summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-09-05 20:50:41 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-05 20:50:41 +0200
commit58ca24158758f1784400d32743373d7d6227d018 (patch)
tree51df01a93eaa3db89d609eb0dce4f8c1f0de768c /kernel
parentMerge tag 'arc-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgu... (diff)
parenttracing/doc: Fix table format in histogram code (diff)
downloadlinux-58ca24158758f1784400d32743373d7d6227d018.tar.xz
linux-58ca24158758f1784400d32743373d7d6227d018.zip
Merge tag 'trace-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt: - simplify the Kconfig use of FTRACE and TRACE_IRQFLAGS_SUPPORT - bootconfig can now start histograms - bootconfig supports group/all enabling - histograms now can put values in linear size buckets - execnames can be passed to synthetic events - introduce "event probes" that attach to other events and can retrieve data from pointers of fields, or record fields as different types (a pointer to a string as a string instead of just a hex number) - various fixes and clean ups * tag 'trace-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (35 commits) tracing/doc: Fix table format in histogram code selftests/ftrace: Add selftest for testing duplicate eprobes and kprobes selftests/ftrace: Add selftest for testing eprobe events on synthetic events selftests/ftrace: Add test case to test adding and removing of event probe selftests/ftrace: Fix requirement check of README file selftests/ftrace: Add clear_dynamic_events() to test cases tracing: Add a probe that attaches to trace events tracing/probes: Reject events which have the same name of existing one tracing/probes: Have process_fetch_insn() take a void * instead of pt_regs tracing/probe: Change traceprobe_set_print_fmt() to take a type tracing/probes: Use struct_size() instead of defining custom macros tracing/probes: Allow for dot delimiter as well as slash for system names tracing/probe: Have traceprobe_parse_probe_arg() take a const arg tracing: Have dynamic events have a ref counter tracing: Add DYNAMIC flag for dynamic events tracing: Replace deprecated CPU-hotplug functions. MAINTAINERS: Add an entry for os noise/latency tracepoint: Fix kerneldoc comments bootconfig/tracing/ktest: Update ktest example for boot-time tracing tools/bootconfig: Use per-group/all enable option in ftrace2bconf script ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/trace/Kconfig6
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/ring_buffer.c8
-rw-r--r--kernel/trace/trace.c10
-rw-r--r--kernel/trace/trace.h18
-rw-r--r--kernel/trace/trace_boot.c302
-rw-r--r--kernel/trace/trace_dynevent.c38
-rw-r--r--kernel/trace/trace_dynevent.h4
-rw-r--r--kernel/trace/trace_eprobe.c903
-rw-r--r--kernel/trace/trace_event_perf.c6
-rw-r--r--kernel/trace/trace_events.c22
-rw-r--r--kernel/trace/trace_events_hist.c143
-rw-r--r--kernel/trace/trace_events_synth.c21
-rw-r--r--kernel/trace/trace_events_trigger.c20
-rw-r--r--kernel/trace/trace_hwlat.c28
-rw-r--r--kernel/trace/trace_kprobe.c49
-rw-r--r--kernel/trace/trace_osnoise.c16
-rw-r--r--kernel/trace/trace_probe.c109
-rw-r--r--kernel/trace/trace_probe.h16
-rw-r--r--kernel/trace/trace_probe_tmpl.h6
-rw-r--r--kernel/trace/trace_uprobe.c40
-rw-r--r--kernel/tracepoint.c4
22 files changed, 1596 insertions, 174 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 3ee23f4d437f..420ff4bc67fd 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -135,10 +135,9 @@ config TRACING_SUPPORT
depends on STACKTRACE_SUPPORT
default y
-if TRACING_SUPPORT
-
menuconfig FTRACE
bool "Tracers"
+ depends on TRACING_SUPPORT
default y if DEBUG_KERNEL
help
Enable the kernel tracing infrastructure.
@@ -1037,6 +1036,3 @@ config HIST_TRIGGERS_DEBUG
If unsure, say N.
endif # FTRACE
-
-endif # TRACING_SUPPORT
-
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index b1c47ccf4f73..6de5d4d63165 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -77,6 +77,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.o
obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o
obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e592d1df6f88..c5a3fbf19617 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2111,7 +2111,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
}
}
- get_online_cpus();
+ cpus_read_lock();
/*
* Fire off all the required work handlers
* We can't schedule on offline CPUs, but it's not necessary
@@ -2143,7 +2143,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
cpu_buffer->nr_pages_to_update = 0;
}
- put_online_cpus();
+ cpus_read_unlock();
} else {
cpu_buffer = buffer->buffers[cpu_id];
@@ -2171,7 +2171,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
goto out_err;
}
- get_online_cpus();
+ cpus_read_lock();
/* Can't run something on an offline CPU. */
if (!cpu_online(cpu_id))
@@ -2183,7 +2183,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
}
cpu_buffer->nr_pages_to_update = 0;
- put_online_cpus();
+ cpus_read_unlock();
}
out:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2755534b0737..2dbf797aa133 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3697,11 +3697,11 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str)
return false;
event = container_of(trace_event, struct trace_event_call, event);
- if (!event->mod)
+ if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module)
return false;
/* Would rather have rodata, but this will suffice */
- if (within_module_core(addr, event->mod))
+ if (within_module_core(addr, event->module))
return true;
return false;
@@ -5543,6 +5543,7 @@ static const char readme_msg[] =
#ifdef CONFIG_HIST_TRIGGERS
"\t s:[synthetic/]<event> <field> [<field>]\n"
#endif
+ "\t e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]\n"
"\t -:[<group>/]<event>\n"
#ifdef CONFIG_KPROBE_EVENTS
"\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
@@ -5552,7 +5553,7 @@ static const char readme_msg[] =
" place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n"
#endif
"\t args: <name>=fetcharg[:type]\n"
- "\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
+ "\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n"
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#else
@@ -5567,6 +5568,8 @@ static const char readme_msg[] =
"\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n"
"\t [unsigned] char/int/long\n"
#endif
+ "\t efield: For event probes ('e' types), the field is on of the fields\n"
+ "\t of the <attached-group>/<attached-event>.\n"
#endif
" events/\t\t- Directory containing all trace event subsystems:\n"
" enable\t\t- Write 0/1 to enable/disable tracing of all events\n"
@@ -5654,6 +5657,7 @@ static const char readme_msg[] =
"\t .execname display a common_pid as a program name\n"
"\t .syscall display a syscall id as a syscall name\n"
"\t .log2 display log2 value rather than raw number\n"
+ "\t .buckets=size display values in groups of size rather than raw number\n"
"\t .usecs display a common_timestamp in microseconds\n\n"
"\t The 'pause' parameter can be used to pause an existing hist\n"
"\t trigger or to start a hist trigger but not log any events\n"
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4a0e693000c6..b7c0f8e160fb 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -126,6 +126,11 @@ struct kprobe_trace_entry_head {
unsigned long ip;
};
+struct eprobe_trace_entry_head {
+ struct trace_entry ent;
+ unsigned int type;
+};
+
struct kretprobe_trace_entry_head {
struct trace_entry ent;
unsigned long func;
@@ -1508,9 +1513,14 @@ static inline int register_trigger_hist_enable_disable_cmds(void) { return 0; }
extern int register_trigger_cmds(void);
extern void clear_event_triggers(struct trace_array *tr);
+enum {
+ EVENT_TRIGGER_FL_PROBE = BIT(0),
+};
+
struct event_trigger_data {
unsigned long count;
int ref;
+ int flags;
struct event_trigger_ops *ops;
struct event_command *cmd_ops;
struct event_filter __rcu *filter;
@@ -1918,6 +1928,14 @@ static inline bool is_good_name(const char *name)
return true;
}
+/* Convert certain expected symbols into '_' when generating event names */
+static inline void sanitize_event_name(char *name)
+{
+ while (*name++ != '\0')
+ if (*name == ':' || *name == '.')
+ *name = '_';
+}
+
/*
* This is a generic way to read and write a u64 value from a file in tracefs.
*
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 94ef2d099e32..1060b0446032 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -171,6 +171,290 @@ trace_boot_add_synth_event(struct xbc_node *node, const char *event)
}
#endif
+#ifdef CONFIG_HIST_TRIGGERS
+static int __init __printf(3, 4)
+append_printf(char **bufp, char *end, const char *fmt, ...)
+{
+ va_list args;
+ int ret;
+
+ if (*bufp == end)
+ return -ENOSPC;
+
+ va_start(args, fmt);
+ ret = vsnprintf(*bufp, end - *bufp, fmt, args);
+ if (ret < end - *bufp) {
+ *bufp += ret;
+ } else {
+ *bufp = end;
+ ret = -ERANGE;
+ }
+ va_end(args);
+
+ return ret;
+}
+
+static int __init
+append_str_nospace(char **bufp, char *end, const char *str)
+{
+ char *p = *bufp;
+ int len;
+
+ while (p < end - 1 && *str != '\0') {
+ if (!isspace(*str))
+ *(p++) = *str;
+ str++;
+ }
+ *p = '\0';
+ if (p == end - 1) {
+ *bufp = end;
+ return -ENOSPC;
+ }
+ len = p - *bufp;
+ *bufp = p;
+ return (int)len;
+}
+
+static int __init
+trace_boot_hist_add_array(struct xbc_node *hnode, char **bufp,
+ char *end, const char *key)
+{
+ struct xbc_node *knode, *anode;
+ const char *p;
+ char sep;
+
+ knode = xbc_node_find_child(hnode, key);
+ if (knode) {
+ anode = xbc_node_get_child(knode);
+ if (!anode) {
+ pr_err("hist.%s requires value(s).\n", key);
+ return -EINVAL;
+ }
+
+ append_printf(bufp, end, ":%s", key);
+ sep = '=';
+ xbc_array_for_each_value(anode, p) {
+ append_printf(bufp, end, "%c%s", sep, p);
+ if (sep == '=')
+ sep = ',';
+ }
+ } else
+ return -ENOENT;
+
+ return 0;
+}
+
+static int __init
+trace_boot_hist_add_one_handler(struct xbc_node *hnode, char **bufp,
+ char *end, const char *handler,
+ const char *param)
+{
+ struct xbc_node *knode, *anode;
+ const char *p;
+ char sep;
+
+ /* Compose 'handler' parameter */
+ p = xbc_node_find_value(hnode, param, NULL);
+ if (!p) {
+ pr_err("hist.%s requires '%s' option.\n",
+ xbc_node_get_data(hnode), param);
+ return -EINVAL;
+ }
+ append_printf(bufp, end, ":%s(%s)", handler, p);
+
+ /* Compose 'action' parameter */
+ knode = xbc_node_find_child(hnode, "trace");
+ if (!knode)
+ knode = xbc_node_find_child(hnode, "save");
+
+ if (knode) {
+ anode = xbc_node_get_child(knode);
+ if (!anode || !xbc_node_is_value(anode)) {
+ pr_err("hist.%s.%s requires value(s).\n",
+ xbc_node_get_data(hnode),
+ xbc_node_get_data(knode));
+ return -EINVAL;
+ }
+
+ append_printf(bufp, end, ".%s", xbc_node_get_data(knode));
+ sep = '(';
+ xbc_array_for_each_value(anode, p) {
+ append_printf(bufp, end, "%c%s", sep, p);
+ if (sep == '(')
+ sep = ',';
+ }
+ append_printf(bufp, end, ")");
+ } else if (xbc_node_find_child(hnode, "snapshot")) {
+ append_printf(bufp, end, ".snapshot()");
+ } else {
+ pr_err("hist.%s requires an action.\n",
+ xbc_node_get_data(hnode));
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int __init
+trace_boot_hist_add_handlers(struct xbc_node *hnode, char **bufp,
+ char *end, const char *param)
+{
+ struct xbc_node *node;
+ const char *p, *handler;
+ int ret;
+
+ handler = xbc_node_get_data(hnode);
+
+ xbc_node_for_each_subkey(hnode, node) {
+ p = xbc_node_get_data(node);
+ if (!isdigit(p[0]))
+ continue;
+ /* All digit started node should be instances. */
+ ret = trace_boot_hist_add_one_handler(node, bufp, end, handler, param);
+ if (ret < 0)
+ break;
+ }
+
+ if (xbc_node_find_child(hnode, param))
+ ret = trace_boot_hist_add_one_handler(hnode, bufp, end, handler, param);
+
+ return ret;
+}
+
+/*
+ * Histogram boottime tracing syntax.
+ *
+ * ftrace.[instance.INSTANCE.]event.GROUP.EVENT.hist[.N] {
+ * keys = <KEY>[,...]
+ * values = <VAL>[,...]
+ * sort = <SORT-KEY>[,...]
+ * size = <ENTRIES>
+ * name = <HISTNAME>
+ * var { <VAR> = <EXPR> ... }
+ * pause|continue|clear
+ * onmax|onchange[.N] { var = <VAR>; <ACTION> [= <PARAM>] }
+ * onmatch[.N] { event = <EVENT>; <ACTION> [= <PARAM>] }
+ * filter = <FILTER>
+ * }
+ *
+ * Where <ACTION> are;
+ *
+ * trace = <EVENT>, <ARG1>[, ...]
+ * save = <ARG1>[, ...]
+ * snapshot
+ */
+static int __init
+trace_boot_compose_hist_cmd(struct xbc_node *hnode, char *buf, size_t size)
+{
+ struct xbc_node *node, *knode;
+ char *end = buf + size;
+ const char *p;
+ int ret = 0;
+
+ append_printf(&buf, end, "hist");
+
+ ret = trace_boot_hist_add_array(hnode, &buf, end, "keys");
+ if (ret < 0) {
+ if (ret == -ENOENT)
+ pr_err("hist requires keys.\n");
+ return -EINVAL;
+ }
+
+ ret = trace_boot_hist_add_array(hnode, &buf, end, "values");
+ if (ret == -EINVAL)
+ return ret;
+ ret = trace_boot_hist_add_array(hnode, &buf, end, "sort");
+ if (ret == -EINVAL)
+ return ret;
+
+ p = xbc_node_find_value(hnode, "size", NULL);
+ if (p)
+ append_printf(&buf, end, ":size=%s", p);
+
+ p = xbc_node_find_value(hnode, "name", NULL);
+ if (p)
+ append_printf(&buf, end, ":name=%s", p);
+
+ node = xbc_node_find_child(hnode, "var");
+ if (node) {
+ xbc_node_for_each_key_value(node, knode, p) {
+ /* Expression must not include spaces. */
+ append_printf(&buf, end, ":%s=",
+ xbc_node_get_data(knode));
+ append_str_nospace(&buf, end, p);
+ }
+ }
+
+ /* Histogram control attributes (mutual exclusive) */
+ if (xbc_node_find_child(hnode, "pause"))
+ append_printf(&buf, end, ":pause");
+ else if (xbc_node_find_child(hnode, "continue"))
+ append_printf(&buf, end, ":continue");
+ else if (xbc_node_find_child(hnode, "clear"))
+ append_printf(&buf, end, ":clear");
+
+ /* Histogram handler and actions */
+ node = xbc_node_find_child(hnode, "onmax");
+ if (node && trace_boot_hist_add_handlers(node, &buf, end, "var") < 0)
+ return -EINVAL;
+ node = xbc_node_find_child(hnode, "onchange");
+ if (node && trace_boot_hist_add_handlers(node, &buf, end, "var") < 0)
+ return -EINVAL;
+ node = xbc_node_find_child(hnode, "onmatch");
+ if (node && trace_boot_hist_add_handlers(node, &buf, end, "event") < 0)
+ return -EINVAL;
+
+ p = xbc_node_find_value(hnode, "filter", NULL);
+ if (p)
+ append_printf(&buf, end, " if %s", p);
+
+ if (buf == end) {
+ pr_err("hist exceeds the max command length.\n");
+ return -E2BIG;
+ }
+
+ return 0;
+}
+
+static void __init
+trace_boot_init_histograms(struct trace_event_file *file,
+ struct xbc_node *hnode, char *buf, size_t size)
+{
+ struct xbc_node *node;
+ const char *p;
+ char *tmp;
+
+ xbc_node_for_each_subkey(hnode, node) {
+ p = xbc_node_get_data(node);
+ if (!isdigit(p[0]))
+ continue;
+ /* All digit started node should be instances. */
+ if (trace_boot_compose_hist_cmd(node, buf, size) == 0) {
+ tmp = kstrdup(buf, GFP_KERNEL);
+ if (trigger_process_regex(file, buf) < 0)
+ pr_err("Failed to apply hist trigger: %s\n", tmp);
+ kfree(tmp);
+ }
+ }
+
+ if (xbc_node_find_child(hnode, "keys")) {
+ if (trace_boot_compose_hist_cmd(hnode, buf, size) == 0) {
+ tmp = kstrdup(buf, GFP_KERNEL);
+ if (trigger_process_regex(file, buf) < 0)
+ pr_err("Failed to apply hist trigger: %s\n", tmp);
+ kfree(tmp);
+ }
+ }
+}
+#else
+static void __init
+trace_boot_init_histograms(struct trace_event_file *file,
+ struct xbc_node *hnode, char *buf, size_t size)
+{
+ /* do nothing */
+}
+#endif
+
static void __init
trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode,
struct xbc_node *enode)
@@ -205,12 +489,18 @@ trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode,
pr_err("Failed to apply filter: %s\n", buf);
}
- xbc_node_for_each_array_value(enode, "actions", anode, p) {
- if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf))
- pr_err("action string is too long: %s\n", p);
- else if (trigger_process_regex(file, buf) < 0)
- pr_err("Failed to apply an action: %s\n", buf);
- }
+ if (IS_ENABLED(CONFIG_HIST_TRIGGERS)) {
+ xbc_node_for_each_array_value(enode, "actions", anode, p) {
+ if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf))
+ pr_err("action string is too long: %s\n", p);
+ else if (trigger_process_regex(file, buf) < 0)
+ pr_err("Failed to apply an action: %s\n", p);
+ }
+ anode = xbc_node_find_child(enode, "hist");
+ if (anode)
+ trace_boot_init_histograms(file, anode, buf, ARRAY_SIZE(buf));
+ } else if (xbc_node_find_value(enode, "actions", NULL))
+ pr_err("Failed to apply event actions because CONFIG_HIST_TRIGGERS is not set.\n");
if (xbc_node_find_value(enode, "enable", NULL)) {
if (trace_event_enable_disable(file, 1, 0) < 0)
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index e57cc0870892..1110112e55bd 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -13,11 +13,49 @@
#include <linux/tracefs.h>
#include "trace.h"
+#include "trace_output.h" /* for trace_event_sem */
#include "trace_dynevent.h"
static DEFINE_MUTEX(dyn_event_ops_mutex);
static LIST_HEAD(dyn_event_ops_list);
+bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call)
+{
+ struct trace_event_call *call;
+ bool ret = false;
+
+ if (WARN_ON_ONCE(!(dyn_call->flags & TRACE_EVENT_FL_DYNAMIC)))
+ return false;
+
+ down_read(&trace_event_sem);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (call == dyn_call) {
+ atomic_inc(&dyn_call->refcnt);
+ ret = true;
+ }
+ }
+ up_read(&trace_event_sem);
+ return ret;
+}
+
+void trace_event_dyn_put_ref(struct trace_event_call *call)
+{
+ if (WARN_ON_ONCE(!(call->flags & TRACE_EVENT_FL_DYNAMIC)))
+ return;
+
+ if (WARN_ON_ONCE(atomic_read(&call->refcnt) <= 0)) {
+ atomic_set(&call->refcnt, 0);
+ return;
+ }
+
+ atomic_dec(&call->refcnt);
+}
+
+bool trace_event_dyn_busy(struct trace_event_call *call)
+{
+ return atomic_read(&call->refcnt) != 0;
+}
+
int dyn_event_register(struct dyn_event_operations *ops)
{
if (!ops || !ops->create || !ops->show || !ops->is_busy ||
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 7754936b57ee..936477a111d3 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -76,13 +76,15 @@ int dyn_event_init(struct dyn_event *ev, struct dyn_event_operations *ops)
return 0;
}
-static inline int dyn_event_add(struct dyn_event *ev)
+static inline int dyn_event_add(struct dyn_event *ev,
+ struct trace_event_call *call)
{
lockdep_assert_held(&event_mutex);
if (!ev || !ev->ops)
return -EINVAL;
+ call->flags |= TRACE_EVENT_FL_DYNAMIC;
list_add_tail(&ev->list, &dyn_event_list);
return 0;
}
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
new file mode 100644
index 000000000000..56a96e9750cf
--- /dev/null
+++ b/kernel/trace/trace_eprobe.c
@@ -0,0 +1,903 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * event probes
+ *
+ * Part of this code was copied from kernel/trace/trace_kprobe.c written by
+ * Masami Hiramatsu <mhiramat@kernel.org>
+ *
+ * Copyright (C) 2021, VMware Inc, Steven Rostedt <rostedt@goodmis.org>
+ * Copyright (C) 2021, VMware Inc, Tzvetomir Stoyanov tz.stoyanov@gmail.com>
+ *
+ */
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/ftrace.h>
+
+#include "trace_dynevent.h"
+#include "trace_probe.h"
+#include "trace_probe_tmpl.h"
+
+#define EPROBE_EVENT_SYSTEM "eprobes"
+
+struct trace_eprobe {
+ /* tracepoint system */
+ const char *event_system;
+
+ /* tracepoint event */
+ const char *event_name;
+
+ struct trace_event_call *event;
+
+ struct dyn_event devent;
+ struct trace_probe tp;
+};
+
+struct eprobe_data {
+ struct trace_event_file *file;
+ struct trace_eprobe *ep;
+};
+
+static int __trace_eprobe_create(int argc, const char *argv[]);
+
+static void trace_event_probe_cleanup(struct trace_eprobe *ep)
+{
+ if (!ep)
+ return;
+ trace_probe_cleanup(&ep->tp);
+ kfree(ep->event_name);
+ kfree(ep->event_system);
+ if (ep->event)
+ trace_event_put_ref(ep->event);
+ kfree(ep);
+}
+
+static struct trace_eprobe *to_trace_eprobe(struct dyn_event *ev)
+{
+ return container_of(ev, struct trace_eprobe, devent);
+}
+
+static int eprobe_dyn_event_create(const char *raw_command)
+{
+ return trace_probe_create(raw_command, __trace_eprobe_create);
+}
+
+static int eprobe_dyn_event_show(struct seq_file *m, struct dyn_event *ev)
+{
+ struct trace_eprobe *ep = to_trace_eprobe(ev);
+ int i;
+
+ seq_printf(m, "e:%s/%s", trace_probe_group_name(&ep->tp),
+ trace_probe_name(&ep->tp));
+ seq_printf(m, " %s.%s", ep->event_system, ep->event_name);
+
+ for (i = 0; i < ep->tp.nr_args; i++)
+ seq_printf(m, " %s=%s", ep->tp.args[i].name, ep->tp.args[i].comm);
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static int unregister_trace_eprobe(struct trace_eprobe *ep)
+{
+ /* If other probes are on the event, just unregister eprobe */
+ if (trace_probe_has_sibling(&ep->tp))
+ goto unreg;
+
+ /* Enabled event can not be unregistered */
+ if (trace_probe_is_enabled(&ep->tp))
+ return -EBUSY;
+
+ /* Will fail if probe is being used by ftrace or perf */
+ if (trace_probe_unregister_event_call(&ep->tp))
+ return -EBUSY;
+
+unreg:
