diff options
Diffstat (limited to 'kernel/trace/trace_uprobe.c')
| -rw-r--r-- | kernel/trace/trace_uprobe.c | 940 |
1 files changed, 746 insertions, 194 deletions
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index c86e6d4f67f..3c9b97e6b1f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -28,47 +28,215 @@ #define UPROBE_EVENT_SYSTEM "uprobes" +struct uprobe_trace_entry_head { + struct trace_entry ent; + unsigned long vaddr[]; +}; + +#define SIZEOF_TRACE_ENTRY(is_return) \ + (sizeof(struct uprobe_trace_entry_head) + \ + sizeof(unsigned long) * (is_return ? 2 : 1)) + +#define DATAOF_TRACE_ENTRY(entry, is_return) \ + ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) + +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; unsigned long nhit; - unsigned int flags; /* For TP_FLAG_* */ - ssize_t size; /* trace entry size */ - unsigned int nr_args; - struct probe_arg args[]; + struct trace_probe tp; }; -#define SIZEOF_TRACE_UPROBE(n) \ - (offsetof(struct trace_uprobe, args) + \ +#define SIZEOF_TRACE_UPROBE(n) \ + (offsetof(struct trace_uprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) static int register_uprobe_event(struct trace_uprobe *tu); -static void unregister_uprobe_event(struct trace_uprobe *tu); +static int unregister_uprobe_event(struct trace_uprobe *tu); static DEFINE_MUTEX(uprobe_lock); static LIST_HEAD(uprobe_list); +struct uprobe_dispatch_data { + struct trace_uprobe *tu; + unsigned long bp_addr; +}; + static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); +static int uretprobe_dispatcher(struct uprobe_consumer *con, + unsigned long func, struct pt_regs *regs); + +#ifdef CONFIG_STACK_GROWSUP +static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) +{ + return addr - (n * sizeof(long)); +} +#else +static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) +{ + return addr + (n * sizeof(long)); +} +#endif + +static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long ret; + unsigned long addr = user_stack_pointer(regs); + + addr = adjust_stack_addr(addr, n); + + if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret))) + return 0; + + return ret; +} + +/* + * Uprobes-specific fetch functions + */ +#define DEFINE_FETCH_stack(type) \ +static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ + void *offset, void *dest) \ +{ \ + *(type *)dest = (type)get_user_stack_nth(regs, \ + ((unsigned long)offset)); \ +} +DEFINE_BASIC_FETCH_FUNCS(stack) +/* No string on the stack entry */ +#define fetch_stack_string NULL +#define fetch_stack_string_size NULL + +#define DEFINE_FETCH_memory(type) \ +static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ + void *addr, void *dest) \ +{ \ + type retval; \ + void __user *vaddr = (void __force __user *) addr; \ + \ + if (copy_from_user(&retval, vaddr, sizeof(type))) \ + *(type *)dest = 0; \ + else \ + *(type *) dest = retval; \ +} +DEFINE_BASIC_FETCH_FUNCS(memory) +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max + * length and relative data location. + */ +static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) +{ + long ret; + u32 rloc = *(u32 *)dest; + int maxlen = get_rloc_len(rloc); + u8 *dst = get_rloc_data(dest); + void __user *src = (void __force __user *) addr; + + if (!maxlen) + return; + + ret = strncpy_from_user(dst, src, maxlen); + + if (ret < 0) { /* Failed to fetch string */ + ((u8 *)get_rloc_data(dest))[0] = '\0'; + *(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc)); + } else { + *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc)); + } +} + +static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) +{ + int len; + void __user *vaddr = (void __force __user *) addr; + + len = strnlen_user(vaddr, MAX_STRING_SIZE); + + if (len == 0 || len > MAX_STRING_SIZE) /* Failed to check length */ + *(u32 *)dest = 0; + else + *(u32 *)dest = len; +} + +static unsigned long translate_user_vaddr(void *file_offset) +{ + unsigned long base_addr; + struct uprobe_dispatch_data *udd; + + udd = (void *) current->utask->vaddr; + + base_addr = udd->bp_addr - udd->tu->offset; + return base_addr + (unsigned long)file_offset; +} + +#define DEFINE_FETCH_file_offset(type) \ +static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs, \ + void *offset, void *dest)\ +{ \ + void *vaddr = (void *)translate_user_vaddr(offset); \ + \ + FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest); \ +} +DEFINE_BASIC_FETCH_FUNCS(file_offset) +DEFINE_FETCH_file_offset(string) +DEFINE_FETCH_file_offset(string_size) + +/* Fetch type information table */ +const struct fetch_type uprobes_fetch_type_table[] = { + /* Special types */ + [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, + sizeof(u32), 1, "__data_loc char[]"), + [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, + string_size, sizeof(u32), 0, "u32"), + /* Basic types */ + ASSIGN_FETCH_TYPE(u8, u8, 0), + ASSIGN_FETCH_TYPE(u16, u16, 0), + ASSIGN_FETCH_TYPE(u32, u32, 0), + ASSIGN_FETCH_TYPE(u64, u64, 0), + ASSIGN_FETCH_TYPE(s8, u8, 1), + ASSIGN_FETCH_TYPE(s16, u16, 1), + ASSIGN_FETCH_TYPE(s32, u32, 1), + ASSIGN_FETCH_TYPE(s64, u64, 1), + + ASSIGN_FETCH_TYPE_END +}; + +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); +} + +static inline bool is_ret_probe(struct trace_uprobe *tu) +{ + return tu->consumer.ret_handler != NULL; +} /* * Allocate new trace_uprobe and initialize it (including uprobes). */ static struct trace_uprobe * -alloc_trace_uprobe(const char *group, const char *event, int nargs) +alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; @@ -82,20 +250,26 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs) if (!tu) return ERR_PTR(-ENOMEM); - tu->call.class = &tu->class; - tu->call.name = kstrdup(event, GFP_KERNEL); - if (!tu->call.name) + tu->tp.call.class = &tu->tp.class; + tu->tp.call.name = kstrdup(event, GFP_KERNEL); + if (!tu->tp.call.name) goto error; - tu->class.system = kstrdup(group, GFP_KERNEL); - if (!tu->class.system) + tu->tp.class.system = kstrdup(group, GFP_KERNEL); + if (!tu->tp.class.system) goto error; INIT_LIST_HEAD(&tu->list); + INIT_LIST_HEAD(&tu->tp.files); + tu->consumer.handler = uprobe_dispatcher; + if (is_ret) + tu->consumer.ret_handler = uretprobe_dispatcher; + init_trace_uprobe_filter(&tu->filter); + tu->tp.call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER; return tu; error: - kfree(tu->call.name); + kfree(tu->tp.call.name); kfree(tu); return ERR_PTR(-ENOMEM); @@ -105,12 +279,12 @@ static void free_trace_uprobe(struct trace_uprobe *tu) { int i; - for (i = 0; i < tu->nr_args; i++) - traceprobe_free_probe_arg(&tu->args[i]); + for (i = 0; i < tu->tp.nr_args; i++) + traceprobe_free_probe_arg(&tu->tp.args[i]); iput(tu->inode); - kfree(tu->call.class->system); - kfree(tu->call.name); + kfree(tu->tp.call.class->system); + kfree(tu->tp.call.name); kfree(tu->filename); kfree(tu); } @@ -120,34 +294,44 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou struct trace_uprobe *tu; list_for_each_entry(tu, &uprobe_list, list) - if (strcmp(tu->call.name, event) == 0 && - strcmp(tu->call.class->system, group) == 0) + if (strcmp(ftrace_event_name(&tu->tp.call), event) == 0 && + strcmp(tu->tp.call.class->system, group) == 0) return tu; return NULL; } /* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ -static void unregister_trace_uprobe(struct trace_uprobe *tu) +static int unregister_trace_uprobe(struct trace_uprobe *tu) { + int ret; + + ret = unregister_uprobe_event(tu); + if (ret) + return ret; + list_del(&tu->list); - unregister_uprobe_event(tu); free_trace_uprobe(tu); + return 0; } /* Register a trace_uprobe and probe_event */ static int register_trace_uprobe(struct trace_uprobe *tu) { - struct trace_uprobe *old_tp; + struct trace_uprobe *old_tu; int ret; mutex_lock(&uprobe_lock); /* register as an event */ - old_tp = find_probe_event(tu->call.name, tu->call.class->system); - if (old_tp) + old_tu = find_probe_event(ftrace_event_name(&tu->tp.call), + tu->tp.call.class->system); + if (old_tu) { /* delete old event */ - unregister_trace_uprobe(old_tp); + ret = unregister_trace_uprobe(old_tu); + if (ret) + goto end; + } ret = register_uprobe_event(tu); if (ret) { @@ -165,7 +349,7 @@ end: /* * Argument syntax: - * - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS] + * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] * * - Remove uprobe: -:[GRP/]EVENT */ @@ -177,20 +361,23 @@ static int create_trace_uprobe(int argc, char **argv) char buf[MAX_EVENT_NAME_LEN]; struct path path; unsigned long offset; - bool is_delete; + bool is_delete, is_return; int i, ret; inode = NULL; ret = 0; is_delete = false; + is_return = false; event = NULL; group = NULL; /* argc must be >= 1 */ if (argv[0][0] == '-') is_delete = true; + else if (argv[0][0] == 'r') + is_return = true; else if (argv[0][0] != 'p') { - pr_info("Probe definition must be started with 'p' or '-'.\n"); + pr_info("Probe definition must be started with 'p', 'r' or '-'.\n"); return -EINVAL; } @@ -217,6 +404,8 @@ static int create_trace_uprobe(int argc, char **argv) group = UPROBE_EVENT_SYSTEM; if (is_delete) { + int ret; + if (!event) { pr_info("Delete command needs an event name.\n"); return -EINVAL; @@ -230,9 +419,9 @@ static int create_trace_uprobe(int argc, char **argv) return -ENOENT; } /* delete an event */ - unregister_trace_uprobe(tu); + ret = unregister_trace_uprobe(tu); mutex_unlock(&uprobe_lock); - return 0; + return ret; } if (argc < 2) { @@ -244,8 +433,10 @@ static int create_trace_uprobe(int argc, char **argv) return -EINVAL; } arg = strchr(argv[1], ':'); - if (!arg) + if (!arg) { + ret = -EINVAL; goto fail_address_parse; + } *arg++ = '\0'; filename = argv[1]; @@ -253,12 +444,18 @@ static int create_trace_uprobe(int argc, char **argv) if (ret) goto fail_address_parse; + inode = igrab(path.dentry->d_inode); + path_put(&path); + + if (!inode || !S_ISREG(inode->i_mode)) { + ret = -EINVAL; + goto fail_address_parse; + } + ret = kstrtoul(arg, 0, &offset); if (ret) goto fail_address_parse; - inode = igrab(path.dentry->d_inode); - argc -= 2; argv += 2; @@ -282,7 +479,7 @@ static int create_trace_uprobe(int argc, char **argv) kfree(tail); } - tu = alloc_trace_uprobe(group, event, argc); + tu = alloc_trace_uprobe(group, event, argc, is_return); if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); ret = PTR_ERR(tu); @@ -301,34 +498,36 @@ static int create_trace_uprobe(int argc, char **argv) /* parse arguments */ ret = 0; for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + struct probe_arg *parg = &tu->tp.args[i]; + /* Increment count for freeing args in error case */ - tu->nr_args++; + tu->tp.nr_args++; /* Parse argument name */ arg = strchr(argv[i], '='); if (arg) { *arg++ = '\0'; - tu->args[i].name = kstrdup(argv[i], GFP_KERNEL); + parg->name = kstrdup(argv[i], GFP_KERNEL); } else { arg = argv[i]; /* If argument name is omitted, set "argN" */ snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); - tu->args[i].name = kstrdup(buf, GFP_KERNEL); + parg->name = kstrdup(buf, GFP_KERNEL); } - if (!tu->args[i].name) { + if (!parg->name) { pr_info("Failed to allocate argument[%d] name.\n", i); ret = -ENOMEM; goto error; } - if (!is_good_name(tu->args[i].name)) { - pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name); + if (!is_good_name(parg->name)) { + pr_info("Invalid argument[%d] name: %s\n", i, parg->name); ret = -EINVAL; goto error; } - if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) { + if (traceprobe_conflict_field_name(parg->name, tu->tp.args, i)) { pr_info("Argument[%d] name '%s' conflicts with " "another field.\n", i, argv[i]); ret = -EINVAL; @@ -336,7 +535,8 @@ static int create_trace_uprobe(int argc, char **argv) } /* Parse fetch argument */ - ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false); + ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg, + is_return, false); if (ret) { pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; @@ -356,21 +556,25 @@ 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; } -static void cleanup_all_probes(void) +static int cleanup_all_probes(void) { struct trace_uprobe *tu; + int ret = 0; mutex_lock(&uprobe_lock); while (!list_empty(&uprobe_list)) { tu = list_entry(uprobe_list.next, struct trace_uprobe, list); - unregister_trace_uprobe(tu); + ret = unregister_trace_uprobe(tu); + if (ret) + break; } mutex_unlock(&uprobe_lock); + return ret; } /* Probes listing interfaces */ @@ -393,13 +597,15 @@ static void probes_seq_stop(struct seq_file *m, void *v) static int probes_seq_show(struct seq_file *m, void *v) { struct trace_uprobe *tu = v; + char c = is_ret_probe(tu) ? 'r' : 'p'; int i; - seq_printf(m, "p:%s/%s", tu->call.class->system, tu->call.name); + seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, + ftrace_event_name(&tu->tp.call)); seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); - for (i = 0; i < tu->nr_args; i++) - seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm); + for (i = 0; i < tu->tp.nr_args; i++) + seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); seq_printf(m, "\n"); return 0; @@ -414,8 +620,13 @@ static const struct seq_operations probes_seq_op = { static int probes_open(struct inode *inode, struct file *file) { - if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - cleanup_all_probes(); + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = cleanup_all_probes(); + if (ret) + return ret; + } return seq_open(file, &probes_seq_op); } @@ -440,7 +651,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_uprobe *tu = v; - seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit); + seq_printf(m, " %s %-44s %15lu\n", tu->filename, + ftrace_event_name(&tu->tp.call), tu->nhit); return 0; } @@ -464,65 +676,200 @@ static const struct file_operations uprobe_profile_ops = { .release = seq_release, }; -/* uprobe handler */ -static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +struct uprobe_cpu_buffer { + struct mutex mutex; + void *buf; +}; +static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; +static int uprobe_buffer_refcnt; + +static int uprobe_buffer_init(void) +{ + int cpu, err_cpu; + + uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer); + if (uprobe_cpu_buffer == NULL) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct page *p = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL, 0); + if (p == NULL) { + err_cpu = cpu; + goto err; + } + per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p); + mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex); + } + + return 0; + +err: + for_each_possible_cpu(cpu) { + if (cpu == err_cpu) + break; + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); + } + + free_percpu(uprobe_cpu_buffer); + return -ENOMEM; +} + +static int uprobe_buffer_enable(void) +{ + int ret = 0; + + BUG_ON(!mutex_is_locked(&event_mutex)); + + if (uprobe_buffer_refcnt++ == 0) { + ret = uprobe_buffer_init(); + if (ret < 0) + uprobe_buffer_refcnt--; + } + + return ret; +} + +static void uprobe_buffer_disable(void) +{ + int cpu; + + BUG_ON(!mutex_is_locked(&event_mutex)); + + if (--uprobe_buffer_refcnt == 0) { + for_each_possible_cpu(cpu) + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, + cpu)->buf); + + free_percpu(uprobe_cpu_buffer); + uprobe_cpu_buffer = NULL; + } +} + +static struct uprobe_cpu_buffer *uprobe_buffer_get(void) +{ + struct uprobe_cpu_buffer *ucb; + int cpu; + + cpu = raw_smp_processor_id(); + ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu); + + /* + * Use per-cpu buffers for fastest access, but we might migrate + * so the mutex makes sure we have sole access to it. + */ + mutex_lock(&ucb->mutex); + + return ucb; +} + +static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) +{ + mutex_unlock(&ucb->mutex); +} + +static void __uprobe_trace_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize, + struct ftrace_event_file *ftrace_file) { struct uprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; - u8 *data; - int size, i, pc; - unsigned long irq_flags; - struct ftrace_event_call *call = &tu->call; + void *data; + int size, esize; + struct ftrace_event_call *call = &tu->tp.call; - tu->nhit++; + WARN_ON(call != ftrace_file->event_call); - local_save_flags(irq_flags); - pc = preempt_count(); + if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) + return; - size = sizeof(*entry) + tu->size; + if (ftrace_trigger_soft_disabled(ftrace_file)) + return; - event = trace_current_buffer_lock_reserve(&buffer, call->event.type, - size, irq_flags, pc); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + size = esize + tu->tp.size + dsize; + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, + call->event.type, size, 0, 0); if (!event) return; entry = ring_buffer_event_data(event); - entry->ip = uprobe_get_swbp_addr(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 (is_ret_probe(tu)) { + entry->vaddr[0] = func; + entry->vaddr[1] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + entry->vaddr[0] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, false); + } + + memcpy(data, ucb->buf, tu->tp.size + dsize); + + event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0); +} + +/* uprobe handler */ +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + struct event_file_link *link; + + if (is_ret_probe(tu)) + return 0; - if (!filter_current_check_discard(buffer, call, entry, event)) - trace_buffer_unlock_commit(buffer, event, irq_flags, pc); + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); + rcu_read_unlock(); + + return 0; +} + +static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + struct event_file_link *link; + + rcu_read_lock(); + list_for_each_entry_rcu(link, &tu->tp.files, list) + __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); + rcu_read_unlock(); } /* Event entry printers */ static enum print_line_t print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { - struct uprobe_trace_entry_head *field; + struct uprobe_trace_entry_head *entry; struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; int i; - field = (struct uprobe_trace_entry_head *)iter->ent; - tu = container_of(event, struct trace_uprobe, call.event); - - if (!trace_seq_printf(s, "%s: (", tu->call.name)) - goto partial; + entry = (struct uprobe_trace_entry_head *)iter->ent; + tu = container_of(event, struct trace_uprobe, tp.call.event); - if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET)) - goto partial; + if (is_ret_probe(tu)) { + if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", + ftrace_event_name(&tu->tp.call), + entry->vaddr[1], entry->vaddr[0])) + goto partial; + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + if (!trace_seq_printf(s, "%s: (0x%lx)", + ftrace_event_name(&tu->tp.call), + entry->vaddr[0])) + goto partial; + data = DATAOF_TRACE_ENTRY(entry, false); + } - if (!trace_seq_puts(s, ")")) - goto partial; + for (i = 0; i < tu->tp.nr_args; i++) { + struct probe_arg *parg = &tu->tp.args[i]; - data = (u8 *)&field[1]; - for (i = 0; i < tu->nr_args; i++) { - if (!tu->args[i].type->print(s, tu->args[i].name, - data + tu->args[i].offset, field)) + if (!parg->type->print(s, parg->name, data + parg->offset, entry)) goto partial; } @@ -533,58 +880,118 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -static int probe_event_enable(struct trace_uprobe *tu, int flag) +typedef bool (*filter_func_t)(struct uprobe_consumer *self, + enum uprobe_filter_ctx ctx, + struct mm_struct *mm); + +static int +probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file, + filter_func_t filter) { - struct uprobe_trace_consumer *utc; - int ret = 0; + bool enabled = trace_probe_is_enabled(&tu->tp); + struct event_file_link *link = NULL; + int ret; - if (!tu->inode || tu->consumer) - return -EINTR; + if (file) { + if (tu->tp.flags & TP_FLAG_PROFILE) + return -EINTR; - utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL); - if (!utc) - return -EINTR; + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; - utc->cons.handler = uprobe_dispatcher; - utc->cons.filter = NULL; - ret = uprobe_register(tu->inode, tu->offset, &utc->cons); - if (ret) { - kfree(utc); - return ret; + link->file = file; + list_add_tail_rcu(&link->list, &tu->tp.files); + + tu->tp.flags |= TP_FLAG_TRACE; + } else { + if (tu->tp.flags & TP_FLAG_TRACE) + return -EINTR; + + tu->tp.flags |= TP_FLAG_PROFILE; } - tu->flags |= flag; - utc->tu = tu; - tu->consumer = utc; + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + + if (enabled) + return 0; + + ret = uprobe_buffer_enable(); + if (ret) + goto err_flags; + + tu->consumer.filter = filter; + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + if (ret) + goto err_buffer; return 0; + + err_buffer: + uprobe_buffer_disable(); + + err_flags: + if (file) { + list_del(&link->list); + kfree(link); + tu->tp.flags &= ~TP_FLAG_TRACE; + } else { + tu->tp.flags &= ~TP_FLAG_PROFILE; + } + return ret; } -static void probe_event_disable(struct trace_uprobe *tu, int flag) +static void +probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file) { - if (!tu->inode || !tu->consumer) + if (!trace_probe_is_enabled(&tu->tp)) return; - uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons); - tu->flags &= ~flag; - kfree(tu->consumer); - tu->consumer = NULL; + if (file) { + struct event_file_link *link; + + link = find_event_file_link(&tu->tp, file); + if (!link) + return; + + list_del_rcu(&link->list); + /* synchronize with u{,ret}probe_trace_func */ + synchronize_sched(); + kfree(link); + + if (!list_empty(&tu->tp.files)) + return; + } + + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer); + tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; + + uprobe_buffer_disable(); } static int uprobe_event_define_fields(struct ftrace_event_call *event_call) { - int ret, i; + int ret, i, size; struct uprobe_trace_entry_head field; - struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data; - - DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); + struct trace_uprobe *tu = event_call->data; + + if (is_ret_probe(tu)) { + DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); + DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0); + size = SIZEOF_TRACE_ENTRY(true); + } else { + DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); + size = SIZEOF_TRACE_ENTRY(false); + } /* Set argument names as fields */ - for (i = 0; i < tu->nr_args; i++) { - ret = trace_define_field(event_call, tu->args[i].type->fmttype, - tu->args[i].name, - sizeof(field) + tu->args[i].offset, - tu->args[i].type->size, - tu->args[i].type->is_signed, + for (i = 0; i < tu->tp.nr_args; i++) { + struct probe_arg *parg = &tu->tp.args[i]; + + ret = trace_define_field(event_call, parg->type->fmttype, + parg->name, size + parg->offset, + parg->type->size, parg->type->is_signed, FILTER_OTHER); if (ret) @@ -593,110 +1000,197 @@ static int uprobe_event_define_fields(struct ftrace_event_call *event_call) return 0; } -#define LEN_OR_ZERO (len ? len - pos : 0) -static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len) +#ifdef CONFIG_PERF_EVENTS +static bool +__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) { - const char *fmt, *arg; - int i; - int pos = 0; + struct perf_event *event; - fmt = "(%lx)"; - arg = "REC->" FIELD_STRING_IP; + if (filter->nr_systemwide) + return true; - /* When len=0, we just calculate the needed length */ + list_for_each_entry(event, &filter->perf_events, hw.tp_list) { + if (event->hw.tp_target->mm == mm) + return true; + } - pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); + return false; +} - for (i = 0; i < tu->nr_args; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s", - tu->args[i].name, tu->args[i].type->fmt); +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_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) + return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); - pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + return 0; +} - for (i = 0; i < tu->nr_args; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", - tu->args[i].name); +static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + int err; + + 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); - return pos; /* return the length of print_fmt */ + err = 0; + if (!done) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) + uprobe_perf_close(tu, event); + } + return err; } -#undef LEN_OR_ZERO -static int set_print_fmt(struct trace_uprobe *tu) +static bool uprobe_perf_filter(struct uprobe_consumer *uc, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) { - char *print_fmt; - int len; - - /* First: called with 0 length to calculate the needed length */ - len = __set_print_fmt(tu, NULL, 0); - print_fmt = kmalloc(len + 1, GFP_KERNEL); - if (!print_fmt) - return -ENOMEM; + struct trace_uprobe *tu; + int ret; - /* Second: actually write the @print_fmt */ - __set_print_fmt(tu, print_fmt, len + 1); - tu->call.print_fmt = print_fmt; + 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 0; + return ret; } -#ifdef CONFIG_PERF_EVENTS -/* uprobe profile handler */ -static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static void __uprobe_perf_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) { - struct ftrace_event_call *call = &tu->call; + struct ftrace_event_call *call = &tu->tp.call; struct uprobe_trace_entry_head *entry; struct hlist_head *head; - u8 *data; - int size, __size, i; + void *data; + int size, esize; int rctx; - __size = sizeof(*entry) + tu->size; - size = ALIGN(__size + sizeof(u32), sizeof(u64)); - size -= sizeof(u32); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + size = esize + tu->tp.size + dsize; + size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; preempt_disable(); + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + goto out; entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); if (!entry) goto out; - entry->ip = uprobe_get_swbp_addr(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 (is_ret_probe(tu)) { + entry->vaddr[0] = func; + entry->vaddr[1] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, true); + } else { + entry->vaddr[0] = instruction_pointer(regs); + data = DATAOF_TRACE_ENTRY(entry, false); + } + + memcpy(data, ucb->buf, tu->tp.size + dsize); - head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head, NULL); + if (size - esize > tu->tp.size + dsize) { + int len = tu->tp.size + dsize; + memset(data + len, 0, size - esize - len); + } + + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); out: preempt_enable(); } + +/* uprobe profile handler */ +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; + + if (!is_ret_probe(tu)) + __uprobe_perf_func(tu, 0, regs, ucb, dsize); + return 0; +} + +static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, + struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, int dsize) +{ + __uprobe_perf_func(tu, func, regs, ucb, dsize); +} #endif /* CONFIG_PERF_EVENTS */ -static -int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) +static int +trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, + void *data) { - struct trace_uprobe *tu = (struct trace_uprobe *)event->data; + struct trace_uprobe *tu = event->data; + struct ftrace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, TP_FLAG_TRACE); + return probe_event_enable(tu, file, NULL); case TRACE_REG_UNREGISTER: - probe_event_disable(tu, TP_FLAG_TRACE); + probe_event_disable(tu, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, TP_FLAG_PROFILE); + return probe_event_enable(tu, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: - probe_event_disable(tu, TP_FLAG_PROFILE); + probe_event_disable(tu, NULL); 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; @@ -706,21 +1200,73 @@ 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; + struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + int ret = 0; + + + tu = container_of(con, struct trace_uprobe, consumer); + tu->nhit++; + + udd.tu = tu; + udd.bp_addr = instruction_pointer(regs); + + current->utask->vaddr = (unsigned long) &udd; - utc = container_of(con, struct uprobe_trace_consumer, cons); - tu = utc->tu; - if (!tu || tu->consumer != utc) + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - if (tu->flags & TP_FLAG_TRACE) - uprobe_trace_func(tu, regs); + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + + if (tu->tp.flags & TP_FLAG_TRACE) + ret |= uprobe_trace_func(tu, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS - if (tu->flags & TP_FLAG_PROFILE) - uprobe_perf_func(tu, regs); + if (tu->tp.flags & TP_FLAG_PROFILE) + ret |= uprobe_perf_func(tu, regs, ucb, dsize); #endif + uprobe_buffer_put(ucb); + return ret; +} + +static int uretprobe_dispatcher(struct uprobe_consumer *con, + unsigned long func, struct pt_regs *regs) +{ + struct trace_uprobe *tu; + struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + + tu = container_of(con, struct trace_uprobe, consumer); + + udd.tu = tu; + udd.bp_addr = func; + + current->utask->vaddr = (unsigned long) &udd; + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + dsize = __get_data_size(&tu->tp, regs); + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + + ucb = uprobe_buffer_get(); + store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + + if (tu->tp.flags & TP_FLAG_TRACE) + uretprobe_trace_func(tu, func, regs, ucb, dsize); + +#ifdef CONFIG_PERF_EVENTS + if (tu->tp.flags & TP_FLAG_PROFILE) + uretprobe_perf_func(tu, func, regs, ucb, dsize); +#endif + uprobe_buffer_put(ucb); return 0; } @@ -730,7 +1276,7 @@ static struct trace_event_functions uprobe_funcs = { static int register_uprobe_event(struct trace_uprobe *tu) { - struct ftrace_event_call *call = &tu->call; + struct ftrace_event_call *call = &tu->tp.call; int ret; /* Initialize ftrace_event_call */ @@ -738,7 +1284,7 @@ static int register_uprobe_event(struct trace_uprobe *tu) call->event.funcs = &uprobe_funcs; call->class->define_fields = uprobe_event_define_fields; - if (set_print_fmt(tu) < 0) + if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) return -ENOMEM; ret = register_ftrace_event(&call->event); @@ -752,7 +1298,8 @@ static int register_uprobe_event(struct trace_uprobe *tu) ret = trace_add_event_call(call); if (ret) { - pr_info("Failed to register uprobe event: %s\n", call->name); + pr_info("Failed to register uprobe event: %s\n", + ftrace_event_name(call)); kfree(call->print_fmt); unregister_ftrace_event(&call->event); } @@ -760,12 +1307,17 @@ static int register_uprobe_event(struct trace_uprobe *tu) return ret; } -static void unregister_uprobe_event(struct trace_uprobe *tu) +static int unregister_uprobe_event(struct trace_uprobe *tu) { + int ret; + /* tu->event is unregistered in trace_remove_event_call() */ - trace_remove_event_call(&tu->call); - kfree(tu->call.print_fmt); - tu->call.print_fmt = NULL; + ret = trace_remove_event_call(&tu->tp.call); + if (ret) + return ret; + kfree(tu->tp.call.print_fmt); + tu->tp.call.print_fmt = NULL; + return 0; } /* Make a trace interface for controling probe points */ |
