Merge branch 'bpf-raw-tracepoints'

Alexei Starovoitov says:

====================
v7->v8:
- moved 'u32 num_args' from 'struct tracepoint' into 'struct bpf_raw_event_map'
  that increases memory overhead, but can be optimized/compressed later.
  Now it's zero changes in tracepoint.[ch]

v6->v7:
- adopted Steven's bpf_raw_tp_map section approach to find tracepoint
  and corresponding bpf probe function instead of kallsyms approach.
  dropped kernel_tracepoint_find_by_name() patch

v5->v6:
- avoid changing semantics of for_each_kernel_tracepoint() function, instead
  introduce kernel_tracepoint_find_by_name() helper

v4->v5:
- adopted Daniel's fancy REPEAT macro in bpf_trace.c in patch 6

v3->v4:
- adopted Linus's CAST_TO_U64 macro to cast any integer, pointer, or small
  struct to u64. That nicely reduced the size of patch 1

v2->v3:
- with Linus's suggestion introduced generic COUNT_ARGS and CONCATENATE macros
  (or rather moved them from apparmor)
  that cleaned up patch 6
- added patch 4 to refactor trace_iwlwifi_dev_ucode_error() from 17 args to 4
  Now any tracepoint with >12 args will have build error

v1->v2:
- simplified api by combing bpf_raw_tp_open(name) + bpf_attach(prog_fd) into
  bpf_raw_tp_open(name, prog_fd) as suggested by Daniel.
  That simplifies bpf_detach as well which is now simple close() of fd.
- fixed memory leak in error path which was spotted by Daniel.
- fixed bpf_get_stackid(), bpf_perf_event_output() called from raw tracepoints
- added more tests
- fixed allyesconfig build caught by buildbot

v1:
This patch set is a different way to address the pressing need to access
task_struct pointers in sched tracepoints from bpf programs.

The first approach simply added these pointers to sched tracepoints:
https://lkml.org/lkml/2017/12/14/753
which Peter nacked.
Few options were discussed and eventually the discussion converged on
doing bpf specific tracepoint_probe_register() probe functions.
Details here:
https://lkml.org/lkml/2017/12/20/929

Patch 1 is kernel wide cleanup of pass-struct-by-value into
pass-struct-by-reference into tracepoints.

Patches 2 and 3 are minor cleanups to address allyesconfig build

Patch 4 refactor trace_iwlwifi_dev_ucode_error from 17 to 4 args

Patch 5 introduces COUNT_ARGS macro

Patch 6 introduces BPF_RAW_TRACEPOINT api.
the auto-cleanup and multiple concurrent users are must have
features of tracing api. For bpf raw tracepoints it 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
  // and attach bpf program to it
  raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);

Ctrl-C of tracing daemon or cmdline tool will automatically
detach bpf program, unload it and unregister tracepoint probe.
More details in patch 6.

Patch 7 - trivial support in libbpf
Patches 8, 9 - user space tests

samples/bpf/test_overhead performance on 1 cpu:

tracepoint    base  kprobe+bpf tracepoint+bpf raw_tracepoint+bpf
task_rename   1.1M   769K        947K            1.0M
urandom_read  789K   697K        750K            755K
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

9 files changed, 171 insertions, 1 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1ab0e520d6fc..8add3493a202 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -178,6 +178,15 @@
 #define TRACE_SYSCALLS()
 #endif
 
+#ifdef CONFIG_BPF_EVENTS
+#define BPF_RAW_TP() STRUCT_ALIGN();					\
+			 VMLINUX_SYMBOL(__start__bpf_raw_tp) = .;	\
+			 KEEP(*(__bpf_raw_tp_map))			\
+			 VMLINUX_SYMBOL(__stop__bpf_raw_tp) = .;
+#else
+#define BPF_RAW_TP()
+#endif
+
 #ifdef CONFIG_SERIAL_EARLYCON
 #define EARLYCON_TABLE() STRUCT_ALIGN();			\
 			 VMLINUX_SYMBOL(__earlycon_table) = .;	\
@@ -249,6 +258,7 @@
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
+	BPF_RAW_TP()							\
 	TRACEPOINT_STR()
 
