diff options
Diffstat (limited to 'kernel/trace/trace_uprobe.c')
| -rw-r--r-- | kernel/trace/trace_uprobe.c | 1714 |
1 files changed, 1213 insertions, 501 deletions
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index d5d0cd368a56..1b4f32e2b9bd 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1,30 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 /* * uprobes-based tracing events * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ +#define pr_fmt(fmt) "trace_uprobe: " fmt +#include <linux/bpf-cgroup.h> +#include <linux/cleanup.h> +#include <linux/ctype.h> +#include <linux/filter.h> #include <linux/module.h> -#include <linux/uaccess.h> -#include <linux/uprobes.h> #include <linux/namei.h> +#include <linux/percpu.h> +#include <linux/rculist.h> +#include <linux/security.h> #include <linux/string.h> +#include <linux/uaccess.h> +#include <linux/uprobes.h> +#include "trace.h" +#include "trace_dynevent.h" #include "trace_probe.h" +#include "trace_probe_tmpl.h" #define UPROBE_EVENT_SYSTEM "uprobes" @@ -40,44 +39,220 @@ struct uprobe_trace_entry_head { #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; +static int trace_uprobe_create(const char *raw_command); +static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); +static int trace_uprobe_release(struct dyn_event *ev); +static bool trace_uprobe_is_busy(struct dyn_event *ev); +static bool trace_uprobe_match(const char *system, const char *event, + int argc, const char **argv, struct dyn_event *ev); + +static struct dyn_event_operations trace_uprobe_ops = { + .create = trace_uprobe_create, + .show = trace_uprobe_show, + .is_busy = trace_uprobe_is_busy, + .free = trace_uprobe_release, + .match = trace_uprobe_match, }; /* * uprobe event core functions */ struct trace_uprobe { - struct list_head list; - struct ftrace_event_class class; - struct ftrace_event_call call; - struct trace_uprobe_filter filter; + struct dyn_event devent; struct uprobe_consumer consumer; - struct inode *inode; + struct path path; char *filename; + struct uprobe *uprobe; 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[]; + unsigned long ref_ctr_offset; + unsigned long __percpu *nhits; + struct trace_probe tp; }; -#define SIZEOF_TRACE_UPROBE(n) \ - (offsetof(struct trace_uprobe, args) + \ - (sizeof(struct probe_arg) * (n))) +static bool is_trace_uprobe(struct dyn_event *ev) +{ + return ev->ops == &trace_uprobe_ops; +} -static int register_uprobe_event(struct trace_uprobe *tu); -static void unregister_uprobe_event(struct trace_uprobe *tu); +static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) +{ + return container_of(ev, struct trace_uprobe, devent); +} + +/** + * for_each_trace_uprobe - iterate over the trace_uprobe list + * @pos: the struct trace_uprobe * for each entry + * @dpos: the struct dyn_event * to use as a loop cursor + */ +#define for_each_trace_uprobe(pos, dpos) \ + for_each_dyn_event(dpos) \ + if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos))) -static DEFINE_MUTEX(uprobe_lock); -static LIST_HEAD(uprobe_list); +static int register_uprobe_event(struct trace_uprobe *tu); +static int unregister_uprobe_event(struct trace_uprobe *tu); -static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs, + __u64 *data); static int uretprobe_dispatcher(struct uprobe_consumer *con, - unsigned long func, struct pt_regs *regs); + unsigned long func, struct pt_regs *regs, + __u64 *data); + +#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 + */ +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size) +{ + void __user *vaddr = (void __force __user *)src; + + return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; +} + +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size) +{ + return probe_mem_read(dest, src, size); +} + +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max + * length and relative data location. + */ +static nokprobe_inline int +fetch_store_string(unsigned long addr, void *dest, void *base) +{ + long ret; + u32 loc = *(u32 *)dest; + int maxlen = get_loc_len(loc); + u8 *dst = get_loc_data(dest, base); + void __user *src = (void __force __user *) addr; + + if (unlikely(!maxlen)) + return -ENOMEM; + + if (addr == FETCH_TOKEN_COMM) + ret = strscpy(dst, current->comm, maxlen); + else + ret = strncpy_from_user(dst, src, maxlen); + if (ret >= 0) { + if (ret == maxlen) + dst[ret - 1] = '\0'; + else + /* + * Include the terminating null byte. In this case it + * was copied by strncpy_from_user but not accounted + * for in ret. + */ + ret++; + *(u32 *)dest = make_data_loc(ret, (void *)dst - base); + } else + *(u32 *)dest = make_data_loc(0, (void *)dst - base); + + return ret; +} + +static nokprobe_inline int +fetch_store_string_user(unsigned long addr, void *dest, void *base) +{ + return fetch_store_string(addr, dest, base); +} + +/* Return the length of string -- including null terminal byte */ +static nokprobe_inline int +fetch_store_strlen(unsigned long addr) +{ + int len; + void __user *vaddr = (void __force __user *) addr; + + if (addr == FETCH_TOKEN_COMM) + len = strlen(current->comm) + 1; + else + len = strnlen_user(vaddr, MAX_STRING_SIZE); + + return (len > MAX_STRING_SIZE) ? 0 : len; +} + +static nokprobe_inline int +fetch_store_strlen_user(unsigned long addr) +{ + return fetch_store_strlen(addr); +} + +static unsigned long translate_user_vaddr(unsigned long 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 + file_offset; +} + +/* Note that we don't verify it, since the code does not come from user space */ +static int +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) +{ + struct pt_regs *regs = rec; + unsigned long val; + int ret; + + /* 1st stage: get value from context */ + switch (code->op) { + case FETCH_OP_REG: + val = regs_get_register(regs, code->param); + break; + case FETCH_OP_STACK: + val = get_user_stack_nth(regs, code->param); + break; + case FETCH_OP_STACKP: + val = user_stack_pointer(regs); + break; + case FETCH_OP_RETVAL: + val = regs_return_value(regs); + break; + case FETCH_OP_COMM: + val = FETCH_TOKEN_COMM; + break; + case FETCH_OP_FOFFS: + val = translate_user_vaddr(code->immediate); + break; + default: + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; + } + code++; + + return process_fetch_insn_bottom(code, val, dest, base); +} +NOKPROBE_SYMBOL(process_fetch_insn) static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { @@ -96,6 +271,64 @@ static inline bool is_ret_probe(struct trace_uprobe *tu) return tu->consumer.ret_handler != NULL; } +static bool trace_uprobe_is_busy(struct dyn_event *ev) +{ + struct trace_uprobe *tu = to_trace_uprobe(ev); + + return trace_probe_is_enabled(&tu->tp); +} + +static bool trace_uprobe_match_command_head(struct trace_uprobe *tu, + int argc, const char **argv) +{ + char buf[MAX_ARGSTR_LEN + 1]; + int len; + + if (!argc) + return true; + + len = strlen(tu->filename); + if (strncmp(tu->filename, argv[0], len) || argv[0][len] != ':') + return false; + + if (tu->ref_ctr_offset == 0) + snprintf(buf, sizeof(buf), "0x%0*lx", + (int)(sizeof(void *) * 2), tu->offset); + else + snprintf(buf, sizeof(buf), "0x%0*lx(0x%lx)", + (int)(sizeof(void *) * 2), tu->offset, + tu->ref_ctr_offset); + if (strcmp(buf, &argv[0][len + 1])) + return false; + + argc--; argv++; + + return trace_probe_match_command_args(&tu->tp, argc, argv); +} + +static bool trace_uprobe_match(const char *system, const char *event, + int argc, const char **argv, struct dyn_event *ev) +{ + struct trace_uprobe *tu = to_trace_uprobe(ev); + + return (event[0] == '\0' || + strcmp(trace_probe_name(&tu->tp), event) == 0) && + (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) && + trace_uprobe_match_command_head(tu, argc, argv); +} + +static nokprobe_inline struct trace_uprobe * +trace_uprobe_primary_from_call(struct trace_event_call *call) +{ + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return NULL; + + return container_of(tp, struct trace_uprobe, tp); +} + /* * Allocate new trace_uprobe and initialize it (including uprobes). */ @@ -103,367 +336,468 @@ static struct trace_uprobe * alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; + int ret; - if (!event || !is_good_name(event)) - return ERR_PTR(-EINVAL); - - if (!group || !is_good_name(group)) - return ERR_PTR(-EINVAL); - - tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); + tu = kzalloc(struct_size(tu, tp.args, nargs), GFP_KERNEL); if (!tu) return ERR_PTR(-ENOMEM); - tu->call.class = &tu->class; - tu->call.name = kstrdup(event, GFP_KERNEL); - if (!tu->call.name) + tu->nhits = alloc_percpu(unsigned long); + if (!tu->nhits) { + ret = -ENOMEM; goto error; + } - tu->class.system = kstrdup(group, GFP_KERNEL); - if (!tu->class.system) + ret = trace_probe_init(&tu->tp, event, group, true, nargs); + if (ret < 0) goto error; - INIT_LIST_HEAD(&tu->list); + dyn_event_init(&tu->devent, &trace_uprobe_ops); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: - kfree(tu->call.name); + free_percpu(tu->nhits); kfree(tu); - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } 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]); + if (!tu) + return; - iput(tu->inode); - kfree(tu->call.class->system); - kfree(tu->call.name); + path_put(&tu->path); + trace_probe_cleanup(&tu->tp); kfree(tu->filename); + free_percpu(tu->nhits); kfree(tu); } static struct trace_uprobe *find_probe_event(const char *event, const char *group) { + struct dyn_event *pos; 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) + for_each_trace_uprobe(tu, pos) + if (strcmp(trace_probe_name(&tu->tp), event) == 0 && + strcmp(trace_probe_group_name(&tu->tp), 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) +/* Unregister a trace_uprobe and probe_event */ +static int unregister_trace_uprobe(struct trace_uprobe *tu) { - list_del(&tu->list); - unregister_uprobe_event(tu); + int ret; + + if (trace_probe_has_sibling(&tu->tp)) + goto unreg; + + /* If there's a reference to the dynamic event */ + if (trace_event_dyn_busy(trace_probe_event_call(&tu->tp))) + return -EBUSY; + + ret = unregister_uprobe_event(tu); + if (ret) + return ret; + +unreg: + dyn_event_remove(&tu->devent); + trace_probe_unlink(&tu->tp); free_trace_uprobe(tu); + return 0; +} + +static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, + struct trace_uprobe *comp) +{ + struct trace_probe_event *tpe = orig->tp.event; + struct inode *comp_inode = d_real_inode(comp->path.dentry); + int i; + + list_for_each_entry(orig, &tpe->probes, tp.list) { + if (comp_inode != d_real_inode(orig->path.dentry) || + comp->offset != orig->offset) + continue; + + /* + * trace_probe_compare_arg_type() ensured that nr_args and + * each argument name and type are same. Let's compare comm. + */ + for (i = 0; i < orig->tp.nr_args; i++) { + if (strcmp(orig->tp.args[i].comm, + comp->tp.args[i].comm)) + break; + } + + if (i == orig->tp.nr_args) + return true; + } + + return false; +} + +static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to) +{ + int ret; + + ret = trace_probe_compare_arg_type(&tu->tp, &to->tp); + if (ret) { + /* Note that argument starts index = 2 */ + trace_probe_log_set_index(ret + 1); + trace_probe_log_err(0, DIFF_ARG_TYPE); + return -EEXIST; + } + if (trace_uprobe_has_same_uprobe(to, tu)) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, SAME_PROBE); + return -EEXIST; + } + + /* Append to existing event */ + ret = trace_probe_append(&tu->tp, &to->tp); + if (!ret) + dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); + + return ret; +} + +/* + * Uprobe with multiple reference counter is not allowed. i.e. + * If inode and offset matches, reference counter offset *must* + * match as well. Though, there is one exception: If user is + * replacing old trace_uprobe with new one(same group/event), + * then we allow same uprobe with new reference counter as far + * as the new one does not conflict with any other existing + * ones. + */ +static int validate_ref_ctr_offset(struct trace_uprobe *new) +{ + struct dyn_event *pos; + struct trace_uprobe *tmp; + struct inode *new_inode = d_real_inode(new->path.dentry); + + for_each_trace_uprobe(tmp, pos) { + if (new_inode == d_real_inode(tmp->path.dentry) && + new->offset == tmp->offset && + new->ref_ctr_offset != tmp->ref_ctr_offset) { + pr_warn("Reference counter offset mismatch."); + return -EINVAL; + } + } + 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); + guard(mutex)(&event_mutex); + + ret = validate_ref_ctr_offset(tu); + if (ret) + return ret; /* register as an event */ - old_tp = find_probe_event(tu->call.name, tu->call.class->system); - if (old_tp) - /* delete old event */ - unregister_trace_uprobe(old_tp); + old_tu = find_probe_event(trace_probe_name(&tu->tp), + trace_probe_group_name(&tu->tp)); + if (old_tu) { + if (is_ret_probe(tu) != is_ret_probe(old_tu)) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, DIFF_PROBE_TYPE); + return -EEXIST; + } + return append_trace_uprobe(tu, old_tu); + } ret = register_uprobe_event(tu); if (ret) { - pr_warning("Failed to register probe event(%d)\n", ret); - goto end; + if (ret == -EEXIST) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, EVENT_EXIST); + } else + pr_warn("Failed to register probe event(%d)\n", ret); + return ret; } - list_add_tail(&tu->list, &uprobe_list); - -end: - mutex_unlock(&uprobe_lock); + dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); return ret; } +DEFINE_FREE(free_trace_uprobe, struct trace_uprobe *, if (_T) free_trace_uprobe(_T)) + /* * Argument syntax: - * - Add uprobe: p|r[:[GRP/]EVENT] PATH:SYMBOL [FETCHARGS] - * - * - Remove uprobe: -:[GRP/]EVENT + * - Add uprobe: p|r[:[GRP/][EVENT]] PATH:OFFSET[%return][(REF)] [FETCHARGS] */ -static int create_trace_uprobe(int argc, char **argv) +static int __trace_uprobe_create(int argc, const char **argv) { - struct trace_uprobe *tu; - struct inode *inode; - char *arg, *event, *group, *filename; - char buf[MAX_EVENT_NAME_LEN]; - struct path path; - unsigned long offset; - bool is_delete, is_return; + struct traceprobe_parse_context *ctx __free(traceprobe_parse_context) = NULL; + struct trace_uprobe *tu __free(free_trace_uprobe) = NULL; + const char *trlog __free(trace_probe_log_clear) = NULL; + const char *event = NULL, *group = UPROBE_EVENT_SYSTEM; + struct path path __free(path_put) = {}; + unsigned long offset, ref_ctr_offset; + char *filename __free(kfree) = NULL; + char *arg, *rctr, *rctr_end, *tmp; + char *gbuf __free(kfree) = NULL; + char *buf __free(kfree) = NULL; + enum probe_print_type ptype; + bool is_return = false; 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') + ref_ctr_offset = 0; + + switch (argv[0][0]) { + case 'r': is_return = true; - else if (argv[0][0] != 'p') { - pr_info("Probe definition must be started with 'p', 'r' or '-'.\n"); - return -EINVAL; + break; + case 'p': + break; + default: + return -ECANCELED; } - if (argv[0][1] == ':') { - event = &argv[0][2]; - arg = strchr(event, '/'); + if (argc < 2) + return -ECANCELED; - if (arg) { - group = event; - event = arg + 1; - event[-1] = '\0'; + trlog = trace_probe_log_init("trace_uprobe", argc, argv); - if (strlen(group) == 0) { - pr_info("Group name is not specified\n"); - return -EINVAL; - } - } - if (strlen(event) == 0) { - pr_info("Event name is not specified\n"); - return -EINVAL; - } + if (argc - 2 > MAX_TRACE_ARGS) { + trace_probe_log_set_index(2); + trace_probe_log_err(0, TOO_MANY_ARGS); + return -E2BIG; } - if (!group) - group = UPROBE_EVENT_SYSTEM; - if (is_delete) { - if (!event) { - pr_info("Delete command needs an event name.\n"); - return -EINVAL; - } - mutex_lock(&uprobe_lock); - tu = find_probe_event(event, group); + if (argv[0][1] == ':') + event = &argv[0][2]; - if (!tu) { - mutex_unlock(&uprobe_lock); - pr_info("Event %s/%s doesn't exist.\n", group, event); - return -ENOENT; - } - /* delete an event */ - unregister_trace_uprobe(tu); - mutex_unlock(&uprobe_lock); - return 0; - } + if (!strchr(argv[1], '/')) + return -ECANCELED; - if (argc < 2) { - pr_info("Probe point is not specified.\n"); - return -EINVAL; + filename = kstrdup(argv[1], GFP_KERNEL); + if (!filename) + return -ENOMEM; + + /* Find the last occurrence, in case the path contains ':' too. */ + arg = strrchr(filename, ':'); + if (!arg || !isdigit(arg[1])) + return -ECANCELED; + + trace_probe_log_set_index(1); /* filename is the 2nd argument */ + + *arg++ = '\0'; + ret = kern_path(filename, LOOKUP_FOLLOW, &path); + if (ret) { + trace_probe_log_err(0, FILE_NOT_FOUND); + return ret; } - if (isdigit(argv[1][0])) { - pr_info("probe point must be have a filename.