely(current_trace && iter->trace->name != current_trace->name)) *iter->trace = *current_trace; - } mutex_unlock(&trace_types_lock); - atomic_inc(&trace_record_cmdline_disabled); + if (iter->snapshot && iter->trace->use_max_tr) + return ERR_PTR(-EBUSY); + + if (!iter->snapshot) + atomic_inc(&trace_record_cmdline_disabled); if (*pos != iter->pos) { iter->ent = NULL; @@ -1942,7 +2016,11 @@ static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; - atomic_dec(&trace_record_cmdline_disabled); + if (iter->snapshot && iter->trace->use_max_tr) + return; + + if (!iter->snapshot) + atomic_dec(&trace_record_cmdline_disabled); trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } @@ -2027,8 +2105,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) unsigned long total; const char *name = "preemption"; - if (type) - name = type->name; + name = type->name; get_total_entries(tr, &total, &entries); @@ -2327,6 +2404,27 @@ static void test_ftrace_alive(struct seq_file *m) seq_printf(m, "# MAY BE MISSING FUNCTION EVENTS\n"); } +#ifdef CONFIG_TRACER_MAX_TRACE +static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) +{ + if (iter->trace->allocated_snapshot) + seq_printf(m, "#\n# * Snapshot is allocated *\n#\n"); + else + seq_printf(m, "#\n# * Snapshot is freed *\n#\n"); + + seq_printf(m, "# Snapshot commands:\n"); + seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n"); + seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); + seq_printf(m, "# Takes a snapshot of the main buffer.\n"); + seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n"); + seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); + seq_printf(m, "# is not a '0' or '1')\n"); +} +#else +/* Should never be called */ +static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { } +#endif + static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; @@ -2338,7 +2436,9 @@ static int s_show(struct seq_file *m, void *v) seq_puts(m, "#\n"); test_ftrace_alive(m); } - if (iter->trace && iter->trace->print_header) + if (iter->snapshot && trace_empty(iter)) + print_snapshot_help(m, iter); + else if (iter->trace && iter->trace->print_header) iter->trace->print_header(m); else trace_default_header(m); @@ -2377,7 +2477,7 @@ static const struct seq_operations tracer_seq_ops = { }; static struct trace_iterator * -__tracing_open(struct inode *inode, struct file *file) +__tracing_open(struct inode *inode, struct file *file, bool snapshot) { long cpu_file = (long) inode->i_private; struct trace_iterator *iter; @@ -2404,16 +2504,16 @@ __tracing_open(struct inode *inode, struct file *file) if (!iter->trace) goto fail; - if (current_trace) - *iter->trace = *current_trace; + *iter->trace = *current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; - if (current_trace && current_trace->print_max) + if (current_trace->print_max || snapshot) iter->tr = &max_tr; else iter->tr = &global_trace; + iter->snapshot = snapshot; iter->pos = -1; mutex_init(&iter->mutex); iter->cpu_file = cpu_file; @@ -2426,8 +2526,13 @@ __tracing_open(struct inode *inode, struct file *file) if (ring_buffer_overruns(iter->tr->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; - /* stop the trace while dumping */ - tracing_stop(); + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[trace_clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + + /* stop the trace while dumping if we are not opening "snapshot" */ + if (!iter->snapshot) + tracing_stop(); if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) { @@ -2490,8 +2595,9 @@ static int tracing_release(struct inode *inode, struct file *file) if (iter->trace && iter->trace->close) iter->trace->close(iter); - /* reenable tracing if it was previously enabled */ - tracing_start(); + if (!iter->snapshot) + /* reenable tracing if it was previously enabled */ + tracing_start(); mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); @@ -2519,7 +2625,7 @@ static int tracing_open(struct inode *inode, struct file *file) } if (file->f_mode & FMODE_READ) { - iter = __tracing_open(inode, file); + iter = __tracing_open(inode, file, false); if (IS_ERR(iter)) ret = PTR_ERR(iter); else if (trace_flags & TRACE_ITER_LATENCY_FMT) @@ -2778,11 +2884,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) return -EINVAL; } -static void set_tracer_flags(unsigned int mask, int enabled) +/* Some tracers require overwrite to stay enabled */ +int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) +{ + if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set) + return -1; + + return 0; +} + +int set_tracer_flag(unsigned int mask, int enabled) { /* do nothing if flag is already set */ if (!!(trace_flags & mask) == !!enabled) - return; + return 0; + + /* Give the tracer a chance to approve the change */ + if (current_trace->flag_changed) + if (current_trace->flag_changed(current_trace, mask, !!enabled)) + return -EINVAL; if (enabled) trace_flags |= mask; @@ -2792,49 +2912,69 @@ static void set_tracer_flags(unsigned int mask, int enabled) if (mask == TRACE_ITER_RECORD_CMD) trace_event_enable_cmd_record(enabled); - if (mask == TRACE_ITER_OVERWRITE) + if (mask == TRACE_ITER_OVERWRITE) { ring_buffer_change_overwrite(global_trace.buffer, enabled); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_change_overwrite(max_tr.buffer, enabled); +#endif + } + + if (mask == TRACE_ITER_PRINTK) + trace_printk_start_stop_comm(enabled); + + return 0; } -static ssize_t -tracing_trace_options_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int trace_set_options(char *option) { - char buf[64]; char *cmp; int neg = 0; - int ret; + int ret = -ENODEV; int i; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); + cmp = strstrip(option); if (strncmp(cmp, "no", 2) == 0) { neg = 1; cmp += 2; } + mutex_lock(&trace_types_lock); + for (i = 0; trace_options[i]; i++) { if (strcmp(cmp, trace_options[i]) == 0) { - set_tracer_flags(1 << i, !neg); + ret = set_tracer_flag(1 << i, !neg); break; } } /* If no option could be set, test the specific tracer options */ - if (!trace_options[i]) { - mutex_lock(&trace_types_lock); + if (!trace_options[i]) ret = set_tracer_option(current_trace, cmp, neg); - mutex_unlock(&trace_types_lock); - if (ret) - return ret; - } + + mutex_unlock(&trace_types_lock); + + return ret; +} + +static ssize_t +tracing_trace_options_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = trace_set_options(buf); + if (ret < 0) + return ret; *ppos += cnt; @@ -2940,56 +3080,6 @@ static const struct file_operations tracing_saved_cmdlines_fops = { }; static ssize_t -tracing_ctrl_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - int r; - - r = sprintf(buf, "%u\n", tracer_enabled); - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static ssize_t -tracing_ctrl_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - struct trace_array *tr = filp->private_data; - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - val = !!val; - - mutex_lock(&trace_types_lock); - if (tracer_enabled ^ val) { - - /* Only need to warn if this is used to change the state */ - WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on"); - - if (val) { - tracer_enabled = 1; - if (current_trace->start) - current_trace->start(tr); - tracing_start(); - } else { - tracer_enabled = 0; - tracing_stop(); - if (current_trace->stop) - current_trace->stop(tr); - } - } - mutex_unlock(&trace_types_lock); - - *ppos += cnt; - - return cnt; -} - -static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -2997,10 +3087,7 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, int r; mutex_lock(&trace_types_lock); - if (current_trace) - r = sprintf(buf, "%s\n", current_trace->name); - else - r = sprintf(buf, "\n"); + r = sprintf(buf, "%s\n", current_trace->name); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -3019,6 +3106,31 @@ static void set_buffer_entries(struct trace_array *tr, unsigned long val) tr->data[cpu]->entries = val; } +/* resize @tr's buffer to the size of @size_tr's entries */ +static int resize_buffer_duplicate_size(struct trace_array *tr, + struct trace_array *size_tr, int cpu_id) +{ + int cpu, ret = 0; + + if (cpu_id == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(tr->buffer, + size_tr->data[cpu]->entries, cpu); + if (ret < 0) + break; + tr->data[cpu]->entries = size_tr->data[cpu]->entries; + } + } else { + ret = ring_buffer_resize(tr->buffer, + size_tr->data[cpu_id]->entries, cpu_id); + if (ret == 0) + tr->data[cpu_id]->entries = + size_tr->data[cpu_id]->entries; + } + + return ret; +} + static int __tracing_resize_ring_buffer(unsigned long size, int cpu) { int ret; @@ -3030,6 +3142,10 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) */ ring_buffer_expanded = 1; + /* May be called before buffers are initialized */ + if (!global_trace.buffer) + return 0; + ret = ring_buffer_resize(global_trace.buffer, size, cpu); if (ret < 0) return ret; @@ -3039,23 +3155,8 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) ret = ring_buffer_resize(max_tr.buffer, size, cpu); if (ret < 0) { - int r = 0; - - if (cpu == RING_BUFFER_ALL_CPUS) { - int i; - for_each_tracing_cpu(i) { - r = ring_buffer_resize(global_trace.buffer, - global_trace.data[i]->entries, - i); - if (r < 0) - break; - } - } else { - r = ring_buffer_resize(global_trace.buffer, - global_trace.data[cpu]->entries, - cpu); - } - + int r = resize_buffer_duplicate_size(&global_trace, + &global_trace, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -3152,6 +3253,7 @@ static int tracing_set_tracer(const char *buf) static struct trace_option_dentry *topts; struct trace_array *tr = &global_trace; struct tracer *t; + bool had_max_tr; int ret = 0; mutex_lock(&trace_types_lock); @@ -3176,9 +3278,24 @@ static int tracing_set_tracer(const char *buf) goto out; trace_branch_disable(); - if (current_trace && current_trace->reset) + + current_trace->enabled = false; + + if (current_trace->reset) current_trace->reset(tr); - if (current_trace && current_trace->use_max_tr) { + + had_max_tr = current_trace->allocated_snapshot; + current_trace = &nop_trace; + + if (had_max_tr && !t->use_max_tr) { + /* + * We need to make sure that the update_max_tr sees that + * current_trace changed to nop_trace to keep it from + * swapping the buffers after we resize it. + * The update_max_tr is called from interrupts disabled + * so a synchronized_sched() is sufficient. + */ + synchronize_sched(); /* * We don't free the ring buffer. instead, resize it because * The max_tr ring buffer has some state (e.g. ring->clock) and @@ -3186,24 +3303,19 @@ static int tracing_set_tracer(const char *buf) */ ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&max_tr, 1); + tracing_reset_online_cpus(&max_tr); + current_trace->allocated_snapshot = false; } destroy_trace_option_files(topts); - current_trace = &nop_trace; - topts = create_trace_option_files(t); - if (t->use_max_tr) { - int cpu; + if (t->use_max_tr && !had_max_tr) { /* we need to make per cpu buffer sizes equivalent */ - for_each_tracing_cpu(cpu) { - ret = ring_buffer_resize(max_tr.buffer, - global_trace.data[cpu]->entries, - cpu); - if (ret < 0) - goto out; - max_tr.data[cpu]->entries = - global_trace.data[cpu]->entries; - } + ret = resize_buffer_duplicate_size(&max_tr, &global_trace, + RING_BUFFER_ALL_CPUS); + if (ret < 0) + goto out; + t->allocated_snapshot = true; } if (t->init) { @@ -3213,6 +3325,7 @@ static int tracing_set_tracer(const char *buf) } current_trace = t; + current_trace->enabled = true; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3311,8 +3424,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) ret = -ENOMEM; goto fail; } - if (current_trace) - *iter->trace = *current_trace; + *iter->trace = *current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; @@ -3325,6 +3437,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[trace_clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; + iter->cpu_file = cpu_file; iter->tr = &global_trace; mutex_init(&iter->mutex); @@ -3385,19 +3501,6 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } } - -void default_wait_pipe(struct trace_iterator *iter) -{ - DEFINE_WAIT(wait); - - prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); - - if (trace_empty(iter)) - schedule(); - - finish_wait(&trace_wait, &wait); -} - /* * This is a make-shift waitqueue. * A tracer might use this callback on some rare cases: @@ -3446,7 +3549,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracer_enabled && iter->pos) + if (!tracing_is_enabled() && iter->pos) break; } @@ -3461,7 +3564,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; - static struct tracer *old_tracer; ssize_t sret; /* return any leftover data */ @@ -3473,10 +3575,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(old_tracer != current_trace && current_trace)) { - old_tracer = current_trace; + if (unlikely(iter->trace->name != current_trace->name)) *iter->trace = *current_trace; - } mutex_unlock(&trace_types_lock); /* @@ -3632,7 +3732,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; - static struct tracer *old_tracer; ssize_t ret; size_t rem; unsigned int i; @@ -3642,10 +3741,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(old_tracer != current_trace && current_trace)) { - old_tracer = current_trace; + if (unlikely(iter->trace->name != current_trace->name)) *iter->trace = *current_trace; - } mutex_unlock(&trace_types_lock); mutex_lock(&iter->mutex); @@ -3955,7 +4052,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, } else entry->buf[cnt] = '\0'; - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); written = cnt; @@ -4016,6 +4113,13 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, if (max_tr.buffer) ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func); + /* + * 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); + tracing_reset_online_cpus(&max_tr); + mutex_unlock(&trace_types_lock); *fpos += cnt; @@ -4030,6 +4134,85 @@ static int tracing_clock_open(struct inode *inode, struct file *file) return single_open(file, tracing_clock_show, NULL); } +#ifdef CONFIG_TRACER_SNAPSHOT +static int tracing_snapshot_open(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter; + int ret = 0; + + if (file->f_mode & FMODE_READ) { + iter = __tracing_open(inode, file, true); + if (IS_ERR(iter)) + ret = PTR_ERR(iter); + } + return ret; +} + +static ssize_t +tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + mutex_lock(&trace_types_lock); + + if (current_trace->use_max_tr) { + ret = -EBUSY; + goto out; + } + + switch (val) { + case 0: + if (current_trace->allocated_snapshot) { + /* free spare buffer */ + ring_buffer_resize(max_tr.buffer, 1, + RING_BUFFER_ALL_CPUS); + set_buffer_entries(&max_tr, 1); + tracing_reset_online_cpus(&max_tr); + current_trace->allocated_snapshot = false; + } + break; + case 1: + if (!current_trace->allocated_snapshot) { + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&max_tr, + &global_trace, RING_BUFFER_ALL_CPUS); + if (ret < 0) + break; + current_trace->allocated_snapshot = true; + } + + local_irq_disable(); + /* Now, we're going to swap */ + update_max_tr(&global_trace, current, smp_processor_id()); + local_irq_enable(); + break; + default: + if (current_trace->allocated_snapshot) + tracing_reset_online_cpus(&max_tr); + break; + } + + if (ret >= 0) { + *ppos += cnt; + ret = cnt; + } +out: + mutex_unlock(&trace_types_lock); + return ret; +} +#endif /* CONFIG_TRACER_SNAPSHOT */ + + static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, @@ -4037,13 +4220,6 @@ static const struct file_operations tracing_max_lat_fops = { .llseek = generic_file_llseek, }; -static const struct file_operations tracing_ctrl_fops = { - .open = tracing_open_generic, - .read = tracing_ctrl_read, - .write = tracing_ctrl_write, - .llseek = generic_file_llseek, -}; - static const struct file_operations set_tracer_fops = { .open = tracing_open_generic, .read = tracing_set_trace_read, @@ -4093,6 +4269,16 @@ static const struct file_operations trace_clock_fops = { .write = tracing_clock_write, }; +#ifdef CONFIG_TRACER_SNAPSHOT +static const struct file_operations snapshot_fops = { + .open = tracing_snapshot_open, + .read = seq_read, + .write = tracing_snapshot_write, + .llseek = tracing_seek, + .release = tracing_release, +}; +#endif /* CONFIG_TRACER_SNAPSHOT */ + struct ftrace_buffer_info { struct trace_array *tr; void *spare; @@ -4260,13 +4446,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -ENOMEM; if (*ppos & (PAGE_SIZE - 1)) { - WARN_ONCE(1, "Ftrace: previous read must page-align\n"); ret = -EINVAL; goto out; } if (len & (PAGE_SIZE - 1)) { - WARN_ONCE(1, "Ftrace: splice_read should page-align\n"); if (len < PAGE_SIZE) { ret = -EINVAL; goto out; @@ -4377,13 +4561,30 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_bytes_cpu(tr->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); - t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); - usec_rem = do_div(t, USEC_PER_SEC); - trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); + if (trace_clocks[trace_clock_id].in_ns) { + /* local or global for trace_clock */ + t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", + t, usec_rem); + + t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); + } else { + /* counter or tsc mode for trace_clock */ + trace_seq_printf(s, "oldest event ts: %llu\n", + ring_buffer_oldest_event_ts(tr->buffer, cpu)); + + trace_seq_printf(s, "now ts: %llu\n", + ring_buffer_time_stamp(tr->buffer, cpu)); + } - t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); - usec_rem = do_div(t, USEC_PER_SEC); - trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); + cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu); + trace_seq_printf(s, "dropped events: %ld\n", cnt); + + cnt = ring_buffer_read_events_cpu(tr->buffer, cpu); + trace_seq_printf(s, "read events: %ld\n", cnt); count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); @@ -4461,7 +4662,7 @@ struct dentry *tracing_init_dentry(void) static