summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
authorBeau Belgrave <beaub@linux.microsoft.com>2024-02-22 00:18:05 +0000
committerSteven Rostedt (Google) <rostedt@goodmis.org>2024-03-18 10:13:03 -0400
commit64805e4039f1687b9857034123a9ec10bb9abddd (patch)
treeddef503d796b1b14c4b61d10278b054249472e5a /kernel/trace
parent1e953de9e9b4ca77a9ce0fc17a0778eba3a4ca64 (diff)
downloadlinux-64805e4039f1687b9857034123a9ec10bb9abddd.tar.gz
linux-64805e4039f1687b9857034123a9ec10bb9abddd.tar.bz2
linux-64805e4039f1687b9857034123a9ec10bb9abddd.zip
tracing/user_events: Introduce multi-format events
Currently user_events supports 1 event with the same name and must have the exact same format when referenced by multiple programs. This opens an opportunity for malicious or poorly thought through programs to create events that others use with different formats. Another scenario is user programs wishing to use the same event name but add more fields later when the software updates. Various versions of a program may be running side-by-side, which is prevented by the current single format requirement. Add a new register flag (USER_EVENT_REG_MULTI_FORMAT) which indicates the user program wishes to use the same user_event name, but may have several different formats of the event. When this flag is used, create the underlying tracepoint backing the user_event with a unique name per-version of the format. It's important that existing ABI users do not get this logic automatically, even if one of the multi format events matches the format. This ensures existing programs that create events and assume the tracepoint name will match exactly continue to work as expected. Add logic to only check multi-format events with other multi-format events and single-format events to only check single-format events during find. Change system name of the multi-format event tracepoint to ensure that multi-format events are isolated completely from single-format events. This prevents single-format names from conflicting with multi-format events if they end with the same suffix as the multi-format events. Add a register_name (reg_name) to the user_event struct which allows for split naming of events. We now have the name that was used to register within user_events as well as the unique name for the tracepoint. Upon registering events ensure matches based on first the reg_name, followed by the fields and format of the event. This allows for multiple events with the same registered name to have different formats. The underlying tracepoint will have a unique name in the format of {reg_name}.{unique_id}. For example, if both "test u32 value" and "test u64 value" are used with the USER_EVENT_REG_MULTI_FORMAT the system would have 2 unique tracepoints. The dynamic_events file would then show the following: u:test u64 count u:test u32 count The actual tracepoint names look like this: test.0 test.1 Both would be under the new user_events_multi system name to prevent the older ABI from being used to squat on multi-formatted events and block their use. Deleting events via "!u:test u64 count" would only delete the first tracepoint that matched that format. When the delete ABI is used all events with the same name will be attempted to be deleted. If per-version deletion is required, user programs should either not use persistent events or delete them via dynamic_events. Link: https://lore.kernel.org/linux-trace-kernel/20240222001807.1463-3-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/trace_events_user.c102
1 files changed, 90 insertions, 12 deletions
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index fce5ed5fec50..70d428c394b6 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -34,7 +34,8 @@
/* Limit how long of an event name plus args within the subsystem. */
#define MAX_EVENT_DESC 512
-#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
+#define EVENT_NAME(user_event) ((user_event)->reg_name)
+#define EVENT_TP_NAME(user_event) ((user_event)->tracepoint.name)
#define MAX_FIELD_ARRAY_SIZE 1024
/*
@@ -54,10 +55,13 @@
* allows isolation for events by various means.
*/
struct user_event_group {
- char *system_name;
- struct hlist_node node;
- struct mutex reg_mutex;
+ char *system_name;
+ char *system_multi_name;
+ struct hlist_node node;
+ struct mutex reg_mutex;
DECLARE_HASHTABLE(register_table, 8);
+ /* ID that moves forward within the group for multi-event names */
+ u64 multi_id;
};
/* Group for init_user_ns mapping, top-most group */
@@ -78,6 +82,7 @@ static unsigned int current_user_events;
*/
struct user_event {
struct user_event_group *group;
+ char *reg_name;
struct tracepoint tracepoint;
struct trace_event_call call;
struct trace_event_class class;
@@ -127,6 +132,8 @@ struct user_event_enabler {
#define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK))
+#define EVENT_MULTI_FORMAT(f) ((f) & USER_EVENT_REG_MULTI_FORMAT)
+
/* Used for asynchronous faulting in of pages */
struct user_event_enabler_fault {
struct work_struct work;
@@ -330,6 +337,7 @@ out:
static void user_event_group_destroy(struct user_event_group *group)
{
kfree(group->system_name);
+ kfree(group->system_multi_name);
kfree(group);
}
@@ -348,6 +356,11 @@ static char *user_event_group_system_name(void)
return system_name;
}
+static char *user_event_group_system_multi_name(void)
+{
+ return kstrdup(USER_EVENTS_MULTI_SYSTEM, GFP_KERNEL);
+}
+
static struct user_event_group *current_user_event_group(void)
{
return init_group;
@@ -367,6 +380,11 @@ static struct user_event_group *user_event_group_create(void)
if (!group->system_name)
goto error;
+ group->system_multi_name = user_event_group_system_multi_name();
+
+ if (!group->system_multi_name)
+ goto error;
+
mutex_init(&group->reg_mutex);
hash_init(group->register_table);
@@ -1482,6 +1500,11 @@ static int destroy_user_event(struct user_event *user)
hash_del(&user->node);
user_event_destroy_validators(user);
+
+ /* If we have different names, both must be freed */
+ if (EVENT_NAME(user) != EVENT_TP_NAME(user))
+ kfree(EVENT_TP_NAME(user));
+
kfree(user->call.print_fmt);
kfree(EVENT_NAME(user));
kfree(user);
@@ -1504,12 +1527,24 @@ static struct user_event *find_user_event(struct user_event_group *group,
*outkey = key;
hash_for_each_possible(group->register_table, user, node, key) {
+ /*
+ * Single-format events shouldn't return multi-format
+ * events. Callers expect the underlying tracepoint to match
+ * the name exactly in these cases. Only check like-formats.
+ */
+ if (EVENT_MULTI_FORMAT(flags) != EVENT_MULTI_FORMAT(user->reg_flags))
+ continue;
+
if (strcmp(EVENT_NAME(user), name))
continue;
if (user_fields_match(user, argc, argv))
return user_event_get(user);
+ /* Scan others if this is a multi-format event */
+ if (EVENT_MULTI_FORMAT(flags))
+ continue;
+
return ERR_PTR(-EADDRINUSE);
}
@@ -1889,8 +1924,12 @@ static bool user_event_match(const char *system, const char *event,
struct user_event *user = container_of(ev, struct user_event, devent);
bool match;
- match = strcmp(EVENT_NAME(user), event) == 0 &&
- (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
+ match = strcmp(EVENT_NAME(user), event) == 0;
+
+ if (match && system) {
+ match = strcmp(system, user->group->system_name) == 0 ||
+ strcmp(system, user->group->system_multi_name) == 0;
+ }
if (match)
match = user_fields_match(user, argc, argv);
@@ -1923,6 +1962,33 @@ static int user_event_trace_register(struct user_event *user)
return ret;
}
+static int user_event_set_tp_name(struct user_event *user)
+{
+ lockdep_assert_held(&user->group->reg_mutex);
+
+ if (EVENT_MULTI_FORMAT(user->reg_flags)) {
+ char *multi_name;
+
+ multi_name = kasprintf(GFP_KERNEL_ACCOUNT, "%s.%llx",
+ user->reg_name, user->group->multi_id);
+
+ if (!multi_name)
+ return -ENOMEM;
+
+ user->call.name = multi_name;
+ user->tracepoint.name = multi_name;
+
+ /* Inc to ensure unique multi-event name next time */
+ user->group->multi_id++;
+ } else {
+ /* Non Multi-format uses register name */
+ user->call.name = user->reg_name;
+ user->tracepoint.name = user->reg_name;
+ }
+
+ return 0;
+}
+
/*
* Parses the event name, arguments and flags then registers if successful.
* The name buffer lifetime is owned by this method for success cases only.
@@ -1985,7 +2051,13 @@ static int user_event_parse(struct user_event_group *group, char *name,
INIT_LIST_HEAD(&user->validators);
user->group = group;
- user->tracepoint.name = name;
+ user->reg_name = name;
+ user->reg_flags = reg_flags;
+
+ ret = user_event_set_tp_name(user);
+
+ if (ret)
+ goto put_user;
ret = user_event_parse_fields(user, args);
@@ -1999,11 +2071,14 @@ static int user_event_parse(struct user_event_group *group, char *name,
user->call.data = user;
user->call.class = &user->class;
- user->call.name = name;
user->call.flags = TRACE_EVENT_FL_TRACEPOINT;
user->call.tp = &user->tracepoint;
user->call.event.funcs = &user_event_funcs;
- user->class.system = group->system_name;
+
+ if (EVENT_MULTI_FORMAT(user->reg_flags))
+ user->class.system = group->system_multi_name;
+ else
+ user->class.system = group->system_name;
user->class.fields_array = user_event_fields_array;
user->class.get_fields = user_event_get_fields;
@@ -2025,8 +2100,6 @@ static int user_event_parse(struct user_event_group *group, char *name,
if (ret)
goto put_user_lock;
- user->reg_flags = reg_flags;
-
if (user->reg_flags & USER_EVENT_REG_PERSIST) {
/* Ensure we track self ref and caller ref (2) */
refcount_set(&user->refcnt, 2);
@@ -2050,6 +2123,11 @@ put_user:
user_event_destroy_fields(user);
user_event_destroy_validators(user);
kfree(user->call.print_fmt);
+
+ /* Caller frees reg_name on error, but not multi-name */
+ if (EVENT_NAME(user) != EVENT_TP_NAME(user))
+ kfree(EVENT_TP_NAME(user));
+
kfree(user);
return ret;
}
@@ -2639,7 +2717,7 @@ static int user_seq_show(struct seq_file *m, void *p)
hash_for_each(group->register_table, i, user, node) {
status = user->status;
- seq_printf(m, "%s", EVENT_NAME(user));
+ seq_printf(m, "%s", EVENT_TP_NAME(user));
if (status != 0)
seq_puts(m, " #");