bpf: Allow to specify user-provided bpf_cookie for BPF perf links

Add ability for users to specify custom u64 value (bpf_cookie) when creating
BPF link for perf_event-backed BPF programs (kprobe/uprobe, perf_event,
tracepoints).

This is useful for cases when the same BPF program is used for attaching and
processing invocation of different tracepoints/kprobes/uprobes in a generic
fashion, but such that each invocation is distinguished from each other (e.g.,
BPF program can look up additional information associated with a specific
kernel function without having to rely on function IP lookups). This enables
new use cases to be implemented simply and efficiently that previously were
possible only through code generation (and thus multiple instances of almost
identical BPF program) or compilation at runtime (BCC-style) on target hosts
(even more expensive resource-wise). For uprobes it is not even possible in
some cases to know function IP before hand (e.g., when attaching to shared
library without PID filtering, in which case base load address is not known
for a library).

This is done by storing u64 bpf_cookie in struct bpf_prog_array_item,
corresponding to each attached and run BPF program. Given cgroup BPF programs
already use two 8-byte pointers for their needs and cgroup BPF programs don't
have (yet?) support for bpf_cookie, reuse that space through union of
cgroup_storage and new bpf_cookie field.

Make it available to kprobe/tracepoint BPF programs through bpf_trace_run_ctx.
This is set by BPF_PROG_RUN_ARRAY, used by kprobe/uprobe/tracepoint BPF
program execution code, which luckily is now also split from
BPF_PROG_RUN_ARRAY_CG. This run context will be utilized by a new BPF helper
giving access to this user-provided cookie value from inside a BPF program.
Generic perf_event BPF programs will access this value from perf_event itself
through passed in BPF program context.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/bpf/20210815070609.987780-6-andrii@kernel.org

4 files changed, 38 insertions, 22 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5ee2ec27c3d4..91f24c7b38a1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2119,13 +2119,13 @@ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
 int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
+			u64 bpf_cookie,
 			struct bpf_prog_array **new_array)
 {
 	int new_prog_cnt, carry_prog_cnt = 0;
-	struct bpf_prog_array_item *existing;
+	struct bpf_prog_array_item *existing, *new;
 	struct bpf_prog_array *array;
 	bool found_exclude = false;
-	int new_prog_idx = 0;
 
 	/* Figure out how many existing progs we need to carry over to
 	 * the new array.
@@ -2162,20 +2162,27 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 	array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
 	if (!array)
 		return -ENOMEM;
+	new = array->items;
 
 	/* Fill in the new prog array */
 	if (carry_prog_cnt) {
 		existing = old_array->items;
-		for (; existing->prog; existing++)
-			if (existing->prog != exclude_prog &&
-			    existing->prog != &dummy_bpf_prog.prog) {
-				array->items[new_prog_idx++].prog =
-					existing->prog;
-			}
+		for (; existing->prog; existing++) {
+			if (existing->prog == exclude_prog ||
+			    existing->prog == &dummy_bpf_prog.prog)
+				continue;
+
+			new->prog = existing->prog;
+			new->bpf_cookie = existing->bpf_cookie;
+			new++;
+		}
 	}
-	if (include_prog)
-		array->items[new_prog_idx++].prog = include_prog;
-	array->items[new_prog_idx].prog = NULL;
+	if (include_prog) {
+		new->prog = include_prog;
+		new->bpf_cookie = bpf_cookie;
+		new++;
+	}
+	new->prog = NULL;
 	*new_array = array;
 	return 0;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 80c03bedd6e6..7420e1334ab2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2963,7 +2963,7 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro
 	}
 
 	event = perf_file->private_data;
-	err = perf_event_set_bpf_prog(event, prog);
+	err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		goto out_put_file;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9fd65667bcb2..2d1e63dd97f2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5643,7 +5643,7 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 		if (IS_ERR(prog))
 			return PTR_ERR(prog);
 
-		err = perf_event_set_bpf_prog(event, prog);
+		err = perf_event_set_bpf_prog(event, prog, 0);
 		if (err) {
 			bpf_prog_put(prog);
 			return err;
@@ -9936,7 +9936,9 @@ out:
 	event->orig_overflow_handler(event, data, regs);
 }
 
-static int perf_event_set_bpf_handler(struct perf_event *event, struct bpf_prog *prog)
+static int perf_event_set_bpf_handler(struct perf_event *event,
+				      struct bpf_prog *prog,
+				      u64 bpf_cookie)
 {
 	if (event->overflow_handler_context)
 		/* hw breakpoint or kernel counter */
@@ -9966,6 +9968,7 @@ static int perf_event_set_bpf_handler(struct perf_event *event, struct bpf_prog
 	}
 
 	event->prog = prog;
+	event->bpf_cookie = bpf_cookie;
 	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
 	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
 	return 0;
@@ -9983,7 +9986,9 @@ static void perf_event_free_bpf_handler(struct perf_event *event)
 	bpf_prog_put(prog);
 }
 #else
-static int perf_event_set_bpf_handler(struct perf_event *event, struct bpf_prog *prog)
+static int perf_event_set_bpf_handler(struct perf_event *event,
+				      struct bpf_prog *prog,
+				      u64 bpf_cookie)
 {
 	return -EOPNOTSUPP;
 }
@@ -10011,12 +10016,13 @@ static inline bool perf_event_is_tracing(struct perf_event *event)
 	return false;
 }
 
-int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog)
+int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
+			    u64 bpf_cookie)
 {
 	bool is_kprobe, is_tracepoint, is_syscall_tp;
 
 	if (!perf_event_is_tracing(event))
-		return perf_event_set_bpf_handler(event, prog);
+		return perf_event_set_bpf_handler(event, prog, bpf_cookie);
 
 	is_kprobe = event->tp_event->flags & TRACE_EVENT_FL_UKPROBE;
 	is_tracepoint = event->tp_event->flags & TRACE_EVENT_FL_TRACEPOINT;
@@ -10042,7 +10048,7 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog)
 			return -EACCES;
 	}
 
-	return perf_event_attach_bpf_prog(event, prog);
+	return perf_event_attach_bpf_prog(event, prog, bpf_cookie);
 }
 
 void perf_event_free_bpf_prog(struct perf_event *event)
@@ -10064,7 +10070,8 @@ static void perf_event_free_filter(struct perf_event *event)
 {
 }
 
-int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog)
+int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
+			    u64 bpf_cookie)
 {
 	return -ENOENT;
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 91867b14b222..57879d28f824 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1675,7 +1675,8 @@ static DEFINE_MUTEX(bpf_event_mutex);
 #define BPF_TRACE_MAX_PROGS 64
 
 int perf_event_attach_bpf_prog(struct perf_event *event,
-			       struct bpf_prog *prog)
+			       struct bpf_prog *prog,
+			       u64 bpf_cookie)
 {
 	struct bpf_prog_array *old_array;
 	struct bpf_prog_array *new_array;
@@ -1702,12 +1703,13 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
 		goto unlock;
 	}
 
-	ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+	ret = bpf_prog_array_copy(old_array, NULL, prog, bpf_cookie, &new_array);
 	if (ret < 0)
 		goto unlock;
 
 	/* set the new array to event->tp_event and set event->prog */
 	event->prog = prog;
+	event->bpf_cookie = bpf_cookie;
 	rcu_assign_pointer(event->tp_event->prog_array, new_array);
 	bpf_prog_array_free(old_array);
 
@@ -1728,7 +1730,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 		goto unlock;
 
 	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
-	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+	ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array);
 	if (ret == -ENOENT)
 		goto unlock;
 	if (ret < 0) {