tracing, perf: Implement BPF programs attached to kprobes

BPF programs, attached to kprobes, provide a safe way to execute
user-defined BPF byte-code programs without being able to crash or
hang the kernel in any way. The BPF engine makes sure that such
programs have a finite execution time and that they cannot break
out of their sandbox.

The user interface is to attach to a kprobe via the perf syscall:

	struct perf_event_attr attr = {
		.type	= PERF_TYPE_TRACEPOINT,
		.config	= event_id,
		...
	};

	event_fd = perf_event_open(&attr,...);
	ioctl(event_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);

'prog_fd' is a file descriptor associated with BPF program
previously loaded.

'event_id' is an ID of the kprobe created.

Closing 'event_fd':

	close(event_fd);

... automatically detaches BPF program from it.

BPF programs can call in-kernel helper functions to:

  - lookup/update/delete elements in maps

  - probe_read - wraper of probe_kernel_read() used to access any
    kernel data structures

BPF programs receive 'struct pt_regs *' as an input ('struct pt_regs' is
architecture dependent) and return 0 to ignore the event and 1 to store
kprobe event into the ring buffer.

Note, kprobes are a fundamentally _not_ a stable kernel ABI,
so BPF programs attached to kprobes must be recompiled for
every kernel version and user must supply correct LINUX_VERSION_CODE
in attr.kern_version during bpf_prog_load() call.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1427312966-8434-4-git-send-email-ast@plumgrid.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/ftrace_event.h

@@ -13,6 +13,7 @@ struct trace_array;
 struct trace_buffer;
 struct tracer;
 struct dentry;
+struct bpf_prog;
 
 struct trace_print_flags {
 	unsigned long		mask;
@@ -306,6 +307,7 @@ struct ftrace_event_call {
 #ifdef CONFIG_PERF_EVENTS
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
+	struct bpf_prog			*prog;
 
 	int	(*perf_perm)(struct ftrace_event_call *,
 			     struct perf_event *);
@@ -551,6 +553,15 @@ event_trigger_unlock_commit_regs(struct ftrace_event_file *file,
 		event_triggers_post_call(file, tt);
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx);
+#else
+static inline unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+{
+	return 1;
+}
+#endif
+
 enum {
 	FILTER_OTHER = 0,
 	FILTER_STATIC_STRING,

include/uapi/linux/bpf.h

@@ -118,6 +118,7 @@ enum bpf_map_type {
 enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
 	BPF_PROG_TYPE_SOCKET_FILTER,
+	BPF_PROG_TYPE_KPROBE,
 };
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -151,6 +152,7 @@ union bpf_attr {
 		__u32		log_level;	/* verbosity level of verifier */
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
+		__u32		kern_version;	/* checked when prog_type=kprobe */
 	};
 } __attribute__((aligned(8)));
 
@@ -162,6 +164,7 @@ enum bpf_func_id {
 	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
 	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
 	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
+	BPF_FUNC_probe_read,      /* int bpf_probe_read(void *dst, int size, void *src) */
 	__BPF_FUNC_MAX_ID,
 };
 

include/uapi/linux/perf_event.h

@@ -381,6 +381,7 @@ struct perf_event_attr {
 #define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
 #define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
 #define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,

kernel/bpf/syscall.c

@@ -16,6 +16,7 @@
 #include <linux/file.h>
 #include <linux/license.h>
 #include <linux/filter.h>
+#include <linux/version.h>
 
 static LIST_HEAD(bpf_map_types);
 
@@ -467,7 +468,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD log_buf
+#define	BPF_PROG_LOAD_LAST_FIELD kern_version
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -492,6 +493,10 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (attr->insn_cnt >= BPF_MAXINSNS)
 		return -EINVAL;
 
+	if (type == BPF_PROG_TYPE_KPROBE &&
+	    attr->kern_version != LINUX_VERSION_CODE)
+		return -EINVAL;
+
 	/* plain bpf_prog allocation */
 	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
 	if (!prog)

kernel/events/core.c

@@ -42,6 +42,8 @@
 #include <linux/module.h>
 #include <linux/mman.h>
 #include <linux/compat.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
 
 #include "internal.h"
 
@@ -3407,6 +3409,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 }
 
 static void perf_event_free_filter(struct perf_event *event);
+static void perf_event_free_bpf_prog(struct perf_event *event);
 
 static void free_event_rcu(struct rcu_head *head)
 {
@@ -3416,6 +3419,7 @@ static void free_event_rcu(struct rcu_head *head)
 	if (event->ns)
 		put_pid_ns(event->ns);
 	perf_event_free_filter(event);
+	perf_event_free_bpf_prog(event);
 	kfree(event);
 }
 
@@ -3928,6 +3932,7 @@ static inline int perf_fget_light(int fd, struct fd *p)
 static int perf_event_set_output(struct perf_event *event,
 				 struct perf_event *output_event);
 static int perf_event_set_filter(struct perf_event *event, void __user *arg);
+static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd);
 
 static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
 {
@@ -3981,6 +3986,9 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 	case PERF_EVENT_IOC_SET_FILTER:
 		return perf_event_set_filter(event, (void __user *)arg);
 
+	case PERF_EVENT_IOC_SET_BPF:
+		return perf_event_set_bpf_prog(event, arg);
+
 	default:
 		return -ENOTTY;
 	}
@@ -6455,6 +6463,49 @@ static void perf_event_free_filter(struct perf_event *event)
 	ftrace_profile_free_filter(event);
 }
 
+static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
+{
+	struct bpf_prog *prog;
+
+	if (event->attr.type != PERF_TYPE_TRACEPOINT)
+		return -EINVAL;
+
+	if (event->tp_event->prog)
+		return -EEXIST;
+
+	if (!(event->tp_event->flags & TRACE_EVENT_FL_KPROBE))
+		/* bpf programs can only be attached to kprobes */
+		return -EINVAL;
+
+	prog = bpf_prog_get(prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->aux->prog_type != BPF_PROG_TYPE_KPROBE) {
+		/* valid fd, but invalid bpf program type */
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	event->tp_event->prog = prog;
+
+	return 0;
+}
+
+static void perf_event_free_bpf_prog(struct perf_event *event)
+{
+	struct bpf_prog *prog;
+
+	if (!event->tp_event)
+		return;
+
+	prog = event->tp_event->prog;
+	if (prog) {
+		event->tp_event->prog = NULL;
+		bpf_prog_put(prog);
+	}
+}
+
 #else
 
 static inline void perf_tp_register(void)
@@ -6470,6 +6521,14 @@ static void perf_event_free_filter(struct perf_event *event)
 {
 }
 
+static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
+{
+	return -ENOENT;
+}
+
+static void perf_event_free_bpf_prog(struct perf_event *event)
+{
+}
 #endif /* CONFIG_EVENT_TRACING */
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT

kernel/trace/Makefile

@@ -53,6 +53,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_BPF_SYSCALL) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)

kernel/trace/bpf_trace.c

@@ -0,0 +1,130 @@
+/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/uaccess.h>
+#include "trace.h"
+
+static DEFINE_PER_CPU(int, bpf_prog_active);
+
+/**
+ * trace_call_bpf - invoke BPF program
+ * @prog: BPF program
+ * @ctx: opaque context pointer
+ *
+ * kprobe handlers execute BPF programs via this helper.
+ * Can be used from static tracepoints in the future.
+ *
+ * Return: BPF programs always return an integer which is interpreted by
+ * kprobe handler as:
+ * 0 - return from kprobe (event is filtered out)
+ * 1 - store kprobe event into ring buffer
+ * Other values are reserved and currently alias to 1
+ */
+unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+{
+	unsigned int ret;
+
+	if (in_nmi()) /* not supported yet */
+		return 1;
+
+	preempt_disable();
+
+	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+		/*
+		 * since some bpf program is already running on this cpu,
+		 * don't call into another bpf program (same or different)
+		 * and don't send kprobe event into ring-buffer,
+		 * so return zero here
+		 */
+		ret = 0;
+		goto out;
+	}
+
+	rcu_read_lock();
+	ret = BPF_PROG_RUN(prog, ctx);
+	rcu_read_unlock();
+
+ out:
+	__this_cpu_dec(bpf_prog_active);
+	preempt_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(trace_call_bpf);
+
+static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	void *dst = (void *) (long) r1;
+	int size = (int) r2;
+	void *unsafe_ptr = (void *) (long) r3;
+
+	return probe_kernel_read(dst, unsafe_ptr, size);
+}
+
+static const struct bpf_func_proto bpf_probe_read_proto = {
+	.func		= bpf_probe_read,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_probe_read:
+		return &bpf_probe_read_proto;
+	default:
+		return NULL;
+	}
+}
+
+/* bpf+kprobe programs can access fields of 'struct pt_regs' */
+static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+	/* check bounds */
+	if (off < 0 || off >= sizeof(struct pt_regs))
+		return false;
+
+	/* only read is allowed */
+	if (type != BPF_READ)
+		return false;
+
+	/* disallow misaligned access */
+	if (off % size != 0)
+		return false;
+
+	return true;
+}
+
+static struct bpf_verifier_ops kprobe_prog_ops = {
+	.get_func_proto  = kprobe_prog_func_proto,
+	.is_valid_access = kprobe_prog_is_valid_access,
+};
+
+static struct bpf_prog_type_list kprobe_tl = {
+	.ops	= &kprobe_prog_ops,
+	.type	= BPF_PROG_TYPE_KPROBE,
+};
+
+static int __init register_kprobe_prog_ops(void)
+{
+	bpf_register_prog_type(&kprobe_tl);
+	return 0;
+}
+late_initcall(register_kprobe_prog_ops);

kernel/trace/trace_kprobe.c

@@ -1134,11 +1134,15 @@ static void
 kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &tk->tp.call;
+	struct bpf_prog *prog = call->prog;
 	struct kprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
 	int rctx;
 
+	if (prog && !trace_call_bpf(prog, regs))
+		return;
+
 	head = this_cpu_ptr(call->perf_events);
 	if (hlist_empty(head))
 		return;
@@ -1165,11 +1169,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		    struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &tk->tp.call;
+	struct bpf_prog *prog = call->prog;
 	struct kretprobe_trace_entry_head *entry;
 	struct hlist_head *head;
 	int size, __size, dsize;
 	int rctx;
 
+	if (prog && !trace_call_bpf(prog, regs))
+		return;
+
 	head = this_cpu_ptr(call->perf_events);
 	if (hlist_empty(head))
 		return;