bpf: introduce helper bpf_get_branch_snapshot

Introduce bpf_get_branch_snapshot(), which allows tracing pogram to get
branch trace from hardware (e.g. Intel LBR). To use the feature, the
user need to create perf_event with proper branch_record filtering
on each cpu, and then calls bpf_get_branch_snapshot in the bpf function.
On Intel CPUs, VLBR event (raw event 0x1b00) can be use for this.

Signed-off-by: Song Liu <songliubraving@fb.com>

include/linux/bpf.h

@@ -2220,4 +2220,6 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 **bin_buf, u32 num_args);
 void bpf_bprintf_cleanup(void);
 
+DECLARE_PER_CPU(struct perf_branch_snapshot, bpf_perf_branch_snapshot);
+
 #endif /* _LINUX_BPF_H */

include/linux/filter.h

@@ -575,7 +575,8 @@ struct bpf_prog {
 				has_callchain_buf:1, /* callchain buffer allocated? */
 				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
 				call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
-				call_get_func_ip:1; /* Do we call get_func_ip() */
+				call_get_func_ip:1, /* Do we call get_func_ip() */
+				call_get_branch:1; /* Do we call get_branch_snapshot() */
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	enum bpf_attach_type	expected_attach_type; /* For some prog types */
 	u32			len;		/* Number of filter blocks */

include/uapi/linux/bpf.h

@@ -4877,6 +4877,21 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		branch trace is taken soon after the trigger point of the
+ *		BPF program, so it may contain some entries after the
+ *		trigger point. The user need to filter these entries
+ *		accordingly.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *
+ *	Return
+ *		> 0, number of valid output entries.
+ *		**-EOPNOTSUPP**, the hardware/kernel does not support this function
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5070,7 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

kernel/bpf/trampoline.c

@@ -10,6 +10,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/module.h>
+#include <linux/static_call.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -564,6 +565,18 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
 u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
 	__acquires(RCU)
 {
+#ifdef CONFIG_PERF_EVENTS
+	/* Calling migrate_disable costs two entries in the LBR. To save
+	 * some entries, we call perf_snapshot_branch_stack before
+	 * migrate_disable to save some entries. This is OK because we
+	 * care about the branch trace before entering the BPF program.
+	 * If migrate happens exactly here, there isn't much we can do to
+	 * preserve the data.
+	 */
+	if (prog->call_get_branch)
+		static_call(perf_snapshot_branch_stack)(
+			this_cpu_ptr(&bpf_perf_branch_snapshot));
+#endif
 	rcu_read_lock();
 	migrate_disable();
 	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {

kernel/bpf/verifier.c

@@ -6446,6 +6446,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		env->prog->call_get_func_ip = true;
 	}
 
+	if (func_id == BPF_FUNC_get_branch_snapshot) {
+		if (env->prog->aux->sleepable) {
+			verbose(env, "sleepable progs cannot call get_branch_snapshot\n");
+			return -ENOTSUPP;
+		}
+		if (!IS_ENABLED(CONFIG_PERF_EVENTS)) {
+			verbose(env, "func %s#%d not supported without CONFIG_PERF_EVENTS\n",
+				func_id_name(func_id), func_id);
+			return -ENOTSUPP;
+		}
+		env->prog->call_get_branch = true;
+	}
 	if (changes_data)
 		clear_all_pkt_pointers(env);
 	return 0;

kernel/trace/bpf_trace.c

@@ -1017,6 +1017,33 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_2(bpf_get_branch_snapshot, void *, buf, u32, size)
+{
+#ifdef CONFIG_PERF_EVENTS
+	u32 max_size;
+
+	if (this_cpu_ptr(&bpf_perf_branch_snapshot)->nr == 0)
+		return -EOPNOTSUPP;
+
+	max_size = this_cpu_ptr(&bpf_perf_branch_snapshot)->nr *
+		sizeof(struct perf_branch_entry);
+	memcpy(buf, this_cpu_ptr(&bpf_perf_branch_snapshot)->entries,
+	       min_t(u32, size, max_size));
+
+	return this_cpu_ptr(&bpf_perf_branch_snapshot)->nr;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
+	.func		= bpf_get_branch_snapshot,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1132,6 +1159,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_get_func_ip:
 		return &bpf_get_func_ip_proto_tracing;
+	case BPF_FUNC_get_branch_snapshot:
+		return &bpf_get_branch_snapshot_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -1863,9 +1892,23 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
 	preempt_enable();
 }
 
+DEFINE_PER_CPU(struct perf_branch_snapshot, bpf_perf_branch_snapshot);
+
 static __always_inline
 void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
 {
+#ifdef CONFIG_PERF_EVENTS
+	/* Calling migrate_disable costs two entries in the LBR. To save
+	 * some entries, we call perf_snapshot_branch_stack before
+	 * migrate_disable to save some entries. This is OK because we
+	 * care about the branch trace before entering the BPF program.
+	 * If migrate happens exactly here, there isn't much we can do to
+	 * preserve the data.
+	 */
+	if (prog->call_get_branch)
+		static_call(perf_snapshot_branch_stack)(
+			this_cpu_ptr(&bpf_perf_branch_snapshot));
+#endif
 	cant_sleep();
 	rcu_read_lock();
 	(void) bpf_prog_run(prog, args);

tools/include/uapi/linux/bpf.h

@@ -4877,6 +4877,21 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		branch trace is taken soon after the trigger point of the
+ *		BPF program, so it may contain some entries after the
+ *		trigger point. The user need to filter these entries
+ *		accordingly.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *
+ *	Return
+ *		> 0, number of valid output entries.
+ *		**-EOPNOTSUPP**, the hardware/kernel does not support this function
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5070,7 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper