[PATCH v2] perf: enable unprivileged syscall tracing with perf trace

[Anubhav Shelat]

Allow unprivileged users to trace their own processes' syscalls using
perf trace, similar to strace without the intrusive overhead of ptrace().

Currently, perf trace requires CAP_PERFMON or paranoid level ≤ 1 even
though the kernel has existing infrastructure (TRACE_EVENT_FL_CAP_ANY)
specifically designed to mark syscall tracepoints as safe for
unprivileged access. To fix this:

1. Loosen the condition in perf_event_open() which requires priviliges
for all events with exclude_kernel=0. This allows perf_event_open() to
bypass the paranoid check for task-attached tracepoint events. Ensure
that sample types which can expose kernel addresses to unprivileged
users are blocked.

2. Make the format and id tracefs files world-readable only for tracepoints
with TRACE_EVENT_FL_CAP_ANY, allowing unprivileged users to see syscall
tracepoint ids without exposing sensitive information.

Also add a check to perf_trace_event_perm() to ensure only TRACE_EVENT_FL_CAP_ANY
events can be traced.

Example usage after this change:
  $ perf trace ls          # works as unprivileged user
  $ perf trace             # system-wide, still requires privileges
  $ perf trace -p 1234     # requires ptrace permission on pid 1234

Assisted-by: Claude:claude-sonnet-4.5
Signed-off-by: Anubhav Shelat <ashelat@xxxxxxxxxx>
---
Changes in v2:
- Add check to block sample types that bypass KASLR, suggested by
  sashiko.
- Link to v1: https://lore.kernel.org/linux-perf-users/20260408123947.23779-2-ashelat@xxxxxxxxxx/
---
 kernel/events/core.c            | 22 +++++++++++++++++++---
 kernel/trace/trace_event_perf.c | 12 +++++++++++-
 kernel/trace/trace_events.c     |  8 ++++++--
 3 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 89b40e439717..db8c674704b2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -13834,9 +13834,25 @@ SYSCALL_DEFINE5(perf_event_open,
 		return err;
 
 	if (!attr.exclude_kernel) {
-		err = perf_allow_kernel();
-		if (err)
-			return err;
+		bool tp_bypass = false;
+
+		if (attr.type == PERF_TYPE_TRACEPOINT && pid != -1) {
+			/*
+			 * Block sample types that expose kernel addresses to
+			 * prevent KASLR bypass
+			 */
+			u64 kaddr_leak = PERF_SAMPLE_CALLCHAIN |
+					 PERF_SAMPLE_BRANCH_STACK |
+					 PERF_SAMPLE_ADDR;
+
+			tp_bypass = !(attr.sample_type & kaddr_leak);
+		}
+
+		if (!tp_bypass) {
+			err = perf_allow_kernel();
+			if (err)
+				return err;
+		}
 	}
 
 	if (attr.namespaces) {
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a6bb7577e8c5..e8347df7ede5 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -73,8 +73,18 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event,
 	}
 
 	/* No tracing, just counting, so no obvious leak */
-	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) {
+		/*
+		 * Only allow CAP_ANY tracepoints for unprivileged
+		 * task-attached events in case kernel context is exposed.
+		 */
+		if (!p_event->attr.exclude_kernel && !perfmon_capable()) {
+			if (!(p_event->attach_state == PERF_ATTACH_TASK &&
+			      (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)))
+				return -EACCES;
+		}
 		return 0;
+	}
 
 	/* Some events are ok to be traced by non-root users... */
 	if (p_event->attach_state == PERF_ATTACH_TASK) {
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 249d1cba72c0..6250b2529376 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3051,7 +3051,9 @@ static int event_callback(const char *name, umode_t *mode, void **data,
 	struct trace_event_call *call = file->event_call;
 
 	if (strcmp(name, "format") == 0) {
-		*mode = TRACE_MODE_READ;
+		*mode = (call->flags & TRACE_EVENT_FL_CAP_ANY) ?
+			(TRACE_MODE_READ | 0004) :
+			TRACE_MODE_READ;
 		*fops = &ftrace_event_format_fops;
 		return 1;
 	}
@@ -3087,7 +3089,9 @@ static int event_callback(const char *name, umode_t *mode, void **data,
 #ifdef CONFIG_PERF_EVENTS
 	if (call->event.type && call->class->reg &&
 	    strcmp(name, "id") == 0) {
-		*mode = TRACE_MODE_READ;
+		*mode = (call->flags & TRACE_EVENT_FL_CAP_ANY) ?
+		(TRACE_MODE_READ | 0004) :
+		TRACE_MODE_READ;
 		*data = (void *)(long)call->event.type;
 		*fops = &ftrace_event_id_fops;
 		return 1;
-- 
2.53.0