/*
- * kprobe based kernel tracer
+ * Kprobes-based tracing events
*
* Created by Masami Hiramatsu <mhiramat@redhat.com>
*
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/ptrace.h>
+#include <linux/perf_event.h>
#include "trace.h"
#include "trace_output.h"
#define MAX_TRACE_ARGS 128
#define MAX_ARGSTR_LEN 63
#define MAX_EVENT_NAME_LEN 64
-
-/* currently, trace_kprobe only supports X86. */
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+ "common_type",
+ "common_flags",
+ "common_preempt_count",
+ "common_pid",
+ "common_tgid",
+ "common_lock_depth",
+ FIELD_STRING_IP,
+ FIELD_STRING_NARGS,
+ FIELD_STRING_RETIP,
+ FIELD_STRING_FUNC,
+};
struct fetch_func {
unsigned long (*func)(struct pt_regs *, void *);
return retval;
}
-static __kprobes unsigned long fetch_argument(struct pt_regs *regs, void *num)
-{
- return regs_get_argument_nth(regs, (unsigned int)((unsigned long)num));
-}
-
static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
void *dummy)
{
return regs_return_value(regs);
}
-static __kprobes unsigned long fetch_ip(struct pt_regs *regs, void *dummy)
-{
- return instruction_pointer(regs);
-}
-
static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
void *dummy)
{
}
/**
- * kprobe_trace_core
+ * Kprobe event core functions
*/
+struct probe_arg {
+ struct fetch_func fetch;
+ const char *name;
+};
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE 1
+#define TP_FLAG_PROFILE 2
+
struct trace_probe {
struct list_head list;
- union {
- struct kprobe kp;
- struct kretprobe rp;
- };
+ struct kretprobe rp; /* Use rp.kp for kprobe use */
unsigned long nhit;
+ unsigned int flags; /* For TP_FLAG_* */
const char *symbol; /* symbol name */
struct ftrace_event_call call;
struct trace_event event;
unsigned int nr_args;
- struct fetch_func args[];
+ struct probe_arg args[];
};
#define SIZEOF_TRACE_PROBE(n) \
(offsetof(struct trace_probe, args) + \
- (sizeof(struct fetch_func) * (n)))
-
-static int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs);
-static int kretprobe_trace_func(struct kretprobe_instance *ri,
- struct pt_regs *regs);
+ (sizeof(struct probe_arg) * (n)))
static __kprobes int probe_is_return(struct trace_probe *tp)
{
- return (tp->rp.handler == kretprobe_trace_func);
+ return tp->rp.handler != NULL;
}
static __kprobes const char *probe_symbol(struct trace_probe *tp)
return tp->symbol ? tp->symbol : "unknown";
}
-static __kprobes long probe_offset(struct trace_probe *tp)
-{
- return (probe_is_return(tp)) ? tp->rp.kp.offset : tp->kp.offset;
-}
-
-static __kprobes void *probe_address(struct trace_probe *tp)
-{
- return (probe_is_return(tp)) ? tp->rp.kp.addr : tp->kp.addr;
-}
-
static int probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
{
int ret = -EINVAL;
- if (ff->func == fetch_argument)
- ret = snprintf(buf, n, "a%lu", (unsigned long)ff->data);
- else if (ff->func == fetch_register) {
+ if (ff->func == fetch_register) {
const char *name;
name = regs_query_register_name((unsigned int)((long)ff->data));
ret = snprintf(buf, n, "%%%s", name);
} else if (ff->func == fetch_stack)
- ret = snprintf(buf, n, "s%lu", (unsigned long)ff->data);
+ ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
else if (ff->func == fetch_memory)
ret = snprintf(buf, n, "@0x%p", ff->data);
else if (ff->func == fetch_symbol) {
struct symbol_cache *sc = ff->data;
- ret = snprintf(buf, n, "@%s%+ld", sc->symbol, sc->offset);
+ if (sc->offset)
+ ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
+ sc->offset);
+ else
+ ret = snprintf(buf, n, "@%s", sc->symbol);
} else if (ff->func == fetch_retvalue)
- ret = snprintf(buf, n, "rv");
- else if (ff->func == fetch_ip)
- ret = snprintf(buf, n, "ra");
+ ret = snprintf(buf, n, "$retval");
else if (ff->func == fetch_stack_address)
- ret = snprintf(buf, n, "sa");
+ ret = snprintf(buf, n, "$stack");
else if (ff->func == fetch_indirect) {
struct indirect_fetch_data *id = ff->data;
size_t l = 0;
static DEFINE_MUTEX(probe_lock);
static LIST_HEAD(probe_list);
-static struct trace_probe *alloc_trace_probe(const char *symbol,
- const char *event, int nargs)
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
+static int kretprobe_dispatcher(struct kretprobe_instance *ri,
+ struct pt_regs *regs);
+
+/* Check the name is good for event/group */
+static int check_event_name(const char *name)
+{
+ if (!isalpha(*name) && *name != '_')
+ return 0;
+ while (*++name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return 0;
+ }
+ return 1;
+}
+
+/*
+ * Allocate new trace_probe and initialize it (including kprobes).