+ dyn_event_remove(&ep->devent);
+ trace_probe_unlink(&ep->tp);
+
+ return 0;
+}
+
+static int eprobe_dyn_event_release(struct dyn_event *ev)
+{
+ struct trace_eprobe *ep = to_trace_eprobe(ev);
+ int ret = unregister_trace_eprobe(ep);
+
+ if (!ret)
+ trace_event_probe_cleanup(ep);
+ return ret;
+}
+
+static bool eprobe_dyn_event_is_busy(struct dyn_event *ev)
+{
+ struct trace_eprobe *ep = to_trace_eprobe(ev);
+
+ return trace_probe_is_enabled(&ep->tp);
+}
+
+static bool eprobe_dyn_event_match(const char *system, const char *event,
+ int argc, const char **argv, struct dyn_event *ev)
+{
+ struct trace_eprobe *ep = to_trace_eprobe(ev);
+
+ return strcmp(trace_probe_name(&ep->tp), event) == 0 &&
+ (!system || strcmp(trace_probe_group_name(&ep->tp), system) == 0) &&
+ trace_probe_match_command_args(&ep->tp, argc, argv);
+}
+
+static struct dyn_event_operations eprobe_dyn_event_ops = {
+ .create = eprobe_dyn_event_create,
+ .show = eprobe_dyn_event_show,
+ .is_busy = eprobe_dyn_event_is_busy,
+ .free = eprobe_dyn_event_release,
+ .match = eprobe_dyn_event_match,
+};
+
+static struct trace_eprobe *alloc_event_probe(const char *group,
+ const char *this_event,
+ struct trace_event_call *event,
+ int nargs)
+{
+ struct trace_eprobe *ep;
+ const char *event_name;
+ const char *sys_name;
+ int ret = -ENOMEM;
+
+ if (!event)
+ return ERR_PTR(-ENODEV);
+
+ sys_name = event->class->system;
+ event_name = trace_event_name(event);
+
+ ep = kzalloc(struct_size(ep, tp.args, nargs), GFP_KERNEL);
+ if (!ep) {
+ trace_event_put_ref(ep->event);
+ goto error;
+ }
+ ep->event = event;
+ ep->event_name = kstrdup(event_name, GFP_KERNEL);
+ if (!ep->event_name)
+ goto error;
+ ep->event_system = kstrdup(sys_name, GFP_KERNEL);
+ if (!ep->event_system)
+ goto error;
+
+ ret = trace_probe_init(&ep->tp, this_event, group, false);
+ if (ret < 0)
+ goto error;
+
+ dyn_event_init(&ep->devent, &eprobe_dyn_event_ops);
+ return ep;
+error:
+ trace_event_probe_cleanup(ep);
+ return ERR_PTR(ret);
+}
+
+static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
+{
+ struct probe_arg *parg = &ep->tp.args[i];
+ struct ftrace_event_field *field;
+ struct list_head *head;
+
+ head = trace_get_fields(ep->event);
+ list_for_each_entry(field, head, link) {
+ if (!strcmp(parg->code->data, field->name)) {
+ kfree(parg->code->data);
+ parg->code->data = field;
+ return 0;
+ }
+ }
+ kfree(parg->code->data);
+ parg->code->data = NULL;
+ return -ENOENT;
+}
+
+static int eprobe_event_define_fields(struct trace_event_call *event_call)
+{
+ int ret;
+ struct eprobe_trace_entry_head field;
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(event_call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENOENT;
+
+ DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0);
+
+ return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
+}
+
+static struct trace_event_fields eprobe_fields_array[] = {
+ { .type = TRACE_FUNCTION_TYPE,
+ .define_fields = eprobe_event_define_fields },
+ {}
+};
+
+/* Event entry printers */
+static enum print_line_t
+print_eprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct eprobe_trace_entry_head *field;
+ struct trace_event_call *pevent;
+ struct trace_event *probed_event;
+ struct trace_seq *s = &iter->seq;
+ struct trace_probe *tp;
+
+ field = (struct eprobe_trace_entry_head *)iter->ent;
+ tp = trace_probe_primary_from_call(
+ container_of(event, struct trace_event_call, event));
+ if (WARN_ON_ONCE(!tp))
+ goto out;
+
+ trace_seq_printf(s, "%s: (", trace_probe_name(tp));
+
+ probed_event = ftrace_find_event(field->type);
+ if (probed_event) {
+ pevent = container_of(probed_event, struct trace_event_call, event);
+ trace_seq_printf(s, "%s.%s", pevent->class->system,
+ trace_event_name(pevent));
+ } else {
+ trace_seq_printf(s, "%u", field->type);
+ }
+
+ trace_seq_putc(s, ')');
+
+ if (print_probe_args(s, tp->args, tp->nr_args,
+ (u8 *)&field[1], field) < 0)
+ goto out;
+
+ trace_seq_putc(s, '\n');
+ out:
+ return trace_handle_return(s);
+}
+
+static unsigned long get_event_field(struct fetch_insn *code, void *rec)
+{
+ struct ftrace_event_field *field = code->data;
+ unsigned long val;
+ void *addr;
+
+ addr = rec + field->offset;
+
+ switch (field->size) {
+ case 1:
+ if (field->is_signed)
+ val = *(char *)addr;
+ else
+ val = *(unsigned char *)addr;
+ break;
+ case 2:
+ if (field->is_signed)
+ val = *(short *)addr;
+ else
+ val = *(unsigned short *)addr;
+ break;
+ case 4:
+ if (field->is_signed)
+ val = *(int *)addr;
+ else
+ val = *(unsigned int *)addr;
+ break;
+ default:
+ if (field->is_signed)
+ val = *(long *)addr;
+ else
+ val = *(unsigned long *)addr;
+ break;
+ }
+ return val;
+}
+
+static int get_eprobe_size(struct trace_probe *tp, void *rec)
+{
+ struct probe_arg *arg;
+ int i, len, ret = 0;
+
+ for (i = 0; i < tp->nr_args; i++) {
+ arg = tp->args + i;
+ if (unlikely(arg->dynamic)) {
+ unsigned long val;
+
+ val = get_event_field(arg->code, rec);
+ len = process_fetch_insn_bottom(arg->code + 1, val, NULL, NULL);
+ if (len > 0)
+ ret += len;
+ }
+ }
+
+ return ret;
+}
+
+/* Kprobe specific fetch functions */
+
+/* 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 *dest,
+ void *base)
+{
+ unsigned long val;
+
+ val = get_event_field(code, rec);
+ return process_fetch_insn_bottom(code + 1, val, dest, base);
+}
+NOKPROBE_SYMBOL(process_fetch_insn)
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+fetch_store_strlen_user(unsigned long addr)
+{
+ const void __user *uaddr = (__force const void __user *)addr;
+
+ return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+}
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+fetch_store_strlen(unsigned long addr)
+{
+ int ret, len = 0;
+ u8 c;
+
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ if (addr < TASK_SIZE)
+ return fetch_store_strlen_user(addr);
+#endif
+
+ do {
+ ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
+ len++;
+ } while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+ return (ret < 0) ? ret : len;
+}
+
+/*
+ * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
+ * with max length and relative data location.
+ */
+static nokprobe_inline int
+fetch_store_string_user(unsigned long addr, void *dest, void *base)
+{
+ const void __user *uaddr = (__force const void __user *)addr;
+ int maxlen = get_loc_len(*(u32 *)dest);
+ void *__dest;
+ long ret;
+
+ if (unlikely(!maxlen))
+ return -ENOMEM;
+
+ __dest = get_loc_data(dest, base);
+
+ ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
+ if (ret >= 0)
+ *(u32 *)dest = make_data_loc(ret, __dest - base);
+
+ return ret;
+}
+
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
+ * length and relative data location.
+ */
+static nokprobe_inline int
+fetch_store_string(unsigned long addr, void *dest, void *base)
+{
+ int maxlen = get_loc_len(*(u32 *)dest);
+ void *__dest;
+ long ret;
+
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ if ((unsigned long)addr < TASK_SIZE)
+ return fetch_store_string_user(addr, dest, base);
+#endif
+
+ if (unlikely(!maxlen))
+ return -ENOMEM;
+
+ __dest = get_loc_data(dest, base);
+
+ /*
+ * Try to get string again, since the string can be changed while
+ * probing.
+ */
+ ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
+ if (ret >= 0)
+ *(u32 *)dest = make_data_loc(ret, __dest - base);
+
+ return ret;
+}
+
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size)
+{
+ const void __user *uaddr = (__force const void __user *)src;
+
+ return copy_from_user_nofault(dest, uaddr, size);
+}
+
+static nokprobe_inline int
+probe_mem_read(void *dest, void *src, size_t size)
+{
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ if ((unsigned long)src < TASK_SIZE)
+ return probe_mem_read_user(dest, src, size);
+#endif
+ return copy_from_kernel_nofault(dest, src, size);
+}
+
+/* eprobe handler */
+static inline void
+__eprobe_trace_func(struct eprobe_data *edata, void *rec)
+{
+ struct eprobe_trace_entry_head *entry;
+ struct trace_event_call *call = trace_probe_event_call(&edata->ep->tp);
+ struct trace_event_buffer fbuffer;
+ int dsize;
+
+ if (WARN_ON_ONCE(call != edata->file->event_call))
+ return;
+
+ if (trace_trigger_soft_disabled(edata->file))
+ return;
+
+ fbuffer.trace_ctx = tracing_gen_ctx();
+ fbuffer.trace_file = edata->file;
+
+ dsize = get_eprobe_size(&edata->ep->tp, rec);
+ fbuffer.regs = NULL;
+
+ fbuffer.event =
+ trace_event_buffer_lock_reserve(&fbuffer.buffer, edata->file,
+ call->event.type,
+ sizeof(*entry) + edata->ep->tp.size + dsize,
+ fbuffer.trace_ctx);
+ if (!fbuffer.event)
+ return;
+
+ entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
+ if (edata->ep->event)
+ entry->type = edata->ep->event->event.type;
+ else
+ entry->type = 0;
+ store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize);
+
+ trace_event_buffer_commit(&fbuffer);
+}
+
+/*
+ * The event probe implementation uses event triggers to get access to
+ * the event it is attached to, but is not an actual trigger. The below
+ * functions are just stubs to fulfill what is needed to use the trigger
+ * infrastructure.
