/* * Infrastructure for profiling code inserted by 'gcc -pg'. * * Copyright (C) 2007-2008 Steven Rostedt * Copyright (C) 2004-2008 Ingo Molnar * * Originally ported from the -rt patch by: * Copyright (C) 2007 Arnaldo Carvalho de Melo * * Based on code in the latency_tracer, that is: * * Copyright (C) 2004-2006 Ingo Molnar * Copyright (C) 2004 Nadia Yvette Chambers */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "trace_output.h" #include "trace_stat.h" #define FTRACE_WARN_ON(cond) \ ({ \ int ___r = cond; \ if (WARN_ON(___r)) \ ftrace_kill(); \ ___r; \ }) #define FTRACE_WARN_ON_ONCE(cond) \ ({ \ int ___r = cond; \ if (WARN_ON_ONCE(___r)) \ ftrace_kill(); \ ___r; \ }) /* hash bits for specific function selection */ #define FTRACE_HASH_BITS 7 #define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) #define FTRACE_HASH_DEFAULT_BITS 10 #define FTRACE_HASH_MAX_BITS 12 #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL) #ifdef CONFIG_DYNAMIC_FTRACE #define INIT_OPS_HASH(opsname) \ .func_hash = &opsname.local_hash, \ .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), #define ASSIGN_OPS_HASH(opsname, val) \ .func_hash = val, \ .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), #else #define INIT_OPS_HASH(opsname) #define ASSIGN_OPS_HASH(opsname, val) #endif static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, INIT_OPS_HASH(ftrace_list_end) }; /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; /* Current function tracing op */ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* What to set function_trace_op to */ static struct ftrace_ops *set_function_trace_op; /* List for set_ftrace_pid's pids. */ LIST_HEAD(ftrace_pids); struct ftrace_pid { struct list_head list; struct pid *pid; }; /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. */ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs); #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs); #else /* See comment below, where ftrace_ops_list_func is defined */ 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_notrace() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ #define do_for_each_ftrace_op(op, list) \ op = rcu_dereference_raw_notrace(list); \ do /* * Optimized for just a single item in the list (as that is the normal case). */ #define while_for_each_ftrace_op(op) \ while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ unlikely((op) != &ftrace_list_end)) static inline void ftrace_ops_init(struct ftrace_ops *ops) { #ifdef CONFIG_DYNAMIC_FTRACE if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) { mutex_init(&ops->local_hash.regex_lock); ops->func_hash = &ops->local_hash; ops->flags |= FTRACE_OPS_FL_INITIALIZED; } #endif } /** * ftrace_nr_registered_ops - return number of ops registered * * Returns the number of ftrace_ops registered and tracing functions */ int ftrace_nr_registered_ops(void) { struct ftrace_ops *ops; int cnt = 0; mutex_lock(&ftrace_lock); for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) cnt++; mutex_unlock(&ftrace_lock); return cnt; } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs) { if (!test_tsk_trace_trace(current)) return; ftrace_pid_function(ip, parent_ip, op, regs); } static void set_ftrace_pid_function(ftrace_func_t func) { /* do not set ftrace_pid_function to itself! */ if (func != ftrace_pid_func) ftrace_pid_function = func; } /** * clear_ftrace_function - reset the ftrace function * * This NULLs the ftrace function and in essence stops * tracing. There may be lag */ void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; ftrace_pid_function = ftrace_stub; } static void control_ops_disable_all(struct ftrace_ops *ops) { int cpu; for_each_possible_cpu(cpu) *per_cpu_ptr(ops->disabled, cpu) = 1; } static int control_ops_alloc(struct ftrace_ops *ops) { int __percpu *disabled; disabled = alloc_percpu(int); if (!disabled) return -ENOMEM; ops->disabled = disabled; control_ops_disable_all(ops); return 0; } static void ftrace_sync(struct work_struct *work) { /* * This function is just a stub to implement a hard force * of synchronize_sched(). This requires synchronizing * tasks even in userspace and idle. * * Yes, function tracing is rude. */ } static void ftrace_sync_ipi(void *data) { /* Probably not needed, but do it anyway */ smp_rmb(); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER static void update_function_graph_func(void); #else static inline void update_function_graph_func(void) { } #endif static void update_ftrace_function(void) { ftrace_func_t func; /* * Prepare the ftrace_ops that the arch callback will use. * If there's only one ftrace_ops registered, the ftrace_ops_list * will point to the ops we want. */ set_function_trace_op = ftrace_ops_list; /* If there's no ftrace_ops registered, just call the stub function */ if (ftrace_ops_list == &ftrace_list_end) { func = ftrace_stub; /* * If we are at the end of the list and this ops is * recursion safe and not dynamic and the arch supports passing ops, * then have the mcount trampoline call the function directly. */ } else if (ftrace_ops_list->next == &ftrace_list_end) { func = ftrace_ops_get_func(ftrace_ops_list); } else { /* Just use the default ftrace_ops */ set_function_trace_op = &ftrace_list_end; func = ftrace_ops_list_func; } update_function_graph_func(); /* If there's no change, then do nothing more here */ if (ftrace_trace_function == func) return; /* * If we are using the list function, it doesn't care * about the function_trace_ops. */ if (func == ftrace_ops_list_func) { ftrace_trace_function = func; /* * Don't even bother setting function_trace_ops, * it would be racy to do so anyway. */ return; } #ifndef CONFIG_DYNAMIC_FTRACE /* * For static tracing, we need to be a bit more careful. * The function change takes affect immediately. Thus, * we need to coorditate the setting of the function_trace_ops * with the setting of the ftrace_trace_function. * * Set the function to the list ops, which will call the * function we want, albeit indirectly, but it handles the * ftrace_ops and doesn't depend on function_trace_op. */ ftrace_trace_function = ftrace_ops_list_func; /* * Make sure all CPUs see this. Yes this is slow, but static * tracing is slow and nasty to have enabled. */ schedule_on_each_cpu(ftrace_sync); /* Now all cpus are using the list ops. */ function_trace_op = set_function_trace_op; /* Make sure the function_trace_op is visible on all CPUs */ smp_wmb(); /* Nasty way to force a rmb on all cpus */ smp_call_function(ftrace_sync_ipi, NULL, 1); /* OK, we are all set to update the ftrace_trace_function now! */ #endif /* !CONFIG_DYNAMIC_FTRACE */ ftrace_trace_function = func; } int using_ftrace_ops_list_func(void) { return ftrace_trace_function == ftrace_ops_list_func; } static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { ops->next = *list; /* * We are entering ops into the list but another * CPU might be walking that list. We need to make sure * the ops->next pointer is valid before another CPU sees * the ops pointer included into the list. */ rcu_assign_pointer(*list, ops); } static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { struct ftrace_ops **p; /* * If we are removing the last function, then simply point * to the ftrace_stub. */ if (*list == ops && ops->next == &ftrace_list_end) { *list = &ftrace_list_end; return 0; } for (p = list; *p != &ftrace_list_end; p = &(*p)->next) if (*p == ops) break; if (*p != ops) return -1; *p = (*p)->next; return 0; } static void add_ftrace_list_ops(struct ftrace_ops **list, struct ftrace_ops *main_ops, struct ftrace_ops *ops) { int first = *list == &ftrace_list_end; add_ftrace_ops(list, ops); if (first) add_ftrace_ops(&ftrace_ops_list, main_ops); } static int remove_ftrace_list_ops(struct ftrace_ops **list, struct ftrace_ops *main_ops, struct ftrace_ops *ops) { int ret = remove_ftrace_ops(list, ops); if (!ret && *list == &ftrace_list_end) ret = remove_ftrace_ops(&ftrace_ops_list, main_ops); return ret; } static void ftrace_update_trampoline(struct ftrace_ops *ops); static int __register_ftrace_function(struct ftrace_ops *ops) { if (ops->flags & FTRACE_OPS_FL_DELETED) return -EINVAL; if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) return -EBUSY; #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. * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant. */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS && !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)) return -EINVAL; if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) ops->flags |= FTRACE_OPS_FL_SAVE_REGS; #endif if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; if (ops->flags & FTRACE_OPS_FL_CONTROL) { if (control_ops_alloc(ops)) return -ENOMEM; add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops); /* The control_ops needs the trampoline update */ ops = &control_ops; } else add_ftrace_ops(&ftrace_ops_list, ops); ftrace_update_trampoline(ops); if (ftrace_enabled) update_ftrace_function(); return 0; } static int __unregister_ftrace_function(struct ftrace_ops *ops) { int ret; if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED))) return -EBUSY; if (ops->flags & FTRACE_OPS_FL_CONTROL) { ret = remove_ftrace_list_ops(&ftrace_control_list, &control_ops, ops); } else ret = remove_ftrace_ops(&ftrace_ops_list, ops); if (ret < 0) return ret; if (ftrace_enabled) update_ftrace_function(); return 0; } static void ftrace_update_pid_func(void) { /* Only do something if we are tracing something */ if (ftrace_trace_function == ftrace_stub) return; update_ftrace_function(); } #ifdef CONFIG_FUNCTION_PROFILER struct ftrace_profile { struct hlist_node node; unsigned long ip; unsigned long counter; #ifdef CONFIG_FUNCTION_GRAPH_TRACER unsigned long long time; unsigned long long time_squared; #endif }; struct ftrace_profile_page { struct ftrace_profile_page *next; unsigned long index; struct ftrace_profile records[]; }; struct ftrace_profile_stat { atomic_t disabled; struct hlist_head *hash; struct ftrace_profile_page *pages; struct ftrace_profile_page *start; struct tracer_stat stat; }; #define PROFILE_RECORDS_SIZE \ (PAGE_SIZE - offsetof(struct ftrace_profile_page, records)) #define PROFILES_PER_PAGE \ (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile)) static int ftrace_profile_enabled __read_mostly; /* ftrace_profile_lock - synchronize the enable and disable of the profiler */ static DEFINE_MUTEX(ftrace_profile_lock); static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats); #define FTRACE_PROFILE_HASH_BITS 10 #define FTRACE_PROFILE_HASH_SIZE (1 << FTRACE_PROFILE_HASH_BITS) static void * function_stat_next(void *v, int idx) { struct ftrace_profile *rec = v; struct ftrace_profile_page *pg; pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK); again: if (idx != 0) rec++; if ((void *)rec >= (void *)&pg->records[pg->index]) { pg = pg->next; if (!pg) return NULL; rec = &pg->records[0]; if (!rec->counter) goto again; } return rec; } static void *function_stat_start(struct tracer_stat *trace) { struct ftrace_profile_stat *stat = container_of(trace, struct ftrace_profile_stat, stat); if (!stat || !stat->start) return NULL; return function_stat_next(&stat->start->records[0], 0); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* function graph compares on total time */ static int function_stat_cmp(void *p1, void *p2) { struct ftrace_profile *a = p1; struct ftrace_profile *b = p2; if (a->time < b->time) return -1; if (a->time > b->time) return 1; else return 0; } #else /* not function graph compares against hits */ static int function_stat_cmp(void *p1, void *p2) { struct ftrace_profile *a = p1; struct ftrace_profile *b = p2; if (a->counter < b->counter) return -1; if (a->counter > b->counter) return 1; else return 0; } #endif static int function_stat_headers(struct seq_file *m) { #ifdef CONFIG_FUNCTION_GRAPH_TRACER seq_puts(m, " Function " "Hit Time Avg s^2\n" " -------- " "--- ---- --- ---\n"); #else seq_puts(m, " Function Hit\n" " -------- ---\n"); #endif return 0; } static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif mutex_lock(&ftrace_profile_lock); /* we raced with function_profile_reset() */ if (unlikely(rec->counter == 0)) { ret = -EBUSY; goto out; } kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); seq_printf(m, " %-30.30s %10lu", str, rec->counter); #ifdef CONFIG_FUNCTION_GRAPH_TRACER seq_puts(m, " "); avg = rec->time; do_div(avg, rec->counter); /* Sample standard deviation (s^2) */ if (rec->counter <= 1) stddev = 0; else { /* * Apply Welford's method: * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) */ stddev = rec->counter * rec->time_squared - rec->time * rec->time; /* * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ do_div(stddev, rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); trace_print_graph_duration(rec->time, &s); trace_seq_puts(&s, " "); trace_print_graph_duration(avg, &s); trace_seq_puts(&s, " "); trace_print_graph_duration(stddev, &s); trace_print_seq(m, &s); #endif seq_putc(m, '\n'); out: mutex_unlock(&ftrace_profile_lock); return ret; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) { struct ftrace_profile_page *pg; pg = stat->pages = stat->start; while (pg) { memset(pg->records, 0, PROFILE_RECORDS_SIZE); pg->index = 0; pg = pg->next; } memset(stat->hash, 0, FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head)); } int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) { struct ftrace_profile_page *pg; int functions; int pages; int i; /* If we already allocated, do nothing */ if (stat->pages) return 0; stat->pages = (void *)get_zeroed_page(GFP_KERNEL); if (!stat->pages) return -ENOMEM; #ifdef CONFIG_DYNAMIC_FTRACE functions = ftrace_update_tot_cnt; #else /* * We do not know the number of functions that exist because * dynamic tracing is what counts them. With past experience * we have around 20K functions. That should be more than enough. * It is highly unlikely we will execute every function in * the kernel. */ functions = 20000; #endif pg = stat->start = stat->pages; pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE); for (i = 1; i < pages; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); if (!pg->next) goto out_free; pg = pg->next; } return 0; out_free: pg = stat->start; while (pg) { unsigned long tmp = (unsigned long)pg; pg = pg->next; free_page(tmp); } stat->pages = NULL; stat->start = NULL; return -ENOMEM; } static int ftrace_profile_init_cpu(int cpu) { struct ftrace_profile_stat *stat; int size; stat = &per_cpu(ftrace_profile_stats, cpu); if (stat->hash) { /* If the profile is already created, simply reset it */ ftrace_profile_reset(stat); return 0; } /* * We are profiling all functions, but usually only a few thousand * functions are hit. We'll make a hash of 1024 items. */ size = FTRACE_PROFILE_HASH_SIZE; stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL); if (!stat->hash) return -ENOMEM; /* Preallocate the function profiling pages */ if (ftrace_profile_pages_init(stat) < 0) { kfree(stat->hash); stat->hash = NULL; return -ENOMEM; } return 0; } static int ftrace_profile_init(void) { int cpu; int ret = 0; for_each_possible_cpu(cpu) { ret = ftrace_profile_init_cpu(cpu); if (ret) break; } return ret; } /* interrupts must be disabled */ static struct ftrace_profile * ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) { struct ftrace_profile *rec; struct hlist_head *hhd; unsigned long key; key = hash_long(ip, FTRACE_PROFILE_HASH_BITS); hhd = &stat->hash[key]; if (hlist_empty(hhd)) return NULL; hlist_for_each_entry_rcu_notrace(rec, hhd, node) { if (rec->ip == ip) return rec; } return NULL; } static void ftrace_add_profile(struct ftrace_profile_stat *stat, struct ftrace_profile *rec) { unsigned long key; key = hash_long(rec->ip, FTRACE_PROFILE_HASH_BITS); hlist_add_head_rcu(&rec->node, &stat->hash[key]); } /* * The memory is already allocated, this simply finds a new record to use. */ static struct ftrace_profile * ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) { struct ftrace_profile *rec = NULL; /* prevent recursion (from NMIs) */ if (atomic_inc_return(&stat->disabled) != 1) goto out; /* * Try to find the function again since an NMI * could have added it */ rec = ftrace_find_profiled_func(stat, ip); if (rec) goto out; if (stat->pages->index == PROFILES_PER_PAGE) { if (!stat->pages->next) goto out; stat->pages = stat->pages->next; } rec = &stat->pages->records[stat->pages->index++]; rec->ip = ip; ftrace_add_profile(stat, rec); out: atomic_dec(&stat->disabled); return rec; } static void function_profile_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; unsigned long flags; if (!ftrace_profile_enabled) return; local_irq_save(flags); stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) goto out; rec = ftrace_find_profiled_func(stat, ip); if (!rec) { rec = ftrace_profile_alloc(stat, ip); if (!rec) goto out; } rec->counter++; out: local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { function_profile_call(trace->func, 0, NULL, NULL); return 1; } static void profile_graph_return(struct ftrace_graph_ret *trace) { struct ftrace_profile_stat *stat; unsigned long long calltime; struct ftrace_profile *rec; unsigned long flags; local_irq_save(flags); stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) goto out; /* If the calltime was zero'd ignore it */ if (!trace->calltime) goto out; calltime = trace->rettime - trace->calltime; if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) { int index; index = trace->depth; /* Append this call time to the parent time to subtract */ if (index) current->ret_stack[index - 1].subtime += calltime; if (current->ret_stack[index].subtime < calltime) calltime -= current->ret_stack[index].subtime; else calltime = 0; } rec = ftrace_find_profiled_func(stat, trace->func); if (rec) { rec->time += calltime; rec->time_squared += calltime * calltime; } out: local_irq_restore(flags); } static int register_ftrace_profiler(void) { return register_ftrace_graph(&profile_graph_return, &profile_graph_entry); } static void unregister_ftrace_profiler(void) { unregister_ftrace_graph(); } #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, INIT_OPS_HASH(ftrace_profile_ops) }; static int register_ftrace_profiler(void) { return register_ftrace_function(&ftrace_profile_ops); } static void unregister_ftrace_profiler(void) { unregister_ftrace_function(&ftrace_profile_ops); } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ static ssize_t ftrace_profile_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; val = !!val; mutex_lock(&ftrace_profile_lock); if (ftrace_profile_enabled ^ val) { if (val) { ret = ftrace_profile_init(); if (ret < 0) { cnt = ret; goto out; } ret = register_ftrace_profiler(); if (ret < 0) { cnt = ret; goto out; } ftrace_profile_enabled = 1; } else { ftrace_profile_enabled = 0; /* * unregister_ftrace_profiler calls stop_machine * so this acts like an synchronize_sched. */ unregister_ftrace_profiler(); } } out: mutex_unlock(&ftrace_profile_lock); *ppos += cnt; return cnt; } static ssize_t ftrace_profile_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[64]; /* big enough to hold a number */ int r; r = sprintf(buf, "%u\n", ftrace_profile_enabled); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static const struct file_operations ftrace_profile_fops = { .open = tracing_open_generic, .read = ftrace_profile_read, .write = ftrace_profile_write, .llseek = default_llseek, }; /* used to initialize the real stat files */ static struct tracer_stat function_stats __initdata = { .name = "functions", .stat_start = function_stat_start, .stat_next = function_stat_next, .stat_cmp = function_stat_cmp, .stat_headers = function_stat_headers, .stat_show = function_stat_show }; static __init void ftrace_profile_debugfs(struct dentry *d_tracer) { struct ftrace_profile_stat *stat; struct dentry *entry; char *name; int ret; int cpu; for_each_possible_cpu(cpu) { stat = &per_cpu(ftrace_profile_stats, cpu); /* allocate enough for function name + cpu number */ name = kmalloc(32, GFP_KERNEL); if (!name) { /* * The files created are permanent, if something happens * we still do not free memory. */ WARN(1, "Could not allocate stat file for cpu %d\n", cpu); return; } stat->stat = function_stats; snprintf(name, 32, "function%d", cpu); stat->stat.name = name; ret = register_stat_tracer(&stat->stat); if (ret) { WARN(1, "Could not register function stat for cpu %d\n", cpu); kfree(name); return; } } entry = debugfs_create_file("function_profile_enabled", 0644, d_tracer, NULL, &ftrace_profile_fops); if (!entry) pr_warning("Could not create debugfs " "'function_profile_enabled' entry\n"); } #else /* CONFIG_FUNCTION_PROFILER */ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) { } #endif /* CONFIG_FUNCTION_PROFILER */ static struct pid * const ftrace_swapper_pid = &init_struct_pid; #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int ftrace_graph_active; #else # define ftrace_graph_active 0 #endif #ifdef CONFIG_DYNAMIC_FTRACE static struct ftrace_ops *removed_ops; /* * Set when doing a global update, like enabling all recs or disabling them. * It is not set when just updating a single ftrace_ops. */ static bool update_all_ops; #ifndef CONFIG_FTRACE_MCOUNT_RECORD # error Dynamic ftrace depends on MCOUNT_RECORD #endif static struct hlist_head ftrace_func_hash[FTRACE_FUNC_HASHSIZE] __read_mostly; struct ftrace_func_probe { struct hlist_node node; struct ftrace_probe_ops *ops; unsigned long flags; unsigned long ip; void *data; struct list_head free_list; }; struct ftrace_func_entry { struct hlist_node hlist; unsigned long ip; }; struct ftrace_hash { unsigned long size_bits; struct hlist_head *buckets; unsigned long count; struct rcu_head rcu; }; /* * We make these constant because no one should touch them, * but they are used as the default "empty hash", to avoid allocating * it all the time. These are in a read only section such that if * anyone does try to modify it, it will cause an exception. */ static const struct hlist_head empty_buckets[1]; static const struct ftrace_hash empty_hash = { .buckets = (struct hlist_head *)empty_buckets, }; #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) static struct ftrace_ops global_ops = { .func = ftrace_stub, .local_hash.notrace_hash = EMPTY_HASH, .local_hash.filter_hash = EMPTY_HASH, INIT_OPS_HASH(global_ops) .