\n"); + if (!d_is_reg(path.dentry)) { + trace_probe_log_err(0, NO_REGULAR_FILE); return -EINVAL; } - arg = strchr(argv[1], ':'); - if (!arg) { - ret = -EINVAL; - goto fail_address_parse; - } - *arg++ = '\0'; - filename = argv[1]; - ret = kern_path(filename, LOOKUP_FOLLOW, &path); - if (ret) - goto fail_address_parse; + /* Parse reference counter offset if specified. */ + rctr = strchr(arg, '('); + if (rctr) { + rctr_end = strchr(rctr, ')'); + if (!rctr_end) { + rctr_end = rctr + strlen(rctr); + trace_probe_log_err(rctr_end - filename, + REFCNT_OPEN_BRACE); + return -EINVAL; + } else if (rctr_end[1] != '\0') { + trace_probe_log_err(rctr_end + 1 - filename, + BAD_REFCNT_SUFFIX); + return -EINVAL; + } - inode = igrab(path.dentry->d_inode); - path_put(&path); + *rctr++ = '\0'; + *rctr_end = '\0'; + ret = kstrtoul(rctr, 0, &ref_ctr_offset); + if (ret) { + trace_probe_log_err(rctr - filename, BAD_REFCNT); + return ret; + } + } - if (!inode || !S_ISREG(inode->i_mode)) { - ret = -EINVAL; - goto fail_address_parse; + /* Check if there is %return suffix */ + tmp = strchr(arg, '%'); + if (tmp) { + if (!strcmp(tmp, "%return")) { + *tmp = '\0'; + is_return = true; + } else { + trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX); + return -EINVAL; + } } + /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); - if (ret) - goto fail_address_parse; - - argc -= 2; - argv += 2; + if (ret) { + trace_probe_log_err(arg - filename, BAD_UPROBE_OFFS); + return ret; + } /* setup a probe */ + trace_probe_log_set_index(0); + if (event) { + gbuf = kmalloc(MAX_EVENT_NAME_LEN, GFP_KERNEL); + if (!gbuf) + return -ENOMEM; + + ret = traceprobe_parse_event_name(&event, &group, gbuf, + event - argv[0]); + if (ret) + return ret; + } + if (!event) { char *tail; char *ptr; tail = kstrdup(kbasename(filename), GFP_KERNEL); - if (!tail) { - ret = -ENOMEM; - goto fail_address_parse; - } + if (!tail) + return -ENOMEM; ptr = strpbrk(tail, ".-_"); if (ptr) *ptr = '\0'; + buf = kmalloc(MAX_EVENT_NAME_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); event = buf; kfree(tail); } + argc -= 2; + argv += 2; + 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); - goto fail_address_parse; + /* This must return -ENOMEM otherwise there is a bug */ + WARN_ON_ONCE(ret != -ENOMEM); + return ret; } tu->offset = offset; - tu->inode = inode; - tu->filename = kstrdup(filename, GFP_KERNEL); - - if (!tu->filename) { - pr_info("Failed to allocate filename.\n"); - ret = -ENOMEM; - goto error; - } + tu->ref_ctr_offset = ref_ctr_offset; + tu->path = path; + /* Clear @path so that it will not freed by path_put() */ + memset(&path, 0, sizeof(path)); + tu->filename = no_free_ptr(filename); + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + ctx->flags = (is_return ? TPARG_FL_RETURN : 0) | TPARG_FL_USER; /* parse arguments */ - ret = 0; - for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { - /* Increment count for freeing args in error case */ - tu->nr_args++; - - /* Parse argument name */ - arg = strchr(argv[i], '='); - if (arg) { - *arg++ = '\0'; - tu->args[i].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); - } - - if (!tu->args[i].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); - ret = -EINVAL; - goto error; - } - - if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) { - pr_info("Argument[%d] name '%s' conflicts with " - "another field.\n", i, argv[i]); - ret = -EINVAL; - goto error; - } - - /* Parse fetch argument */ - ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false); - if (ret) { - pr_info("Parse error at argument[%d]. (%d)\n", i, ret); - goto error; - } + for (i = 0; i < argc; i++) { + trace_probe_log_set_index(i + 2); + ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i], ctx); + if (ret) + return ret; } - ret = register_trace_uprobe(tu); - if (ret) - goto error; - return 0; - -error: - free_trace_uprobe(tu); - return ret; - -fail_address_parse: - if (inode) - iput(inode); + ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; + ret = traceprobe_set_print_fmt(&tu->tp, ptype); + if (ret < 0) + return ret; - pr_info("Failed to parse address or file.\n"); + ret = register_trace_uprobe(tu); + if (!ret) + tu = NULL; return ret; } -static void cleanup_all_probes(void) +int trace_uprobe_create(const char *raw_command) { - struct trace_uprobe *tu; - - mutex_lock(&uprobe_lock); - while (!list_empty(&uprobe_list)) { - tu = list_entry(uprobe_list.next, struct trace_uprobe, list); - unregister_trace_uprobe(tu); - } - mutex_unlock(&uprobe_lock); + return trace_probe_create(raw_command, __trace_uprobe_create); } -/* Probes listing interfaces */ -static void *probes_seq_start(struct seq_file *m, loff_t *pos) +static int create_or_delete_trace_uprobe(const char *raw_command) { - mutex_lock(&uprobe_lock); - return seq_list_start(&uprobe_list, *pos); -} + int ret; -static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) -{ - return seq_list_next(v, &uprobe_list, pos); + if (raw_command[0] == '-') + return dyn_event_release(raw_command, &trace_uprobe_ops); + + ret = dyn_event_create(raw_command, &trace_uprobe_ops); + return ret == -ECANCELED ? -EINVAL : ret; } -static void probes_seq_stop(struct seq_file *m, void *v) +static int trace_uprobe_release(struct dyn_event *ev) { - mutex_unlock(&uprobe_lock); + struct trace_uprobe *tu = to_trace_uprobe(ev); + + return unregister_trace_uprobe(tu); } -static int probes_seq_show(struct seq_file *m, void *v) +/* Probes listing interfaces */ +static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev) { - struct trace_uprobe *tu = v; + struct trace_uprobe *tu = to_trace_uprobe(ev); char c = is_ret_probe(tu) ? 'r' : 'p'; int i; - seq_printf(m, "%c:%s/%s", c, tu->call.class->system, tu->call.name); - seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); + seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, trace_probe_group_name(&tu->tp), + trace_probe_name(&tu->tp), tu->filename, + (int)(sizeof(void *) * 2), tu->offset); - for (i = 0; i < tu->nr_args; i++) - seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm); + if (tu->ref_ctr_offset) + seq_printf(m, "(0x%lx)", tu->ref_ctr_offset); - seq_printf(m, "\n"); + 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_putc(m, '\n'); return 0; } +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct dyn_event *ev = v; + + if (!is_trace_uprobe(ev)) + return 0; + + return trace_uprobe_show(m, ev); +} + static const struct seq_operations probes_seq_op = { - .start = probes_seq_start, - .next = probes_seq_next, - .stop = probes_seq_stop, - .show = probes_seq_show + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, + .show = probes_seq_show }; 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; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = dyn_events_release_all(&trace_uprobe_ops); + if (ret) + return ret; + } return seq_open(file, &probes_seq_op); } @@ -471,7 +805,8 @@ static int probes_open(struct inode *inode, struct file *file) static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe); + return trace_parse_run_command(file, buffer, count, ppos, + create_or_delete_trace_uprobe); } static const struct file_operations uprobe_events_ops = { @@ -486,21 +821,41 @@ static const struct file_operations uprobe_events_ops = { /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { - struct trace_uprobe *tu = v; + struct dyn_event *ev = v; + struct trace_uprobe *tu; + unsigned long nhits; + int cpu; + + if (!is_trace_uprobe(ev)) + return 0; + + tu = to_trace_uprobe(ev); - seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit); + nhits = 0; + for_each_possible_cpu(cpu) { + nhits += per_cpu(*tu->nhits, cpu); + } + + seq_printf(m, " %s %-44s %15lu\n", tu->filename, + trace_probe_name(&tu->tp), nhits); return 0; } static const struct seq_operations profile_seq_op = { - .start = probes_seq_start, - .next = probes_seq_next, - .stop = probes_seq_stop, + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, .show = probes_profile_seq_show }; static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } @@ -512,23 +867,151 @@ static const struct file_operations uprobe_profile_ops = { .release = seq_release, }; -static void uprobe_trace_print(struct trace_uprobe *tu, - unsigned long func, struct pt_regs *regs) +struct uprobe_cpu_buffer { + struct mutex mutex; + void *buf; + int dsize; +}; +static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; +static int uprobe_buffer_refcnt; +#define MAX_UCB_BUFFER_SIZE PAGE_SIZE + +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) +{ + if (!ucb) + return; + mutex_unlock(&ucb->mutex); +} + +static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, + struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) +{ + struct uprobe_cpu_buffer *ucb; + int dsize, esize; + + if (*ucbp) + return *ucbp; + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + dsize = __get_data_size(&tu->tp, regs, NULL); + + ucb = uprobe_buffer_get(); + ucb->dsize = tu->tp.size + dsize; + + if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) { + ucb->dsize = MAX_UCB_BUFFER_SIZE; + dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size; + } + + store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); + + *ucbp = ucb; + return ucb; +} + +static void __uprobe_trace_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer *ucb, + struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; - struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_event_buffer fbuffer; void *data; - int size, i; - struct ftrace_event_call *call = &tu->call; + int size, esize; + struct trace_event_call *call = trace_probe_event_call(&tu->tp); + + WARN_ON(call != trace_file->event_call); + + if (trace_trigger_soft_disabled(trace_file)) + return; - size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - event = trace_current_buffer_lock_reserve(&buffer, call->event.type, - size + tu->size, 0, 0); - if (!event) + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); + size = esize + ucb->dsize; + entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); + if (!entry) return; - entry = ring_buffer_event_data(event); if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); @@ -538,25 +1021,44 @@ static void uprobe_trace_print(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); } - for (i = 0; i < tu->nr_args; i++) - call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); + memcpy(data, ucb->buf, ucb->dsize); - if (!filter_current_check_discard(buffer, call, entry, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); + trace_event_buffer_commit(&fbuffer); } /* uprobe handler */ -static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) { - if (!is_ret_probe(tu)) - uprobe_trace_print(tu, 0, regs); + struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; + + if (is_ret_probe(tu)) + return 0; + + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + + rcu_read_lock(); + trace_probe_for_each_link_rcu(link, &tu->tp) + __uprobe_trace_func(tu, 0, regs, ucb, link->file); + rcu_read_unlock(); + return 0; } static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, - struct pt_regs *regs) + struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) { - uprobe_trace_print(tu, func, regs); + struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; + + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + + rcu_read_lock(); + trace_probe_for_each_link_rcu(link, &tu->tp) + __uprobe_trace_func(tu, func, regs, ucb, link->file); + rcu_read_unlock(); } /* Event entry printers */ @@ -567,155 +1069,175 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; - int i; entry = (struct uprobe_trace_entry_head *)iter->ent; - tu = container_of(event, struct trace_uprobe, call.event); + tu = trace_uprobe_primary_from_call( + container_of(event, struct trace_event_call, event)); + if (unlikely(!tu)) + goto out; if (is_ret_probe(tu)) { - if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->call.name, - entry->vaddr[1], entry->vaddr[0])) - goto partial; + trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", + trace_probe_name(&tu->tp), + entry->vaddr[1], entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, true); } else { - if (!trace_seq_printf(s, "%s: (0x%lx)", tu->call.name, - entry->vaddr[0])) - goto partial; + trace_seq_printf(s, "%s: (0x%lx)", + trace_probe_name(&tu->tp), + entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, false); } - for (i = 0; i < tu->nr_args; i++) { - if (!tu->args[i].type->print(s, tu->args[i].name, - data + tu->args[i].offset, entry)) - goto partial; - } - - if (trace_seq_puts(s, "\n")) - return TRACE_TYPE_HANDLED; + if (trace_probe_print_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) + goto out; -partial: - return TRACE_TYPE_PARTIAL_LINE; -} + trace_seq_putc(s, '\n'); -static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu) -{ - return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE); + out: + return trace_handle_return(s); } -typedef bool (*filter_func_t)(struct uprobe_consumer *self, - enum uprobe_filter_ctx ctx, - struct mm_struct *mm); +typedef bool (*filter_func_t)(struct uprobe_consumer *self, struct mm_struct *mm); -static int -probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) +static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { - int ret = 0; - - if (is_trace_uprobe_enabled(tu)) - return -EINTR; + struct inode *inode = d_real_inode(tu->path.dentry); + struct uprobe *uprobe; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - - tu->flags |= flag; tu->consumer.filter = filter; - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); - if (ret) - tu->flags &= ~flag; + uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); + if (IS_ERR(uprobe)) + return PTR_ERR(uprobe); - return ret; + tu->uprobe = uprobe; + return 0; } -static void probe_event_disable(struct trace_uprobe *tu, int flag) +static void __probe_event_disable(struct trace_probe *tp) { - if (!is_trace_uprobe_enabled(tu)) - return; + struct trace_uprobe *tu; + bool sync = false; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->flags &= ~flag; + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { + if (!tu->uprobe) + continue; + + uprobe_unregister_nosync(tu->uprobe, &tu->consumer); + sync = true; + tu->uprobe = NULL; + } + if (sync) + uprobe_unregister_sync(); } -static int uprobe_event_define_fields(struct ftrace_event_call *event_call) +static int probe_event_enable(struct trace_event_call *call, + struct trace_event_file *file, filter_func_t filter) { - int ret, i, size; - struct uprobe_trace_entry_head field; - struct trace_uprobe *tu = event_call->data; + struct trace_probe *tp; + struct trace_uprobe *tu; + bool enabled; + int ret; - 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); + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + enabled = trace_probe_is_enabled(tp); + + /* This may also change "enabled" state */ + if (file) { + if (trace_probe_test_flag(tp, TP_FLAG_PROFILE)) + return -EINTR; + + ret = trace_probe_add_file(tp, file); + if (ret < 0) + return ret; } else { - DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); - size = SIZEOF_TRACE_ENTRY(false); + if (trace_probe_test_flag(tp, TP_FLAG_TRACE)) + return -EINTR; + + trace_probe_set_flag(tp, TP_FLAG_PROFILE); } - /* 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, - size + tu->args[i].offset, - tu->args[i].type->size, - tu->args[i].type->is_signed, - FILTER_OTHER); - if (ret) - return ret; + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); + + if (enabled) + return 0; + + ret = uprobe_buffer_enable(); + if (ret) + goto err_flags; + + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { + ret = trace_uprobe_enable(tu, filter); + if (ret) { + __probe_event_disable(tp); + goto err_buffer; + } } + return 0; -} -#define LEN_OR_ZERO (len ? len - pos : 0) -static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len) -{ - const char *fmt, *arg; - int i; - int pos = 0; + err_buffer: + uprobe_buffer_disable(); - if (is_ret_probe(tu)) { - fmt = "(%lx <- %lx)"; - arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; - } else { - fmt = "(%lx)"; - arg = "REC->" FIELD_STRING_IP; - } + err_flags: + if (file) + trace_probe_remove_file(tp, file); + else + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); + + return ret; +} - /* When len=0, we just calculate the needed length */ +static void probe_event_disable(struct trace_event_call *call, + struct trace_event_file *file) +{ + struct trace_probe *tp; - pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return; - 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); - } + if (!trace_probe_is_enabled(tp)) + return; - pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + if (file) { + if (trace_probe_remove_file(tp, file) < 0) + return; - for (i = 0; i < tu->nr_args; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", - tu->args[i].name); - } + if (trace_probe_is_enabled(tp)) + return; + } else + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); - return pos; /* return the length of print_fmt */ + __probe_event_disable(tp); + uprobe_buffer_disable(); } -#undef LEN_OR_ZERO -static int set_print_fmt(struct trace_uprobe *tu) +static int uprobe_event_define_fields(struct trace_event_call *event_call) { - char *print_fmt; - int len; + int ret, size; + struct uprobe_trace_entry_head field; + struct trace_uprobe *tu; - /* 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; + tu = trace_uprobe_primary_from_call(event_call); + if (unlikely(!tu)) + return -ENODEV; - /* Second: actually write the @print_fmt */ - __set_print_fmt(tu, print_fmt, len + 1); - tu->call.print_fmt = print_fmt; + 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); + } - return 0; + return traceprobe_define_arg_fields(event_call, size, &tu->tp); } #ifdef CONFIG_PERF_EVENTS @@ -724,11 +1246,8 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) { struct perf_event *event; - if (filter->nr_systemwide) - return true; - list_for_each_entry(event, &filter->perf_events, hw.tp_list) { - if (event->hw.tp_target->mm == mm) + if (event->hw.target->mm == mm) return true; } @@ -736,17 +1255,40 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) +{ + return __uprobe_perf_filter(filter, event->hw.target->mm); +} + +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm); + bool done; + + write_lock(&filter->rwlock); + if (event->hw.target) { + list_del(&event->hw.tp_list); + done = filter->nr_systemwide || + (event->hw.target->flags & PF_EXITING) || + trace_uprobe_filter_event(filter, event); + } else { + filter->nr_systemwide--; + done = filter->nr_systemwide; + } + write_unlock(&filter->rwlock); + + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); - if (event->hw.tp_target) { + write_lock(&filter->rwlock); + if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid * uprobe_apply(). current->mm must be probed and we can rely @@ -755,69 +1297,123 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = 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); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - if (!done) - uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - - return 0; + return done; } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) { - bool done; + struct trace_probe *tp; + struct trace_uprobe *tu; + int ret = 0; - 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; + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { + ret = uprobe_apply(tu->uprobe, &tu->consumer, false); + if (ret) + break; } - write_unlock(&tu->filter.rwlock); - if (!done) - uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + return ret; +} + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *tp; + struct trace_uprobe *tu; + int err = 0; - return 0; + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { + err = uprobe_apply(tu->uprobe, &tu->consumer, true); + if (err) { + uprobe_perf_close(call, event); + break; + } + } + + return err; } -static bool uprobe_perf_filter(struct uprobe_consumer *uc, - enum uprobe_filter_ctx ctx, struct mm_struct *mm) +static bool uprobe_perf_filter(struct uprobe_consumer *uc, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = tu->tp.event->filter; + + /* + * speculative short-circuiting check to avoid unnecessarily taking + * filter->rwlock below, if the uprobe has system-wide consumer + */ + if (READ_ONCE(filter->nr_systemwide)) + return true; + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } -static void uprobe_perf_print(struct trace_uprobe *tu, - unsigned long func, struct pt_regs *regs) +static void __uprobe_perf_func(struct trace_uprobe *tu, + unsigned long func, struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) { - struct ftrace_event_call *call = &tu->call; + struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; + struct uprobe_cpu_buffer *ucb; struct hlist_head *head; void *data; - int size, rctx, i; + int size, esize; + int rctx; + +#ifdef CONFIG_BPF_EVENTS + if (bpf_prog_array_valid(call)) { + const struct bpf_prog_array *array; + u32 ret; + + rcu_read_lock_trace(); + array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); + ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run); + rcu_read_unlock_trace(); + if (!ret) + return; + } +#endif /* CONFIG_BPF_EVENTS */ + + esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); - size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32); + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + size = esize + ucb->dsize; + size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; @@ -826,7 +1422,7 @@ static void uprobe_perf_print(struct trace_uprobe *tu, if (hlist_empty(head)) goto out; - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) goto out; @@ -839,98 +1435,155 @@ static void uprobe_perf_print(struct trace_uprobe *tu, data = DATAOF_TRACE_ENTRY(entry, false); } - for (i = 0; i < tu->nr_args; i++) - call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); + memcpy(data, ucb->buf, ucb->dsize); - perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + if (size - esize > ucb->dsize) + memset(data + ucb->dsize, 0, size - esize - ucb->dsize); + + perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, + head, NULL); out: preempt_enable(); } /* uprobe profile handler */ -static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) { - if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + if (!uprobe_perf_filter(&tu->consumer, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) - uprobe_perf_print(tu, 0, regs); + __uprobe_perf_func(tu, 0, regs, ucbp); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, - struct pt_regs *regs) + struct pt_regs *regs, + struct uprobe_cpu_buffer **ucbp) { - uprobe_perf_print(tu, func, regs); + __uprobe_perf_func(tu, func, regs, ucbp); +} + +int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, + const char **filename, u64 *probe_offset, + u64 *probe_addr, bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_uprobe *tu; + + if (perf_type_tracepoint) + tu = find_probe_event(pevent, group); + else + tu = trace_uprobe_primary_from_call(event->tp_event); + if (!tu) + return -EINVAL; + + *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE + : BPF_FD_TYPE_UPROBE; + *filename = tu->filename; + *probe_offset = tu->offset; + *probe_addr = tu->ref_ctr_offset; + return 0; } #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 trace_event_call *event, enum trace_reg type, + void *data) { - struct trace_uprobe *tu = event->data; + struct trace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, TP_FLAG_TRACE, NULL); + return probe_event_enable(event, file, NULL); case TRACE_REG_UNREGISTER: - probe_event_disable(tu, TP_FLAG_TRACE); + probe_event_disable(event, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter); + return probe_event_enable(event, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: - probe_event_disable(tu, TP_FLAG_PROFILE); + probe_event_disable(event, NULL); return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_open(tu, data); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_close(tu, data); + return uprobe_perf_close(event, data); #endif default: return 0; } - return 0; } -static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) +static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs, + __u64 *data) { struct trace_uprobe *tu; + struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb = NULL; + unsigned int flags; int ret = 0; tu = container_of(con, struct trace_uprobe, consumer); - tu->nhit++; - if (tu->flags & TP_FLAG_TRACE) - ret |= uprobe_trace_func(tu, regs); + this_cpu_inc(*tu->nhits); + + udd.tu = tu; + udd.bp_addr = instruction_pointer(regs); + + current->utask->vaddr = (unsigned long) &udd; + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + flags = trace_probe_load_flag(&tu->tp); + if (flags & TP_FLAG_TRACE) + ret |= uprobe_trace_func(tu, regs, &ucb); #ifdef CONFIG_PERF_EVENTS - if (tu->flags & TP_FLAG_PROFILE) - ret |= uprobe_perf_func(tu, regs); + if (flags & TP_FLAG_PROFILE) + ret |= uprobe_perf_func(tu, regs, &ucb); #endif + uprobe_buffer_put(ucb); return ret; } static int uretprobe_dispatcher(struct uprobe_consumer *con, - unsigned long func, struct pt_regs *regs) + unsigned long func, struct pt_regs *regs, + __u64 *data) { struct trace_uprobe *tu; + struct uprobe_dispatch_data udd; + struct uprobe_cpu_buffer *ucb = NULL; + unsigned int flags; tu = container_of(con, struct trace_uprobe, consumer); - if (tu->flags & TP_FLAG_TRACE) - uretprobe_trace_func(tu, func, regs); + udd.tu = tu; + udd.bp_addr = func; + + current->utask->vaddr = (unsigned long) &udd; + + if (WARN_ON_ONCE(!uprobe_cpu_buffer)) + return 0; + + flags = trace_probe_load_flag(&tu->tp); + if (flags & TP_FLAG_TRACE) + uretprobe_trace_func(tu, func, regs, &ucb); #ifdef CONFIG_PERF_EVENTS - if (tu->flags & TP_FLAG_PROFILE) - uretprobe_perf_func(tu, func, regs); + if (flags & TP_FLAG_PROFILE) + uretprobe_perf_func(tu, func, regs, &ucb); #endif + uprobe_buffer_put(ucb); return 0; } @@ -938,59 +1591,118 @@ static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; +static struct trace_event_fields uprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = uprobe_event_define_fields }, + {} +}; + +static inline void init_trace_event_call(struct trace_uprobe *tu) +{ + struct trace_event_call *call = trace_probe_event_call(&tu->tp); + call->event.funcs = &uprobe_funcs; + call->class->fields_array = uprobe_fields_array; + + call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; + call->class->reg = trace_uprobe_register; +} + static int register_uprobe_event(struct trace_uprobe *tu) { - struct ftrace_event_call *call = &tu->call; + init_trace_event_call(tu); + + return trace_probe_register_event_call(&tu->tp); +} + +static int unregister_uprobe_event(struct trace_uprobe *tu) +{ + return trace_probe_unregister_event_call(&tu->tp); +} + +#ifdef CONFIG_PERF_EVENTS +struct trace_event_call * +create_local_trace_uprobe(char *name, unsigned long offs, + unsigned long ref_ctr_offset, bool is_return) +{ + enum probe_print_type ptype; + struct trace_uprobe *tu; + struct path path; int ret; - /* Initialize ftrace_event_call */ - INIT_LIST_HEAD(&call->class->fields); - call->event.funcs = &uprobe_funcs; - call->class->define_fields = uprobe_event_define_fields; + ret = kern_path(name, LOOKUP_FOLLOW, &path); + if (ret) + return ERR_PTR(ret); - if (set_print_fmt(tu) < 0) - return -ENOMEM; + if (!d_is_reg(path.dentry)) { + path_put(&path); + return ERR_PTR(-EINVAL); + } - ret = register_ftrace_event(&call->event); - if (!ret) { - kfree(call->print_fmt); - return -ENODEV; + /* + * local trace_kprobes are not added to dyn_event, so they are never + * searched in find_trace_kprobe(). Therefore, there is no concern of + * duplicated name "DUMMY_EVENT" here. + */ + tu = alloc_trace_uprobe(UPROBE_EVENT_SYSTEM, "DUMMY_EVENT", 0, + is_return); + + if (IS_ERR(tu)) { + pr_info("Failed to allocate trace_uprobe.(%d)\n", + (int)PTR_ERR(tu)); + path_put(&path); + return ERR_CAST(tu); } - call->flags = 0; - call->class->reg = trace_uprobe_register; - call->data = tu; - ret = trace_add_event_call(call); - if (ret) { - pr_info("Failed to register uprobe event: %s\n", call->name); - kfree(call->print_fmt); - unregister_ftrace_event(&call->event); + tu->offset = offs; + tu->path = path; + tu->ref_ctr_offset = ref_ctr_offset; + tu->filename = kstrdup(name, GFP_KERNEL); + if (!tu->filename) { + ret = -ENOMEM; + goto error; } - return ret; + init_trace_event_call(tu); + + ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; + if (traceprobe_set_print_fmt(&tu->tp, ptype) < 0) { + ret = -ENOMEM; + goto error; + } + + return trace_probe_event_call(&tu->tp); +error: + free_trace_uprobe(tu); + return ERR_PTR(ret); } -static void unregister_uprobe_event(struct trace_uprobe *tu) +void destroy_local_trace_uprobe(struct trace_event_call *event_call) { - /* 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; + struct trace_uprobe *tu; + + tu = trace_uprobe_primary_from_call(event_call); + + free_trace_uprobe(tu); } +#endif /* CONFIG_PERF_EVENTS */ -/* Make a trace interface for controling probe points */ +/* Make a trace interface for controlling probe points */ static __init int init_uprobe_trace(void) { - struct dentry *d_tracer; + int ret; + + ret = dyn_event_register(&trace_uprobe_ops); + if (ret) + return ret; - d_tracer = tracing_init_dentry(); - if (!d_tracer) + ret = tracing_init_dentry(); + if (ret) return 0; - trace_create_file("uprobe_events", 0644, d_tracer, + trace_create_file("uprobe_events", TRACE_MODE_WRITE, NULL, NULL, &uprobe_events_ops); /* Profile interface */ - trace_create_file("uprobe_profile", 0444, d_tracer, + trace_create_file("uprobe_profile", TRACE_MODE_READ, NULL, NULL, &uprobe_profile_ops); return 0; } |