+ */
+static int eprobe_trigger_init(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ return 0;
+}
+
+static void eprobe_trigger_free(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+
+}
+
+static int eprobe_trigger_print(struct seq_file *m,
+ struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
+{
+ /* Do not print eprobe event triggers */
+ return 0;
+}
+
+static void eprobe_trigger_func(struct event_trigger_data *data,
+ struct trace_buffer *buffer, void *rec,
+ struct ring_buffer_event *rbe)
+{
+ struct eprobe_data *edata = data->private_data;
+
+ __eprobe_trace_func(edata, rec);
+}
+
+static struct event_trigger_ops eprobe_trigger_ops = {
+ .func = eprobe_trigger_func,
+ .print = eprobe_trigger_print,
+ .init = eprobe_trigger_init,
+ .free = eprobe_trigger_free,
+};
+
+static int eprobe_trigger_cmd_func(struct event_command *cmd_ops,
+ struct trace_event_file *file,
+ char *glob, char *cmd, char *param)
+{
+ return -1;
+}
+
+static int eprobe_trigger_reg_func(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct trace_event_file *file)
+{
+ return -1;
+}
+
+static void eprobe_trigger_unreg_func(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *data,
+ struct trace_event_file *file)
+{
+
+}
+
+static struct event_trigger_ops *eprobe_trigger_get_ops(char *cmd,
+ char *param)
+{
+ return &eprobe_trigger_ops;
+}
+
+static struct event_command event_trigger_cmd = {
+ .name = "eprobe",
+ .trigger_type = ETT_EVENT_EPROBE,
+ .flags = EVENT_CMD_FL_NEEDS_REC,
+ .func = eprobe_trigger_cmd_func,
+ .reg = eprobe_trigger_reg_func,
+ .unreg = eprobe_trigger_unreg_func,
+ .unreg_all = NULL,
+ .get_trigger_ops = eprobe_trigger_get_ops,
+ .set_filter = NULL,
+};
+
+static struct event_trigger_data *
+new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
+{
+ struct event_trigger_data *trigger;
+ struct eprobe_data *edata;
+
+ edata = kzalloc(sizeof(*edata), GFP_KERNEL);
+ trigger = kzalloc(sizeof(*trigger), GFP_KERNEL);
+ if (!trigger || !edata) {
+ kfree(edata);
+ kfree(trigger);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ trigger->flags = EVENT_TRIGGER_FL_PROBE;
+ trigger->count = -1;
+ trigger->ops = &eprobe_trigger_ops;
+
+ /*
+ * EVENT PROBE triggers are not registered as commands with
+ * register_event_command(), as they are not controlled by the user
+ * from the trigger file
+ */
+ trigger->cmd_ops = &event_trigger_cmd;
+
+ INIT_LIST_HEAD(&trigger->list);
+ RCU_INIT_POINTER(trigger->filter, NULL);
+
+ edata->file = file;
+ edata->ep = ep;
+ trigger->private_data = edata;
+
+ return trigger;
+}
+
+static int enable_eprobe(struct trace_eprobe *ep,
+ struct trace_event_file *eprobe_file)
+{
+ struct event_trigger_data *trigger;
+ struct trace_event_file *file;
+ struct trace_array *tr = eprobe_file->tr;
+
+ file = find_event_file(tr, ep->event_system, ep->event_name);
+ if (!file)
+ return -ENOENT;
+ trigger = new_eprobe_trigger(ep, eprobe_file);
+ if (IS_ERR(trigger))
+ return PTR_ERR(trigger);
+
+ list_add_tail_rcu(&trigger->list, &file->triggers);
+
+ trace_event_trigger_enable_disable(file, 1);
+ update_cond_flag(file);
+
+ return 0;
+}
+
+static struct trace_event_functions eprobe_funcs = {
+ .trace = print_eprobe_event
+};
+
+static int disable_eprobe(struct trace_eprobe *ep,
+ struct trace_array *tr)
+{
+ struct event_trigger_data *trigger;
+ struct trace_event_file *file;
+ struct eprobe_data *edata;
+
+ file = find_event_file(tr, ep->event_system, ep->event_name);
+ if (!file)
+ return -ENOENT;
+
+ list_for_each_entry(trigger, &file->triggers, list) {
+ if (!(trigger->flags & EVENT_TRIGGER_FL_PROBE))
+ continue;
+ edata = trigger->private_data;
+ if (edata->ep == ep)
+ break;
+ }
+ if (list_entry_is_head(trigger, &file->triggers, list))
+ return -ENODEV;
+
+ list_del_rcu(&trigger->list);
+
+ trace_event_trigger_enable_disable(file, 0);
+ update_cond_flag(file);
+ return 0;
+}
+
+static int enable_trace_eprobe(struct trace_event_call *call,
+ struct trace_event_file *file)
+{
+ struct trace_probe *pos, *tp;
+ struct trace_eprobe *ep;
+ bool enabled;
+ int ret = 0;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+ enabled = trace_probe_is_enabled(tp);
+
+ /* This also changes "enabled" state */
+ if (file) {
+ ret = trace_probe_add_file(tp, file);
+ if (ret)
+ return ret;
+ } else
+ trace_probe_set_flag(tp, TP_FLAG_PROFILE);
+
+ if (enabled)
+ return 0;
+
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ ep = container_of(pos, struct trace_eprobe, tp);
+ ret = enable_eprobe(ep, file);
+ if (ret)
+ break;
+ enabled = true;
+ }
+
+ if (ret) {
+ /* Failed to enable one of them. Roll back all */
+ if (enabled)
+ disable_eprobe(ep, file->tr);
+ if (file)
+ trace_probe_remove_file(tp, file);
+ else
+ trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
+ }
+
+ return ret;
+}
+
+static int disable_trace_eprobe(struct trace_event_call *call,
+ struct trace_event_file *file)
+{
+ struct trace_probe *pos, *tp;
+ struct trace_eprobe *ep;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+
+ if (file) {
+ if (!trace_probe_get_file_link(tp, file))
+ return -ENOENT;
+ if (!trace_probe_has_single_file(tp))
+ goto out;
+ trace_probe_clear_flag(tp, TP_FLAG_TRACE);
+ } else
+ trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
+
+ if (!trace_probe_is_enabled(tp)) {
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ ep = container_of(pos, struct trace_eprobe, tp);
+ disable_eprobe(ep, file->tr);
+ }
+ }
+
+ out:
+ if (file)
+ /*
+ * Synchronization is done in below function. For perf event,
+ * file == NULL and perf_trace_event_unreg() calls
+ * tracepoint_synchronize_unregister() to ensure synchronize
+ * event. We don't need to care about it.
+ */
+ trace_probe_remove_file(tp, file);
+
+ return 0;
+}
+
+static int eprobe_register(struct trace_event_call *event,
+ enum trace_reg type, void *data)
+{
+ struct trace_event_file *file = data;
+
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return enable_trace_eprobe(event, file);
+ case TRACE_REG_UNREGISTER:
+ return disable_trace_eprobe(event, file);
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ case TRACE_REG_PERF_UNREGISTER:
+ case TRACE_REG_PERF_OPEN:
+ case TRACE_REG_PERF_CLOSE:
+ case TRACE_REG_PERF_ADD:
+ case TRACE_REG_PERF_DEL:
+ return 0;
+#endif
+ }
+ return 0;
+}
+
+static inline void init_trace_eprobe_call(struct trace_eprobe *ep)
+{
+ struct trace_event_call *call = trace_probe_event_call(&ep->tp);
+
+ call->flags = TRACE_EVENT_FL_EPROBE;
+ call->event.funcs = &eprobe_funcs;
+ call->class->fields_array = eprobe_fields_array;
+ call->class->reg = eprobe_register;
+}
+
+static struct trace_event_call *
+find_and_get_event(const char *system, const char *event_name)
+{
+ struct trace_event_call *tp_event;
+ const char *name;
+
+ list_for_each_entry(tp_event, &ftrace_events, list) {
+ /* Skip other probes and ftrace events */
+ if (tp_event->flags &
+ (TRACE_EVENT_FL_IGNORE_ENABLE |
+ TRACE_EVENT_FL_KPROBE |
+ TRACE_EVENT_FL_UPROBE |
+ TRACE_EVENT_FL_EPROBE))
+ continue;
+ if (!tp_event->class->system ||
+ strcmp(system, tp_event->class->system))
+ continue;
+ name = trace_event_name(tp_event);
+ if (!name || strcmp(event_name, name))
+ continue;
+ if (!trace_event_try_get_ref(tp_event)) {
+ return NULL;
+ break;
+ }
+ return tp_event;
+ break;
+ }
+ return NULL;
+}
+
+static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[], int i)
+{
+ unsigned int flags = TPARG_FL_KERNEL | TPARG_FL_TPOINT;
+ int ret;
+
+ ret = traceprobe_parse_probe_arg(&ep->tp, i, argv[i], flags);
+ if (ret)
+ return ret;
+
+ if (ep->tp.args[i].code->op == FETCH_OP_TP_ARG)
+ ret = trace_eprobe_tp_arg_update(ep, i);
+
+ return ret;
+}
+
+static int __trace_eprobe_create(int argc, const char *argv[])
+{
+ /*
+ * Argument syntax:
+ * e[:[GRP/]ENAME] SYSTEM.EVENT [FETCHARGS]
+ * Fetch args:
+ * <name>=$<field>[:TYPE]
+ */
+ const char *event = NULL, *group = EPROBE_EVENT_SYSTEM;
+ const char *sys_event = NULL, *sys_name = NULL;
+ struct trace_event_call *event_call;
+ struct trace_eprobe *ep = NULL;
+ char buf1[MAX_EVENT_NAME_LEN];
+ char buf2[MAX_EVENT_NAME_LEN];
+ int ret = 0;
+ int i;
+
+ if (argc < 2 || argv[0][0] != 'e')
+ return -ECANCELED;
+
+ trace_probe_log_init("event_probe", argc, argv);
+
+ event = strchr(&argv[0][1], ':');
+ if (event) {
+ event++;
+ ret = traceprobe_parse_event_name(&event, &group, buf1,
+ event - argv[0]);
+ if (ret)
+ goto parse_error;
+ } else {
+ strscpy(buf1, argv[1], MAX_EVENT_NAME_LEN);
+ sanitize_event_name(buf1);
+ event = buf1;
+ }
+ if (!is_good_name(event) || !is_good_name(group))
+ goto parse_error;
+
+ sys_event = argv[1];
+ ret = traceprobe_parse_event_name(&sys_event, &sys_name, buf2,
+ sys_event - argv[1]);
+ if (ret || !sys_name)
+ goto parse_error;
+ if (!is_good_name(sys_event) || !is_good_name(sys_name))
+ goto parse_error;
+
+ mutex_lock(&event_mutex);
+ event_call = find_and_get_event(sys_name, sys_event);
+ ep = alloc_event_probe(group, event, event_call, argc - 2);
+ mutex_unlock(&event_mutex);
+
+ if (IS_ERR(ep)) {
+ ret = PTR_ERR(ep);
+ /* This must return -ENOMEM, else there is a bug */
+ WARN_ON_ONCE(ret != -ENOMEM);
+ goto error; /* We know ep is not allocated */
+ }
+
+ argc -= 2; argv += 2;
+ /* parse arguments */
+ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ trace_probe_log_set_index(i + 2);
+ ret = trace_eprobe_tp_update_arg(ep, argv, i);
+ if (ret)
+ goto error;
+ }
+ ret = traceprobe_set_print_fmt(&ep->tp, PROBE_PRINT_EVENT);
+ if (ret < 0)
+ goto error;
+ init_trace_eprobe_call(ep);
+ mutex_lock(&event_mutex);
+ ret = trace_probe_register_event_call(&ep->tp);
+ if (ret) {
+ if (ret == -EEXIST) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(0, EVENT_EXIST);
+ }
+ mutex_unlock(&event_mutex);
+ goto error;
+ }
+ ret = dyn_event_add(&ep->devent, &ep->tp.event->call);
+ mutex_unlock(&event_mutex);
+ return ret;
+parse_error:
+ ret = -EINVAL;
+error:
+ trace_event_probe_cleanup(ep);
+ return ret;
+}
+
+/*
+ * Register dynevent at core_initcall. This allows kernel to setup eprobe
+ * events in postcore_initcall without tracefs.
+ */
+static __init int trace_events_eprobe_init_early(void)
+{
+ int err = 0;
+
+ err = dyn_event_register(&eprobe_dyn_event_ops);
+ if (err)
+ pr_warn("Could not register eprobe_dyn_event_ops\n");
+
+ return err;
+}
+core_initcall(trace_events_eprobe_init_early);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 03be4435d103..6aed10e2f7ce 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -177,7 +177,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
}
}
out:
- module_put(tp_event->mod);
+ trace_event_put_ref(tp_event);
}
static int perf_trace_event_open(struct perf_event *p_event)
@@ -224,10 +224,10 @@ int perf_trace_init(struct perf_event *p_event)
list_for_each_entry(tp_event, &ftrace_events, list) {
if (tp_event->event.type == event_id &&
tp_event->class && tp_event->class->reg &&
- try_module_get(tp_event->mod)) {
+ trace_event_try_get_ref(tp_event)) {
ret = perf_trace_event_init(tp_event, p_event);
if (ret)
- module_put(tp_event->mod);
+ trace_event_put_ref(tp_event);
break;
}
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 80e96989770e..1349b6de5eeb 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2525,7 +2525,10 @@ __register_event(struct trace_event_call *call, struct module *mod)
return ret;
list_add(&call->list, &ftrace_events);
- call->mod = mod;
+ if (call->flags & TRACE_EVENT_FL_DYNAMIC)
+ atomic_set(&call->refcnt, 0);
+ else
+ call->module = mod;
return 0;
}
@@ -2839,7 +2842,9 @@ static void trace_module_remove_events(struct module *mod)
down_write(&trace_event_sem);
list_for_each_entry_safe(call, p, &ftrace_events, list) {
- if (call->mod == mod)
+ if ((call->flags & TRACE_EVENT_FL_DYNAMIC) || !call->module)
+ continue;
+ if (call->module == mod)
__trace_remove_event_call(call);
}
up_write(&trace_event_sem);
@@ -2982,7 +2987,7 @@ struct trace_event_file *trace_get_event_file(const char *instance,
}
/* Don't let event modules unload while in use */
- ret = try_module_get(file->event_call->mod);
+ ret = trace_event_try_get_ref(file->event_call);
if (!ret) {
trace_array_put(tr);
ret = -EBUSY;
@@ -3012,7 +3017,7 @@ EXPORT_SYMBOL_GPL(trace_get_event_file);
void trace_put_event_file(struct trace_event_file *file)
{
mutex_lock(&event_mutex);
- module_put(file->event_call->mod);
+ trace_event_put_ref(file->event_call);
mutex_unlock(&event_mutex);
trace_array_put(file->tr);
@@ -3147,7 +3152,7 @@ static int free_probe_data(void *data)
if (!edata->ref) {
/* Remove the SOFT_MODE flag */
__ftrace_event_enable_disable(edata->file, 0, 1);
- module_put(edata->file->event_call->mod);
+ trace_event_put_ref(edata->file->event_call);
kfree(edata);
}
return 0;
@@ -3280,7 +3285,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash,
out_reg:
/* Don't let event modules unload while probe registered */
- ret = try_module_get(file->event_call->mod);
+ ret = trace_event_try_get_ref(file->event_call);
if (!ret) {
ret = -EBUSY;
goto out_free;
@@ -3310,7 +3315,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash,
out_disable:
__ftrace_event_enable_disable(file, 0, 1);
out_put:
- module_put(file->event_call->mod);
+ trace_event_put_ref(file->event_call);
out_free:
kfree(data);
goto out;
@@ -3376,7 +3381,8 @@ void __trace_early_add_events(struct trace_array *tr)
list_for_each_entry(call, &ftrace_events, list) {
/* Early boot up should not have any modules loaded */
- if (WARN_ON_ONCE(call->mod))
+ if (!(call->flags & TRACE_EVENT_FL_DYNAMIC) &&
+ WARN_ON_ONCE(call->module))
continue;
ret = __trace_early_add_new_event(call, tr);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index a48aa2a2875b..9d91b1c06957 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -121,6 +121,7 @@ struct hist_field {
unsigned int size;
unsigned int offset;
unsigned int is_signed;
+ unsigned long buckets;
const char *type;
struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
struct hist_trigger_data *hist_data;
@@ -219,6 +220,27 @@ static u64 hist_field_log2(struct hist_field *hist_field,
return (u64) ilog2(roundup_pow_of_two(val));
}
+static u64 hist_field_bucket(struct hist_field *hist_field,
+ struct tracing_map_elt *elt,
+ struct trace_buffer *buffer,
+ struct ring_buffer_event *rbe,
+ void *event)
+{
+ struct hist_field *operand = hist_field->operands[0];
+ unsigned long buckets = hist_field->buckets;
+
+ u64 val = operand->fn(operand, elt, buffer, rbe, event);
+
+ if (WARN_ON_ONCE(!buckets))
+ return val;
+
+ if (val >= LONG_MAX)
+ val = div64_ul(val, buckets);
+ else
+ val = (u64)((unsigned long)val / buckets);
+ return val * buckets;
+}
+
static u64 hist_field_plus(struct hist_field *hist_field,
struct tracing_map_elt *elt,
struct trace_buffer *buffer,
@@ -318,6 +340,7 @@ enum hist_field_flags {
HIST_FIELD_FL_VAR_REF = 1 << 14,
HIST_FIELD_FL_CPU = 1 << 15,
HIST_FIELD_FL_ALIAS = 1 << 16,
+ HIST_FIELD_FL_BUCKET = 1 << 17,
};
struct var_defs {
@@ -1109,7 +1132,8 @@ static const char *hist_field_name(struct hist_field *field,
if (field->field)
field_name = field->field->name;
else if (field->flags & HIST_FIELD_FL_LOG2 ||
- field->flags & HIST_FIELD_FL_ALIAS)
+ field->flags & HIST_FIELD_FL_ALIAS ||
+ field->flags & HIST_FIELD_FL_BUCKET)
field_name = hist_field_name(field->operands[0], ++level);
else if (field->flags & HIST_FIELD_FL_CPU)
field_name = "common_cpu";
@@ -1396,17 +1420,17 @@ static int hist_trigger_elt_data_alloc(struct tracing_map_elt *elt)
struct hist_trigger_data *hist_data = elt->map->private_data;
unsigned int size = TASK_COMM_LEN;
struct hist_elt_data *elt_data;
- struct hist_field *key_field;
+ struct hist_field *hist_field;
unsigned int i, n_str;
elt_data = kzalloc(sizeof(*elt_data), GFP_KERNEL);
if (!elt_data)
return -ENOMEM;
- for_each_hist_key_field(i, hist_data) {
- key_field = hist_data->fields[i];
+ for_each_hist_field(i, hist_data) {
+ hist_field = hist_data->fields[i];
- if (key_field->flags & HIST_FIELD_FL_EXECNAME) {
+ if (hist_field->flags & HIST_FIELD_FL_EXECNAME) {
elt_data->comm = kzalloc(size, GFP_KERNEL);
if (!elt_data->comm) {
kfree(elt_data);
@@ -1470,6 +1494,8 @@ static const char *get_hist_field_flags(struct hist_field *hist_field)
flags_str = "syscall";
else if (hist_field->flags & HIST_FIELD_FL_LOG2)
flags_str = "log2";
+ else if (hist_field->flags & HIST_FIELD_FL_BUCKET)
+ flags_str = "buckets";
else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP_USECS)
flags_str = "usecs";
@@ -1590,7 +1616,9 @@ static void __destroy_hist_field(struct hist_field *hist_field)
kfree(hist_field->var.name);
kfree(hist_field->name);
- kfree(hist_field->type);
+
+ /* Can likely be a const */
+ kfree_const(hist_field->type);
kfree(hist_field->system);
kfree(hist_field->event_name);
@@ -1647,9 +1675,7 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (flags & HIST_FIELD_FL_HITCOUNT) {
hist_field->fn = hist_field_counter;
hist_field->size = sizeof(u64);
- hist_field->type = kstrdup("u64", GFP_KERNEL);
- if (!hist_field->type)
- goto free;
+ hist_field->type = "u64";
goto out;
}
@@ -1658,12 +1684,13 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
goto out;
}
- if (flags & HIST_FIELD_FL_LOG2) {
- unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
- hist_field->fn = hist_field_log2;
+ if (flags & (HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET)) {
+ unsigned long fl = flags & ~(HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET);
+ hist_field->fn = flags & HIST_FIELD_FL_LOG2 ? hist_field_log2 :
+ hist_field_bucket;
hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
hist_field->size = hist_field->operands[0]->size;
- hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL);
+ hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL);
if (!hist_field->type)
goto free;
goto out;
@@ -1672,18 +1699,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (flags & HIST_FIELD_FL_TIMESTAMP) {
hist_field->fn = hist_field_timestamp;
hist_field->size = sizeof(u64);
- hist_field->type = kstrdup("u64", GFP_KERNEL);
- if (!hist_field->type)
- goto free;
+ hist_field->type = "u64";
goto out;
}
if (flags & HIST_FIELD_FL_CPU) {
hist_field->fn = hist_field_cpu;
hist_field->size = sizeof(int);
- hist_field->type = kstrdup("unsigned int", GFP_KERNEL);
- if (!hist_field->type)
- goto free;
+ hist_field->type = "unsigned int";
goto out;
}
@@ -1696,7 +1719,7 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
flags |= HIST_FIELD_FL_STRING;
hist_field->size = MAX_FILTER_STR_VAL;
- hist_field->type = kstrdup(field->type, GFP_KERNEL);
+ hist_field->type = kstrdup_const(field->type, GFP_KERNEL);
if (!hist_field->type)
goto free;
@@ -1709,7 +1732,7 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
} else {
hist_field->size = field->size;
hist_field->is_signed = field->is_signed;
- hist_field->type = kstrdup(field->type, GFP_KERNEL);
+ hist_field->type = kstrdup_const(field->type, GFP_KERNEL);
if (!hist_field->type)
goto free;
@@ -1795,7 +1818,7 @@ static int init_var_ref(struct hist_field *ref_field,
}
}
- ref_field->type = kstrdup(var_field->type, GFP_KERNEL);
+ ref_field->type = kstrdup_const(var_field->type, GFP_KERNEL);
if (!ref_field->type) {
err = -ENOMEM;
goto free;
@@ -1953,7 +1976,7 @@ static struct hist_field *parse_var_ref(struct hist_trigger_data *hist_data,
static struct ftrace_event_field *
parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
- char *field_str, unsigned long *flags)
+ char *field_str, unsigned long *flags, unsigned long *buckets)
{
struct ftrace_event_field *field = NULL;
char *field_name, *modifier, *str;
@@ -1980,7 +2003,22 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
*flags |= HIST_FIELD_FL_LOG2;
else if (strcmp(modifier, "usecs") == 0)
*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
- else {
+ else if (strncmp(modifier, "bucket", 6) == 0) {
+ int ret;
+
+ modifier += 6;
+
+ if (*modifier == 's')
+ modifier++;
+ if (*modifier != '=')
+ goto error;
+ modifier++;
+ ret = kstrtoul(modifier, 0, buckets);
+ if (ret || !(*buckets))
+ goto error;
+ *flags |= HIST_FIELD_FL_BUCKET;
+ } else {
+ error:
hist_err(tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(modifier));
field = ERR_PTR(-EINVAL);
goto out;
@@ -2049,6 +2087,7 @@ static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
char *s, *ref_system = NULL, *ref_event = NULL, *ref_var = str;
struct ftrace_event_field *field = NULL;
struct hist_field *hist_field = NULL;
+ unsigned long buckets = 0;
int ret = 0;
s = strchr(str, '.');
@@ -2086,7 +2125,7 @@ static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
} else
str = s;
- field = parse_field(hist_data, file, str, flags);
+ field = parse_field(hist_data, file, str, flags, &buckets);
if (IS_ERR(field)) {
ret = PTR_ERR(field);
goto out;
@@ -2097,6 +2136,7 @@ static struct hist_field *parse_atom(struct hist_trigger_data *hist_data,
ret = -ENOMEM;
goto out;
}
+ hist_field->buckets = buckets;
return hist_field;
out:
@@ -2171,7 +2211,7 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data,
expr->operands[0] = operand1;
expr->operator = FIELD_OP_UNARY_MINUS;
expr->name = expr_str(expr, 0);
- expr->type = kstrdup(operand1->type, GFP_KERNEL);
+ expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
if (!expr->type) {
ret = -ENOMEM;
goto free;
@@ -2311,7 +2351,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
expr->operator = field_op;
expr->name = expr_str(expr, 0);
- expr->type = kstrdup(operand1->type, GFP_KERNEL);
+ expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
if (!expr->type) {
ret = -ENOMEM;
goto free;
@@ -2699,10 +2739,10 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
var->var.hist_data = var->hist_data = hist_data;
var->size = size;
var->var.name = kstrdup(name, GFP_KERNEL);
- var->type = kstrdup(type, GFP_KERNEL);
+ var->type = kstrdup_const(type, GFP_KERNEL);
if (!var->var.name || !var->type) {
+ kfree_const(var->type);
kfree(var->var.name);
- kfree(var->type);
kfree(var);
var = ERR_PTR(-ENOMEM);
}
@@ -3731,6 +3771,41 @@ static int create_val_field(struct hist_trigger_data *hist_data,
return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0);
}
+static const char *no_comm = "(no comm)";
+
+static u64 hist_field_execname(struct hist_field *hist_field,
+ struct tracing_map_elt *elt,
+ struct trace_buffer *buffer,
+ struct ring_buffer_event *rbe,
+ void *event)
+{
+ struct hist_elt_data *elt_data;
+
+ if (WARN_ON_ONCE(!elt))
+ return (u64)(unsigned long)no_comm;
+
+ elt_data = elt->private_data;
+
+ if (WARN_ON_ONCE(!elt_data->comm))
+ return (u64)(unsigned long)no_comm;
+
+ return (u64)(unsigned long)(elt_data->comm);
+}
+
+/* Convert a var that points to common_pid.execname to a string */
+static void update_var_execname(struct hist_field *hist_field)
+{
+ hist_field->flags = HIST_FIELD_FL_STRING | HIST_FIELD_FL_VAR |
+ HIST_FIELD_FL_EXECNAME;
+ hist_field->size = MAX_FILTER_STR_VAL;
+ hist_field->is_signed = 0;
+
+ kfree_const(hist_field->type);
+ hist_field->type = "char[]";
+
+ hist_field->fn = hist_field_execname;
+}
+
static int create_var_field(struct hist_trigger_data *hist_data,
unsigned int val_idx,
struct trace_event_file *file,
@@ -3755,6 +3830,9 @@ static int create_var_field(struct hist_trigger_data *hist_data,
ret = __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags);
+ if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_EXECNAME)
+ update_var_execname(hist_data->fields[val_idx]);
+
if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_STRING)
hist_data->fields[val_idx]->var_str_idx = hist_data->n_var_str++;
@@ -4698,6 +4776,11 @@ static void hist_trigger_print_key(struct seq_file *m,
} else if (key_field->flags & HIST_FIELD_FL_LOG2) {
seq_printf(m, "%s: ~ 2^%-2llu", field_name,
*(u64 *)(key + key_field->offset));
+ } else if (key_field->flags & HIST_FIELD_FL_BUCKET) {
+ unsigned long buckets = key_field->buckets;
+ uval = *(u64 *)(key + key_field->offset);
+ seq_printf(m, "%s: ~ %llu-%llu", field_name,
+ uval, uval + buckets -1);
} else if (key_field->flags & HIST_FIELD_FL_STRING) {
seq_printf(m, "%s: %-50s", field_name,
(char *)(key + key_field->offset));
@@ -5137,6 +5220,8 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
seq_printf(m, ".%s", flags);
}
}
+ if (hist_field->buckets)
+ seq_printf(m, "=%ld", hist_field->buckets);
}
static int event_hist_trigger_print(struct seq_file *m,
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 9315fc03e303..d54094b7a9d7 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1298,7 +1298,7 @@ static int __create_synth_event(const char *name, const char *raw_fields)
}
ret = register_synth_event(event);
if (!ret)
- dyn_event_add(&event->devent);
+ dyn_event_add(&event->devent, &event->call);
else
free_synth_event(event);
out:
@@ -1369,13 +1369,15 @@ static int destroy_synth_event(struct synth_event *se)
int ret;
if (se->ref)
- ret = -EBUSY;
- else {
- ret = unregister_synth_event(se);
- if (!ret) {
- dyn_event_remove(&se->devent);
- free_synth_event(se);
- }
+ return -EBUSY;
+
+ if (trace_event_dyn_busy(&se->call))
+ return -EBUSY;
+
+ ret = unregister_synth_event(se);
+ if (!ret) {
+ dyn_event_remove(&se->devent);
+ free_synth_event(se);
}
return ret;
@@ -2102,6 +2104,9 @@ static int synth_event_release(struct dyn_event *ev)
if (event->ref)
return -EBUSY;
+ if (trace_event_dyn_busy(&event->call))
+ return -EBUSY;
+
ret = unregister_synth_event(event);
if (ret)
return ret;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index cf84d0f6583a..3d5c07239a2a 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -124,6 +124,18 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos)
return seq_list_next(t, &event_file->triggers, pos);
}
+static bool check_user_trigger(struct trace_event_file *file)
+{
+ struct event_trigger_data *data;
+
+ list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->flags & EVENT_TRIGGER_FL_PROBE)
+ continue;
+ return true;
+ }
+ return false;
+}
+
static void *trigger_start(struct seq_file *m, loff_t *pos)
{
struct trace_event_file *event_file;
@@ -134,7 +146,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos)
if (unlikely(!event_file))
return ERR_PTR(-ENODEV);
- if (list_empty(&event_file->triggers))
+ if (list_empty(&event_file->triggers) || !check_user_trigger(event_file))
return *pos == 0 ? SHOW_AVAILABLE_TRIGGERS : NULL;
return seq_list_start(&event_file->triggers, *pos);
@@ -1334,7 +1346,7 @@ void event_enable_trigger_free(struct event_trigger_ops *ops,
if (!data->ref) {
/* Remove the SOFT_MODE flag */
trace_event_enable_disable(enable_data->file, 0, 1);
- module_put(enable_data->file->event_call->mod);
+ trace_event_put_ref(enable_data->file->event_call);
trigger_data_free(data);
kfree(enable_data);
}
@@ -1481,7 +1493,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
out_reg:
/* Don't let event modules unload while probe registered */
- ret = try_module_get(event_enable_file->event_call->mod);
+ ret = trace_event_try_get_ref(event_enable_file->event_call);
if (!ret) {
ret = -EBUSY;
goto out_free;
@@ -1510,7 +1522,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
out_disable:
trace_event_enable_disable(event_enable_file, 0, 1);
out_put:
- module_put(event_enable_file->event_call->mod);
+ trace_event_put_ref(event_enable_file->event_call);
out_free:
if (cmd_ops->set_filter)
cmd_ops->set_filter(NULL, trigger_data, NULL);
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 14f46aae1981..1b83d75eb103 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -325,10 +325,10 @@ static void move_to_next_cpu(void)
if (!cpumask_equal(current_mask, current->cpus_ptr))
goto change_mode;
- get_online_cpus();
+ cpus_read_lock();
cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
next_cpu = cpumask_next(raw_smp_processor_id(), current_mask);
- put_online_cpus();
+ cpus_read_unlock();
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(current_mask);
@@ -398,7 +398,7 @@ static void stop_single_kthread(void)
struct hwlat_kthread_data *kdata = get_cpu_data();
struct task_struct *kthread;
- get_online_cpus();
+ cpus_read_lock();
kthread = kdata->kthread;
if (!kthread)
@@ -408,7 +408,7 @@ static void stop_single_kthread(void)
kdata->kthread = NULL;
out_put_cpus:
- put_online_cpus();
+ cpus_read_unlock();
}
@@ -425,14 +425,14 @@ static int start_single_kthread(struct trace_array *tr)
struct task_struct *kthread;
int next_cpu;
- get_online_cpus();
+ cpus_read_lock();
if (kdata->kthread)
goto out_put_cpus;
kthread = kthread_create(kthread_fn, NULL, "hwlatd");
if (IS_ERR(kthread)) {
pr_err(BANNER "could not start sampling thread\n");
- put_online_cpus();
+ cpus_read_unlock();
return -ENOMEM;
}
@@ -452,7 +452,7 @@ static int start_single_kthread(struct trace_array *tr)
wake_up_process(kthread);
out_put_cpus:
- put_online_cpus();
+ cpus_read_unlock();
return 0;
}
@@ -479,10 +479,10 @@ static void stop_per_cpu_kthreads(void)
{
unsigned int cpu;
- get_online_cpus();
+ cpus_read_lock();
for_each_online_cpu(cpu)
stop_cpu_kthread(cpu);
- put_online_cpus();
+ cpus_read_unlock();
}
/*
@@ -515,7 +515,7 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
mutex_lock(&trace_types_lock);
mutex_lock(&hwlat_data.lock);
- get_online_cpus();
+ cpus_read_lock();
if (!hwlat_busy || hwlat_data.thread_mode != MODE_PER_CPU)
goto out_unlock;
@@ -526,7 +526,7 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
start_cpu_kthread(cpu);
out_unlock:
- put_online_cpus();
+ cpus_read_unlock();
mutex_unlock(&hwlat_data.lock);
mutex_unlock(&trace_types_lock);
}
@@ -582,7 +582,7 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
unsigned int cpu;
int retval;
- get_online_cpus();
+ cpus_read_lock();
/*
* Run only on CPUs in which hwlat is allowed to run.
