// SPDX-License-Identifier: GPL-2.0/* * event tracer * * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> * * - Added format output of fields of the trace point. * This was based off of work by Tom Zanussi <tzanussi@gmail.com>. * */ #define pr_fmt(fmt) fmt #include <linux/workqueue.h>#include <linux/security.h>#include <linux/spinlock.h>#include <linux/kthread.h>#include <linux/tracefs.h>#include <linux/uaccess.h>#include <linux/module.h>#include <linux/ctype.h>#include <linux/sort.h>#include <linux/slab.h>#include <linux/delay.h> #include <trace/events/sched.h>#include <trace/syscall.h> #include <asm/setup.h> #include "trace_output.h" #undef TRACE_SYSTEM#define TRACE_SYSTEM "TRACE_SYSTEM" DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events);static LIST_HEAD(ftrace_generic_fields);static LIST_HEAD(ftrace_common_fields);static bool eventdir_initialized; static LIST_HEAD(module_strings); struct module_string { struct list_head next; struct module *module; char *str;}; #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) static struct kmem_cache *field_cachep;static struct kmem_cache *file_cachep; static inline int system_refcount(struct event_subsystem *system){ return system->ref_count;} static int system_refcount_inc(struct event_subsystem *system){ return system->ref_count++;} static int system_refcount_dec(struct event_subsystem *system){ return --system->ref_count;} /* Double loops, do not use break, only goto's work */#define do_for_each_event_file(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ list_for_each_entry(file, &tr->events, list) #define do_for_each_event_file_safe(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ struct trace_event_file *___n; \ list_for_each_entry_safe(file, ___n, &tr->events, list) #define while_for_each_event_file() \ } static struct ftrace_event_field *__find_event_field(struct list_head *head, char *name){ struct ftrace_event_field *field; list_for_each_entry(field, head, link) { if (!strcmp(field->name, name)) return field; } return NULL;} struct ftrace_event_field *trace_find_event_field(struct trace_event_call *call, char *name){ struct ftrace_event_field *field; struct list_head *head; head = trace_get_fields(call); field = __find_event_field(head, name); if (field) return field; field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; return __find_event_field(&ftrace_common_fields, name);} static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len){ struct ftrace_event_field *field; field = kmem_cache_alloc(field_cachep, GFP_TRACE); if (!field) return -ENOMEM; field->name = name; field->type = type; if (filter_type == FILTER_OTHER) field->filter_type = filter_assign_type(type); else field->filter_type = filter_type; field->offset = offset; field->size = size; field->is_signed = is_signed; field->len = len; list_add(&field->link, head); return 0;} int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type){ struct list_head *head; if (WARN_ON(!call->class)) return 0; head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, is_signed, filter_type, 0);}EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len){ struct list_head *head; if (WARN_ON(!call->class)) return 0; head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, is_signed, filter_type, len);} #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ filter_type, 0); \ if (ret) \ return ret; #define __common_field(type, item) \ ret = __trace_define_field(&ftrace_common_fields, #type, \ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ is_signed_type(type), FILTER_OTHER, 0); \ if (ret) \ return ret; static int trace_define_generic_fields(void){ int ret; __generic_field(int, CPU, FILTER_CPU); __generic_field(int, cpu, FILTER_CPU); __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); return ret;} static int trace_define_common_fields(void){ int ret; struct trace_entry ent; __common_field(unsigned short, type); __common_field(unsigned char, flags); /* Holds both preempt_count and migrate_disable */ __common_field(unsigned char, preempt_count); __common_field(int, pid); return ret;} static void trace_destroy_fields(struct trace_event_call *call){ struct ftrace_event_field *field, *next; struct list_head *head; head = trace_get_fields(call); list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); kmem_cache_free(field_cachep, field); }} /* * run-time version of trace_event_get_offsets_<call>() that returns the last * accessible offset of trace fields excluding __dynamic_array bytes */int trace_event_get_offsets(struct trace_event_call *call){ struct ftrace_event_field *tail; struct list_head *head; head = trace_get_fields(call); /* * head->next points to the last field with the largest offset, * since it was added last by trace_define_field() */ tail = list_first_entry(head, struct ftrace_event_field, link); return tail->offset + tail->size;} /* * Check if the referenced field is an array and return true, * as arrays are OK to dereference. */static bool test_field(const char *fmt, struct trace_event_call *call){ struct trace_event_fields *field = call->class->fields_array; const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) return false; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') break; } len = p - fmt; for (; field->type; field++) { if (strncmp(field->name, fmt, len) || field->name[len]) continue; array_descriptor = strchr(field->type, '['); /* This is an array and is OK to dereference. */ return array_descriptor != NULL; } return false;} /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and * much later referenced after the pointer was freed. Dereferencing * pointers are OK, if it is dereferenced into the event itself. */static void test_event_printk(struct trace_event_call *call){ u64 dereference_flags = 0; bool first = true; const char *fmt, *c, *r, *a; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; int i; fmt = call->print_fmt; if (!fmt) return; for (i = 0; fmt[i]; i++) { switch (fmt[i]) { case '\\': i++; if (!fmt[i]) return; continue; case '"': case '\'': /* * The print fmt starts with a string that * is processed first to find %p* usage, * then after the first string, the print fmt * contains arguments that are used to check * if the dereferenced %p* usage is safe. */ if (first) { if (fmt[i] == '\'') continue; if (in_quote) { arg = 0; first = false; /* * If there was no %p* uses * the fmt is OK. */ if (!dereference_flags) return; } } if (in_quote) { if (in_quote == fmt[i]) in_quote = 0; } else { in_quote = fmt[i]; } continue; case '%': if (!first || !in_quote) continue; i++; if (!fmt[i]) return; switch (fmt[i]) { case '%': continue; case 'p': /* Find dereferencing fields */ switch (fmt[i + 1]) { case 'B': case 'R': case 'r': case 'b': case 'M': case 'm': case 'I': case 'i': case 'E': case 'U': case 'V': case 'N': case 'a': case 'd': case 'D': case 'g': case 't': case 'C': case 'O': case 'f': if (WARN_ONCE(arg == 63, "Too many args for event: %s", trace_event_name(call))) return; dereference_flags |= 1ULL << arg; } break; default: { bool star = false; int j; /* Increment arg if %*s exists. */ for (j = 0; fmt[i + j]; j++) { if (isdigit(fmt[i + j]) || fmt[i + j] == '.') continue; if (fmt[i + j] == '*') { star = true; continue; } if ((fmt[i + j] == 's') && star) arg++; break; } break; } /* default */ } /* switch */ arg++; continue; case '(': if (in_quote) continue; parens++; continue; case ')': if (in_quote) continue; parens--; if (WARN_ONCE(parens < 0, "Paren mismatch for event: %s\narg='%s'\n%*s", trace_event_name(call), fmt + start_arg, (i - start_arg) + 5, "^")) return; continue; case ',': if (in_quote || parens) continue; i++; while (isspace(fmt[i])) i++; start_arg = i; if (!(dereference_flags & (1ULL << arg))) goto next_arg; /* Find the REC-> in the argument */ c = strchr(fmt + i, ','); r = strstr(fmt + i, "REC->"); if (r && (!c || r < c)) { /* * Addresses of events on the buffer, * or an array on the buffer is * OK to dereference. * There's ways to fool this, but * this is to catch common mistakes, * not malicious code. */ a = strchr(fmt + i, '&'); if ((a && (a < r)) || test_field(r, call)) dereference_flags &= ~(1ULL << arg); } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && (!c || r < c)) { dereference_flags &= ~(1ULL << arg); } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && (!c || r < c)) { dereference_flags &= ~(1ULL << arg); } next_arg: i--; arg++; } } /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored * at the trace event time may no longer exist when the trace * event is printed, dereferencing to the original source is * unsafe. The source of the dereference must be copied into the * event itself, and the dereference must access the copy instead. */ if (WARN_ON_ONCE(dereference_flags)) { arg = 1; while (!(dereference_flags & 1)) { dereference_flags >>= 1; arg++; } pr_warn("event %s has unsafe dereference of argument %d\n", trace_event_name(call), arg); pr_warn("print_fmt: %s\n", fmt); }} int trace_event_raw_init(struct trace_event_call *call){ int id; id = register_trace_event(&call->event); if (!id) return -ENODEV; test_event_printk(call); return 0;}EXPORT_SYMBOL_GPL(trace_event_raw_init); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file){ struct trace_array *tr = trace_file->tr; struct trace_array_cpu *data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; pid_list = rcu_dereference_raw(tr->filtered_pids); no_pid_list = rcu_dereference_raw(tr->filtered_no_pids); if (!pid_list && !no_pid_list) return false; data = this_cpu_ptr(tr->array_buffer.data); return data->ignore_pid;}EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid); void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, struct trace_event_file *trace_file, unsigned long len){ struct trace_event_call *event_call = trace_file->event_call; if ((trace_file->flags & EVENT_FILE_FL_PID_FILTER) && trace_event_ignore_this_pid(trace_file))Lines 1–500 of 4160. Load more