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, }; /* * This is used by __kernel_text_address() to return true if the * address is on a dynamically allocated trampoline that would * not return true for either core_kernel_text() or * is_module_text_address(). */ bool is_ftrace_trampoline(unsigned long addr) { struct ftrace_ops *op; bool ret = false; /* * Some of the ops may be dynamically allocated, * they are freed after a synchronize_sched(). */ preempt_disable_notrace(); do_for_each_ftrace_op(op, ftrace_ops_list) { /* * This is to check for dynamically allocated trampolines. * Trampolines that are in kernel text will have * core_kernel_text() return true. */ if (op->trampoline && op->trampoline_size) if (addr >= op->trampoline && addr < op->trampoline + op->trampoline_size) { ret = true; goto out; } } while_for_each_ftrace_op(op); out: preempt_enable_notrace(); return ret; } struct ftrace_page { struct ftrace_page *next; struct dyn_ftrace *records; int index; int size; }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) #define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) /* estimate from running different kernels */ #define NR_TO_INIT 10000 static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; static bool __always_inline ftrace_hash_empty(struct ftrace_hash *hash) { return !hash || !hash->count; } static struct ftrace_func_entry * ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) { unsigned long key; struct ftrace_func_entry *entry; struct hlist_head *hhd; if (ftrace_hash_empty(hash)) return NULL; if (hash->size_bits > 0) key = hash_long(ip, hash->size_bits); else key = 0; hhd = &hash->buckets[key]; hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) { if (entry->ip == ip) return entry; } return NULL; } static void __add_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry) { struct hlist_head *hhd; unsigned long key; if (hash->size_bits) key = hash_long(entry->ip, hash->size_bits); else key = 0; hhd = &hash->buckets[key]; hlist_add_head(&entry->hlist, hhd); hash->count++; } static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) { struct ftrace_func_entry *entry; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; entry->ip = ip; __add_hash_entry(hash, entry); return 0; } static void free_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry) { hlist_del(&entry->hlist); kfree(entry); hash->count--; } static void remove_hash_entry(struct ftrace_hash *hash, struct ftrace_func_entry *entry) { hlist_del(&entry->hlist); hash->count--; } static void ftrace_hash_clear(struct ftrace_hash *hash) { struct hlist_head *hhd; struct hlist_node *tn; struct ftrace_func_entry *entry; int size = 1 << hash->size_bits; int i; if (!hash->count) return; for (i = 0; i < size; i++) { hhd = &hash->buckets[i]; hlist_for_each_entry_safe(entry, tn, hhd, hlist) free_hash_entry(hash, entry); } FTRACE_WARN_ON(hash->count); } static void free_ftrace_hash(struct ftrace_hash *hash) { if (!hash || hash == EMPTY_HASH) return; ftrace_hash_clear(hash); kfree(hash->buckets); kfree(hash); } static void __free_ftrace_hash_rcu(struct rcu_head *rcu) { struct ftrace_hash *hash; hash = container_of(rcu, struct ftrace_hash, rcu); free_ftrace_hash(hash); } static void free_ftrace_hash_rcu(struct ftrace_hash *hash) { if (!hash || hash == EMPTY_HASH) return; call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); } void ftrace_free_filter(struct ftrace_ops *ops) { ftrace_ops_init(ops); free_ftrace_hash(ops->func_hash->filter_hash); free_ftrace_hash(ops->func_hash->notrace_hash); } static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { struct ftrace_hash *hash; int size; hash = kzalloc(sizeof(*hash), GFP_KERNEL); if (!hash) return NULL; size = 1 << size_bits; hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL); if (!hash->buckets) { kfree(hash); return NULL; } hash->size_bits = size_bits; return hash; } static struct ftrace_hash * alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) { struct ftrace_func_entry *entry; struct ftrace_hash *new_hash; int size; int ret; int i; new_hash = alloc_ftrace_hash(size_bits); if (!new_hash) return NULL; /* Empty hash? */ if (ftrace_hash_empty(hash)) return new_hash; size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { ret = add_hash_entry(new_hash, entry->ip); if (ret < 0) goto free_hash; } } FTRACE_WARN_ON(new_hash->count != hash->count); return new_hash; free_hash: free_ftrace_hash(new_hash); return NULL; } static void ftrace_hash_rec_disable_modify(struct ftrace_ops *ops, int filter_hash); static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash); static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, struct ftrace_hash *new_hash); static int 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 *tn; struct hlist_head *hhd; struct ftrace_hash *new_hash; int size = src->count; int bits = 0; int ret; int i; /* Reject setting notrace hash on IPMODIFY ftrace_ops */ if (ops->flags & FTRACE_OPS_FL_IPMODIFY && !enable) return -EINVAL; /* * If the new source is empty, just free dst and assign it * the empty_hash. */ if (!src->count) { new_hash = EMPTY_HASH; goto update; } /* * Make the hash size about 1/2 the # found */ for (size /= 2; size; size >>= 1) bits++; /* Don't allocate too much */ if (bits > FTRACE_HASH_MAX_BITS) bits = FTRACE_HASH_MAX_BITS; new_hash = alloc_ftrace_hash(bits); if (!new_hash) return -ENOMEM; size = 1 << src->size_bits; for (i = 0; i < size; i++) { hhd = &src->buckets[i]; hlist_for_each_entry_safe(entry, tn, hhd, hlist) { remove_hash_entry(src, entry); __add_hash_entry(new_hash, entry); } } update: /* Make sure this can be applied if it is IPMODIFY ftrace_ops */ if (enable) { /* IPMODIFY should be updated only when filter_hash updating */ ret = ftrace_hash_ipmodify_update(ops, new_hash); if (ret < 0) { free_ftrace_hash(new_hash); return ret; } } /* * Remove the current set, update the hash and add * them back. */ ftrace_hash_rec_disable_modify(ops, enable); rcu_assign_pointer(*dst, new_hash); ftrace_hash_rec_enable_modify(ops, enable); return 0; } static bool hash_contains_ip(unsigned long ip, struct ftrace_ops_hash *hash) { /* * The function record is a match if it exists in the filter * hash and not in the notrace hash. Note, an emty hash is * considered a match for the filter hash, but an empty * notrace hash is considered not in the notrace