*/
@@ -596,12 +596,12 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
if (retval)
goto out_error;
}
- put_online_cpus();
+ cpus_read_unlock();
return 0;
out_error:
- put_online_cpus();
+ cpus_read_unlock();
stop_per_cpu_kthreads();
return retval;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ea6178cb5e33..3a64ba4bbad6 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -80,10 +80,6 @@ static struct trace_kprobe *to_trace_kprobe(struct dyn_event *ev)
for_each_dyn_event(dpos) \
if (is_trace_kprobe(dpos) && (pos = to_trace_kprobe(dpos)))
-#define SIZEOF_TRACE_KPROBE(n) \
- (offsetof(struct trace_kprobe, tp.args) + \
- (sizeof(struct probe_arg) * (n)))
-
static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
{
return tk->rp.handler != NULL;
@@ -265,7 +261,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
struct trace_kprobe *tk;
int ret = -ENOMEM;
- tk = kzalloc(SIZEOF_TRACE_KPROBE(nargs), GFP_KERNEL);
+ tk = kzalloc(struct_size(tk, tp.args, nargs), GFP_KERNEL);
if (!tk)
return ERR_PTR(ret);
@@ -543,6 +539,10 @@ static int unregister_trace_kprobe(struct trace_kprobe *tk)
if (trace_probe_is_enabled(&tk->tp))
return -EBUSY;
+ /* If there's a reference to the dynamic event */
+ if (trace_event_dyn_busy(trace_probe_event_call(&tk->tp)))
+ return -EBUSY;
+
/* Will fail if probe is being used by ftrace or perf */
if (unregister_kprobe_event(tk))
return -EBUSY;
@@ -618,7 +618,7 @@ static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to)
if (ret)
trace_probe_unlink(&tk->tp);
else
- dyn_event_add(&tk->devent);
+ dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp));
return ret;
}
@@ -647,7 +647,11 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
/* Register new event */
ret = register_kprobe_event(tk);
if (ret) {
- pr_warn("Failed to register probe event(%d)\n", ret);
+ 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);
goto end;
}
@@ -661,7 +665,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
if (ret < 0)
unregister_kprobe_event(tk);
else
- dyn_event_add(&tk->devent);
+ dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp));
end:
mutex_unlock(&event_mutex);
@@ -703,14 +707,6 @@ static struct notifier_block trace_kprobe_module_nb = {
.priority = 1 /* Invoked after kprobe module callback */
};
-/* Convert certain expected symbols into '_' when generating event names */
-static inline void sanitize_event_name(char *name)
-{
- while (*name++ != '\0')
- if (*name == ':' || *name == '.')
- *name = '_';
-}
-
static int __trace_kprobe_create(int argc, const char *argv[])
{
/*
@@ -742,6 +738,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
bool is_return = false;
char *symbol = NULL, *tmp = NULL;
const char *event = NULL, *group = KPROBE_EVENT_SYSTEM;
+ enum probe_print_type ptype;
int maxactive = 0;
long offset = 0;
void *addr = NULL;
@@ -869,20 +866,14 @@ static int __trace_kprobe_create(int argc, const char *argv[])
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
- tmp = kstrdup(argv[i], GFP_KERNEL);
- if (!tmp) {
- ret = -ENOMEM;
- goto error;
- }
-
trace_probe_log_set_index(i + 2);
- ret = traceprobe_parse_probe_arg(&tk->tp, i, tmp, flags);
- kfree(tmp);
+ ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], flags);
if (ret)
goto error; /* This can be -ENOMEM */
}
- ret = traceprobe_set_print_fmt(&tk->tp, is_return);
+ ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+ ret = traceprobe_set_print_fmt(&tk->tp, ptype);
if (ret < 0)
goto error;
@@ -1330,9 +1321,10 @@ probe_mem_read(void *dest, void *src, size_t size)
/* 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, struct pt_regs *regs, void *dest,
+process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
void *base)
{
+ struct pt_regs *regs = rec;
unsigned long val;
retry:
@@ -1806,6 +1798,7 @@ struct trace_event_call *
create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
bool is_return)
{
+ enum probe_print_type ptype;
struct trace_kprobe *tk;
int ret;
char *event;
@@ -1829,7 +1822,9 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
init_trace_event_call(tk);
- if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) {
+ ptype = trace_kprobe_is_return(tk) ?
+ PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+ if (traceprobe_set_print_fmt(&tk->tp, ptype) < 0) {
ret = -ENOMEM;
goto error;
}
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index b61eefe5ccf5..65b08b8e5bf8 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1498,12 +1498,12 @@ static void stop_per_cpu_kthreads(void)
{
int cpu;
- get_online_cpus();
+ cpus_read_lock();
for_each_online_cpu(cpu)
stop_kthread(cpu);
- put_online_cpus();
+ cpus_read_unlock();
}
/*
@@ -1551,7 +1551,7 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
int retval;
int cpu;
- get_online_cpus();
+ cpus_read_lock();
/*
* Run only on CPUs in which trace and osnoise are allowed to run.
*/
@@ -1572,7 +1572,7 @@ static int start_per_cpu_kthreads(struct trace_array *tr)
}
}
- put_online_cpus();
+ cpus_read_unlock();
return 0;
}
@@ -1590,7 +1590,7 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
goto out_unlock_trace;
mutex_lock(&interface_lock);
- get_online_cpus();
+ cpus_read_lock();
if (!cpumask_test_cpu(cpu, &osnoise_cpumask))
goto out_unlock;
@@ -1601,7 +1601,7 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
start_kthread(cpu);
out_unlock:
- put_online_cpus();
+ cpus_read_unlock();
mutex_unlock(&interface_lock);
out_unlock_trace:
mutex_unlock(&trace_types_lock);
@@ -1743,11 +1743,11 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
/*
* osnoise_cpumask is read by CPU hotplug operations.
*/
- get_online_cpus();
+ cpus_read_lock();
cpumask_copy(&osnoise_cpumask, osnoise_cpumask_new);
- put_online_cpus();
+ cpus_read_unlock();
mutex_unlock(&interface_lock);
if (running)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 15413ad7cef2..3ed2a3f37297 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -233,6 +233,9 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
int len;
slash = strchr(event, '/');
+ if (!slash)
+ slash = strchr(event, '.');
+
if (slash) {
if (slash == event) {
trace_probe_log_err(offset, NO_GROUP_NAME);
@@ -316,6 +319,13 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
code->op = FETCH_OP_ARG;
code->param = (unsigned int)param - 1;
#endif
+ } else if (flags & TPARG_FL_TPOINT) {
+ if (code->data)
+ return -EFAULT;
+ code->data = kstrdup(arg, GFP_KERNEL);
+ if (!code->data)
+ return -ENOMEM;
+ code->op = FETCH_OP_TP_ARG;
} else
goto inval_var;
@@ -540,26 +550,34 @@ static int __parse_bitfield_probe_arg(const char *bf,
}
/* String length checking wrapper */
-static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
+static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
struct probe_arg *parg, unsigned int flags, int offset)
{
struct fetch_insn *code, *scode, *tmp = NULL;
char *t, *t2, *t3;
+ char *arg;
int ret, len;
+ arg = kstrdup(argv, GFP_KERNEL);
+ if (!arg)
+ return -ENOMEM;
+
+ ret = -EINVAL;
len = strlen(arg);
if (len > MAX_ARGSTR_LEN) {
trace_probe_log_err(offset, ARG_TOO_LONG);
- return -EINVAL;
+ goto out;
} else if (len == 0) {
trace_probe_log_err(offset, NO_ARG_BODY);
- return -EINVAL;
+ goto out;
}
+ ret = -ENOMEM;
parg->comm = kstrdup(arg, GFP_KERNEL);
if (!parg->comm)
- return -ENOMEM;
+ goto out;
+ ret = -EINVAL;
t = strchr(arg, ':');
if (t) {
*t = '\0';
@@ -571,22 +589,22 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
offset += t2 + strlen(t2) - arg;
trace_probe_log_err(offset,
ARRAY_NO_CLOSE);
- return -EINVAL;
+ goto out;
} else if (t3[1] != '\0') {
trace_probe_log_err(offset + t3 + 1 - arg,
BAD_ARRAY_SUFFIX);
- return -EINVAL;
+ goto out;
}
*t3 = '\0';
if (kstrtouint(t2, 0, &parg->count) || !parg->count) {
trace_probe_log_err(offset + t2 - arg,
BAD_ARRAY_NUM);
- return -EINVAL;
+ goto out;
}
if (parg->count > MAX_ARRAY_LEN) {
trace_probe_log_err(offset + t2 - arg,
ARRAY_TOO_BIG);
- return -EINVAL;
+ goto out;
}
}
}
@@ -598,29 +616,30 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
/* The type of $comm must be "string", and not an array. */
if (parg->count || (t && strcmp(t, "string")))
- return -EINVAL;
+ goto out;
parg->type = find_fetch_type("string");
} else
parg->type = find_fetch_type(t);
if (!parg->type) {
trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_TYPE);
- return -EINVAL;
+ goto out;
}
parg->offset = *size;
*size += parg->type->size * (parg->count ?: 1);
+ ret = -ENOMEM;
if (parg->count) {
len = strlen(parg->type->fmttype) + 6;
parg->fmt = kmalloc(len, GFP_KERNEL);
if (!parg->fmt)
- return -ENOMEM;
+ goto out;
snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
parg->count);
}
code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
if (!code)
- return -ENOMEM;
+ goto out;
code[FETCH_INSN_MAX - 1].op = FETCH_OP_END;
ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1],
@@ -628,19 +647,20 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
if (ret)
goto fail;
+ ret = -EINVAL;
/* Store operation */
if (!strcmp(parg->type->name, "string") ||
!strcmp(parg->type->name, "ustring")) {
if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF &&
code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM &&
- code->op != FETCH_OP_DATA) {
+ code->op != FETCH_OP_DATA && code->op != FETCH_OP_TP_ARG) {
trace_probe_log_err(offset + (t ? (t - arg) : 0),
BAD_STRING);
- ret = -EINVAL;
goto fail;
}
if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM ||
- code->op == FETCH_OP_DATA) || parg->count) {
+ code->op == FETCH_OP_DATA) || code->op == FETCH_OP_TP_ARG ||
+ parg->count) {
/*
* IMM, DATA and COMM is pointing actual address, those
* must be kept, and if parg->count != 0, this is an
@@ -650,7 +670,6 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
code++;
if (code->op != FETCH_OP_NOP) {
trace_probe_log_err(offset, TOO_MANY_OPS);
- ret = -EINVAL;
goto fail;
}
}
@@ -672,7 +691,6 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
code++;
if (code->op != FETCH_OP_NOP) {
trace_probe_log_err(offset, TOO_MANY_OPS);
- ret = -EINVAL;
goto fail;
}
code->op = FETCH_OP_ST_RAW;
@@ -687,6 +705,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
goto fail;
}
}
+ ret = -EINVAL;
/* Loop(Array) operation */
if (parg->count) {
if (scode->op != FETCH_OP_ST_MEM &&
@@ -694,13 +713,11 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
scode->op != FETCH_OP_ST_USTRING) {
trace_probe_log_err(offset + (t ? (t - arg) : 0),
BAD_STRING);
- ret = -EINVAL;
goto fail;
}
code++;
if (code->op != FETCH_OP_NOP) {
