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>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-3-songliubraving@fb.com

include/uapi/linux/bpf.h

@@ -4877,6 +4877,27 @@ 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, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5076,7 @@ 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 = {
@@ -526,7 +527,7 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 }
 
 #define NO_START_TIME 1
-static u64 notrace bpf_prog_start_time(void)
+static __always_inline u64 notrace bpf_prog_start_time(void)
 {
 	u64 start = NO_START_TIME;
 

kernel/trace/bpf_trace.c

@@ -1017,6 +1017,34 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags)
+{
+#ifndef CONFIG_X86
+	return -ENOENT;
+#else
+	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
+	u32 entry_cnt = size / br_entry_size;
+
+	entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt);
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	if (!entry_cnt)
+		return -ENOENT;
+
+	return entry_cnt * br_entry_size;
+#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 +1160,8 @@ 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);
 	}

tools/include/uapi/linux/bpf.h

@@ -4877,6 +4877,27 @@ 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, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5076,7 @@ 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