hash. */ return (ftrace_hash_empty(hash->filter_hash) || ftrace_lookup_ip(hash->filter_hash, ip)) && (ftrace_hash_empty(hash->notrace_hash) || !ftrace_lookup_ip(hash->notrace_hash, ip)); } /* * Test the hashes for this ops to see if we want to call * the ops->func or not. * * It's a match if the ip is in the ops->filter_hash or * the filter_hash does not exist or is empty, * AND * the ip is not in the ops->notrace_hash. * * This needs to be called with preemption disabled as * the hashes are freed with call_rcu_sched(). */ static int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { struct ftrace_ops_hash hash; int ret; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS /* * There's a small race when adding ops that the ftrace handler * that wants regs, may be called without them. We can not * allow that handler to be called if regs is NULL. */ if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS)) return 0; #endif hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash); hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash); if (hash_contains_ip(ip, &hash)) ret = 1; else ret = 0; return ret; } /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. */ #define do_for_each_ftrace_rec(pg, rec) \ for (pg = ftrace_pages_start; pg; pg = pg->next) { \ int _____i; \ for (_____i = 0; _____i < pg->index; _____i++) { \ rec = &pg->records[_____i]; #define while_for_each_ftrace_rec() \ } \ } static int ftrace_cmp_recs(const void *a, const void *b) { const struct dyn_ftrace *key = a; const struct dyn_ftrace *rec = b; if (key->flags < rec->ip) return -1; if (key->ip >= rec->ip + MCOUNT_INSN_SIZE) return 1; return 0; } static unsigned long ftrace_location_range(unsigned long start, unsigned long end) { struct ftrace_page *pg; struct dyn_ftrace *rec; struct dyn_ftrace key; key.ip = start; key.flags = end; /* overload flags, as it is unsigned long */ for (pg = ftrace_pages_start; pg; pg = pg->next) { if (end < pg->records[0].ip || start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) continue; rec = bsearch(&key, pg->records, pg->index, sizeof(struct dyn_ftrace), ftrace_cmp_recs); if (rec) return rec->ip; } return 0; } /** * ftrace_location - return true if the ip giving is a traced location * @ip: the instruction pointer to check * * Returns rec->ip if @ip given is a pointer to a ftrace location. * That is, the instruction that is either a NOP or call to * the function tracer. It checks the ftrace internal tables to * determine if the address belongs or not. */ unsigned long ftrace_location(unsigned long ip) { return ftrace_location_range(ip, ip); } /** * ftrace_text_reserved - return true if range contains an ftrace location * @start: start of range to search * @end: end of range to search (inclusive). @end points to the last byte to check. * * Returns 1 if @start and @end contains a ftrace location. * That is, the instruction that is either a NOP or call to * the function tracer. It checks the ftrace internal tables to * determine if the address belongs or not. */ int ftrace_text_reserved(const void *start, const void *end) { unsigned long ret; ret = ftrace_location_range((unsigned long)start, (unsigned long)end); return (int)!!ret; } /* Test if ops registered to this rec needs regs */ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) { struct ftrace_ops *ops; bool keep_regs = false; for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { /* pass rec in as regs to have non-NULL val */ if (ftrace_ops_test(ops, rec->ip, rec)) { if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { keep_regs = true; break; } } } return keep_regs; } static void __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) { struct ftrace_hash *hash; struct ftrace_hash *other_hash; struct ftrace_page *pg; struct dyn_ftrace *rec; int count = 0; int all = 0; /* Only update if the ops has been registered */ if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) return; /* * In the filter_hash case: * If the count is zero, we update all records. * Otherwise we just update the items in the hash. * * In the notrace_hash case: * We enable the update in the hash. * As disabling notrace means enabling the tracing, * and enabling notrace means disabling, the inc variable * gets inversed. */ if (filter_hash) { hash = ops->func_hash->filter_hash; other_hash = ops->func_hash->notrace_hash; if (ftrace_hash_empty(hash)) all = 1; } else { inc = !inc; hash = ops->func_hash->notrace_hash; other_hash = ops->func_hash->filter_hash; /* * If the notrace hash has no items, * then there's nothing to do. */ if (ftrace_hash_empty(hash)) return; } do_for_each_ftrace_rec(pg, rec) { int in_other_hash = 0; int in_hash = 0; int match = 0; if (all) { /* * Only the filter_hash affects all records. * Update if the record is not in the notrace hash. */ if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip)) match = 1; } else { in_hash = !!ftrace_lookup_ip(hash, rec->ip); in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip); /* * If filter_hash is set, we want to match all functions * that are in the hash but not in the other hash. * * If filter_hash is not set, then we are decrementing. * That means we match anything that is in the hash * and also in the other_hash. That is, we need to turn * off functions in the other hash because they are disabled * by this hash. */ if (filter_hash && in_hash && !in_other_hash) match = 1; else if (!filter_hash && in_hash && (in_other_hash || ftrace_hash_empty(other_hash))) match = 1; } if (!match) continue; if (inc) { rec->flags++; if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) return; /* * If there's only a single callback registered to a * function, and the ops has a trampoline registered * for it, then we can call it directly. */ if (ftrace_rec_count(rec) == 1 && ops->trampoline) rec->flags |= FTRACE_FL_TRAMP; else /* * If we are adding another function callback * to this function, and the previous had a * custom trampoline in use, then we need to go * back to the default trampoline. */ rec->flags &= ~FTRACE_FL_TRAMP; /* * If any ops wants regs saved for this function * then all ops will get saved regs. */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0)) return; rec->flags--; /* * If the rec had REGS enabled and the ops that is * being removed had REGS set, then see if there is * still any ops for this record that wants regs. * If not, we can stop recording them. */ if (ftrace_rec_count(rec) > 0 && rec->flags & FTRACE_FL_REGS && ops->flags & FTRACE_OPS_FL_SAVE_REGS) { if (!test_rec_ops_needs_regs(rec)) rec->flags &= ~FTRACE_FL_REGS; } /* * If the rec had TRAMP enabled, then it needs to * be cleared. As TRAMP can only be enabled iff * there is only a single ops attached to it. * In otherwords, always disable it on decrementing. * In the future, we may set it if rec count is * decremented to one, and the ops that is left * has a trampoline. */ rec->flags &= ~FTRACE_FL_TRAMP; /* * flags will be cleared in ftrace_check_record() * if rec count is zero. */ } count++; /* Shortcut, if we handled all records, we are done. */ if (!all && count == hash->count) return; } while_for_each_ftrace_rec(); } static void ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash) { __ftrace_hash_rec_update(ops, filter_hash, 0); } static void ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash) { __ftrace_hash_rec_update(ops, filter_hash, 1); } static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops, int filter_hash, int inc) { struct ftrace_ops *op; __ftrace_hash_rec_update(ops, filter_hash, inc); if (ops->func_hash != &global_ops.local_hash) return; /* * If the ops shares the global_ops hash, then we need to update * all ops that are enabled and use this hash. */ do_for_each_ftrace_op(op, ftrace_ops_list) { /* Already done */ if (op == ops) continue; if (op->func_hash == &global_ops.local_hash) __ftrace_hash_rec_update(op, filter_hash, inc); } while_for_each_ftrace_op(op); } static void ftrace_hash_rec_disable_modify(struct ftrace_ops *ops, int filter_hash) { ftrace_hash_rec_update_modify(ops, filter_hash, 0); } static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash) { ftrace_hash_rec_update_modify(ops, filter_hash, 1); } /* * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK * or no-needed to update, -EBUSY if it detects a conflict of the flag * on a ftrace_rec, and -EINVAL if the new_hash tries to trace all recs. * Note that old_hash and new_hash has below meanings * - If the hash is NULL, it hits all recs (if IPMODIFY is set, this is rejected) * - If the hash is EMPTY_HASH, it hits nothing * - Anything else hits the recs which match the hash entries. */ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, struct ftrace_hash *old_hash, struct ftrace_hash *new_hash) { struct ftrace_page *pg; struct dyn_ftrace *rec, *end = NULL; int in_old, in_new; /* Only update if the ops has been registered */ if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) return 0; if (!(ops->flags & FTRACE_OPS_FL_IPMODIFY)) return 0; /* * Since the IPMODIFY is a very address sensitive action, we do not * allow ftrace_ops to set all functions to new hash. */ if (!new_hash || !old_hash) return -EINVAL; /* Update rec->flags */ do_for_each_ftrace_rec(pg, rec) { /* We need to update only differences of filter_hash */ in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); if (in_old == in_new) continue; if (in_new) { /* New entries must ensure no others are using it */ if (rec->flags & FTRACE_FL_IPMODIFY) goto rollback; rec->flags |= FTRACE_FL_IPMODIFY; } else /* Removed entry */ rec->flags &= ~FTRACE_FL_IPMODIFY; } while_for_each_ftrace_rec(); return 0; rollback: end = rec; /* Roll back what we did above */ do_for_each_ftrace_rec(pg, rec) { if (rec == end) goto err_out; in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); if (in_old == in_new) continue; if (in_new) rec->flags &= ~FTRACE_FL_IPMODIFY; else rec->flags |= FTRACE_FL_IPMODIFY; } while_for_each_ftrace_rec(); err_out: return -EBUSY; } static int ftrace_hash_ipmodify_enable(struct ftrace_ops *ops) { struct ftrace_hash *hash = ops->func_hash->filter_hash; if (ftrace_hash_empty(hash)) hash = NULL; return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash); } /* Disabling always succeeds */ static void ftrace_hash_ipmodify_disable(struct ftrace_ops *ops) { struct ftrace_hash *hash = ops->func_hash->filter_hash; if (ftrace_hash_empty(hash)) hash = NULL; __ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH); } static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, struct ftrace_hash *new_hash) { struct ftrace_hash *old_hash = ops->func_hash->filter_hash; if (ftrace_hash_empty(old_hash)) old_hash = NULL; if (ftrace_hash_empty(new_hash)) new_hash = NULL; return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash); } static void print_ip_ins(const char *fmt, unsigned char *p) { int i; printk(KERN_CONT "%s", fmt); for (i = 0; i < MCOUNT_INSN_SIZE; i++) printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); } static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); /** * ftrace_bug - report and shutdown function tracer * @failed: The failed type (EFAULT, EINVAL, EPERM) * @rec: The record that failed * * The arch code that enables or disables the function tracing * can call ftrace_bug() when it has detected a problem in * modifying the code. @failed should be one of either: * EFAULT - if the problem happens on reading the @ip address * EINVAL - if what is read at @ip is not what was expected * EPERM - if the problem happens on writting to the @ip address */ void ftrace_bug(int failed, struct dyn_ftrace *rec) { unsigned long ip = rec ? rec->ip : 0; switch (failed) { case -EFAULT: FTRACE_WARN_ON_ONCE(1); pr_info("ftrace faulted on modifying "); print_ip_sym(ip); break; case -EINVAL: FTRACE_WARN_ON_ONCE(1); pr_info("ftrace failed to modify "); print_ip_sym(ip); print_ip_ins(" actual: ", (unsigned char *)ip); pr_cont("\n"); break; case -EPERM: FTRACE_WARN_ON_ONCE(1); pr_info("ftrace faulted on writing "); print_ip_sym(ip); break; default: FTRACE_WARN_ON_ONCE(1); pr_info("ftrace faulted on unknown error "); print_ip_sym(ip); } if (rec) { struct ftrace_ops *ops = NULL; pr_info("ftrace record flags: %lx\n", rec->flags); pr_cont(" (%ld)%s", ftrace_rec_count(rec), rec->flags & FTRACE_FL_REGS ? " R" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) pr_cont("\ttramp: %pS", (void *)ops->trampoline); else pr_cont("\ttramp: ERROR!"); } ip = ftrace_get_addr_curr(rec); pr_cont(" expected tramp: %lx\n", ip); } } static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) { unsigned long flag = 0UL; /* * If we are updating calls: * * If the record has a ref count, then we need to enable it * because someone is using it. * * Otherwise we make sure its disabled. * * If we are disabling calls, then disable all records that * are enabled. */ if (enable && ftrace_rec_count(rec)) flag = FTRACE_FL_ENABLED; /* * If enabling and the REGS flag does not match the REGS_EN, or * the TRAMP flag doesn't match the TRAMP_EN, then do not ignore * this record. Set flags to fail the compare against ENABLED. */ if (flag) { if (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)) flag |= FTRACE_FL_REGS; if (!(rec->flags & FTRACE_FL_TRAMP) != !(rec->flags & FTRACE_FL_TRAMP_EN)) flag |= FTRACE_FL_TRAMP; } /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) return FTRACE_UPDATE_IGNORE; if (flag) { /* Save off if rec is being enabled (for return value) */ flag ^= rec->flags & FTRACE_FL_ENABLED; if (update) { rec->flags |= FTRACE_FL_ENABLED; if (flag & FTRACE_FL_REGS) { if (rec->flags & FTRACE_FL_REGS) rec->flags |= FTRACE_FL_REGS_EN; else rec->flags &= ~FTRACE_FL_REGS_EN; } if (flag & FTRACE_FL_TRAMP) { if (rec->flags & FTRACE_FL_TRAMP) rec->flags |= FTRACE_FL_TRAMP_EN; else rec->flags &= ~FTRACE_FL_TRAMP_EN; } } /* * If this record is being updated from a nop, then * return UPDATE_MAKE_CALL. * Otherwise, * return UPDATE_MODIFY_CALL to tell the caller to convert * from the save regs, to a non-save regs function or * vice versa, or from a trampoline call. */ if (flag & FTRACE_FL_ENABLED) return FTRACE_UPDATE_MAKE_CALL; return FTRACE_UPDATE_MODIFY_CALL; } if (update) { /* If there's no more users, clear all flags */ if (!ftrace_rec_count(rec)) rec->flags = 0; else /* * Just disable the record, but keep the ops TRAMP * and REGS states. The _EN flags must be disabled though. */ rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN | FTRACE_FL_REGS_EN); } return FTRACE_UPDATE_MAKE_NOP; } /** * ftrace_update_record, set a record that now is tracing or not * @rec: the record to update * @enable: set to 1 if the record is tracing, zero to force disable * * The records that represent all functions that can be traced need * to be updated when tracing has been enabled. */ int ftrace_update_record(struct dyn_ftrace *rec, int enable) { return ftrace_check_record(rec, enable, 1); } /** * ftrace_test_record, check if the record has been enabled or not * @rec: the record to test * @enable: set to 1 to check if enabled, 0 if it is disabled * * The arch code may need to test if a record is already set to * tracing to determine how to modify the function code that it * represents. */ int ftrace_test_record(struct dyn_ftrace *rec, int enable) { return ftrace_check_record(rec, enable, 0); } static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) { struct ftrace_ops *op; unsigned long ip = rec->ip; do_for_each_ftrace_op(op, ftrace_ops_list) { if (!op->trampoline) continue; if (hash_contains_ip(ip, op->func_hash)) return op; } while_for_each_ftrace_op(op); return NULL; } static struct ftrace_ops * ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec) { struct ftrace_ops *op; unsigned long ip = rec->ip; /* * Need to check removed ops first. * If they are being removed, and this rec has a tramp, * and this rec is in the ops list, then it would be the * one with the tramp. */ if (removed_ops) { if (hash_contains_ip(ip, &removed_ops->old_hash)) return removed_ops; } /* * Need to find the current trampoline for a rec. * Now, a trampoline is only attached to a rec if there * was a single 'ops' attached to it. But this can be called * when we are adding another op to the rec or removing the * current one. Thus, if the op is being added, we can * ignore it because it hasn't attached itself to the rec * yet. * * If an ops is being modified (hooking to different functions) * then we don't care about the new functions that are being * added, just the old ones (that are probably being removed). * * If we are adding an ops to a function that already is using * a trampoline, it needs to be removed (trampolines are only * for single ops connected), then an ops that is not being * modified also needs to be checked. */ do_for_each_ftrace_op(op, ftrace_ops_list) { if (!op->trampoline) continue; /* * If the ops is being added, it hasn't gotten to * the point to be removed from this tree yet. */ if (op->flags & FTRACE_OPS_FL_ADDING) continue; /* * If the ops is being modified and is in the old * hash, then it is probably being removed from this * function. */ if ((op->flags & FTRACE_OPS_FL_MODIFYING) && hash_contains_ip(ip, &op->old_hash)) return op; /* * If the ops is not being added or modified, and it's * in its normal filter hash, then this must be the one * we want! */ if (!(op->flags & FTRACE_OPS_FL_MODIFYING) && hash_contains_ip(ip, op->func_hash)) return op; } while_for_each_ftrace_op(op); return NULL; } static struct ftrace_ops * ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) { struct ftrace_ops *op; unsigned long ip = rec->ip; do_for_each_ftrace_op(op, ftrace_ops_list) { /* pass rec in as regs to have non-NULL val */ if (hash_contains_ip(ip, op->func_hash)) return op; } while_for_each_ftrace_op(op); return NULL; } /** * ftrace_get_addr_new - Get the call address to set to * @rec: The ftrace record descriptor * * If the record has the FTRACE_FL_REGS set, that means that it * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS * is not not set, then it wants to convert to the normal callback. * * Returns the address of the trampoline to set to */ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) { struct ftrace_ops *ops; /* Trampolines take precedence over regs */ if (rec->flags & FTRACE_FL_TRAMP) { ops = ftrace_find_tramp_ops_new(rec); if (FTRACE_WARN_ON(!ops || !ops->trampoline)) { pr_warn("Bad trampoline accounting at: %p (%pS) (%lx)\n", (void *)rec->ip, (void *)rec->ip, rec->flags); /* Ftrace is shutting down, return anything */ return (unsigned long)FTRACE_ADDR; } return ops->trampoline; } if (rec->flags & FTRACE_FL_REGS) return (unsigned long)FTRACE_REGS_ADDR; else return (unsigned long)FTRACE_ADDR; } /** * ftrace_get_addr_curr - Get the call address that is already there * @rec: The ftrace record descriptor * * The FTRACE_FL_REGS_EN is set when the record already points to * a function that saves all the regs. Basically the '_EN' version * represents the current state of the function. * * Returns the address of the trampoline that is currently being called */ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) { struct ftrace_ops *ops; /* Trampolines take precedence over regs */ if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_curr(rec); if (FTRACE_WARN_ON(!ops)) { pr_warning("Bad trampoline accounting at: %p (%pS)\n", (void *)rec->ip, (void *)rec->ip); /* Ftrace is shutting down, return anything */ return (unsigned long)FTRACE_ADDR; } return ops->trampoline; } if (rec->flags & FTRACE_FL_REGS_EN) return (unsigned long)FTRACE_REGS_ADDR; else return (unsigned long)FTRACE_ADDR; } static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_old_addr; unsigned long ftrace_addr; int ret; ftrace_addr = ftrace_get_addr_new(rec); /* This needs to be done before we call ftrace_update_record */ ftrace_old_addr = ftrace_get_addr_curr(rec); ret = ftrace_update_record(rec, enable); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; case FTRACE_UPDATE_MAKE_CALL: return ftrace_make_call(rec, ftrace_addr); case FTRACE_UPDATE_MAKE_NOP: return ftrace_make_nop(NULL, rec, ftrace_old_addr); case FTRACE_UPDATE_MODIFY_CALL: return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } return -1; /* unknow ftrace bug */ } void __weak ftrace_replace_code(int enable) { struct dyn_ftrace *rec; struct ftrace_page *pg; int failed; if (unlikely(ftrace_disabled)) return; do_for_each_ftrace_rec(pg, rec) { failed = __ftrace_replace_code(rec, enable); if (failed) { ftrace_bug(failed, rec); /* Stop processing */ return; } } while_for_each_ftrace_rec(); } struct ftrace_rec_iter { struct ftrace_page *pg; int index; }; /** * ftrace_rec_iter_start, start up iterating over traced functions * * Returns an iterator handle that is used to iterate over all * the records that represent address locations where functions * are traced. * * May return NULL if no records are available. */ struct ftrace_rec_iter *ftrace_rec_iter_start(void) { /* * We only use a single iterator. * Protected by the ftrace_lock mutex. */ static struct ftrace_rec_iter ftrace_rec_iter; struct ftrace_rec_iter *iter = &ftrace_rec_iter; iter->pg = ftrace_pages_start; iter->index = 0; /* Could have empty pages */ while (iter->pg && !iter->pg->index) iter->pg = iter->pg->next; if (!iter->pg) return NULL; return iter; } /** * ftrace_rec_iter_next, get the next record to process. * @iter: The handle to the iterator. * * Returns the next iterator after the given iterator @iter. */ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter) { iter->index++; if (iter->index >= iter->pg->index) { iter->pg = iter->pg->next; iter->index = 0; /* Could have empty pages */ while (iter->pg && !iter->pg->index) iter->pg = iter->pg->next; } if (!iter->pg) return NULL; return iter; } /** * ftrace_rec_iter_record, get the record at the iterator location * @iter: The current iterator location * * Returns the record that the current @iter is at. */ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) { return &iter->pg->records[iter->index]; } static int ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) { int ret; if (unlikely(ftrace_disabled)) return 0; ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, rec); return 0; } return 1; } /* * archs can override this function if they must do something * before the modifying code is performed. */ int __weak ftrace_arch_code_modify_prepare(void) { return 0; } /* * archs can override this function if they must do something * after the modifying code is performed. */ int __weak ftrace_arch_code_modify_post_process(void) { return 0; } void ftrace_modify_all_code(int command) { int update = command & FTRACE_UPDATE_TRACE_FUNC; int err = 0; /* * If the ftrace_caller calls a ftrace_ops func directly, * we need to make sure that it only traces functions it * expects to trace. When doing the switch of functions, * we need to update to the ftrace_ops_list_func first * before the transition between old and new calls are set, * as the ftrace_ops_list_func will check the ops hashes * to make sure the ops are having the right functions * traced. */ if (update) { err = ftrace_update_ftrace_func(ftrace_ops_list_func); if (FTRACE_WARN_ON(err)) return; } if (command & FTRACE_UPDATE_CALLS) ftrace_replace_code(1); else if (command & FTRACE_DISABLE_CALLS) ftrace_replace_code(0); if (update && ftrace_trace_function != ftrace_ops_list_func) { function_trace_op = set_function_trace_op; smp_wmb(); /* If irqs are disabled, we are in stop machine */ if (!irqs_disabled()) smp_call_function(ftrace_sync_ipi, NULL, 1); err = ftrace_update_ftrace_func(ftrace_trace_function); if (FTRACE_WARN_ON(err)) return; } if (command & FTRACE_START_FUNC_RET) err = ftrace_enable_ftrace_graph_caller(); else if (command & FTRACE_STOP_FUNC_RET) err = ftrace_disable_ftrace_graph_caller(); FTRACE_WARN_ON(err); } static int __ftrace_modify_code(void *data) { int *command = data; ftrace_modify_all_code(*command); return 0; } /** * ftrace_run_stop_machine, go back to the stop machine method * @command: The command to tell ftrace what to do * * If an arch needs to fall back to the stop machine method, the * it can call this function. */ void ftrace_run_stop_machine(int command) { stop_machine(__ftrace_modify_code, &command, NULL); } /** * arch_ftrace_update_code, modify the code to trace or not trace * @command: The command that needs to be done * * Archs can override this function if it does not need to * run stop_machine() to modify code. */ void __weak arch_ftrace_update_code(int command) { ftrace_run_stop_machine(command); } static void ftrace_run_update_code(int command) { int ret; ret = ftrace_arch_code_modify_prepare(); FTRACE_WARN_ON(ret); if (ret) return; /* * By default we use stop_machine() to modify the code. * But archs can do what ever they want as long as it * is safe. The stop_machine() is the safest, but also * produces the most overhead. */ arch_ftrace_update_code(command); ret = ftrace_arch_code_modify_post_process(); FTRACE_WARN_ON(ret); } static void ftrace_run_modify_code(struct ftrace_ops *ops, int command, struct ftrace_ops_hash *old_hash) { ops->flags |= FTRACE_OPS_FL_MODIFYING; ops->old_hash.filter_hash = old_hash->filter_hash; ops->old_hash.notrace_hash = old_hash->notrace_hash; ftrace_run_update_code(command); ops->old_hash.filter_hash = NULL; ops->old_hash.notrace_hash = NULL; ops->flags &= ~FTRACE_OPS_FL_MODIFYING; } static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops) { } static void control_ops_free(struct ftrace_ops *ops) { free_percpu(ops->disabled); } static void ftrace_startup_enable(int command) { if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; command |= FTRACE_UPDATE_TRACE_FUNC; } if (!command || !ftrace_enabled) return; ftrace_run_update_code(command); } static void ftrace_startup_all(int command) { update_all_ops = true; ftrace_startup_enable(command); update_all_ops = false; } static int ftrace_startup(struct ftrace_ops *ops, int command) { int ret; if (unlikely(ftrace_disabled)) return -ENODEV; ret = __register_ftrace_function(ops); if (ret) return ret; ftrace_start_up++; command |= FTRACE_UPDATE_CALLS; /* * Note that ftrace probes uses this to start up * and modify functions it will probe. But we still * set the ADDING flag for modification, as probes * do not have trampolines. If they add them in the * future, then the probes will need to distinguish * between adding and updating probes. */ ops->flags |= FTRACE_OPS_FL_ENABLED | FTRACE_OPS_FL_ADDING; ret = ftrace_hash_ipmodify_enable(ops); if (ret < 0) { /* Rollback registration process */ __unregister_ftrace_function(ops); ftrace_start_up--; ops->flags &= ~FTRACE_OPS_FL_ENABLED; return ret; } ftrace_hash_rec_enable(ops, 1); ftrace_startup_enable(command); ops->flags &= ~FTRACE_OPS_FL_ADDING; return 0; } static int ftrace_shutdown(struct ftrace_ops *ops, int command) { int ret; if (unlikely(ftrace_disabled)) return -ENODEV; ret = __unregister_ftrace_function(ops); if (ret) return ret; ftrace_start_up--; /* * Just warn in case of unbalance, no need to kill ftrace, it's not * critical but the ftrace_call callers may be never nopped again after * further ftrace uses. */ WARN_ON_ONCE(ftrace_start_up < 0); /* Disabling ipmodify never fails */ ftrace_hash_ipmodify_disable(ops); ftrace_hash_rec_disable(ops, 1); ops->flags &= ~FTRACE_OPS_FL_ENABLED; command |= FTRACE_UPDATE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; command |= FTRACE_UPDATE_TRACE_FUNC; } if (!command || !ftrace_enabled) { /* * If these are control ops, they still need their * per_cpu field freed. Since, function tracing is * not currently active, we can just free them * without synchronizing all CPUs. */ if (ops->flags & FTRACE_OPS_FL_CONTROL) control_ops_free(ops); return 0; } /* * If the ops uses a trampoline, then it needs to be * tested first on update. */ ops->flags |= FTRACE_OPS_FL_REMOVING; removed_ops = ops; /* The trampoline logic checks the old hashes */ ops->old_hash.filter_hash = ops->func_hash->filter_hash; ops->old_hash.notrace_hash = ops->func_hash->notrace_hash; ftrace_run_update_code(command); /* * If there's no more ops registered with ftrace, run a * sanity check to make sure all rec flags are cleared. */ if (ftrace_ops_list == &ftrace_list_end) { struct ftrace_page *pg; struct dyn_ftrace *rec; do_for_each_ftrace_rec(pg, rec) { if (FTRACE_WARN_ON_ONCE(rec->flags)) pr_warn(" %pS flags:%lx\n", (void *)rec->ip, rec->flags); } while_for_each_ftrace_rec(); } ops->old_hash.filter_hash = NULL; ops->old_hash.notrace_hash = NULL; removed_ops = NULL; ops->flags &= ~FTRACE_OPS_FL_REMOVING; /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. * The same g