struct dentry *d_percpu; -struct dentry *tracing_dentry_percpu(void) +static struct dentry *tracing_dentry_percpu(void) { static int once; struct dentry *d_tracer; @@ -4611,7 +4812,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; - set_tracer_flags(1 << index, val); + + mutex_lock(&trace_types_lock); + ret = set_tracer_flag(1 << index, val); + mutex_unlock(&trace_types_lock); + + if (ret < 0) + return ret; *ppos += cnt; @@ -4788,10 +4995,17 @@ rb_simple_write(struct file *filp, const char __user *ubuf, return ret; if (buffer) { - if (val) + mutex_lock(&trace_types_lock); + if (val) { ring_buffer_record_on(buffer); - else + if (current_trace->start) + current_trace->start(tr); + } else { ring_buffer_record_off(buffer); + if (current_trace->stop) + current_trace->stop(tr); + } + mutex_unlock(&trace_types_lock); } (*ppos)++; @@ -4815,9 +5029,6 @@ static __init int tracer_init_debugfs(void) d_tracer = tracing_init_dentry(); - trace_create_file("tracing_enabled", 0644, d_tracer, - &global_trace, &tracing_ctrl_fops); - trace_create_file("trace_options", 0644, d_tracer, NULL, &tracing_iter_fops); @@ -4873,6 +5084,11 @@ static __init int tracer_init_debugfs(void) &ftrace_update_tot_cnt, &tracing_dyn_info_fops); #endif +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_tracer, + (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops); +#endif + create_trace_options_dir(); for_each_tracing_cpu(cpu) @@ -4981,6 +5197,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (disable_tracing) ftrace_kill(); + /* Simulate the iterator */ trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { @@ -4992,10 +5209,6 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) /* don't look at user memory in panic mode */ trace_flags &= ~TRACE_ITER_SYM_USEROBJ; - /* Simulate the iterator */ - iter.tr = &global_trace; - iter.trace = current_trace; - switch (oops_dump_mode) { case DUMP_ALL: iter.cpu_file = TRACE_PIPE_ALL_CPU; @@ -5089,6 +5302,7 @@ __init static int tracer_alloc_buffers(void) /* Only allocate trace_printk buffers if a trace_printk exists */ if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); /* To save memory, keep the ring buffer size to its minimum */ @@ -5136,9 +5350,10 @@ __init static int tracer_alloc_buffers(void) #endif trace_init_cmdlines(); + init_irq_work(&trace_work_wakeup, trace_wake_up); register_tracer(&nop_trace); - current_trace = &nop_trace; + /* All seems OK, enable tracing */ tracing_disabled = 0; @@ -5147,6 +5362,13 @@ __init static int tracer_alloc_buffers(void) register_die_notifier(&trace_die_notifier); + while (trace_boot_options) { + char *option; + + option = strsep(&trace_boot_options, ","); + trace_set_options(option); + } + return 0; out_free_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c15f528c1af4..2081971367ea 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -283,24 +283,70 @@ struct tracer { enum print_line_t (*print_line)(struct trace_iterator *iter); /* If you handled the flag setting, return 0 */ int (*set_flag)(u32 old_flags, u32 bit, int set); + /* Return 0 if OK with change, else return non-zero */ + int (*flag_changed)(struct tracer *tracer, + u32 mask, int set); struct tracer *next; struct tracer_flags *flags; - int print_max; - int use_max_tr; + bool print_max; + bool use_max_tr; + bool allocated_snapshot; + bool enabled; }; /* Only current can touch trace_recursion */ -#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0) -#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0) -/* Ring buffer has the 10 LSB bits to count */ -#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff) - -/* for function tracing recursion */ -#define TRACE_INTERNAL_BIT (1<<11) -#define TRACE_GLOBAL_BIT (1<<12) -#define TRACE_CONTROL_BIT (1<<13) +/* + * For function tracing recursion: + * The order of these bits are important. + * + * When function tracing occurs, the following steps are made: + * If arch does not support a ftrace feature: + * call internal function (uses INTERNAL bits) which calls... + * If callback is registered to the "global" list, the list + * function is called and recursion checks the GLOBAL bits. + * then this function calls... + * The function callback, which can use the FTRACE bits to + * check for recursion. + * + * Now if the arch does not suppport a feature, and it calls + * the global list function which calls the ftrace callback + * all three of these steps will do a recursion protection. + * There's no reason to do one if the previous caller already + * did. The recursion that we are protecting against will + * go through the same steps again. + * + * To prevent the multiple recursion checks, if a recursion + * bit is set that is higher than the MAX bit of the current + * check, then we know that the check was made by the previous + * caller, and we can skip the current check. + */ +enum { + TRACE_BUFFER_BIT, + TRACE_BUFFER_NMI_BIT, + TRACE_BUFFER_IRQ_BIT, + TRACE_BUFFER_SIRQ_BIT, + + /* Start of function recursion bits */ + TRACE_FTRACE_BIT, + TRACE_FTRACE_NMI_BIT, + TRACE_FTRACE_IRQ_BIT, + TRACE_FTRACE_SIRQ_BIT, + + /* GLOBAL_BITs must be greater than FTRACE_BITs */ + TRACE_GLOBAL_BIT, + TRACE_GLOBAL_NMI_BIT, + TRACE_GLOBAL_IRQ_BIT, + TRACE_GLOBAL_SIRQ_BIT, + + /* INTERNAL_BITs must be greater than GLOBAL_BITs */ + TRACE_INTERNAL_BIT, + TRACE_INTERNAL_NMI_BIT, + TRACE_INTERNAL_IRQ_BIT, + TRACE_INTERNAL_SIRQ_BIT, + + TRACE_CONTROL_BIT, /* * Abuse of the trace_recursion. @@ -309,11 +355,77 @@ struct tracer { * was called in irq context but we have irq tracing off. Since this * can only be modified by current, we can reuse trace_recursion. */ -#define TRACE_IRQ_BIT (1<<13) + TRACE_IRQ_BIT, +}; + +#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) +#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) +#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) -#define trace_recursion_set(bit) do { (current)->trace_recursion |= (bit); } while (0) -#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(bit); } while (0) -#define trace_recursion_test(bit) ((current)->trace_recursion & (bit)) +#define TRACE_CONTEXT_BITS 4 + +#define TRACE_FTRACE_START TRACE_FTRACE_BIT +#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_GLOBAL_START TRACE_GLOBAL_BIT +#define TRACE_GLOBAL_MAX ((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_CONTEXT_MASK TRACE_LIST_MAX + +static __always_inline int trace_get_context_bit(void) +{ + int bit; + + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; + + return bit; +} + +static __always_inline int trace_test_and_set_recursion(int start, int max) +{ + unsigned int val = current->trace_recursion; + int bit; + + /* A previous recursion check was made */ + if ((val & TRACE_CONTEXT_MASK) > max) + return 0; + + bit = trace_get_context_bit() + start; + if (unlikely(val & (1 << bit))) + return -1; + + val |= 1 << bit; + current->trace_recursion = val; + barrier(); + + return bit; +} + +static __always_inline void trace_clear_recursion(int bit) +{ + unsigned int val = current->trace_recursion; + + if (!bit) + return; + + bit = 1 << bit; + val &= ~bit; + + barrier(); + current->trace_recursion = val; +} #define TRACE_PIPE_ALL_CPU -1 @@ -327,7 +439,6 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu) int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); -void trace_wake_up(void); void tracing_reset(struct trace_array *tr, int cpu); void tracing_reset_online_cpus(struct trace_array *tr); void tracing_reset_current(int cpu); @@ -349,9 +460,6 @@ trace_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long len, unsigned long flags, int pc); -void trace_buffer_unlock_commit(struct ring_buffer *buffer, - struct ring_buffer_event *event, - unsigned long flags, int pc); struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data); @@ -359,6 +467,9 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); +void __buffer_unlock_commit(struct ring_buffer *buffer, + struct ring_buffer_event *event); + int trace_empty(struct trace_iterator *iter); void *trace_find_next_entry_inc(struct trace_iterator *iter); @@ -367,7 +478,6 @@ void trace_init_global_iter(struct trace_iterator *iter); void tracing_iter_reset(struct trace_iterator *iter, int cpu); -void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); void ftrace(struct trace_array *tr, @@ -407,12 +517,7 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr); void tracing_stop_sched_switch_record(void); void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); -void unregister_tracer(struct tracer *type); int is_tracing_stopped(void); -enum trace_file_type { - TRACE_FILE_LAT_FMT = 1, - TRACE_FILE_ANNOTATE = 2, -}; extern cpumask_var_t __read_mostly tracing_buffer_mask; @@ -841,6 +946,9 @@ extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; void trace_printk_init_buffers(void); +void trace_printk_start_comm(void); +int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); +int set_tracer_flag(unsigned int mask, int enabled); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 8d3538b4ea5f..95e96842ed29 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -77,7 +77,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) entry->correct = val == expect; if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); out: atomic_dec(&tr->data[cpu]->disabled); @@ -199,7 +199,7 @@ __init static int init_branch_tracer(void) } return register_tracer(&branch_trace); } -device_initcall(init_branch_tracer); +core_initcall(init_branch_tracer); #else static inline diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 394783531cbb..aa8f5f48dae6 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -21,8 +21,6 @@ #include <linux/ktime.h> #include <linux/trace_clock.h> -#include "trace.h" - /* * trace_clock_local(): the simplest and least coherent tracing clock. * @@ -44,6 +42,7 @@ u64 notrace trace_clock_local(void) return clock; } +EXPORT_SYMBOL_GPL(trace_clock_local); /* * trace_clock(): 'between' trace clock. Not completely serialized, @@ -86,7 +85,7 @@ u64 notrace trace_clock_global(void) local_irq_save(flags); this_cpu = raw_smp_processor_id(); - now = cpu_clock(this_cpu); + now = sched_clock_cpu(this_cpu); /* * If in an NMI context then dont risk lockups and return the * cpu_clock() time: diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index d608d09d08c0..57e9b284250c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,7 +116,6 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); - __common_field(int, padding); return ret; } @@ -491,19 +490,6 @@ static void t_stop(struct seq_file *m, void *p) mutex_unlock(&event_mutex); } -static int -ftrace_event_seq_open(struct inode *inode, struct file *file) -{ - const struct seq_operations *seq_ops; - - if ((file->f_mode & FMODE_WRITE) && - (file->f_flags & O_TRUNC)) - ftrace_clear_events(); - - seq_ops = inode->i_private; - return seq_open(file, seq_ops); -} - static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -980,6 +966,9 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return r; } +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 const struct seq_operations show_event_seq_ops = { .start = t_start, .next = t_next, @@ -995,14 +984,14 @@ static const struct seq_operations show_set_event_seq_ops = { }; static const struct file_operations ftrace_avail_fops = { - .open = ftrace_event_seq_open, + .open = ftrace_event_avail_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations ftrace_set_event_fops = { - .open = ftrace_event_seq_open, + .open = ftrace_event_set_open, .read = seq_read, .write = ftrace_event_write, .llseek = seq_lseek, @@ -1078,6 +1067,26 @@ static struct dentry *event_trace_events_dir(void) return d_events; } +static int +ftrace_event_avail_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_event_seq_ops; + + return seq_open(file, seq_ops); +} + +static int +ftrace_event_set_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_set_event_seq_ops; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_clear_events(); + + return seq_open(file, seq_ops); +} + static struct dentry * event_subsystem_dir(const char *name, struct dentry *d_events) { @@ -1489,6 +1498,9 @@ static __init int event_trace_enable(void) if (ret) pr_warn("Failed to enable trace event: %s\n", token); } + + trace_printk_start_comm(); + return 0; } @@ -1505,15 +1517,13 @@ static __init int event_trace_init(void) return 0; entry = debugfs_create_file("available_events", 0444, d_tracer, - (void *)&show_event_seq_ops, - &ftrace_avail_fops); + NULL, &ftrace_avail_fops); if (!entry) pr_warning("Could not create debugfs " "'available_events' entry\n"); entry = debugfs_create_file("set_event", 0644, d_tracer, - (void *)&show_set_event_seq_ops, - &ftrace_set_event_fops); + NULL, &ftrace_set_event_fops); if (!entry) pr_warning("Could not create debugfs " "'set_event' entry\n"); @@ -1749,7 +1759,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, entry->ip = ip; entry->parent_ip = parent_ip; - trace_nowake_buffer_unlock_commit(buffer, event, flags, pc); + trace_buffer_unlock_commit(buffer, event, flags, pc); out: atomic_dec(&per_cpu(ftrace_test_event_disable, cpu)); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c154797a7ff7..e5b0ca8b8d4d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1000,9 +1000,9 @@ static int init_pred(struct filter_parse_state *ps, } } else { if (field->is_signed) - ret = strict_strtoll(pred->regex.pattern, 0, &val); + ret = kstrtoll(pred->regex.pattern, 0, &val); else - ret = strict_strtoull(pred->regex.pattern, 0, &val); + ret = kstrtoull(pred->regex.pattern, 0, &val); if (ret) { parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0); return -EINVAL; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 507a7a9630bf..601152523326 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -7,7 +7,7 @@ * Based on code from the latency_tracer, that is: * * Copyright (C) 2004-2006 Ingo Molnar - * Copyright (C) 2004 William Lee Irwin III + * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/ring_buffer.h> #include <linux/debugfs.h> @@ -47,34 +47,6 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(tr); } -static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) -{ - struct trace_array *tr = func_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu; - int pc; - - if (unlikely(!ftrace_function_enabled)) - return; - - pc = preempt_count(); - preempt_disable_notrace(); - local_save_flags(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - - if (likely(disabled == 1)) - trace_function(tr, ip, parent_ip, flags, pc); - - atomic_dec(&data->disabled); - preempt_enable_notrace(); -} - /* Our option */ enum { TRACE_FUNC_OPT_STACK = 0x1, @@ -85,34 +57,34 @@ static struct tracer_flags func_flags; static void function_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) - { struct trace_array *tr = func_trace; struct trace_array_cpu *data; unsigned long flags; - long disabled; + int bit; int cpu; int pc; if (unlikely(!ftrace_function_enabled)) return; - /* - * Need to use raw, since this must be called before the - * recursive protection is performed. - */ - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); + pc = preempt_count(); + preempt_disable_notrace(); - if (likely(disabled == 1)) { - pc = preempt_count(); + bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); + if (bit < 0) + goto out; + + cpu = smp_processor_id(); + data = tr->data[cpu]; + if (!atomic_read(&data->disabled)) { + local_save_flags(flags); trace_function(tr, ip, parent_ip, flags, pc); } + trace_clear_recursion(bit); - atomic_dec(&data->disabled); - local_irq_restore(flags); + out: + preempt_enable_notrace(); } static void @@ -185,11 +157,6 @@ static void tracing_start_function_trace(void) { ftrace_function_enabled = 0; - if (trace_flags & TRACE_ITER_PREEMPTONLY) - trace_ops.func = function_trace_call_preempt_only; - else - trace_ops.func = function_trace_call; - if (func_flags.val & TRACE_FUNC_OPT_STACK) register_ftrace_function(&trace_stack_ops); else @@ -366,7 +333,7 @@ ftrace_trace_onoff_callback(struct ftrace_hash *hash, * We use the callback data field (which is a pointer) * as our counter. */ - ret = strict_strtoul(number, 0, (unsigned long *)&count); + ret = kstrtoul(number, 0, (unsigned long *)&count); if (ret) return ret; @@ -411,5 +378,4 @@ static __init int init_function_trace(void) init_func_cmd_traceon(); return register_tracer(&function_trace); } -device_initcall(init_function_trace); - +core_initcall(init_function_trace); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 99b4378393d5..39ada66389cc 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -47,6 +47,8 @@ struct fgraph_data { #define TRACE_GRAPH_PRINT_ABS_TIME 0x20 #define TRACE_GRAPH_PRINT_IRQS 0x40 +static unsigned int max_depth; + static struct tracer_opt trace_opts[] = { /* Display overruns? (for self-debug purpose) */ { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) }, @@ -189,10 +191,16 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); - ftrace_graph_return(&trace); barrier(); current->curr_ret_stack--; + /* + * The trace should run after decrementing the ret counter + * in case an interrupt were to come in. We don't want to + * lose the interrupt if max_depth is set. + */ + ftrace_graph_return(&trace); + if (unlikely(!ret)) { ftrace_graph_stop(); WARN_ON(1); @@ -223,7 +231,7 @@ int __trace_graph_entry(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->graph_ent = *trace; if (!filter_current_check_discard(buffer, call, entry, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); return 1; } @@ -250,8 +258,9 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return 0; /* trace it when it is-nested-in or is a function enabled. */ - if (!(trace->depth || ftrace_graph_addr(trace->func)) || - ftrace_graph_ignore_irqs()) + if ((!(trace->depth || ftrace_graph_addr(trace->func)) || + ftrace_graph_ignore_irqs()) || + (max_depth && trace->depth >= max_depth)) return 0; local_irq_save(flags); @@ -327,7 +336,7 @@ void __trace_graph_return(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->ret = *trace; if (!filter_current_check_discard(buffer, call, entry, event)) - ring_buffer_unlock_commit(buffer, event); + __buffer_unlock_commit(buffer, event); } void trace_graph_return(struct ftrace_graph_ret *trace) @@ -1457,6 +1466,59 @@ static struct tracer graph_trace __read_mostly = { #endif }; + +static ssize_t +graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + max_depth = val; + + *ppos += cnt; + + return cnt; +} + +static ssize_t +graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/ + int n; + + n = sprintf(buf, "%d\n", max_depth); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static const struct file_operations graph_depth_fops = { + .open = tracing_open_generic, + .write = graph_depth_write, + .read = graph_depth_read, + .llseek = generic_file_llseek, +}; + +static __init int init_graph_debugfs(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + trace_create_file("max_graph_depth", 0644, d_tracer, + NULL, &graph_depth_fops); + + return 0; +} +fs_initcall(init_graph_debugfs); + static __init int init_graph_trace(void) { max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); @@ -1474,4 +1536,4 @@ static __init int init_graph_trace(void) return register_tracer(&graph_trace); } -device_initcall(init_graph_trace); +core_initcall(init_graph_trace); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index d98ee8283b29..443b25b43b4f 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -7,7 +7,7 @@ * From code in the latency_tracer, that is: * * Copyright (C) 2004-2006 Ingo Molnar - * Copyright (C) 2004 William Lee Irwin III + * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/kallsyms.h> #include <linux/debugfs.h> @@ -32,7 +32,7 @@ enum { static int trace_type __read_mostly; -static int save_lat_flag; +static int save_flags; static void stop_irqsoff_tracer(struct trace_array *tr, int graph); static int start_irqsoff_tracer(struct trace_array *tr, int graph); @@ -558,8 +558,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph) static void __irqsoff_tracer_init(struct trace_array *tr) { - save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT; - trace_flags |= TRACE_ITER_LATENCY_FMT; + save_flags = trace_flags; + + /* non overwrite screws up the latency tracers */ + set_tracer_flag(TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; irqsoff_trace = tr; @@ -573,10 +576,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr) static void irqsoff_tracer_reset(struct trace_array *tr) { + int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; + int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + stop_irqsoff_tracer(tr, is_graph()); - if (!save_lat_flag) - trace_flags &= ~TRACE_ITER_LATENCY_FMT; + set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); } static void irqsoff_tracer_start(struct trace_array *tr) @@ -604,17 +610,18 @@ static struct tracer irqsoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = irqsoff_print_header, .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_irqsoff, #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; # define register_irqsoff(trace) register_tracer(&trace) #else @@ -637,17 +644,18 @@ static struct tracer preemptoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = irqsoff_print_header, .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptoff, #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; # define register_preemptoff(trace) register_tracer(&trace) #else @@ -672,17 +680,18 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .reset = irqsoff_tracer_reset, .start = irqsoff_tracer_start, .stop = irqsoff_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = irqsoff_print_header, .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptirqsoff, #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; # define register_preemptirqsoff(trace) register_tracer(&trace) @@ -698,4 +707,4 @@ __init static int init_irqsoff_tracer(void) return 0; } -device_initcall(init_irqsoff_tracer); +core_initcall(init_irqsoff_tracer); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1a2117043bb1..1865d5f76538 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -444,7 +444,7 @@ static int create_trace_probe(int argc, char **argv) return -EINVAL; } /* an address specified */ - ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr); + ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr); if (ret) { pr_info("Failed to parse address.\n"); return ret; @@ -751,8 +751,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_nowake_buffer_unlock_commit_regs(buffer, event, - irq_flags, pc, regs); + trace_buffer_unlock_commit_regs(buffer, event, + irq_flags, pc, regs); } /* Kretprobe handler */ @@ -784,8 +784,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_nowake_buffer_unlock_commit_regs(buffer, event, - irq_flags, pc, regs); + trace_buffer_unlock_commit_regs(buffer, event, + irq_flags, pc, regs); } /* Event entry printers */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 123b189c732c..697e88d13907 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -610,24 +610,54 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) return trace_print_lat_fmt(s, entry); } -static unsigned long preempt_mark_thresh = 100; +static unsigned long preempt_mark_thresh_us = 100; static int -lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, - unsigned long rel_usecs) +lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) { - return trace_seq_printf(s, " %4lldus%c: ", abs_usecs, - rel_usecs > preempt_mark_thresh ? '!' : - rel_usecs > 1 ? '+' : ' '); + unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE; + unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS; + unsigned long long abs_ts = iter->ts - iter->tr->time_start; + unsigned long long rel_ts = next_ts - iter->ts; + struct trace_seq *s = &iter->seq; + + if (in_ns) { + abs_ts = ns2usecs(abs_ts); + rel_ts = ns2usecs(rel_ts); + } + + if (verbose && in_ns) { + unsigned long abs_usec = do_div(abs_ts, USEC_PER_MSEC); + unsigned long abs_msec = (unsigned long)abs_ts; + unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC); + unsigned long rel_msec = (unsigned long)rel_ts; + + return trace_seq_printf( + s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ", + ns2usecs(iter->ts), + abs_msec, abs_usec, + rel_msec, rel_usec); + } else if (verbose && !in_ns) { + return trace_seq_printf( + s, "[%016llx] %lld (+%lld): ", + iter->ts, abs_ts, rel_ts); + } else if (!verbose && in_ns) { + return trace_seq_printf( + s, " %4lldus%c: ", + abs_ts, + rel_ts > preempt_mark_thresh_us ? '!' : + rel_ts > 1 ? '+' : ' '); + } else { /* !verbose && !in_ns */ + return trace_seq_printf(s, " %4lld: ", abs_ts); + } } int trace_print_context(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry = iter->ent; - unsigned long long t = ns2usecs(iter->ts); - unsigned long usec_rem = do_div(t, USEC_PER_SEC); - unsigned long secs = (unsigned long)t; + unsigned long long t; + unsigned long secs, usec_rem; char comm[TASK_COMM_LEN]; int ret; @@ -644,8 +674,13 @@ int trace_print_context(struct trace_iterator *iter) return 0; } - return trace_seq_printf(s, " %5lu.%06lu: ", - secs, usec_rem); + if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) { + t = ns2usecs(iter->ts); + usec_rem = do_div(t, USEC_PER_SEC); + secs = (unsigned long)t; + return trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem); + } else + return trace_seq_printf(s, " %12llu: ", iter->ts); } int trace_print_lat_context(struct trace_iterator *iter) @@ -659,36 +694,29 @@ int trace_print_lat_context(struct trace_iterator *iter) *next_entry = trace_find_next_entry(iter, NULL, &next_ts); unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); - unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start); - unsigned long rel_usecs; /* Restore the original ent_size */ iter->ent_size = ent_size; if (!next_entry) next_ts = iter->ts; - rel_usecs = ns2usecs(next_ts - iter->ts); if (verbose) { char comm[TASK_COMM_LEN]; trace_find_cmdline(entry->pid, comm); - ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]" - " %ld.%03ldms (+%ld.%03ldms): ", comm, - entry->pid, iter->cpu, entry->flags, - entry->preempt_count, iter->idx, - ns2usecs(iter->ts), - abs_usecs / USEC_PER_MSEC, - abs_usecs % USEC_PER_MSEC, - rel_usecs / USEC_PER_MSEC, - rel_usecs % USEC_PER_MSEC); + ret = trace_seq_printf( + s, "%16s %5d %3d %d %08x %08lx ", + comm, entry->pid, iter->cpu, entry->flags, + entry->preempt_count, iter->idx); } else { ret = lat_print_generic(s, entry, iter->cpu); - if (ret) - ret = lat_print_timestamp(s, abs_usecs, rel_usecs); } + if (ret) + ret = lat_print_timestamp(iter, next_ts); + return ret; } @@ -711,12 +739,11 @@ static int task_state_char(unsigned long state) struct trace_event *ftrace_find_event(int type) { struct trace_event *event; - struct hlist_node *n; unsigned key; key = type & (EVENT_HASHSIZE - 1); - hlist_for_each_entry(event, n, &event_hash[key], node) { + hlist_for_each_entry(event, &event_hash[key], node) { if (event->type == type) return event; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index daa9980153af..412e959709b4 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -441,7 +441,7 @@ static const struct fetch_type *find_fetch_type(const char *type) goto fail; type++; - if (strict_strtoul(type, 0, &bs)) + if (kstrtoul(type, 0, &bs)) goto fail; switch (bs) { @@ -501,8 +501,8 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset) tmp = strchr(symbol, '+'); if (tmp) { - /* skip sign because strict_strtol doesn't accept '+' */ - ret = strict_strtoul(tmp + 1, 0, offset); + /* skip sign because kstrtoul doesn't accept '+' */ + ret = kstrtoul(tmp + 1, 0, offset); if (ret) return ret; @@ -533,7 +533,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, else ret = -EINVAL; } else if (isdigit(arg[5])) { - ret = strict_strtoul(arg + 5, 10, ¶m); + ret = kstrtoul(arg + 5, 10, ¶m); if (ret || param > PARAM_MAX_STACK) ret = -EINVAL; else { @@ -579,7 +579,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, case '@': /* memory or symbol */ if (isdigit(arg[1])) { - ret = strict_strtoul(arg + 1, 0, ¶m); + ret = kstrtoul(arg + 1, 0, ¶m); if (ret) break; @@ -597,14 +597,14 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, break; case '+': /* deref memory */ - arg++; /* Skip '+', because strict_strtol() rejects it. */ + arg++; /* Skip '+', because kstrtol() rejects it. */ case '-': tmp = strchr(arg, '('); if (!tmp) break; *tmp = '\0'; - ret = strict_strtol(arg, 0, &offset); + ret = kstrtol(arg, 0, &offset); if (ret) break; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 933708677814..5c7e09d10d74 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -66,7 +66,6 @@ #define TP_FLAG_TRACE 1 #define TP_FLAG_PROFILE 2 #define TP_FLAG_REGISTERED 4 -#define TP_FLAG_UPROBE 8 /* data_rloc: data relative location, compatible with u32 */ diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 7e62c0a18456..3374c792ccd8 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -102,9 +102,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_cpu = task_cpu(wakee); if (!filter_check_discard(call, entry, buffer, event)) - ring_buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr->buffer, flags, 6, pc); - ftrace_trace_userstack(tr->buffer, flags, pc); + trace_buffer_unlock_commit(buffer, event, flags, pc); } static void diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 02170c00c413..fde652c9a511 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -7,7 +7,7 @@ * Based on code from the latency_tracer, that is: * * Copyright (C) 2004-2006 Ingo Molnar - * Copyright (C) 2004 William Lee Irwin III + * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/module.h> #include <linux/fs.h> @@ -15,8 +15,8 @@ #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/ftrace.h> +#include <linux/sched/rt.h> #include <trace/events/sched.h> - #include "trace.h" static struct trace_array *wakeup_trace; @@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr); static int wakeup_graph_entry(struct ftrace_graph_ent *trace); static void wakeup_graph_return(struct ftrace_graph_ret *trace); -static int save_lat_flag; +static int save_flags; #define TRACE_DISPLAY_GRAPH 1 @@ -540,8 +540,11 @@ static void stop_wakeup_tracer(struct trace_array *tr) static int __wakeup_tracer_init(struct trace_array *tr) { - save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT; - trace_flags |= TRACE_ITER_LATENCY_FMT; + save_flags = trace_flags; + + /* non overwrite screws up the latency tracers */ + set_tracer_flag(TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; wakeup_trace = tr; @@ -563,12 +566,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr) static void wakeup_tracer_reset(struct trace_array *tr) { + int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; + int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + stop_wakeup_tracer(tr); /* make sure we put back any tasks we are tracing */ wakeup_reset(tr); - if (!save_lat_flag) - trace_flags &= ~TRACE_ITER_LATENCY_FMT; + set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); } static void wakeup_tracer_start(struct trace_array *tr) @@ -589,17 +595,18 @@ static struct tracer wakeup_tracer __read_mostly = .reset = wakeup_tracer_reset, .start = wakeup_tracer_start, .stop = wakeup_tracer_stop, - .print_max = 1, + .print_max = true, .print_header = wakeup_print_header, .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif .open = wakeup_trace_open, .close = wakeup_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; static struct tracer wakeup_rt_tracer __read_mostly = @@ -610,17 +617,18 @@ static struct tracer wakeup_rt_tracer __read_mostly = .start = wakeup_tracer_start, .stop = wakeup_tracer_stop, .wait_pipe = poll_wait_pipe, - .print_max = 1, + .print_max = true, .print_header = wakeup_print_header, .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif .open = wakeup_trace_open, .close = wakeup_trace_close, - .use_max_tr = 1, + .use_max_tr = true, }; __init static int init_wakeup_tracer(void) @@ -637,4 +645,4 @@ __init static int init_wakeup_tracer(void) return 0; } -device_initcall(init_wakeup_tracer); +core_initcall(init_wakeup_tracer); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 2c00a691a540..51c819c12c29 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -320,7 +320,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, int (*func)(void)) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; unsigned long count; char *func_name; int ret; @@ -331,7 +330,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, /* enable tracing, and record the filter function */ ftrace_enabled = 1; - tracer_enabled = 1; /* passed in by parameter to fool gcc from optimizing */ func(); @@ -395,7 +393,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; /* Enable tracing on all functions again */ ftrace_set_global_filter(NULL, 0, 1); @@ -418,7 +415,8 @@ static void trace_selftest_test_recursion_func(unsigned long ip, * The ftrace infrastructure should provide the recursion * protection. If not, this will crash the kernel! */ - trace_selftest_recursion_cnt++; + if (trace_selftest_recursion_cnt++ > 10) + return; DYN_FTRACE_TEST_NAME(); } @@ -452,11 +450,9 @@ static int trace_selftest_function_recursion(void) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; char *func_name; int len; int ret; - int cnt; /* The previous test PASSED */ pr_cont("PASSED\n"); @@ -465,7 +461,6 @@ trace_selftest_function_recursion(void) /* enable tracing, and record the filter function */ ftrace_enabled = 1; - tracer_enabled = 1; /* Handle PPC64 '.' name */ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); @@ -515,26 +510,16 @@ trace_selftest_function_recursion(void) unregister_ftrace_function(&test_recsafe_probe); - /* - * If arch supports all ftrace features, and no other task - * was on the list, we should be fine. - */ - if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC) - cnt = 2; /* Should have recursed */ - else - cnt = 1; - ret = -1; - if (trace_selftest_recursion_cnt != cnt) { - pr_cont("*callback not called expected %d times (%d)* ", - cnt, trace_selftest_recursion_cnt); + if (trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called expected 2 times (%d)* ", + trace_selftest_recursion_cnt); goto out; } ret = 0; out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; return ret; } @@ -569,13 +554,12 @@ static int trace_selftest_function_regs(void) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; char *func_name; int len; int ret; int supported = 0; -#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS supported = 1; #endif @@ -586,7 +570,6 @@ trace_selftest_function_regs(void) /* enable tracing, and record the filter function */ ftrace_enabled = 1; - tracer_enabled = 1; /* Handle PPC64 '.' name */ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); @@ -648,7 +631,6 @@ trace_selftest_function_regs(void) ret = 0; out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; return ret; } @@ -662,7 +644,6 @@ int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) { int save_ftrace_enabled = ftrace_enabled; - int save_tracer_enabled = tracer_enabled; unsigned long count; int ret; @@ -671,7 +652,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* start the tracing */ ftrace_enabled = 1; - tracer_enabled = 1; ret = tracer_init(trace, tr); if (ret) { @@ -708,7 +688,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ret = trace_selftest_function_regs(); out: ftrace_enabled = save_ftrace_enabled; - tracer_enabled = save_tracer_enabled; /* kill ftrace totally if we failed */ if (ret) @@ -1106,6 +1085,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); + printk("ret = %d\n", ret); if (!ret) ret = trace_test_buffer(&max_tr, &count); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0c1b165778e5..83a8b5b7bd35 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -33,7 +33,6 @@ static unsigned long max_stack_size; static arch_spinlock_t max_stack_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; -static int stack_trace_disabled __read_mostly; static DEFINE_PER_CPU(int, trace_active); static DEFINE_MUTEX(stack_sysctl_mutex); @@ -116,9 +115,6 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, { int cpu; - if (unlikely(!ftrace_enabled || stack_trace_disabled)) - return; - preempt_disable_notrace(); cpu = raw_smp_processor_id(); @@ -326,7 +322,7 @@ static const struct file_operations stack_trace_filter_fops = { .open = stack_trace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 2485a7d09b11..7a809e321058 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -1,5 +1,6 @@ #include <trace/syscall.h> #include <trace/events/syscalls.h> +#include <linux/syscalls.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> /* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */ @@ -21,9 +22,6 @@ static int syscall_enter_register(struct ftrace_event_call *event, static int syscall_exit_register(struct ftrace_event_call *event, enum trace_reg type, void *data); -static int syscall_enter_define_fields(struct ftrace_event_call *call); -static int syscall_exit_define_fields(struct ftrace_event_call *call); - static struct list_head * syscall_get_enter_fields(struct ftrace_event_call *call) { @@ -32,30 +30,6 @@ syscall_get_enter_fields(struct ftrace_event_call *call) return &entry->enter_fields; } -struct trace_event_functions enter_syscall_print_funcs = { - .trace = print_syscall_enter, -}; - -struct trace_event_functions exit_syscall_print_funcs = { - .trace = print_syscall_exit, -}; - -struct ftrace_event_class event_class_syscall_enter = { - .system = "syscalls", - .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, - .get_fields = syscall_get_enter_fields, - .raw_init = init_syscall_trace, -}; - -struct ftrace_event_class event_class_syscall_exit = { - .system = "syscalls", - .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, - .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), - .raw_init = init_syscall_trace, -}; - extern struct syscall_metadata *__start_syscalls_metadata[]; extern struct syscall_metadata *__stop_syscalls_metadata[]; @@ -74,6 +48,38 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name } #endif +#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS +/* + * Some architectures that allow for 32bit applications + * to run on a 64bit kernel, do not map the syscalls for + * the 32bit tasks the same as they do for 64bit tasks. + * + * *cough*x86*cough* + * + * In such a case, instead of reporting the wrong syscalls, + * simply ignore them. + * + * For an arch to ignore the compat syscalls it needs to + * define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as + * define the function arch_trace_is_compat_syscall() to let + * the tracing system know that it should ignore it. + */ +static int +trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs) +{ + if (unlikely(arch_trace_is_compat_syscall(regs))) + return -1; + + return syscall_get_nr(task, regs); +} +#else +static inline int +trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs) +{ + return syscall_get_nr(task, regs); +} +#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */ + static __init struct syscall_metadata * find_syscall_meta(unsigned long syscall) { @@ -104,7 +110,7 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr) return syscalls_metadata[nr]; } -enum print_line_t +static enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags, struct trace_event *event) { @@ -157,7 +163,7 @@ end: return TRACE_TYPE_HANDLED; } -enum print_line_t +static enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags, struct trace_event *event) { @@ -297,16 +303,16 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call) return ret; } -void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) +static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) { struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; struct ring_buffer *buffer; - int size; int syscall_nr; + int size; - syscall_nr = syscall_get_nr(current, regs); + syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; if (!test_bit(syscall_nr, enabled_enter_syscalls)) @@ -332,7 +338,7 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) +static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) { struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; @@ -340,7 +346,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) struct ring_buffer *buffer; int syscall_nr; - syscall_nr = syscall_get_nr(current, regs); + syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; if (!test_bit(syscall_nr, enabled_exit_syscalls)) @@ -364,7 +370,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -int reg_event_syscall_enter(struct ftrace_event_call *call) +static int reg_event_syscall_enter(struct ftrace_event_call *call) { int ret = 0; int num; @@ -383,7 +389,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call) return ret; } -void unreg_event_syscall_enter(struct ftrace_event_call *call) +static void unreg_event_syscall_enter(struct ftrace_event_call *call) { int num; @@ -398,7 +404,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call) mutex_unlock(&syscall_trace_lock); } -int reg_event_syscall_exit(struct ftrace_event_call *call) +static int reg_event_syscall_exit(struct ftrace_event_call *call) { int ret = 0; int num; @@ -417,7 +423,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call) return ret; } -void unreg_event_syscall_exit(struct ftrace_event_call *call) +static void unreg_event_syscall_exit(struct ftrace_event_call *call) { int num; @@ -432,7 +438,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call) mutex_unlock(&syscall_trace_lock); } -int init_syscall_trace(struct ftrace_event_call *call) +static int init_syscall_trace(struct ftrace_event_call *call) { int id; int num; @@ -457,12 +463,36 @@ int init_syscall_trace(struct ftrace_event_call *call) return id; } +struct trace_event_functions enter_syscall_print_funcs = { + .trace = print_syscall_enter, +}; + +struct trace_event_functions exit_syscall_print_funcs = { + .trace = print_syscall_exit, +}; + +struct ftrace_event_class event_class_syscall_enter = { + .system = "syscalls", + .reg = syscall_enter_register, + .define_fields = syscall_enter_define_fields, + .get_fields = syscall_get_enter_fields, + .raw_init = init_syscall_trace, +}; + +struct ftrace_event_class event_class_syscall_exit = { + .system = "syscalls", + .reg = syscall_exit_register, + .define_fields = syscall_exit_define_fields, + .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), + .raw_init = init_syscall_trace, +}; + unsigned long __init __weak arch_syscall_addr(int nr) { return (unsigned long)sys_call_table[nr]; } -int __init init_ftrace_syscalls(void) +static int __init init_ftrace_syscalls(void) { struct syscall_metadata *meta; unsigned long addr; @@ -505,7 +535,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) int rctx; int size; - syscall_nr = syscall_get_nr(current, regs); + syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) @@ -537,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } -int perf_sysenter_enable(struct ftrace_event_call *call) +static int perf_sysenter_enable(struct ftrace_event_call *call) { int ret = 0; int num; @@ -558,7 +588,7 @@ int perf_sysenter_enable(struct ftrace_event_call *call) return ret; } -void perf_sysenter_disable(struct ftrace_event_call *call) +static void perf_sysenter_disable(struct ftrace_event_call *call) { int num; @@ -581,7 +611,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) int rctx; int size; - syscall_nr = syscall_get_nr(current, regs); + syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) @@ -615,7 +645,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } -int perf_sysexit_enable(struct ftrace_event_call *call) +static int perf_sysexit_enable(struct ftrace_event_call *call) { int ret = 0; int num; @@ -636,7 +666,7 @@ int perf_sysexit_enable(struct ftrace_event_call *call) return ret; } -void perf_sysexit_disable(struct ftrace_event_call *call) +static void perf_sysexit_disable(struct ftrace_event_call *call) { int num; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 03003cd7dd96..8dad2a92dee9 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -22,25 +22,27 @@ #include <linux/uaccess.h> #include <linux/uprobes.h> #include <linux/namei.h> +#include <linux/string.h> #include "trace_probe.h" #define UPROBE_EVENT_SYSTEM "uprobes" +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + /* * uprobe event core functions */ -struct trace_uprobe; -struct uprobe_trace_consumer { - struct uprobe_consumer cons; - struct trace_uprobe *tu; -}; - struct trace_uprobe { struct list_head list; struct ftrace_event_class class; struct ftrace_event_call call; - struct uprobe_trace_consumer *consumer; + struct trace_uprobe_filter filter; + struct uprobe_consumer consumer; struct inode *inode; char *filename; unsigned long offset; @@ -63,6 +65,18 @@ static LIST_HEAD(uprobe_list); static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); +static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) +{ + rwlock_init(&filter->rwlock); + filter->nr_systemwide = 0; + INIT_LIST_HEAD(&filter->perf_events); +} + +static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) +{ + return !filter->nr_systemwide && list_empty(&filter->perf_events); +} + /* * Allocate new trace_uprobe and initialize it (including uprobes). */ @@ -91,6 +105,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs) goto error; INIT_LIST_HEAD(&tu->list); + tu->consumer.handler = uprobe_dispatcher; + init_trace_uprobe_filter(&tu->filter); return tu; error: @@ -189,7 +205,7 @@ static int create_trace_uprobe(int argc, char **argv) if (argv[0][0] == '-') is_delete = true; else if (argv[0][0] != 'p') { - pr_info("Probe definition must be started with 'p', 'r' or" " '-'.\n"); + pr_info("Probe definition must be started with 'p' or '-'.\n"); return -EINVAL; } @@ -252,27 +268,32 @@ static int create_trace_uprobe(int argc, char **argv) if (ret) goto fail_address_parse; - ret = strict_strtoul(arg, 0, &offset); - if (ret) + inode = igrab(path.dentry->d_inode); + path_put(&path); + + if (!inode || !S_ISREG(inode->i_mode)) { + ret = -EINVAL; goto fail_address_parse; + } - inode = igrab(path.dentry->d_inode); + ret = kstrtoul(arg, 0, &offset); + if (ret) + goto fail_address_parse; argc -= 2; argv += 2; /* setup a probe */ if (!event) { - char *tail = strrchr(filename, '/'); + char *tail; char *ptr; - ptr = kstrdup((tail ? tail + 1 : filename), GFP_KERNEL); - if (!ptr) { + tail = kstrdup(kbasename(filename), GFP_KERNEL); + if (!tail) { ret = -ENOMEM; goto fail_address_parse; } - tail = ptr; ptr = strpbrk(tail, ".-_"); if (ptr) *ptr = '\0'; @@ -356,7 +377,7 @@ fail_address_parse: if (inode) iput(inode); - pr_info("Failed to parse address.\n"); + pr_info("Failed to parse address or file.\n"); return ret; } @@ -465,7 +486,7 @@ static const struct file_operations uprobe_profile_ops = { }; /* uprobe handler */ -static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) { struct uprobe_trace_entry_head *entry; struct ring_buffer_event *event; @@ -475,8 +496,6 @@ static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) unsigned long irq_flags; struct ftrace_event_call *call = &tu->call; - tu->nhit++; - local_save_flags(irq_flags); pc = preempt_count(); @@ -485,16 +504,18 @@ static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) event = trace_current_buffer_lock_reserve(&buffer, call->event.type, size, irq_flags, pc); if (!event) - return; + return 0; entry = ring_buffer_event_data(event); - entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + entry->ip = instruction_pointer(task_pt_regs(current)); data = (u8 *)&entry[1]; for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); if (!filter_current_check_discard(buffer, call, entry, event)) trace_buffer_unlock_commit(buffer, event, irq_flags, pc); + + return 0; } /* Event entry printers */ @@ -533,42 +554,43 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -static int probe_event_enable(struct trace_uprobe *tu, int flag) +static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu) { - struct uprobe_trace_consumer *utc; - int ret = 0; + return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE); +} - if (!tu->inode || tu->consumer) - return -EINTR; +typedef bool (*filter_func_t)(struct uprobe_consumer *self, + enum uprobe_filter_ctx ctx, + struct mm_struct *mm); - utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL); - if (!utc) +static int +probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) +{ + int ret = 0; + + if (is_trace_uprobe_enabled(tu)) return -EINTR; - utc->cons.handler = uprobe_dispatcher; - utc->cons.filter = NULL; - ret = uprobe_register(tu->inode, tu->offset, &utc->cons); - if (ret) { - kfree(utc); - return ret; - } + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); tu->flags |= flag; - utc->tu = tu; - tu->consumer = utc; + tu->consumer.filter = filter; + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + if (ret) + tu->flags &= ~flag; - return 0; + return ret; } static void probe_event_disable(struct trace_uprobe *tu, int flag) { - if (!tu->inode || !tu->consumer) + if (!is_trace_uprobe_enabled(tu)) return; - uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons); + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->flags &= ~flag; - kfree(tu->consumer); - tu->consumer = NULL; } static int uprobe_event_define_fields(struct ftrace_event_call *event_call) @@ -642,8 +664,96 @@ static int set_print_fmt(struct trace_uprobe *tu) } #ifdef CONFIG_PERF_EVENTS +static bool +__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) +{ + struct perf_event *event; + + if (filter->nr_systemwide) + return true; + + list_for_each_entry(event, &filter->perf_events, hw.tp_list) { + if (event->hw.tp_target->mm == mm) + return true; + } + + return false; +} + +static inline bool +uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +{ + return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm); +} + +static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + + write_lock(&tu->filter.rwlock); + if (event->hw.tp_target) { + /* + * event->parent != NULL means copy_process(), we can avoid + * uprobe_apply(). current->mm must be probed and we can rely + * on dup_mmap() which preserves the already installed bp's. + * + * attr.enable_on_exec means that exec/mmap will install the + * breakpoints we need. + */ + done = tu->filter.nr_systemwide || + event->parent || event->attr.enable_on_exec || + uprobe_filter_event(tu, event); + list_add(&event->hw.tp_list, &tu->filter.perf_events); + } else { + done = tu->filter.nr_systemwide; + tu->filter.nr_systemwide++; + } + write_unlock(&tu->filter.rwlock); + + if (!done) + uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + + return 0; +} + +static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + + write_lock(&tu->filter.rwlock); + if (event->hw.tp_target) { + list_del(&event->hw.tp_list); + done = tu->filter.nr_systemwide || + (event->hw.tp_target->flags & PF_EXITING) || + uprobe_filter_event(tu, event); + } else { + tu->filter.nr_systemwide--; + done = tu->filter.nr_systemwide; + } + write_unlock(&tu->filter.rwlock); + + if (!done) + uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + + return 0; +} + +static bool uprobe_perf_filter(struct uprobe_consumer *uc, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + struct trace_uprobe *tu; + int ret; + + tu = container_of(uc, struct trace_uprobe, consumer); + read_lock(&tu->filter.rwlock); + ret = __uprobe_perf_filter(&tu->filter, mm); + read_unlock(&tu->filter.rwlock); + + return ret; +} + /* uprobe profile handler */ -static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) { struct ftrace_event_call *call = &tu->call; struct uprobe_trace_entry_head *entry; @@ -652,11 +762,14 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) int size, __size, i; int rctx; + if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; + __size = sizeof(*entry) + tu->size; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) - return; + return 0; preempt_disable(); @@ -664,7 +777,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) if (!entry) goto out; - entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + entry->ip = instruction_pointer(task_pt_regs(current)); data = (u8 *)&entry[1]; for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); @@ -674,6 +787,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) out: preempt_enable(); + return 0; } #endif /* CONFIG_PERF_EVENTS */ @@ -684,7 +798,7 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, TP_FLAG_TRACE); + return probe_event_enable(tu, TP_FLAG_TRACE, NULL); case TRACE_REG_UNREGISTER: probe_event_disable(tu, TP_FLAG_TRACE); @@ -692,11 +806,18 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, TP_FLAG_PROFILE); + return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: probe_event_disable(tu, TP_FLAG_PROFILE); return 0; + + case TRACE_REG_PERF_OPEN: + return uprobe_perf_open(tu, data); + + case TRACE_REG_PERF_CLOSE: + return uprobe_perf_close(tu, data); + #endif default: return 0; @@ -706,22 +827,20 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { - struct uprobe_trace_consumer *utc; struct trace_uprobe *tu; + int ret = 0; - utc = container_of(con, struct uprobe_trace_consumer, cons); - tu = utc->tu; - if (!tu || tu->consumer != utc) - return 0; + tu = container_of(con, struct trace_uprobe, consumer); + tu->nhit++; if (tu->flags & TP_FLAG_TRACE) - uprobe_trace_func(tu, regs); + ret |= uprobe_trace_func(tu, regs); #ifdef CONFIG_PERF_EVENTS if (tu->flags & TP_FLAG_PROFILE) - uprobe_perf_func(tu, regs); + ret |= uprobe_perf_func(tu, regs); #endif - return 0; + return ret; } static struct trace_event_functions uprobe_funcs = { |