trace_probe_log_err(offset, TOO_MANY_OPS);
- ret = -EINVAL;
goto fail;
}
code->op = FETCH_OP_LP_ARRAY;
@@ -709,6 +726,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
code++;
code->op = FETCH_OP_END;
+ ret = 0;
/* Shrink down the code buffer */
parg->code = kcalloc(code - tmp + 1, sizeof(*code), GFP_KERNEL);
if (!parg->code)
@@ -724,6 +742,8 @@ fail:
kfree(code->data);
}
kfree(tmp);
+out:
+ kfree(arg);
return ret;
}
@@ -745,11 +765,11 @@ static int traceprobe_conflict_field_name(const char *name,
return 0;
}
-int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, char *arg,
+int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg,
unsigned int flags)
{
struct probe_arg *parg = &tp->args[i];
- char *body;
+ const char *body;
/* Increment count for freeing args in error case */
tp->nr_args++;
@@ -839,19 +859,29 @@ int traceprobe_update_arg(struct probe_arg *arg)
/* When len=0, we just calculate the needed length */
#define LEN_OR_ZERO (len ? len - pos : 0)
static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
- bool is_return)
+ enum probe_print_type ptype)
{
struct probe_arg *parg;
int i, j;
int pos = 0;
const char *fmt, *arg;
- if (!is_return) {
+ switch (ptype) {
+ case PROBE_PRINT_NORMAL:
fmt = "(%lx)";
arg = "REC->" FIELD_STRING_IP;
- } else {
+ break;
+ case PROBE_PRINT_RETURN:
fmt = "(%lx <- %lx)";
arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ break;
+ case PROBE_PRINT_EVENT:
+ fmt = "(%u)";
+ arg = "REC->" FIELD_STRING_TYPE;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return 0;
}
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
@@ -900,20 +930,20 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
}
#undef LEN_OR_ZERO
-int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return)
+int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype)
{
struct trace_event_call *call = trace_probe_event_call(tp);
int len;
char *print_fmt;
/* First: called with 0 length to calculate the needed length */
- len = __set_print_fmt(tp, NULL, 0, is_return);
+ len = __set_print_fmt(tp, NULL, 0, ptype);
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, is_return);
+ __set_print_fmt(tp, print_fmt, len + 1, ptype);
call->print_fmt = print_fmt;
return 0;
@@ -1029,11 +1059,36 @@ error:
return ret;
}
+static struct trace_event_call *
+find_trace_event_call(const char *system, const char *event_name)
+{
+ struct trace_event_call *tp_event;
+ const char *name;
+
+ list_for_each_entry(tp_event, &ftrace_events, list) {
+ if (!tp_event->class->system ||
+ strcmp(system, tp_event->class->system))
+ continue;
+ name = trace_event_name(tp_event);
+ if (!name || strcmp(event_name, name))
+ continue;
+ return tp_event;
+ }
+
+ return NULL;
+}
+
int trace_probe_register_event_call(struct trace_probe *tp)
{
struct trace_event_call *call = trace_probe_event_call(tp);
int ret;
+ lockdep_assert_held(&event_mutex);
+
+ if (find_trace_event_call(trace_probe_group_name(tp),
+ trace_probe_name(tp)))
+ return -EEXIST;
+
ret = register_trace_event(&call->event);
if (!ret)
return -ENODEV;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 227d518e5ba5..99e7a5df025e 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -38,6 +38,7 @@
#define FIELD_STRING_IP "__probe_ip"
#define FIELD_STRING_RETIP "__probe_ret_ip"
#define FIELD_STRING_FUNC "__probe_func"
+#define FIELD_STRING_TYPE "__probe_type"
#undef DEFINE_FIELD
#define DEFINE_FIELD(type, item, name, is_signed) \
@@ -102,6 +103,7 @@ enum fetch_op {
FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */
// Stage 5 (loop) op
FETCH_OP_LP_ARRAY, /* Array: .param = loop count */
+ FETCH_OP_TP_ARG, /* Trace Point argument */
FETCH_OP_END,
FETCH_NOP_SYMBOL, /* Unresolved Symbol holder */
};
@@ -351,10 +353,11 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char
#define TPARG_FL_RETURN BIT(0)
#define TPARG_FL_KERNEL BIT(1)
#define TPARG_FL_FENTRY BIT(2)
-#define TPARG_FL_MASK GENMASK(2, 0)
+#define TPARG_FL_TPOINT BIT(3)
+#define TPARG_FL_MASK GENMASK(3, 0)
extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
- char *arg, unsigned int flags);
+ const char *argv, unsigned int flags);
extern int traceprobe_update_arg(struct probe_arg *arg);
extern void traceprobe_free_probe_arg(struct probe_arg *arg);
@@ -363,7 +366,13 @@ extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
int traceprobe_parse_event_name(const char **pevent, const char **pgroup,
char *buf, int offset);
-extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return);
+enum probe_print_type {
+ PROBE_PRINT_NORMAL,
+ PROBE_PRINT_RETURN,
+ PROBE_PRINT_EVENT,
+};
+
+extern int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype);
#ifdef CONFIG_PERF_EVENTS
extern struct trace_event_call *
@@ -399,6 +408,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(NO_EVENT_NAME, "Event name is not specified"), \
C(EVENT_TOO_LONG, "Event name is too long"), \
C(BAD_EVENT_NAME, "Event name must follow the same rules as C identifiers"), \
+ C(EVENT_EXIST, "Given group/event name is already used by another event"), \
C(RETVAL_ON_PROBE, "$retval is not available on probe"), \
C(BAD_STACK_NUM, "Invalid stack number"), \
C(BAD_ARG_NUM, "Invalid argument number"), \
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index f003c5d02a3a..b3bdb8ddb862 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -54,7 +54,7 @@ fetch_apply_bitfield(struct fetch_insn *code, void *buf)
* If dest is NULL, don't store result and return required dynamic data size.
*/
static int
-process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs,
+process_fetch_insn(struct fetch_insn *code, void *rec,
void *dest, void *base);
static nokprobe_inline int fetch_store_strlen(unsigned long addr);
static nokprobe_inline int
@@ -188,7 +188,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs)
/* Store the value of each argument */
static nokprobe_inline void
-store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
+store_trace_args(void *data, struct trace_probe *tp, void *rec,
int header_size, int maxlen)
{
struct probe_arg *arg;
@@ -203,7 +203,7 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
/* Point the dynamic data area if needed */
if (unlikely(arg->dynamic))
*dl = make_data_loc(maxlen, dyndata - base);
- ret = process_fetch_insn(arg->code, regs, dl, base);
+ ret = process_fetch_insn(arg->code, rec, dl, base);
if (unlikely(ret < 0 && arg->dynamic)) {
*dl = make_data_loc(0, dyndata - base);
} else {
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 9b50869a5ddb..225ce569bf8f 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -83,10 +83,6 @@ static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev)
for_each_dyn_event(dpos) \
if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos)))
-#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 int unregister_uprobe_event(struct trace_uprobe *tu);
@@ -217,9 +213,10 @@ static unsigned long translate_user_vaddr(unsigned long 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, struct pt_regs *regs, void *dest,
+process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
void *base)
{
+ struct pt_regs *regs = rec;
unsigned long val;
/* 1st stage: get value from context */
@@ -340,7 +337,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
struct trace_uprobe *tu;
int ret;
- tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL);
+ tu = kzalloc(struct_size(tu, tp.args, nargs), GFP_KERNEL);
if (!tu)
return ERR_PTR(-ENOMEM);
@@ -393,6 +390,10 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
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;
@@ -455,7 +456,7 @@ static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to)
/* Append to existing event */
ret = trace_probe_append(&tu->tp, &to->tp);
if (!ret)
- dyn_event_add(&tu->devent);
+ dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp));
return ret;
}
@@ -514,11 +515,15 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
ret = register_uprobe_event(tu);
if (ret) {
- pr_warn("Failed to register probe event(%d)\n", ret);
+ 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);
goto end;
}
- dyn_event_add(&tu->devent);
+ dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp));
end:
mutex_unlock(&event_mutex);
@@ -536,6 +541,7 @@ static int __trace_uprobe_create(int argc, const char **argv)
const char *event = NULL, *group = UPROBE_EVENT_SYSTEM;
char *arg, *filename, *rctr, *rctr_end, *tmp;
char buf[MAX_EVENT_NAME_LEN];
+ enum probe_print_type ptype;
struct path path;
unsigned long offset, ref_ctr_offset;
bool is_return = false;
@@ -680,21 +686,15 @@ static int __trace_uprobe_create(int argc, const char **argv)
/* parse arguments */
for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
- tmp = kstrdup(argv[i], GFP_KERNEL);
- if (!tmp) {
- ret = -ENOMEM;
- goto error;
- }
-
trace_probe_log_set_index(i + 2);
- ret = traceprobe_parse_probe_arg(&tu->tp, i, tmp,
+ ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i],
is_return ? TPARG_FL_RETURN : 0);
- kfree(tmp);
if (ret)
goto error;
}
- ret = traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu));
+ ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+ ret = traceprobe_set_print_fmt(&tu->tp, ptype);
if (ret < 0)
goto error;
@@ -1585,6 +1585,7 @@ 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;
@@ -1619,7 +1620,8 @@ create_local_trace_uprobe(char *name, unsigned long offs,
tu->filename = kstrdup(name, GFP_KERNEL);
init_trace_event_call(tu);
- if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) {
+ ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
+ if (traceprobe_set_print_fmt(&tu->tp, ptype) < 0) {
ret = -ENOMEM;
goto error;
}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index efd14c79fab4..64ea283f2f86 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -577,7 +577,7 @@ bool trace_module_has_bad_taint(struct module *mod)
static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list);
/**
- * register_tracepoint_notifier - register tracepoint coming/going notifier
+ * register_tracepoint_module_notifier - register tracepoint coming/going notifier
* @nb: notifier block
*
* Notifiers registered with this function are called on module
@@ -603,7 +603,7 @@ end:
EXPORT_SYMBOL_GPL(register_tracepoint_module_notifier);
/**
- * unregister_tracepoint_notifier - unregister tracepoint coming/going notifier
+ * unregister_tracepoint_module_notifier - unregister tracepoint coming/going notifier
* @nb: notifier block
*
* The notifier block callback should expect a "struct tp_module" data