Merge branch 'bpf-perf'

Alexei Starovoitov says:

====================
bpf_perf_event_output helper

Over the last year there were multiple attempts to let eBPF programs
output data into perf events by He Kuang and Wangnan.
The last one was:
https://lkml.org/lkml/2015/7/20/736
It was almost perfect with exception that all bpf programs would sent
data into one global perf_event.
This patch set takes different approach by letting user space
open independent PERF_COUNT_SW_BPF_OUTPUT events, so that program
output won't collide.

Wangnan is working on corresponding perf patches.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 60 insertions, 6 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index f2d9e698c753..e3cfe46b074f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -295,6 +295,8 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
 		return (void *)attr;
 
 	if (attr->type != PERF_TYPE_RAW &&
+	    !(attr->type == PERF_TYPE_SOFTWARE &&
+	      attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
 	    attr->type != PERF_TYPE_HARDWARE) {
 		perf_event_release_kernel(event);
 		return ERR_PTR(-EINVAL);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1d6b97be79e1..b56cf51f8d42 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -245,6 +245,7 @@ static const struct {
 } func_limit[] = {
 	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
 	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
+	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
 };
 
 static void print_verifier_state(struct verifier_env *env)
@@ -910,7 +911,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 		 * don't allow any other map type to be passed into
 		 * the special func;
 		 */
-		if (bool_map != bool_func)
+		if (bool_func && bool_map != bool_func)
 			return -EINVAL;
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b11756f9b6dc..64754bfecd70 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5286,9 +5286,15 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_RAW) {
 		if (data->raw) {
-			perf_output_put(handle, data->raw->size);
-			__output_copy(handle, data->raw->data,
-					   data->raw->size);
+			u32 raw_size = data->raw->size;
+			u32 real_size = round_up(raw_size + sizeof(u32),
+						 sizeof(u64)) - sizeof(u32);
+			u64 zero = 0;
+
+			perf_output_put(handle, real_size);
+			__output_copy(handle, data->raw->data, raw_size);
+			if (real_size - raw_size)
+				__output_copy(handle, &zero, real_size - raw_size);
 		} else {
 			struct {
 				u32	size;
@@ -5420,8 +5426,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		else
 			size += sizeof(u32);
 
-		WARN_ON_ONCE(size & (sizeof(u64)-1));
-		header->size += size;
+		header->size += round_up(size, sizeof(u64));
 	}
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0fe96c7c8803..47febbe7998e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -215,6 +215,50 @@ const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+{
+	struct pt_regs *regs = (struct pt_regs *) (long) r1;
+	struct bpf_map *map = (struct bpf_map *) (long) r2;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	void *data = (void *) (long) r4;
+	struct perf_sample_data sample_data;
+	struct perf_event *event;
+	struct perf_raw_record raw = {
+		.size = size,
+		.data = data,
+	};
+
+	if (unlikely(index >= array->map.max_entries))
+		return -E2BIG;
+
+	event = (struct perf_event *)array->ptrs[index];
+	if (unlikely(!event))
+		return -ENOENT;
+
+	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
+		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
+		return -EINVAL;
+
+	if (unlikely(event->oncpu != smp_processor_id()))
+		return -EOPNOTSUPP;
+
+	perf_sample_data_init(&sample_data, 0, 0);
+	sample_data.raw = &raw;
+	perf_event_output(event, &sample_data, regs);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto = {
+	.func		= bpf_perf_event_output,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_STACK,
+	.arg5_type	= ARG_CONST_STACK_SIZE,
+};
+
 static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -242,6 +286,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_perf_event_read:
 		return &bpf_perf_event_read_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto;
 	default:
 		return NULL;
 	}