bpf: add bpf_get_stack helper

Currently, stackmap and bpf_get_stackid helper are provided
for bpf program to get the stack trace. This approach has
a limitation though. If two stack traces have the same hash,
only one will get stored in the stackmap table,
so some stack traces are missing from user perspective.

This patch implements a new helper, bpf_get_stack, will
send stack traces directly to bpf program. The bpf program
is able to see all stack traces, and then can do in-kernel
processing or send stack traces to user space through
shared map or bpf_perf_event_output.

Acked-by: Alexei Starovoitov <ast@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 40 insertions, 2 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index da77a9388947..1afb606a18b9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1767,6 +1767,40 @@ union bpf_attr {
  * 		**CONFIG_XFRM** configuration option.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * 	Description
+ *		Return a user or a kernel stack in bpf program provided buffer.
+ *		To achieve this, the helper needs *ctx*, which is a pointer
+ *		to the context on which the tracing program is executed.
+ *		To store the stacktrace, the bpf program provides *buf* with
+ *		a nonnegative *size*.
+ *
+ *		The last argument, *flags*, holds the number of stack frames to
+ *		skip (from 0 to 255), masked with
+ *		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ *		the following flags:
+ *
+ *		**BPF_F_USER_STACK**
+ *			Collect a user space stack instead of a kernel stack.
+ *		**BPF_F_USER_BUILD_ID**
+ *			Collect buildid+offset instead of ips for user stack,
+ *			only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ *		**bpf_get_stack**\ () can collect up to
+ *		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ *		to sufficient large buffer size. Note that
+ *		this limit can be controlled with the **sysctl** program, and
+ *		that it should be manually increased in order to profile long
+ *		user stacks (such as stacks for Java programs). To do so, use:
+ *
+ *	::
+ *
+ *		# sysctl kernel.perf_event_max_stack=<new value>
+ *
+ * 	Return
+ * 		a non-negative value equal to or less than size on success, or
+ * 		a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1835,7 +1869,8 @@ union bpf_attr {
 	FN(msg_pull_data),		\
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
-	FN(skb_get_xfrm_state),
+	FN(skb_get_xfrm_state),		\
+	FN(get_stack),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1869,11 +1904,14 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
 #define BPF_F_TUNINFO_IPV6		(1ULL << 0)
 
-/* BPF_FUNC_get_stackid flags. */
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
 #define BPF_F_SKIP_FIELD_MASK		0xffULL
 #define BPF_F_USER_STACK		(1ULL << 8)
+/* flags used by BPF_FUNC_get_stackid only. */
 #define BPF_F_FAST_STACK_CMP		(1ULL << 9)
 #define BPF_F_REUSE_STACKID		(1ULL << 10)
+/* flags used by BPF_FUNC_get_stack only. */
+#define BPF_F_USER_BUILD_ID		(1ULL << 11)
 
 /* BPF_FUNC_skb_set_tunnel_key flags. */
 #define BPF_F_ZERO_CSUM_TX		(1ULL << 1)