+ */
+static struct trace_probe *alloc_trace_probe(const char *group,
+ const char *event,
+ void *addr,
+ const char *symbol,
+ unsigned long offs,
+ int nargs, int is_return)
{
struct trace_probe *tp;
+ int ret = -ENOMEM;
tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
if (!tp)
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
if (symbol) {
tp->symbol = kstrdup(symbol, GFP_KERNEL);
if (!tp->symbol)
goto error;
- }
- if (!event)
+ tp->rp.kp.symbol_name = tp->symbol;
+ tp->rp.kp.offset = offs;
+ } else
+ tp->rp.kp.addr = addr;
+
+ if (is_return)
+ tp->rp.handler = kretprobe_dispatcher;
+ else
+ tp->rp.kp.pre_handler = kprobe_dispatcher;
+
+ if (!event || !check_event_name(event)) {
+ ret = -EINVAL;
goto error;
+ }
+
tp->call.name = kstrdup(event, GFP_KERNEL);
if (!tp->call.name)
goto error;
+ if (!group || !check_event_name(group)) {
+ ret = -EINVAL;
+ goto error;
+ }
+
+ tp->call.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->call.system)
+ goto error;
+
INIT_LIST_HEAD(&tp->list);
return tp;
error:
+ kfree(tp->call.name);
kfree(tp->symbol);
kfree(tp);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
+}
+
+static void free_probe_arg(struct probe_arg *arg)
+{
+ if (arg->fetch.func == fetch_symbol)
+ free_symbol_cache(arg->fetch.data);
+ else if (arg->fetch.func == fetch_indirect)
+ free_indirect_fetch_data(arg->fetch.data);
+ kfree(arg->name);
}
static void free_trace_probe(struct trace_probe *tp)
int i;
for (i = 0; i < tp->nr_args; i++)
- if (tp->args[i].func == fetch_symbol)
- free_symbol_cache(tp->args[i].data);
- else if (tp->args[i].func == fetch_indirect)
- free_indirect_fetch_data(tp->args[i].data);
+ free_probe_arg(&tp->args[i]);
+ kfree(tp->call.system);
kfree(tp->call.name);
kfree(tp->symbol);
kfree(tp);
}
-static struct trace_probe *find_probe_event(const char *event)
+static struct trace_probe *find_probe_event(const char *event,
+ const char *group)
{
struct trace_probe *tp;
list_for_each_entry(tp, &probe_list, list)
- if (!strcmp(tp->call.name, event))
+ if (strcmp(tp->call.name, event) == 0 &&
+ strcmp(tp->call.system, group) == 0)
return tp;
return NULL;
}
-static void __unregister_trace_probe(struct trace_probe *tp)
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static void unregister_trace_probe(struct trace_probe *tp)
{
if (probe_is_return(tp))
unregister_kretprobe(&tp->rp);
else
- unregister_kprobe(&tp->kp);
-}
-
-/* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static void unregister_trace_probe(struct trace_probe *tp)
-{
- unregister_probe_event(tp);
- __unregister_trace_probe(tp);
+ unregister_kprobe(&tp->rp.kp);
list_del(&tp->list);
+ unregister_probe_event(tp);
}
/* Register a trace_probe and probe_event */
mutex_lock(&probe_lock);
+ /* register as an event */
+ old_tp = find_probe_event(tp->call.name, tp->call.system);
+ if (old_tp) {
+ /* delete old event */
+ unregister_trace_probe(old_tp);
+ free_trace_probe(old_tp);
+ }
+ ret = register_probe_event(tp);
+ if (ret) {
+ pr_warning("Faild to register probe event(%d)\n", ret);
+ goto end;
+ }
+
+ tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
if (probe_is_return(tp))
ret = register_kretprobe(&tp->rp);
else
- ret = register_kprobe(&tp->kp);
+ ret = register_kprobe(&tp->rp.kp);
if (ret) {
pr_warning("Could not insert probe(%d)\n", ret);
if (ret == -EILSEQ) {
pr_warning("Probing address(0x%p) is not an "
"instruction boundary.\n",
- probe_address(tp));
+ tp->rp.kp.addr);
ret = -EINVAL;
}
- goto end;
- }
- /* register as an event */
- old_tp = find_probe_event(tp->call.name);
- if (old_tp) {
- /* delete old event */
- unregister_trace_probe(old_tp);
- free_trace_probe(old_tp);
- }
- ret = register_probe_event(tp);
- if (ret) {
- pr_warning("Faild to register probe event(%d)\n", ret);
- __unregister_trace_probe(tp);
- }
- list_add_tail(&tp->list, &probe_list);
+ unregister_probe_event(tp);
+ } else
+ list_add_tail(&tp->list, &probe_list);
end:
mutex_unlock(&probe_lock);
return ret;
}
/* Split symbol and offset. */
-static int split_symbol_offset(char *symbol, long *offset)
+static int split_symbol_offset(char *symbol, unsigned long *offset)