// SPDX-License-Identifier: GPL-2.0 /* * event tracer * * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> * * - Added format output of fields of the trace point. * This was based off of work by Tom Zanussi <tzanussi@gmail.com>. * */ #define pr_fmt(fmt) fmt #include <linux/workqueue.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/tracefs.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/delay.h> #include <trace/events/sched.h> #include <trace/syscall.h> #include <asm/setup.h> #include "trace_output.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM "TRACE_SYSTEM" DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events); static LIST_HEAD(ftrace_generic_fields); static LIST_HEAD(ftrace_common_fields); static bool eventdir_initialized; static LIST_HEAD(module_strings); struct module_string { struct list_head next; struct module *module; char *str; }; #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) static struct kmem_cache *field_cachep; static struct kmem_cache *file_cachep; static inline int system_refcount(struct event_subsystem *system) { return system->ref_count; } static int system_refcount_inc(struct event_subsystem *system) { return system->ref_count++; } static int system_refcount_dec(struct event_subsystem *system) { return --system->ref_count; } /* Double loops, do not use break, only goto's work */ #define do_for_each_event_file(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ list_for_each_entry(file, &tr->events, list) #define do_for_each_event_file_safe(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ struct trace_event_file *___n; \ list_for_each_entry_safe(file, ___n, &tr->events, list) #define while_for_each_event_file() \ } static struct ftrace_event_field * __find_event_field(struct list_head *head, char *name) { struct ftrace_event_field *field; list_for_each_entry(field, head, link) { if (!strcmp(field->name, name)) return field; } return NULL; } struct ftrace_event_field * trace_find_event_field(struct trace_event_call *call, char *name) { struct ftrace_event_field *field; struct list_head *head; head = trace_get_fields(call); field = __find_event_field(head, name); if (field) return field; field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len) { struct ftrace_event_field *field; field = kmem_cache_alloc(field_cachep, GFP_TRACE); if (!field) return -ENOMEM; field->name = name; field->type = type; if (filter_type == FILTER_OTHER) field->filter_type = filter_assign_type(type); else field->filter_type = filter_type; field->offset = offset; field->size = size; field->is_signed = is_signed; field->len = len; list_add(&field->link, head); return 0; } int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type) { struct list_head *head; if (WARN_ON(!call->class)) return 0; head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, is_signed, filter_type, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len) { struct list_head *head; if (WARN_ON(!call->class)) return 0; head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, is_signed, filter_type, len); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ filter_type, 0); \ if (ret) \ return ret; #define __common_field(type, item) \ ret = __trace_define_field(&ftrace_common_fields, #type, \ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ is_signed_type(type), FILTER_OTHER, 0); \ if (ret) \ return ret; static int trace_define_generic_fields(void) { int ret; __generic_field(int, CPU, FILTER_CPU); __generic_field(int, cpu, FILTER_CPU); __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); return ret; } static int trace_define_common_fields(void) { int ret; struct trace_entry ent; __common_field(unsigned short, type); __common_field(unsigned char, flags); /* Holds both preempt_count and migrate_disable */ __common_field(unsigned char, preempt_count); __common_field(int, pid); return ret; } static void trace_destroy_fields(struct trace_event_call *call) { struct ftrace_event_field *field, *next; struct list_head *head; head = trace_get_fields(call); list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); kmem_cache_free(field_cachep, field); } } /* * run-time version of trace_event_get_offsets_<call>() that returns the last * accessible offset of trace fields excluding __dynamic_array bytes */ int trace_event_get_offsets(struct trace_event_call *call) { struct ftrace_event_field *tail; struct list_head *head; head = trace_get_fields(call); /* * head->next points to the last field with the largest offset, * since it was added last by trace_define_field() */ tail = list_first_entry(head, struct ftrace_event_field, link); return tail->offset + tail->size; } /* * Check if the referenced field is an array and return true, * as arrays are OK to dereference. */ static bool test_field(const char *fmt, struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) return false; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') break; } len = p - fmt; for (; field->type; field++) { if (strncmp(field->name, fmt, len) || field->name[len]) continue; array_descriptor = strchr(field->type, '['); /* This is an array and is OK to dereference. */ return array_descriptor != NULL; } return false; } /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and * much later referenced after the pointer was freed. Dereferencing * pointers are OK, if it is dereferenced into the event itself. */ static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; bool first = true; const char *fmt, *c, *r, *a; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; int i; fmt = call->print_fmt; if (!fmt) return; for (i = 0; fmt[i]; i++) { switch (fmt[i]) { case '\\': i++; if (!fmt[i]) return; continue; case '"': case '\'': /* * The print fmt starts with a string that * is processed first to find %p* usage, * then after the first string, the print fmt * contains arguments that are used to check * if the dereferenced %p* usage is safe. */ if (first) { if (fmt[i] == '\'') continue; if (in_quote) { arg = 0; first = false; /* * If there was no %p* uses * the fmt is OK. */ if (!dereference_flags) return; } } if (in_quote) { if (in_quote == fmt[i]) in_quote = 0; } else { in_quote = fmt[i]; } continue; case '%': if (!first || !in_quote) continue; i++; if (!fmt[i]) return; switch (fmt[i]) { case '%': continue; case 'p': /* Find dereferencing fields */ switch (fmt[i + 1]) { case 'B': case 'R': case 'r': case 'b': case 'M': case 'm': case 'I': case 'i': case 'E': case 'U': case 'V': case 'N': case 'a': case 'd': case 'D': case 'g': case 't': case 'C': case 'O': case 'f': if (WARN_ONCE(arg == 63, "Too many args for event: %s", trace_event_name(call))) return; dereference_flags |= 1ULL << arg; } break; default: { bool star = false; int j; /* Increment arg if %*s exists. */ for (j = 0; fmt[i + j]; j++) { if (isdigit(fmt[i + j]) || fmt[i + j] == '.') continue; if (fmt[i + j] == '*') { star = true; continue; } if ((fmt[i + j] == 's') && star) arg++; break; } break; } /* default */ } /* switch */ arg++; continue; case '(': if (in_quote) continue; parens++; continue; case ')': if (in_quote) continue; parens--; if (WARN_ONCE(parens < 0, "Paren mismatch for event: %s\narg='%s'\n%*s", trace_event_name(call), fmt + start_arg, (i - start_arg) + 5, "^")) return; continue; case ',': if (in_quote || parens) continue; i++; while (isspace(fmt[i])) i++; start_arg = i; if (!(dereference_flags & (1ULL << arg))) goto next_arg; /* Find the REC-> in the argument */ c = strchr(fmt + i, ','); r = strstr(fmt + i, "REC->"); if (r && (!c || r < c)) { /* * Addresses of events on the buffer, * or an array on the buffer is * OK to dereference. * There's ways to fool this, but * this is to catch common mistakes, * not malicious code. */ a = strchr(fmt + i, '&'); if ((a && (a < r)) || test_field(r, call)) dereference_flags &= ~(1ULL << arg); } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && (!c || r < c)) { dereference_flags &= ~(1ULL << arg); } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && (!c || r < c)) { dereference_flags &= ~(1ULL << arg); } next_arg: i--; arg++; } } /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored * at the trace event time may no longer exist when the trace * event is printed, dereferencing to the original source is * unsafe. The source of the dereference must be copied into the * event itself, and the dereference must access the copy instead. */ if (WARN_ON_ONCE(dereference_flags)) { arg = 1; while (!(dereference_flags & 1)) { dereference_flags >>= 1; arg++; } pr_warn("event %s has unsafe dereference of argument %d\n", trace_event_name(call), arg); pr_warn("print_fmt: %s\n", fmt); } } int trace_event_raw_init(struct trace_event_call *call) { int id; id = register_trace_event(&call->event); if (!id) return -ENODEV; test_event_printk(call); return 0; } EXPORT_SYMBOL_GPL(trace_event_raw_init); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file) { struct trace_array *tr = trace_file->tr; struct trace_array_cpu *data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; pid_list = rcu_dereference_raw(tr->filtered_pids); no_pid_list = rcu_dereference_raw(tr->filtered_no_pids); if (!pid_list && !no_pid_list) return false; data = this_cpu_ptr(tr->array_buffer.data); return data->ignore_pid; } EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid); void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, struct trace_event_file *trace_file, unsigned long len) { struct trace_event_call *event_call = trace_file->event_call; if ((trace_file->flags & EVENT_FILE_FL_PID_FILTER) && trace_event_ignore_this_pid(trace_file))