 /*
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5e2e8a49fb21..6d7243bfb0ff 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -19,6 +19,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
 BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
 BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3fd291503576..293fa0677fba 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -919,6 +919,13 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
 
+/* This counts to 12. Any more, it will return 13th argument. */
+#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
+#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __CONCAT(a, b) a ## b
+#define CONCATENATE(a, b) __CONCAT(a, b)
+
 /**
  * container_of - cast a member of a structure out to the containing structure
  * @ptr:	the pointer to the member.
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 8a1442c4e513..b0357cd198b0 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -468,6 +468,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
 int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog);
 void perf_event_detach_bpf_prog(struct perf_event *event);
 int perf_event_query_prog_array(struct perf_event *event, void __user *info);
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
 #else
 static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
@@ -487,6 +490,18 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info)
 {
 	return -EOPNOTSUPP;
 }
+static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+{
+	return -EOPNOTSUPP;
+}
+static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+{
+	return -EOPNOTSUPP;
+}
+static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+{
+	return NULL;
+}
 #endif
 
 enum {
@@ -546,6 +561,33 @@ extern void ftrace_profile_free_filter(struct perf_event *event);
 void perf_trace_buf_update(void *record, u16 type);
 void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp);
 
+void bpf_trace_run1(struct bpf_prog *prog, u64 arg1);
+void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2);
+void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3);
+void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3, u64 arg4);
+void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3, u64 arg4, u64 arg5);
+void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3, u64 arg4, u64 arg5, u64 arg6);
+void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7);
+void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+		    u64 arg8);
+void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		    u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+		    u64 arg8, u64 arg9);
+void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+		     u64 arg8, u64 arg9, u64 arg10);
+void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+		     u64 arg8, u64 arg9, u64 arg10, u64 arg11);
+void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2,
+		     u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+		     u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12);
 void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
 			       struct trace_event_call *call, u64 count,
 			       struct pt_regs *regs, struct hlist_head *head,
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index 64ed7064f1fa..22c5a46e9693 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -35,4 +35,10 @@ struct tracepoint {
 	struct tracepoint_func __rcu *funcs;
 };
 
+struct bpf_raw_event_map {
+	struct tracepoint	*tp;
+	void			*bpf_func;
+	u32			num_args;
+} __aligned(32);
+
 #endif
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
new file mode 100644
index 000000000000..505dae0bed80
--- /dev/null
+++ b/include/trace/bpf_probe.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#undef TRACE_SYSTEM_VAR
+
+#ifdef CONFIG_BPF_EVENTS
+
+#undef __entry
+#define __entry entry
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
+
+#undef __get_dynamic_array_len
+#define __get_dynamic_array_len(field)	\
+		((__entry->__data_loc_##field >> 16) & 0xffff)
+
+#undef __get_str
+#define __get_str(field) ((char *)__get_dynamic_array(field))
+
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
+#undef __perf_count
+#define __perf_count(c)	(c)
+
+#undef __perf_task
+#define __perf_task(t)	(t)
+
+/* cast any integer, pointer, or small struct to u64 */
+#define UINTTYPE(size) \
+	__typeof__(__builtin_choose_expr(size == 1,  (u8)1, \
+		   __builtin_choose_expr(size == 2, (u16)2, \
+		   __builtin_choose_expr(size == 4, (u32)3, \
+		   __builtin_choose_expr(size == 8, (u64)4, \
+					 (void)5)))))
+#define __CAST_TO_U64(x) ({ \
+	typeof(x) __src = (x); \
+	UINTTYPE(sizeof(x)) __dst; \
+	memcpy(&__dst, &__src, sizeof(__dst)); \
+	(u64)__dst; })
+
+#define __CAST1(a,...) __CAST_TO_U64(a)
+#define __CAST2(a,...) __CAST_TO_U64(a), __CAST1(__VA_ARGS__)
+#define __CAST3(a,...) __CAST_TO_U64(a), __CAST2(__VA_ARGS__)
+#define __CAST4(a,...) __CAST_TO_U64(a), __CAST3(__VA_ARGS__)
+#define __CAST5(a,...) __CAST_TO_U64(a), __CAST4(__VA_ARGS__)
+#define __CAST6(a,...) __CAST_TO_U64(a), __CAST5(__VA_ARGS__)
+#define __CAST7(a,...) __CAST_TO_U64(a), __CAST6(__VA_ARGS__)
+#define __CAST8(a,...) __CAST_TO_U64(a), __CAST7(__VA_ARGS__)
+#define __CAST9(a,...) __CAST_TO_U64(a), __CAST8(__VA_ARGS__)
+#define __CAST10(a,...) __CAST_TO_U64(a), __CAST9(__VA_ARGS__)
+#define __CAST11(a,...) __CAST_TO_U64(a), __CAST10(__VA_ARGS__)
+#define __CAST12(a,...) __CAST_TO_U64(a), __CAST11(__VA_ARGS__)
+/* tracepoints with more than 12 arguments will hit build error */
+#define CAST_TO_U64(...) CONCATENATE(__CAST, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+static notrace void							\
+__bpf_trace_##call(void *__data, proto)					\
+{									\
+	struct bpf_prog *prog = __data;					\
+	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args));	\
+}
+
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * bpf probe will fail to compile unless it too is updated.
+ */
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+static inline void bpf_test_probe_##call(void)				\
+{									\
+	check_trace_callback_type_##call(__bpf_trace_##template);	\
+}									\
+static struct bpf_raw_event_map	__used					\
+	__attribute__((section("__bpf_raw_tp_map")))			\
+__bpf_trace_tp_map_##call = {						\
+	.tp		= &__tracepoint_##call,				\
+	.bpf_func	= (void *)__bpf_trace_##template,		\
+	.num_args	= COUNT_ARGS(args),				\
+};
+
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_BPF_EVENTS */
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index d9e3d4aa3f6e..cb30c5532144 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -95,6 +95,7 @@
 #ifdef TRACEPOINTS_ENABLED
 #include <trace/trace_events.h>
 #include <trace/perf.h>
+#include <trace/bpf_probe.h>
 #endif
 
 #undef TRACE_EVENT
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 06c87f9f720c..795698925d20 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -491,7 +491,7 @@ DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node,
 
 TRACE_EVENT(f2fs_truncate_partial_nodes,
 
-	TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err),
+	TP_PROTO(struct inode *inode, nid_t *nid, int depth, int err),
 
 	TP_ARGS(inode, nid, depth, err),
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 18b7c510c511..1878201c2d77 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -94,6 +94,7 @@ enum bpf_cmd {
 	BPF_MAP_GET_FD_BY_ID,
 	BPF_OBJ_GET_INFO_BY_FD,
 	BPF_PROG_QUERY,
+	BPF_RAW_TRACEPOINT_OPEN,
 };
 
 enum bpf_map_type {
@@ -134,6 +135,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_SKB,
 	BPF_PROG_TYPE_CGROUP_DEVICE,
 	BPF_PROG_TYPE_SK_MSG,
+	BPF_PROG_TYPE_RAW_TRACEPOINT,
 };
 
 enum bpf_attach_type {
@@ -344,6 +346,11 @@ union bpf_attr {
 		__aligned_u64	prog_ids;
 		__u32		prog_cnt;
 	} query;
+
+	struct {
+		__u64 name;
+		__u32 prog_fd;
+	} raw_tracepoint;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -1152,4 +1159,8 @@ struct bpf_cgroup_dev_ctx {
 	__u32 minor;
 };
 
+struct bpf_raw_tracepoint_args {
+	__u64 args[0];
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */