bpf: introduce BPF_RAW_TRACEPOINT

Introduce BPF_PROG_TYPE_RAW_TRACEPOINT bpf program type to access
kernel internal arguments of the tracepoints in their raw form.

>From bpf program point of view the access to the arguments look like:
struct bpf_raw_tracepoint_args {
       __u64 args[0];
};

int bpf_prog(struct bpf_raw_tracepoint_args *ctx)
{
  // program can read args[N] where N depends on tracepoint
  // and statically verified at program load+attach time
}

kprobe+bpf infrastructure allows programs access function arguments.
This feature allows programs access raw tracepoint arguments.

Similar to proposed 'dynamic ftrace events' there are no abi guarantees
to what the tracepoints arguments are and what their meaning is.
The program needs to type cast args properly and use bpf_probe_read()
helper to access struct fields when argument is a pointer.

For every tracepoint __bpf_trace_##call function is prepared.
In assembler it looks like:
(gdb) disassemble __bpf_trace_xdp_exception
Dump of assembler code for function __bpf_trace_xdp_exception:
   0xffffffff81132080 <+0>:     mov    %ecx,%ecx
   0xffffffff81132082 <+2>:     jmpq   0xffffffff811231f0 <bpf_trace_run3>

where

TRACE_EVENT(xdp_exception,
        TP_PROTO(const struct net_device *dev,
                 const struct bpf_prog *xdp, u32 act),

The above assembler snippet is casting 32-bit 'act' field into 'u64'
to pass into bpf_trace_run3(), while 'dev' and 'xdp' args are passed as-is.
All of ~500 of __bpf_trace_*() functions are only 5-10 byte long
and in total this approach adds 7k bytes to .text.

This approach gives the lowest possible overhead
while calling trace_xdp_exception() from kernel C code and
transitioning into bpf land.
Since tracepoint+bpf are used at speeds of 1M+ events per second
this is valuable optimization.

The new BPF_RAW_TRACEPOINT_OPEN sys_bpf command is introduced
that returns anon_inode FD of 'bpf-raw-tracepoint' object.

The user space looks like:
// load bpf prog with BPF_PROG_TYPE_RAW_TRACEPOINT type
prog_fd = bpf_prog_load(...);
// receive anon_inode fd for given bpf_raw_tracepoint with prog attached
raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);

Ctrl-C of tracing daemon or cmdline tool that uses this feature
will automatically detach bpf program, unload it and
unregister tracepoint probe.

On the kernel side the __bpf_raw_tp_map section of pointers to
tracepoint definition and to __bpf_trace_*() probe function is used
to find a tracepoint with "xdp_exception" name and
corresponding __bpf_trace_xdp_exception() probe function
which are passed to tracepoint_probe_register() to connect probe
with tracepoint.

Addition of bpf_raw_tracepoint doesn't interfere with ftrace and perf
tracepoint mechanisms. perf_event_open() can be used in parallel
on the same tracepoint.
Multiple bpf_raw_tracepoint_open("xdp_exception", prog_fd) are permitted.
Each with its own bpf program. The kernel will execute
all tracepoint probes and all attached bpf programs.

In the future bpf_raw_tracepoints can be extended with
query/introspection logic.

__bpf_raw_tp_map section logic was contributed by Steven Rostedt

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

2 files changed, 261 insertions, 0 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 77d45bd9f507..95ca2523fa6e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1315,6 +1315,81 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
+struct bpf_raw_tracepoint {
+	struct bpf_raw_event_map *btp;
+	struct bpf_prog *prog;
+};
+
+static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_raw_tracepoint *raw_tp = filp->private_data;
+
+	if (raw_tp->prog) {
+		bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
+		bpf_prog_put(raw_tp->prog);
+	}
+	kfree(raw_tp);
+	return 0;
+}
+
+static const struct file_operations bpf_raw_tp_fops = {
+	.release	= bpf_raw_tracepoint_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
+};
+
+#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
+
+static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
+{
+	struct bpf_raw_tracepoint *raw_tp;
+	struct bpf_raw_event_map *btp;
+	struct bpf_prog *prog;
+	char tp_name[128];
+	int tp_fd, err;
+
+	if (strncpy_from_user(tp_name, u64_to_user_ptr(attr->raw_tracepoint.name),
+			      sizeof(tp_name) - 1) < 0)
+		return -EFAULT;
+	tp_name[sizeof(tp_name) - 1] = 0;
+
+	btp = bpf_find_raw_tracepoint(tp_name);
+	if (!btp)
+		return -ENOENT;
+
+	raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
+	if (!raw_tp)
+		return -ENOMEM;
+	raw_tp->btp = btp;
+
+	prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
+				 BPF_PROG_TYPE_RAW_TRACEPOINT);
+	if (IS_ERR(prog)) {
+		err = PTR_ERR(prog);
+		goto out_free_tp;
+	}
+
+	err = bpf_probe_register(raw_tp->btp, prog);
+	if (err)
+		goto out_put_prog;
+
+	raw_tp->prog = prog;
+	tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp,
+				 O_CLOEXEC);
+	if (tp_fd < 0) {
+		bpf_probe_unregister(raw_tp->btp, prog);
+		err = tp_fd;
+		goto out_put_prog;
+	}
+	return tp_fd;
+
+out_put_prog:
+	bpf_prog_put(prog);
+out_free_tp:
+	kfree(raw_tp);
+	return err;
+}
+
 #ifdef CONFIG_CGROUP_BPF
 
 #define BPF_PROG_ATTACH_LAST_FIELD attach_flags
@@ -1925,6 +2000,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_OBJ_GET_INFO_BY_FD:
 		err = bpf_obj_get_info_by_fd(&attr, uattr);
 		break;
+	case BPF_RAW_TRACEPOINT_OPEN:
+		err = bpf_raw_tracepoint_open(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7f9691c86b6e..463e72d18c4c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -735,6 +735,86 @@ static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
 	}
 }
 
+/*
+ * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
+ * to avoid potential recursive reuse issue when/if tracepoints are added
+ * inside bpf_*_event_output and/or bpf_get_stack_id
+ */
+static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
+	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+	perf_fetch_caller_regs(regs);
+	return ____bpf_perf_event_output(regs, map, flags, data, size);
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
+	.func		= bpf_perf_event_output_raw_tp,
+	.gpl_only	= true,
+	.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_MEM,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
+BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
+	   struct bpf_map *, map, u64, flags)
+{
+	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+	perf_fetch_caller_regs(regs);
+	/* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
+	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+			       flags, 0, 0);
+}
+
+static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
+	.func		= bpf_get_stackid_raw_tp,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *raw_tp_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto_raw_tp;
+	case BPF_FUNC_get_stackid:
+		return &bpf_get_stackid_proto_raw_tp;
+	default:
+		return tracing_func_proto(func_id);
+	}
+}
+
+static bool raw_tp_prog_is_valid_access(int off, int size,
+					enum bpf_access_type type,
+					struct bpf_insn_access_aux *info)
+{
+	/* largest tracepoint in the kernel has 12 args */
+	if (off < 0 || off >= sizeof(__u64) * 12)
+		return false;
+	if (type != BPF_READ)
+		return false;
+	if (off % size != 0)
+		return false;
+	return true;
+}
+
+const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
+	.get_func_proto  = raw_tp_prog_func_proto,
+	.is_valid_access = raw_tp_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops raw_tracepoint_prog_ops = {
+};
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -908,3 +988,106 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 
 	return ret;
 }
+
+extern struct bpf_raw_event_map __start__bpf_raw_tp[];
+extern struct bpf_raw_event_map __stop__bpf_raw_tp[];
+
+struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+{
+	struct bpf_raw_event_map *btp = __start__bpf_raw_tp;
+
+	for (; btp < __stop__bpf_raw_tp; btp++) {
+		if (!strcmp(btp->tp->name, name))
+			return btp;
+	}
+	return NULL;
+}
+
+static __always_inline
+void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
+{
+	rcu_read_lock();
+	preempt_disable();
+	(void) BPF_PROG_RUN(prog, args);
+	preempt_enable();
+	rcu_read_unlock();
+}
+
+#define UNPACK(...)			__VA_ARGS__
+#define REPEAT_1(FN, DL, X, ...)	FN(X)
+#define REPEAT_2(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__)
+#define REPEAT_3(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__)
+#define REPEAT_4(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__)
+#define REPEAT_5(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__)
+#define REPEAT_6(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__)
+#define REPEAT_7(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__)
+#define REPEAT_8(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__)
+#define REPEAT_9(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__)
+#define REPEAT_10(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__)
+#define REPEAT_11(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__)
+#define REPEAT_12(FN, DL, X, ...)	FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__)
+#define REPEAT(X, FN, DL, ...)		REPEAT_##X(FN, DL, __VA_ARGS__)
+
+#define SARG(X)		u64 arg##X
+#define COPY(X)		args[X] = arg##X
+
+#define __DL_COM	(,)
+#define __DL_SEM	(;)
+
+#define __SEQ_0_11	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
+
+#define BPF_TRACE_DEFN_x(x)						\
+	void bpf_trace_run##x(struct bpf_prog *prog,			\
+			      REPEAT(x, SARG, __DL_COM, __SEQ_0_11))	\
+	{								\
+		u64 args[x];						\
+		REPEAT(x, COPY, __DL_SEM, __SEQ_0_11);			\
+		__bpf_trace_run(prog, args);				\
+	}								\
+	EXPORT_SYMBOL_GPL(bpf_trace_run##x)
+BPF_TRACE_DEFN_x(1);
+BPF_TRACE_DEFN_x(2);
+BPF_TRACE_DEFN_x(3);
+BPF_TRACE_DEFN_x(4);
+BPF_TRACE_DEFN_x(5);
+BPF_TRACE_DEFN_x(6);
+BPF_TRACE_DEFN_x(7);
+BPF_TRACE_DEFN_x(8);
+BPF_TRACE_DEFN_x(9);
+BPF_TRACE_DEFN_x(10);
+BPF_TRACE_DEFN_x(11);
+BPF_TRACE_DEFN_x(12);
+
+static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+	struct tracepoint *tp = btp->tp;
+
+	/*
+	 * check that program doesn't access arguments beyond what's
+	 * available in this tracepoint
+	 */
+	if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64))
+		return -EINVAL;
+
+	return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
+}
+
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+	int err;
+
+	mutex_lock(&bpf_event_mutex);
+	err = __bpf_probe_register(btp, prog);
+	mutex_unlock(&bpf_event_mutex);
+	return err;
+}
+
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+	int err;
+
+	mutex_lock(&bpf_event_mutex);
+	err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
+	mutex_unlock(&bpf_event_mutex);
+	return err;
+}