{
char *tmp;
int ret;
return -EINVAL;
tmp = strchr(symbol, '+');
- if (!tmp)
- tmp = strchr(symbol, '-');
-
if (tmp) {
/* skip sign because strict_strtol doesn't accept '+' */
- ret = strict_strtol(tmp + 1, 0, offset);
+ ret = strict_strtoul(tmp + 1, 0, offset);
if (ret)
return ret;
- if (*tmp == '-')
- *offset = -(*offset);
*tmp = '\0';
} else
*offset = 0;
#define PARAM_MAX_ARGS 16
#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
-static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+static int parse_probe_vars(char *arg, struct fetch_func *ff, int is_return)
{
int ret = 0;
unsigned long param;
- long offset;
- char *tmp;
- switch (arg[0]) {
- case 'a': /* argument */
- ret = strict_strtoul(arg + 1, 10, ¶m);
- if (ret || param > PARAM_MAX_ARGS)
- ret = -EINVAL;
- else {
- ff->func = fetch_argument;
- ff->data = (void *)param;
- }
- break;
- case 'r': /* retval or retaddr */
- if (is_return && arg[1] == 'v') {
+ if (strcmp(arg, "retval") == 0) {
+ if (is_return) {
ff->func = fetch_retvalue;
ff->data = NULL;
- } else if (is_return && arg[1] == 'a') {
- ff->func = fetch_ip;
- ff->data = NULL;
} else
ret = -EINVAL;
- break;
- case '%': /* named register */
- ret = regs_query_register_offset(arg + 1);
- if (ret >= 0) {
- ff->func = fetch_register;
- ff->data = (void *)(unsigned long)ret;
- ret = 0;
- }
- break;
- case 's': /* stack */
- if (arg[1] == 'a') {
+ } else if (strncmp(arg, "stack", 5) == 0) {
+ if (arg[5] == '\0') {
ff->func = fetch_stack_address;
ff->data = NULL;
- } else {
- ret = strict_strtoul(arg + 1, 10, ¶m);
+ } else if (isdigit(arg[5])) {
+ ret = strict_strtoul(arg + 5, 10, ¶m);
if (ret || param > PARAM_MAX_STACK)
ret = -EINVAL;
else {
ff->func = fetch_stack;
ff->data = (void *)param;
}
+ } else
+ ret = -EINVAL;
+ } else
+ ret = -EINVAL;
+ return ret;
+}
+
+/* Recursive argument parser */
+static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+ int ret = 0;
+ unsigned long param;
+ long offset;
+ char *tmp;
+
+ switch (arg[0]) {
+ case '$':
+ ret = parse_probe_vars(arg + 1, ff, is_return);
+ break;
+ case '%': /* named register */
+ ret = regs_query_register_offset(arg + 1);
+ if (ret >= 0) {
+ ff->func = fetch_register;
+ ff->data = (void *)(unsigned long)ret;
+ ret = 0;
}
break;
case '@': /* memory or symbol */
ret = split_symbol_offset(arg + 1, &offset);
if (ret)
break;
- ff->data = alloc_symbol_cache(arg + 1,
- offset);
+ ff->data = alloc_symbol_cache(arg + 1, offset);
if (ff->data)
ff->func = fetch_symbol;
else
if (!id)
return -ENOMEM;
id->offset = offset;
- ret = parse_probe_arg(arg, &id->orig, is_return);
+ ret = __parse_probe_arg(arg, &id->orig, is_return);
if (ret)
kfree(id);
else {
return ret;
}
+/* String length checking wrapper */
+static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+ if (strlen(arg) > MAX_ARGSTR_LEN) {
+ pr_info("Argument is too long.: %s\n", arg);
+ return -ENOSPC;
+ }
+ return __parse_probe_arg(arg, ff, is_return);
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+ struct probe_arg *args, int narg)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+ if (strcmp(reserved_field_names[i], name) == 0)
+ return 1;
+ for (i = 0; i < narg; i++)
+ if (strcmp(args[i].name, name) == 0)
+ return 1;
+ return 0;
+}
+
static int create_trace_probe(int argc, char **argv)
{
/*
* Argument syntax:
- * - Add kprobe: p[:EVENT] SYMBOL[+OFFS|-OFFS]|ADDRESS [FETCHARGS]
- * - Add kretprobe: r[:EVENT] SYMBOL[+0] [FETCHARGS]
+ * - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
+ * - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
* Fetch args:
- * aN : fetch Nth of function argument. (N:0-)
- * rv : fetch return value
- * ra : fetch return address
- * sa : fetch stack address
- * sN : fetch Nth of stack (N:0-)
+ * $retval : fetch return value
+ * $stack : fetch stack address
+ * $stackN : fetch Nth of stack (N:0-)
* @ADDR : fetch memory at ADDR (ADDR should be in kernel)
* @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
* %REG : fetch register REG
* Indirect memory fetch:
* +|-offs(ARG) : fetch memory at ARG +|- offs address.
+ * Alias name of args:
+ * NAME=FETCHARG : set NAME as alias of FETCHARG.
*/
struct trace_probe *tp;
- struct kprobe *kp;
int i, ret = 0;
- int is_return = 0;
- char *symbol = NULL, *event = NULL;
- long offset = 0;
+ int is_return = 0, is_delete = 0;
+ char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+ unsigned long offset = 0;
void *addr = NULL;
+ char buf[MAX_EVENT_NAME_LEN];
- if (argc < 2)
- return -EINVAL;
-
+ /* argc must be >= 1 */
if (argv[0][0] == 'p')
is_return = 0;
else if (argv[0][0] == 'r')
is_return = 1;
- else
+ else if (argv[0][0] == '-')
+ is_delete = 1;
+ else {
+ pr_info("Probe definition must be started with 'p', 'r' or"
+ " '-'.\n");
return -EINVAL;
+ }
if (argv[0][1] == ':') {
event = &argv[0][2];
+ if (strchr(event, '/')) {
+ group = event;
+ event = strchr(group, '/') + 1;
+ event[-1] = '\0';
+ if (strlen(group) == 0) {
+ pr_info("Group name is not specified\n");
+ return -EINVAL;
+ }
+ }
if (strlen(event) == 0) {
- pr_info("Event name is not specifiled\n");
+ pr_info("Event name is not specified\n");
return -EINVAL;
}
}
+ if (!group)
+ group = KPROBE_EVENT_SYSTEM;
+ if (is_delete) {
+ if (!event) {
+ pr_info("Delete command needs an event name.\n");
+ return -EINVAL;
+ }
+ tp = find_probe_event(event, group);
+ if (!tp) {
+ pr_info("Event %s/%s doesn't exist.\n", group, event);
+ return -ENOENT;
+ }
+ /* delete an event */
+ unregister_trace_probe(tp);
+ free_trace_probe(tp);
+ return 0;
+ }
+
+ if (argc < 2) {
+ pr_info("Probe point is not specified.\n");
+ return -EINVAL;
+ }
if (isdigit(argv[1][0])) {
- if (is_return)
+ if (is_return) {
+ pr_info("Return probe point must be a symbol.\n");
return -EINVAL;
+ }
/* an address specified */
- ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
- if (ret)
+ ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr);
+ if (ret) {
+ pr_info("Failed to parse address.\n");
return ret;
+ }
} else {
/* a symbol specified */
symbol = argv[1];
/* TODO: support .init module functions */
ret = split_symbol_offset(symbol, &offset);
- if (ret)
+ if (ret) {
+ pr_info("Failed to parse symbol.\n");
return ret;
- if (offset && is_return)
+ }
+ if (offset && is_return) {
+ pr_info("Return probe must be used without offset.\n");
return -EINVAL;
+ }
}
argc -= 2; argv += 2;
/* setup a probe */
if (!event) {
/* Make a new event name */
- char buf[MAX_EVENT_NAME_LEN];
if (symbol)
- snprintf(buf, MAX_EVENT_NAME_LEN, "%c@%s%+ld",
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld",
is_return ? 'r' : 'p', symbol, offset);
else
- snprintf(buf, MAX_EVENT_NAME_LEN, "%c@0x%p",
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p",
is_return ? 'r' : 'p', addr);
- tp = alloc_trace_probe(symbol, buf, argc);
- } else
- tp = alloc_trace_probe(symbol, event, argc);
- if (IS_ERR(tp))
+ event = buf;
+ }
+ tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+ is_return);
+ if (IS_ERR(tp)) {
+ pr_info("Failed to allocate trace_probe.(%d)\n",
+ (int)PTR_ERR(tp));
return PTR_ERR(tp);
-
- if (is_return) {
- kp = &tp->rp.kp;
- tp->rp.handler = kretprobe_trace_func;
- } else {
- kp = &tp->kp;
- tp->kp.pre_handler = kprobe_trace_func;
}
- if (tp->symbol) {
- kp->symbol_name = tp->symbol;
- kp->offset = offset;
- } else
- kp->addr = addr;
-
/* parse arguments */
ret = 0;
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
- if (strlen(argv[i]) > MAX_ARGSTR_LEN) {
- pr_info("Argument%d(%s) is too long.\n", i, argv[i]);
- ret = -ENOSPC;
+ /* Parse argument name */
+ arg = strchr(argv[i], '=');
+ if (arg)
+ *arg++ = '\0';
+ else
+ arg = argv[i];
+
+ if (conflict_field_name(argv[i], tp->args, i)) {
+ pr_info("Argument%d name '%s' conflicts with "
+ "another field.\n", i, argv[i]);
+ ret = -EINVAL;
goto error;
}
- ret = parse_probe_arg(argv[i], &tp->args[i], is_return);
- if (ret)
+
+ tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ if (!tp->args[i].name) {
+ pr_info("Failed to allocate argument%d name '%s'.\n",
+ i, argv[i]);
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ /* Parse fetch argument */
+ ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+ if (ret) {
+ pr_info("Parse error at argument%d. (%d)\n", i, ret);
+ kfree(tp->args[i].name);
goto error;
+ }
+
+ tp->nr_args++;
}
- tp->nr_args = i;
ret = register_trace_probe(tp);
if (ret)
char buf[MAX_ARGSTR_LEN + 1];
seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
- seq_printf(m, ":%s", tp->call.name);
+ seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
- if (tp->symbol)
- seq_printf(m, " %s%+ld", probe_symbol(tp), probe_offset(tp));
+ if (!tp->symbol)
+ seq_printf(m, " 0x%p", tp->rp.kp.addr);
+ else if (tp->rp.kp.offset)
+ seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
else
- seq_printf(m, " 0x%p", probe_address(tp));
+ seq_printf(m, " %s", probe_symbol(tp));
for (i = 0; i < tp->nr_args; i++) {
- ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i]);
+ ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
if (ret < 0) {
pr_warning("Argument%d decoding error(%d).\n", i, ret);
return ret;
}
- seq_printf(m, " %s", buf);
+ seq_printf(m, " %s=%s", tp->args[i].name, buf);
}
seq_printf(m, "\n");
return 0;
struct trace_probe *tp = v;
seq_printf(m, " %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
- probe_is_return(tp) ? tp->rp.kp.nmissed : tp->kp.nmissed);
+ tp->rp.kp.nmissed);
return 0;
}
};
/* Kprobe handler */
-static __kprobes int kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
{
- struct trace_probe *tp = container_of(kp, struct trace_probe, kp);
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
struct kprobe_trace_entry *entry;
struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
int size, i, pc;
unsigned long irq_flags;
struct ftrace_event_call *call = &tp->call;
size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
- event = trace_current_buffer_lock_reserve(call->id, size,
+ event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
irq_flags, pc);
if (!event)
- return 0;
+ return;
entry = ring_buffer_event_data(event);
entry->nargs = tp->nr_args;
entry->ip = (unsigned long)kp->addr;
for (i = 0; i < tp->nr_args; i++)
- entry->args[i] = call_fetch(&tp->args[i], regs);
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- if (!filter_current_check_discard(call, entry, event))
- trace_nowake_buffer_unlock_commit(event, irq_flags, pc);
- return 0;
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
}
/* Kretprobe handler */
-static __kprobes int kretprobe_trace_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
struct kretprobe_trace_entry *entry;
struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
int size, i, pc;
unsigned long irq_flags;
struct ftrace_event_call *call = &tp->call;
size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
- event = trace_current_buffer_lock_reserve(call->id, size,
+ event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
irq_flags, pc);
if (!event)
- return 0;
+ return;
entry = ring_buffer_event_data(event);
entry->nargs = tp->nr_args;
- entry->func = (unsigned long)probe_address(tp);
+ entry->func = (unsigned long)tp->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
for (i = 0; i < tp->nr_args; i++)
- entry->args[i] = call_fetch(&tp->args[i], regs);
-
- if (!filter_current_check_discard(call, entry, event))
- trace_nowake_buffer_unlock_commit(event, irq_flags, pc);
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- return 0;
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
}
/* Event entry printers */
{
struct kprobe_trace_entry *field;
struct trace_seq *s = &iter->seq;
+ struct trace_event *event;
+ struct trace_probe *tp;
int i;
field = (struct kprobe_trace_entry *)iter->ent;
+ event = ftrace_find_event(field->ent.type);
+ tp = container_of(event, struct trace_probe, event);
+
+ if (!trace_seq_printf(s, "%s: (", tp->call.name))
+ goto partial;
if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
goto partial;
- if (!trace_seq_puts(s, ":"))
+ if (!trace_seq_puts(s, ")"))
goto partial;
for (i = 0; i < field->nargs; i++)
- if (!trace_seq_printf(s, " 0x%lx", field->args[i]))
+ if (!trace_seq_printf(s, " %s=%lx",
+ tp->args[i].name, field->args[i]))
goto partial;
if (!trace_seq_puts(s, "\n"))
{
struct kretprobe_trace_entry *field;
struct trace_seq *s = &iter->seq;
+ struct trace_event *event;
+ struct trace_probe *tp;
int i;
field = (struct kretprobe_trace_entry *)iter->ent;
+ event = ftrace_find_event(field->ent.type);
+ tp = container_of(event, struct trace_probe, event);
+
+ if (!trace_seq_printf(s, "%s: (", tp->call.name))
+ goto partial;
if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
goto partial;
if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
goto partial;
- if (!trace_seq_puts(s, ":"))
+ if (!trace_seq_puts(s, ")"))
goto partial;
for (i = 0; i < field->nargs; i++)
- if (!trace_seq_printf(s, " 0x%lx", field->args[i]))
+ if (!trace_seq_printf(s, " %s=%lx",
+ tp->args[i].name, field->args[i]))
goto partial;
if (!trace_seq_puts(s, "\n"))
{
struct trace_probe *tp = (struct trace_probe *)call->data;
+ tp->flags |= TP_FLAG_TRACE;
if (probe_is_return(tp))
return enable_kretprobe(&tp->rp);
else
- return enable_kprobe(&tp->kp);
+ return enable_kprobe(&tp->rp.kp);
}
static void probe_event_disable(struct ftrace_event_call *call)
{
struct trace_probe *tp = (struct trace_probe *)call->data;
- if (probe_is_return(tp))
- disable_kretprobe(&tp->rp);
- else
- disable_kprobe(&tp->kp);
+ tp->flags &= ~TP_FLAG_TRACE;
+ if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
+ if (probe_is_return(tp))
+ disable_kretprobe(&tp->rp);
+ else
+ disable_kprobe(&tp->rp.kp);
+ }
}
static int probe_event_raw_init(struct ftrace_event_call *event_call)
{
INIT_LIST_HEAD(&event_call->fields);
- init_preds(event_call);
+
return 0;
}
{
int ret, i;
struct kprobe_trace_entry field;
- char buf[MAX_ARGSTR_LEN + 1];
struct trace_probe *tp = (struct trace_probe *)event_call->data;
- ret = trace_define_common_fields(event_call);
- if (!ret)
- return ret;
-
- DEFINE_FIELD(unsigned long, ip, "ip", 0);
- DEFINE_FIELD(int, nargs, "nargs", 1);
- for (i = 0; i < tp->nr_args; i++) {
- /* Set argN as a field */
- sprintf(buf, "arg%d", i);
- DEFINE_FIELD(unsigned long, args[i], buf, 0);
- /* Set argument string as an alias field */
- ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i]);
- if (ret < 0)
- return ret;
- DEFINE_FIELD(unsigned long, args[i], buf, 0);
- }
+ DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++)
+ DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
return 0;
}
{
int ret, i;
struct kretprobe_trace_entry field;
- char buf[MAX_ARGSTR_LEN + 1];
struct trace_probe *tp = (struct trace_probe *)event_call->data;
- ret = trace_define_common_fields(event_call);
- if (!ret)
- return ret;
+ DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+ DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+ /* Set argument names as fields */
+ for (i = 0; i < tp->nr_args; i++)
+ DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+ return 0;
+}
+
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
+{
+ int i;
+ int pos = 0;
+
+ const char *fmt, *arg;
+
+ if (!probe_is_return(tp)) {
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+ } else {
+ fmt = "(%lx <- %lx)";
+ arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ }
+
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
- DEFINE_FIELD(unsigned long, func, "func", 0);
- DEFINE_FIELD(unsigned long, ret_ip, "ret_ip", 0);
- DEFINE_FIELD(int, nargs, "nargs", 1);
for (i = 0; i < tp->nr_args; i++) {
- /* Set argN as a field */
- sprintf(buf, "arg%d", i);
- DEFINE_FIELD(unsigned long, args[i], buf, 0);
- /* Set argument string as an alias field */
- ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i]);
- if (ret < 0)
- return ret;
- DEFINE_FIELD(unsigned long, args[i], buf, 0);
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx",
+ tp->args[i].name);
}
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+ tp->args[i].name);
+ }
+
+#undef LEN_OR_ZERO
+
+ /* return the length of print_fmt */
+ return pos;
+}
+
+static int set_print_fmt(struct trace_probe *tp)
+{
+ int len;
+ char *print_fmt;
+
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_print_fmt(tp, NULL, 0);
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
+
+ /* Second: actually write the @print_fmt */
+ __set_print_fmt(tp, print_fmt, len + 1);
+ tp->call.print_fmt = print_fmt;
+
return 0;
}
-static int __probe_event_show_format(struct trace_seq *s,
- struct trace_probe *tp, const char *fmt,
- const char *arg)
+#ifdef CONFIG_PERF_EVENTS
+
+/* Kprobe profile handler */
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
+ struct pt_regs *regs)
{
- int i, ret;
- char buf[MAX_ARGSTR_LEN + 1];
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+ struct ftrace_event_call *call = &tp->call;
+ struct kprobe_trace_entry *entry;
+ int size, __size, i;
+ unsigned long irq_flags;
+ int rctx;
- /* Show aliases */
- for (i = 0; i < tp->nr_args; i++) {
- ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i]);
- if (ret < 0)
- return ret;
- if (!trace_seq_printf(s, "\talias: %s;\toriginal: arg%d;\n",
- buf, i))
- return 0;
- }
- /* Show format */
- if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
- return 0;
+ __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+ "profile buffer not large enough"))
+ return;
+
+ entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+ if (!entry)
+ return;
+ entry->nargs = tp->nr_args;
+ entry->ip = (unsigned long)kp->addr;
for (i = 0; i < tp->nr_args; i++)
- if (!trace_seq_puts(s, " 0x%lx"))
- return 0;
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- if (!trace_seq_printf(s, "\", %s", arg))
- return 0;
+ perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
+}
+
+/* Kretprobe profile handler */
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
+ struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+ struct ftrace_event_call *call = &tp->call;
+ struct kretprobe_trace_entry *entry;
+ int size, __size, i;
+ unsigned long irq_flags;
+ int rctx;
+ __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+ "profile buffer not large enough"))
+ return;
+
+ entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+ if (!entry)
+ return;
+
+ entry->nargs = tp->nr_args;
+ entry->func = (unsigned long)tp->rp.kp.addr;
+ entry->ret_ip = (unsigned long)ri->ret_addr;
for (i = 0; i < tp->nr_args; i++)
- if (!trace_seq_printf(s, ", arg%d", i))
- return 0;
+ entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- return trace_seq_puts(s, "\n");
+ perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
+ irq_flags, regs);
}
-#undef SHOW_FIELD
-#define SHOW_FIELD(type, item, name) \
- do { \
- ret = trace_seq_printf(s, "\tfield: " #type " %s;\t" \
- "offset:%u;\tsize:%u;\n", name, \
- (unsigned int)offsetof(typeof(field), item),\
- (unsigned int)sizeof(type)); \
- if (!ret) \
- return 0; \
- } while (0)
-
-static int kprobe_event_show_format(struct ftrace_event_call *call,
- struct trace_seq *s)
+static int probe_perf_enable(struct ftrace_event_call *call)
{
- struct kprobe_trace_entry field __attribute__((unused));
- int ret, i;
- char buf[8];
struct trace_probe *tp = (struct trace_probe *)call->data;
- SHOW_FIELD(unsigned long, ip, "ip");
- SHOW_FIELD(int, nargs, "nargs");
+ tp->flags |= TP_FLAG_PROFILE;
- /* Show fields */
- for (i = 0; i < tp->nr_args; i++) {
- sprintf(buf, "arg%d", i);
- SHOW_FIELD(unsigned long, args[i], buf);
- }
- trace_seq_puts(s, "\n");
-
- return __probe_event_show_format(s, tp, "%lx:", "ip");
+ if (probe_is_return(tp))
+ return enable_kretprobe(&tp->rp);
+ else
+ return enable_kprobe(&tp->rp.kp);
}
-static int kretprobe_event_show_format(struct ftrace_event_call *call,
- struct trace_seq *s)
+static void probe_perf_disable(struct ftrace_event_call *call)
{
- struct kretprobe_trace_entry field __attribute__((unused));
- int ret, i;
- char buf[8];
struct trace_probe *tp = (struct trace_probe *)call->data;
- SHOW_FIELD(unsigned long, func, "func");
- SHOW_FIELD(unsigned long, ret_ip, "ret_ip");
- SHOW_FIELD(int, nargs, "nargs");
+ tp->flags &= ~TP_FLAG_PROFILE;
- /* Show fields */
- for (i = 0; i < tp->nr_args; i++) {
- sprintf(buf, "arg%d", i);
- SHOW_FIELD(unsigned long, args[i], buf);
+ if (!(tp->flags & TP_FLAG_TRACE)) {
+ if (probe_is_return(tp))
+ disable_kretprobe(&tp->rp);
+ else
+ disable_kprobe(&tp->rp.kp);
}
- trace_seq_puts(s, "\n");
+}
+#endif /* CONFIG_PERF_EVENTS */
+
- return __probe_event_show_format(s, tp, "%lx <- %lx:",
- "func, ret_ip");
+static __kprobes
+int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+
+ if (tp->flags & TP_FLAG_TRACE)
+ kprobe_trace_func(kp, regs);
+#ifdef CONFIG_PERF_EVENTS
+ if (tp->flags & TP_FLAG_PROFILE)
+ kprobe_perf_func(kp, regs);
+#endif
+ return 0; /* We don't tweek kernel, so just return 0 */
+}
+
+static __kprobes
+int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+ struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+
+ if (tp->flags & TP_FLAG_TRACE)
+ kretprobe_trace_func(ri, regs);
+#ifdef CONFIG_PERF_EVENTS
+ if (tp->flags & TP_FLAG_PROFILE)
+ kretprobe_perf_func(ri, regs);
+#endif
+ return 0; /* We don't tweek kernel, so just return 0 */
}
static int register_probe_event(struct trace_probe *tp)
int ret;
/* Initialize ftrace_event_call */
- call->system = "kprobes";
if (probe_is_return(tp)) {
tp->event.trace = print_kretprobe_event;
call->raw_init = probe_event_raw_init;
- call->show_format = kretprobe_event_show_format;
call->define_fields = kretprobe_event_define_fields;
} else {
tp->event.trace = print_kprobe_event;
call->raw_init = probe_event_raw_init;
- call->show_format = kprobe_event_show_format;
call->define_fields = kprobe_event_define_fields;
}
+ if (set_print_fmt(tp) < 0)
+ return -ENOMEM;
call->event = &tp->event;
call->id = register_ftrace_event(&tp->event);
- if (!call->id)
+ if (!call->id) {
+ kfree(call->print_fmt);
return -ENODEV;
- call->enabled = 1;
+ }
+ call->enabled = 0;
call->regfunc = probe_event_enable;
call->unregfunc = probe_event_disable;
+
+#ifdef CONFIG_PERF_EVENTS
+ call->perf_event_enable = probe_perf_enable;
+ call->perf_event_disable = probe_perf_disable;
+#endif
call->data = tp;
ret = trace_add_event_call(call);
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
+ kfree(call->print_fmt);
unregister_ftrace_event(&tp->event);
}
return ret;
{
/* tp->event is unregistered in trace_remove_event_call() */
trace_remove_event_call(&tp->call);
+ kfree(tp->call.print_fmt);
}
/* Make a debugfs interface for controling probe points */
static __init int kprobe_trace_self_tests_init(void)
{
- int ret;
+ int ret, warn = 0;
int (*target)(int, int, int, int, int, int);
+ struct trace_probe *tp;
target = kprobe_trace_selftest_target;
pr_info("Testing kprobe tracing: ");
ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
- "a1 a2 a3 a4 a5 a6");
- if (WARN_ON_ONCE(ret))
- pr_warning("error enabling function entry\n");
+ "$stack $stack0 +0($stack)");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on probing function entry.\n");
+ warn++;
+ } else {
+ /* Enable trace point */
+ tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tp == NULL)) {
+ pr_warning("error on getting new probe.\n");
+ warn++;
+ } else
+ probe_event_enable(&tp->call);
+ }
ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
- "ra rv");
- if (WARN_ON_ONCE(ret))
- pr_warning("error enabling function return\n");
+ "$retval");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on probing function return.\n");
+ warn++;
+ } else {
+ /* Enable trace point */
+ tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM);
+ if (WARN_ON_ONCE(tp == NULL)) {
+ pr_warning("error on getting new probe.\n");
+ warn++;
+ } else
+ probe_event_enable(&tp->call);
+ }
+
+ if (warn)
+ goto end;
ret = target(1, 2, 3, 4, 5, 6);
- cleanup_all_probes();
+ ret = command_trace_probe("-:testprobe");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on deleting a probe.\n");
+ warn++;
+ }
- pr_cont("OK\n");
+ ret = command_trace_probe("-:testprobe2");
+ if (WARN_ON_ONCE(ret)) {
+ pr_warning("error on deleting a probe.\n");
+ warn++;
+ }
+
+end:
+ cleanup_all_probes();
+ if (warn)
+ pr_cont("NG: Some tests are failed. Please check them.\n");
+ else
+ pr_cont("OK\n");
return 0;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff