[PATCH bpf-next 2/3] bpf: introduce helper bpf_get_branch_trace

[Song Liu]

Introduce bpf_get_branch_trace(), 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_trace in the bpf function.
On Intel CPUs, VLBR event (raw event 0x1b00) can be use for this.

Signed-off-by: Song Liu <songliubraving@xxxxxx>
---
 include/linux/filter.h         |  3 ++-
 include/uapi/linux/bpf.h       | 16 ++++++++++++++++
 kernel/bpf/trampoline.c        | 15 +++++++++++++++
 kernel/bpf/verifier.c          |  7 +++++++
 kernel/trace/bpf_trace.c       | 30 ++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++
 6 files changed, 86 insertions(+), 1 deletion(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7d248941ecea3..8c30712f56ab2 100644
--- a/include/linux/filter.h
+++ b/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_trace() */
 	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 */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 191f0b286ee39..4b1ddb76603a5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4871,6 +4871,21 @@ union bpf_attr {
  * 	Return
  *		Value specified by user at BPF link creation/attachment time
  *		or 0, if it was not specified.
+ *
+ * long bpf_get_branch_trace(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.
+ *		**-EOPNOTSUP**, the hardware/kernel does not support this function
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5048,6 +5063,7 @@ union bpf_attr {
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
+	FN(get_branch_trace),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index fe1e857324e66..c36d3d7366cc9 100644
--- a/kernel/bpf/trampoline.c
+++ b/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 +565,20 @@ static void notrace inc_misses_counter(struct bpf_prog *prog)
 u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
 	__acquires(RCU)
 {
+	/* 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) {
+#ifdef CONFIG_HAVE_STATIC_CALL
+		static_call(perf_snapshot_branch_stack)();
+#else
+		perf_snapshot_branch_stack();
+#endif
+	}
 	rcu_read_lock();
 	migrate_disable();
 	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f5a0077c99811..292d2b471892a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6446,6 +6446,13 @@ 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_trace) {
+		if (env->prog->aux->sleepable) {
+			verbose(env, "sleepable progs cannot call get_branch_trace\n");
+			return -ENOTSUPP;
+		}
+		env->prog->call_get_branch = true;
+	}
 	if (changes_data)
 		clear_all_pkt_pointers(env);
 	return 0;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index cbc73c08c4a4e..fe0a653190a5f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1002,6 +1002,19 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_2(bpf_get_branch_trace, void *, buf, u32, size)
+{
+	return perf_read_branch_snapshot(buf, size);
+}
+
+static const struct bpf_func_proto bpf_get_branch_trace_proto = {
+	.func		= bpf_get_branch_trace,
+	.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)
 {
@@ -1115,6 +1128,8 @@ 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_trace:
+		return &bpf_get_branch_trace_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -1849,6 +1864,21 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
 static __always_inline
 void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
 {
+	/* 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) {
+#ifdef CONFIG_HAVE_STATIC_CALL
+		static_call(perf_snapshot_branch_stack)();
+#else
+		perf_snapshot_branch_stack();
+#endif
+	}
+
 	cant_sleep();
 	rcu_read_lock();
 	(void) bpf_prog_run(prog, args);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 191f0b286ee39..4b1ddb76603a5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4871,6 +4871,21 @@ union bpf_attr {
  * 	Return
  *		Value specified by user at BPF link creation/attachment time
  *		or 0, if it was not specified.
+ *
+ * long bpf_get_branch_trace(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.
+ *		**-EOPNOTSUP**, the hardware/kernel does not support this function
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5048,6 +5063,7 @@ union bpf_attr {
 	FN(timer_cancel),		\
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
+	FN(get_branch_trace),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
2.30.2