From c06b0229579806f5b5e14af64cf9c5dc771445b3 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:07 -0700
Subject: bpf: Support 'X' in bpf_seq_printf() helper

'X' tells kernel to print hex with upper case letters.
/proc/net/tcp{4,6} seq_file show() used this, and
supports it in bpf_seq_printf() helper too.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230807.3988014-1-yhs@fb.com
---
 kernel/trace/bpf_trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a3ac7de98baa..b44505f56b6d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -681,7 +681,8 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 		}
 
 		if (fmt[i] != 'i' && fmt[i] != 'd' &&
-		    fmt[i] != 'u' && fmt[i] != 'x') {
+		    fmt[i] != 'u' && fmt[i] != 'x' &&
+		    fmt[i] != 'X') {
 			err = -EINVAL;
 			goto out;
 		}
-- 
cgit v1.3-18-gd494


From 72e2b2b66f9c1225e51fc4a1c1e8512959195b76 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:08 -0700
Subject: bpf: Allow tracing programs to use bpf_jiffies64() helper

/proc/net/tcp{4,6} uses jiffies for various computations.
Let us add bpf_jiffies64() helper to tracing program
so bpf_iter and other programs can use it.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230808.3988073-1-yhs@fb.com
---
 kernel/trace/bpf_trace.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel/trace')

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b44505f56b6d..0159f12d2af5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1135,6 +1135,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ringbuf_discard_proto;
 	case BPF_FUNC_ringbuf_query:
 		return &bpf_ringbuf_query_proto;
+	case BPF_FUNC_jiffies64:
+		return &bpf_jiffies64_proto;
 	default:
 		return NULL;
 	}
-- 
cgit v1.3-18-gd494


From af7ec13833619e17f03aa73a785a2f871da6d66b Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:09 -0700
Subject: bpf: Add bpf_skc_to_tcp6_sock() helper

The helper is used in tracing programs to cast a socket
pointer to a tcp6_sock pointer.
The return value could be NULL if the casting is illegal.

A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added
so the verifier is able to deduce proper return types for the helper.

Different from the previous BTF_ID based helpers,
the bpf_skc_to_tcp6_sock() argument can be several possible
btf_ids. More specifically, all possible socket data structures
with sock_common appearing in the first in the memory layout.
This patch only added socket types related to tcp and udp.

All possible argument btf_id and return value btf_id
for helper bpf_skc_to_tcp6_sock() are pre-calculcated and
cached. In the future, it is even possible to precompute
these btf_id's at kernel build time.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com
---
 include/linux/bpf.h            | 12 +++++++
 include/uapi/linux/bpf.h       |  9 ++++-
 kernel/bpf/btf.c               |  1 +
 kernel/bpf/verifier.c          | 43 ++++++++++++++++------
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 82 ++++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h |  9 ++++-
 8 files changed, 148 insertions(+), 12 deletions(-)

(limited to 'kernel/trace')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1e1501ee53ce..c0e38ad07848 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -265,6 +265,7 @@ enum bpf_return_type {
 	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
 	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
+	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -287,6 +288,12 @@ struct bpf_func_proto {
 		enum bpf_arg_type arg_type[5];
 	};
 	int *btf_id; /* BTF ids of arguments */
+	bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is
+						    * valid. Often used if more
+						    * than one btf id is permitted
+						    * for this argument.
+						    */
+	int *ret_btf_id; /* return value btf_id */
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -1524,6 +1531,7 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
+void init_btf_sock_ids(struct btf *btf);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
 					union bpf_attr *attr)
@@ -1549,6 +1557,9 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
+static inline void init_btf_sock_ids(struct btf *btf)
+{
+}
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
@@ -1638,6 +1649,7 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
 extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d9737d51dd19..e90ad07b291a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3255,6 +3255,12 @@ union bpf_attr {
  * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
  * 		is returned or the error code -EACCES in case the skb is not
  * 		subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3392,7 +3398,8 @@ union bpf_attr {
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
-	FN(csum_level),
+	FN(csum_level),			\
+	FN(skc_to_tcp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e377d1981730..4c3007f428b1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3674,6 +3674,7 @@ struct btf *btf_parse_vmlinux(void)
 		goto errout;
 
 	bpf_struct_ops_init(btf, log);
+	init_btf_sock_ids(btf);
 
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7460f967cb75..7de98906ddf4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3800,12 +3800,14 @@ static int int_ptr_type_to_size(enum bpf_arg_type type)
 	return -EINVAL;
 }
 
-static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
-			  enum bpf_arg_type arg_type,
-			  struct bpf_call_arg_meta *meta)
+static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+			  struct bpf_call_arg_meta *meta,
+			  const struct bpf_func_proto *fn)
 {
+	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected_type, type = reg->type;
+	enum bpf_arg_type arg_type = fn->arg_type[arg];
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -3885,9 +3887,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
-		if (reg->btf_id != meta->btf_id) {
-			verbose(env, "Helper has type %s got %s in R%d\n",
-				kernel_type_name(meta->btf_id),
+		if (!fn->check_btf_id) {
+			if (reg->btf_id != meta->btf_id) {
+				verbose(env, "Helper has type %s got %s in R%d\n",
+					kernel_type_name(meta->btf_id),
+					kernel_type_name(reg->btf_id), regno);
+
+				return -EACCES;
+			}
+		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
+			verbose(env, "Helper does not support %s in R%d\n",
 				kernel_type_name(reg->btf_id), regno);
 
 			return -EACCES;
@@ -4709,10 +4718,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		err = btf_resolve_helper_id(&env->log, fn, i);
-		if (err > 0)
-			meta.btf_id = err;
-		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		if (!fn->check_btf_id) {
+			err = btf_resolve_helper_id(&env->log, fn, i);
+			if (err > 0)
+				meta.btf_id = err;
+		}
+		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
 	}
@@ -4815,6 +4826,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
+	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+		int ret_btf_id;
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+		ret_btf_id = *fn->ret_btf_id;
+		if (ret_btf_id == 0) {
+			verbose(env, "invalid return type %d of func %s#%d\n",
+				fn->ret_type, func_id_name(func_id), func_id);
+			return -EINVAL;
+		}
+		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0159f12d2af5..2a97a268f533 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1515,6 +1515,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_output_proto;
 	case BPF_FUNC_xdp_output:
 		return &bpf_xdp_output_proto;
+	case BPF_FUNC_skc_to_tcp6_sock:
+		return &bpf_skc_to_tcp6_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index c713b6b8938f..176e27d75c51 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -47,6 +47,7 @@
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <net/sch_generic.h>
 #include <net/cls_cgroup.h>
 #include <net/dst_metadata.h>
@@ -9225,3 +9226,84 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog)
 {
 	bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog);
 }
+
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, "inet_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, "inet_connection_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, "inet_request_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, "inet_timewait_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, "request_sock")		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, "sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, "sock_common")		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, "tcp_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, "tcp_request_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, "tcp_timewait_sock")	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, "tcp6_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, "udp_sock")			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, "udp6_sock")
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+static int btf_sock_ids[MAX_BTF_SOCK_TYPE];
+
+#ifdef CONFIG_BPF_SYSCALL
+static const char *bpf_sock_types[] = {
+#define BTF_SOCK_TYPE(name, str) str,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+};
+
+void init_btf_sock_ids(struct btf *btf)
+{
+	int i, btf_id;
+
+	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) {
+		btf_id = btf_find_by_name_kind(btf, bpf_sock_types[i],
+					       BTF_KIND_STRUCT);
+		if (btf_id > 0)
+			btf_sock_ids[i] = btf_id;
+	}
+}
+#endif
+
+static bool check_arg_btf_id(u32 btf_id, u32 arg)
+{
+	int i;
+
+	/* only one argument, no need to check arg */
+	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
+		if (btf_sock_ids[i] == btf_id)
+			return true;
+	return false;
+}
+
+BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
+{
+	/* tcp6_sock type is not generated in dwarf and hence btf,
+	 * trigger an explicit type generation here.
+	 */
+	BTF_TYPE_EMIT(struct tcp6_sock);
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP &&
+	    sk->sk_family == AF_INET6)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
+	.func			= bpf_skc_to_tcp6_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
+};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 91fa668fa860..6c2f64118651 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -421,6 +421,7 @@ class PrinterHelpers(Printer):
             'struct sockaddr',
             'struct tcphdr',
             'struct seq_file',
+            'struct tcp6_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -458,6 +459,7 @@ class PrinterHelpers(Printer):
             'struct sockaddr',
             'struct tcphdr',
             'struct seq_file',
+            'struct tcp6_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d9737d51dd19..e90ad07b291a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3255,6 +3255,12 @@ union bpf_attr {
  * 		case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
  * 		is returned or the error code -EACCES in case the skb is not
  * 		subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3392,7 +3398,8 @@ union bpf_attr {
 	FN(ringbuf_submit),		\
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
-	FN(csum_level),
+	FN(csum_level),			\
+	FN(skc_to_tcp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.3-18-gd494


From 478cfbdf5f13dfe09cfd0b1cbac821f5e27f6108 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:11 -0700
Subject: bpf: Add bpf_skc_to_{tcp, tcp_timewait, tcp_request}_sock() helpers

Three more helpers are added to cast a sock_common pointer to
an tcp_sock, tcp_timewait_sock or a tcp_request_sock for
tracing programs.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230811.3988277-1-yhs@fb.com
---
 include/linux/bpf.h            |  3 ++
 include/uapi/linux/bpf.h       | 23 +++++++++++++++-
 kernel/trace/bpf_trace.c       |  6 ++++
 net/core/filter.c              | 62 ++++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  6 ++++
 tools/include/uapi/linux/bpf.h | 23 +++++++++++++++-
 6 files changed, 121 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c0e38ad07848..c23998cf6699 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1650,6 +1650,9 @@ extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e90ad07b291a..b9412ab275f3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3261,6 +3261,24 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3399,7 +3417,10 @@ union bpf_attr {
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
 	FN(csum_level),			\
-	FN(skc_to_tcp6_sock),
+	FN(skc_to_tcp6_sock),		\
+	FN(skc_to_tcp_sock),		\
+	FN(skc_to_tcp_timewait_sock),	\
+	FN(skc_to_tcp_request_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2a97a268f533..48d935b0d87c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1517,6 +1517,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_output_proto;
 	case BPF_FUNC_skc_to_tcp6_sock:
 		return &bpf_skc_to_tcp6_sock_proto;
+	case BPF_FUNC_skc_to_tcp_sock:
+		return &bpf_skc_to_tcp_sock_proto;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		return &bpf_skc_to_tcp_timewait_sock_proto;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		return &bpf_skc_to_tcp_request_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index 176e27d75c51..0b4e5aed7e20 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -74,6 +74,7 @@
 #include <net/lwtunnel.h>
 #include <net/ipv6_stubs.h>
 #include <net/bpf_sk_storage.h>
+#include <net/transp_v6.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -9307,3 +9308,64 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.check_btf_id		= check_arg_btf_id,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
+
+BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk)
+{
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
+	.func			= bpf_skc_to_tcp_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+};
+
+BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk)
+{
+	if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT)
+		return (unsigned long)sk;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT)
+		return (unsigned long)sk;
+#endif
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
+	.func			= bpf_skc_to_tcp_timewait_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
+};
+
+BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk)
+{
+	if (sk->sk_prot == &tcp_prot  && sk->sk_state == TCP_NEW_SYN_RECV)
+		return (unsigned long)sk;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV)
+		return (unsigned long)sk;
+#endif
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
+	.func			= bpf_skc_to_tcp_request_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
+};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6c2f64118651..d886657c6aaa 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -422,6 +422,9 @@ class PrinterHelpers(Printer):
             'struct tcphdr',
             'struct seq_file',
             'struct tcp6_sock',
+            'struct tcp_sock',
+            'struct tcp_timewait_sock',
+            'struct tcp_request_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -460,6 +463,9 @@ class PrinterHelpers(Printer):
             'struct tcphdr',
             'struct seq_file',
             'struct tcp6_sock',
+            'struct tcp_sock',
+            'struct tcp_timewait_sock',
+            'struct tcp_request_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e90ad07b291a..b9412ab275f3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3261,6 +3261,24 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ *	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3399,7 +3417,10 @@ union bpf_attr {
 	FN(ringbuf_discard),		\
 	FN(ringbuf_query),		\
 	FN(csum_level),			\
-	FN(skc_to_tcp6_sock),
+	FN(skc_to_tcp6_sock),		\
+	FN(skc_to_tcp_sock),		\
+	FN(skc_to_tcp_timewait_sock),	\
+	FN(skc_to_tcp_request_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.3-18-gd494


From 0d4fad3e57df2bf61e8ffc8d12a34b1caf9b8835 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 23 Jun 2020 16:08:15 -0700
Subject: bpf: Add bpf_skc_to_udp6_sock() helper

The helper is used in tracing programs to cast a socket
pointer to a udp6_sock pointer.
The return value could be NULL if the casting is illegal.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200623230815.3988481-1-yhs@fb.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  9 ++++++++-
 kernel/trace/bpf_trace.c       |  2 ++
 net/core/filter.c              | 22 ++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h |  9 ++++++++-
 6 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c23998cf6699..3d2ade703a35 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1653,6 +1653,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b9412ab275f3..0cb8ec948816 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3279,6 +3279,12 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3420,7 +3426,8 @@ union bpf_attr {
 	FN(skc_to_tcp6_sock),		\
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
-	FN(skc_to_tcp_request_sock),
+	FN(skc_to_tcp_request_sock),	\
+	FN(skc_to_udp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 48d935b0d87c..5d59dda5f661 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1523,6 +1523,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_to_tcp_timewait_sock_proto;
 	case BPF_FUNC_skc_to_tcp_request_sock:
 		return &bpf_skc_to_tcp_request_sock_proto;
+	case BPF_FUNC_skc_to_udp6_sock:
+		return &bpf_skc_to_udp6_sock_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index 0b4e5aed7e20..c796e141ea8e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9369,3 +9369,25 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.check_btf_id		= check_arg_btf_id,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
+
+BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk)
+{
+	/* udp6_sock type is not generated in dwarf and hence btf,
+	 * trigger an explicit type generation here.
+	 */
+	BTF_TYPE_EMIT(struct udp6_sock);
+	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP &&
+	    sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6)
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
+	.func			= bpf_skc_to_udp6_sock,
+	.gpl_only		= false,
+	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
+	.arg1_type		= ARG_PTR_TO_BTF_ID,
+	.check_btf_id		= check_arg_btf_id,
+	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
+};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index d886657c6aaa..6bab40ff442e 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -425,6 +425,7 @@ class PrinterHelpers(Printer):
             'struct tcp_sock',
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
+            'struct udp6_sock',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -466,6 +467,7 @@ class PrinterHelpers(Printer):
             'struct tcp_sock',
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
+            'struct udp6_sock',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b9412ab275f3..0cb8ec948816 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3279,6 +3279,12 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or NULL otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3420,7 +3426,8 @@ union bpf_attr {
 	FN(skc_to_tcp6_sock),		\
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
-	FN(skc_to_tcp_request_sock),
+	FN(skc_to_tcp_request_sock),	\
+	FN(skc_to_udp6_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.3-18-gd494


From fa28dcb82a38f8e3993b0fae9106b1a80b59e4f0 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 29 Jun 2020 23:28:44 -0700
Subject: bpf: Introduce helper bpf_get_task_stack()

Introduce helper bpf_get_task_stack(), which dumps stack trace of given
task. This is different to bpf_get_stack(), which gets stack track of
current task. One potential use case of bpf_get_task_stack() is to call
it from bpf_iter__task and dump all /proc/<pid>/stack to a seq_file.

bpf_get_task_stack() uses stack_trace_save_tsk() instead of
get_perf_callchain() for kernel stack. The benefit of this choice is that
stack_trace_save_tsk() doesn't require changes in arch/. The downside of
using stack_trace_save_tsk() is that stack_trace_save_tsk() dumps the
stack trace to unsigned long array. For 32-bit systems, we need to
translate it to u64 array.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630062846.664389-3-songliubraving@fb.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 37 +++++++++++++++++++-
 kernel/bpf/stackmap.c          | 77 +++++++++++++++++++++++++++++++++++++++---
 kernel/bpf/verifier.c          |  4 ++-
 kernel/trace/bpf_trace.c       |  2 ++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h | 37 +++++++++++++++++++-
 7 files changed, 153 insertions(+), 7 deletions(-)

(limited to 'kernel/trace')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3d2ade703a35..0cd7f6884c5c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1627,6 +1627,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
+extern const struct bpf_func_proto bpf_get_task_stack_proto;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0cb8ec948816..da9bf35a26f8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3285,6 +3285,39 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, 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 *task*, which is a valid
+ *		pointer to struct task_struct. 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_task_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),			\
@@ -3427,7 +3460,9 @@ union bpf_attr {
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
 	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),
+	FN(skc_to_udp6_sock),		\
+	FN(get_task_stack),		\
+	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 071f98d0f7c6..5ad72ab2276b 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -348,6 +348,40 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 }
 
+static struct perf_callchain_entry *
+get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
+{
+	struct perf_callchain_entry *entry;
+	int rctx;
+
+	entry = get_callchain_entry(&rctx);
+
+	if (!entry)
+		return NULL;
+
+	entry->nr = init_nr +
+		stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
+				     sysctl_perf_event_max_stack - init_nr, 0);
+
+	/* stack_trace_save_tsk() works on unsigned long array, while
+	 * perf_callchain_entry uses u64 array. For 32-bit systems, it is
+	 * necessary to fix this mismatch.
+	 */
+	if (__BITS_PER_LONG != 64) {
+		unsigned long *from = (unsigned long *) entry->ip;
+		u64 *to = entry->ip;
+		int i;
+
+		/* copy data from the end to avoid using extra buffer */
+		for (i = entry->nr - 1; i >= (int)init_nr; i--)
+			to[i] = (u64)(from[i]);
+	}
+
+	put_callchain_entry(rctx);
+
+	return entry;
+}
+
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags)
 {
@@ -448,8 +482,8 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
-	   u64, flags)
+static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
+			    void *buf, u32 size, u64 flags)
 {
 	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
@@ -471,13 +505,22 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	if (unlikely(size % elem_size))
 		goto clear;
 
+	/* cannot get valid user stack for task without user_mode regs */
+	if (task && user && !user_mode(regs))
+		goto err_fault;
+
 	num_elem = size / elem_size;
 	if (sysctl_perf_event_max_stack < num_elem)
 		init_nr = 0;
 	else
 		init_nr = sysctl_perf_event_max_stack - num_elem;
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
+
+	if (kernel && task)
+		trace = get_callchain_entry_for_task(task, init_nr);
+	else
+		trace = get_perf_callchain(regs, init_nr, kernel, user,
+					   sysctl_perf_event_max_stack,
+					   false, false);
 	if (unlikely(!trace))
 		goto err_fault;
 
@@ -505,6 +548,12 @@ clear:
 	return err;
 }
 
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, buf, size, flags);
+}
+
 const struct bpf_func_proto bpf_get_stack_proto = {
 	.func		= bpf_get_stack,
 	.gpl_only	= true,
@@ -515,6 +564,26 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	struct pt_regs *regs = task_pt_regs(task);
+
+	return __bpf_get_stack(regs, task, buf, size, flags);
+}
+
+static int bpf_get_task_stack_btf_ids[5];
+const struct bpf_func_proto bpf_get_task_stack_proto = {
+	.func		= bpf_get_task_stack,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= bpf_get_task_stack_btf_ids,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7de98906ddf4..b608185e1ffd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4864,7 +4864,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	if (err)
 		return err;
 
-	if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+	if ((func_id == BPF_FUNC_get_stack ||
+	     func_id == BPF_FUNC_get_task_stack) &&
+	    !env->prog->has_callchain_buf) {
 		const char *err_str;
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5d59dda5f661..977ba3b6f6c6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1137,6 +1137,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ringbuf_query_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
+	case BPF_FUNC_get_task_stack:
+		return &bpf_get_task_stack_proto;
 	default:
 		return NULL;
 	}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6bab40ff442e..6843376733df 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -426,6 +426,7 @@ class PrinterHelpers(Printer):
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
             'struct udp6_sock',
+            'struct task_struct',
 
             'struct __sk_buff',
             'struct sk_msg_md',
@@ -468,6 +469,7 @@ class PrinterHelpers(Printer):
             'struct tcp_timewait_sock',
             'struct tcp_request_sock',
             'struct udp6_sock',
+            'struct task_struct',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0cb8ec948816..da9bf35a26f8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3285,6 +3285,39 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or NULL otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, 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 *task*, which is a valid
+ *		pointer to struct task_struct. 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_task_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),			\
@@ -3427,7 +3460,9 @@ union bpf_attr {
 	FN(skc_to_tcp_sock),		\
 	FN(skc_to_tcp_timewait_sock),	\
 	FN(skc_to_tcp_request_sock),	\
-	FN(skc_to_udp6_sock),
+	FN(skc_to_udp6_sock),		\
+	FN(get_task_stack),		\
+	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.3-18-gd494


From 2df6bb5493f83c7e818f66c384ea337c1b3da228 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 29 Jun 2020 23:28:45 -0700
Subject: bpf: Allow %pB in bpf_seq_printf() and bpf_trace_printk()

This makes it easy to dump stack trace in text.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630062846.664389-4-songliubraving@fb.com
---
 kernel/trace/bpf_trace.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'kernel/trace')

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 977ba3b6f6c6..1d874d8e4384 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -376,7 +376,7 @@ static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
 
 /*
  * Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
  */
 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 	   u64, arg2, u64, arg3)
@@ -420,6 +420,11 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 				goto fmt_str;
 			}
 
+			if (fmt[i + 1] == 'B') {
+				i++;
+				goto fmt_next;
+			}
+
 			/* disallow any further format extensions */
 			if (fmt[i + 1] != 0 &&
 			    !isspace(fmt[i + 1]) &&
@@ -636,7 +641,8 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 		if (fmt[i] == 'p') {
 			if (fmt[i + 1] == 0 ||
 			    fmt[i + 1] == 'K' ||
-			    fmt[i + 1] == 'x') {
+			    fmt[i + 1] == 'x' ||
+			    fmt[i + 1] == 'B') {
 				/* just kernel pointers */
 				params[fmt_cnt] = args[fmt_cnt];
 				fmt_cnt++;
-- 
cgit v1.3-18-gd494


From c9a0f3b85e09dd16665b639cb884490410619434 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 11 Jul 2020 23:53:24 +0200
Subject: bpf: Resolve BTF IDs in vmlinux image

Using BTF_ID_LIST macro to define lists for several helpers
using BTF arguments.

And running resolve_btfids on vmlinux elf object during linking,
so the .BTF_ids section gets the IDs resolved.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200711215329.41165-5-jolsa@kernel.org
---
 Makefile                 | 3 ++-
 kernel/bpf/stackmap.c    | 5 ++++-
 kernel/trace/bpf_trace.c | 9 +++++++--
 net/core/filter.c        | 9 +++++++--
 scripts/link-vmlinux.sh  | 6 ++++++
 5 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'kernel/trace')

diff --git a/Makefile b/Makefile
index 017e775b3288..462f1a75fcb3 100644
--- a/Makefile
+++ b/Makefile
@@ -448,6 +448,7 @@ OBJSIZE		= $(CROSS_COMPILE)size
 STRIP		= $(CROSS_COMPILE)strip
 endif
 PAHOLE		= pahole
+RESOLVE_BTFIDS	= $(objtree)/tools/bpf/resolve_btfids/resolve_btfids
 LEX		= flex
 YACC		= bison
 AWK		= awk
@@ -510,7 +511,7 @@ GCC_PLUGINS_CFLAGS :=
 CLANG_FLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE LEX YACC AWK INSTALLKERNEL
+export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
 export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
 export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ
 export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a6c361ed7937..48d8e739975f 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -9,6 +9,7 @@
 #include <linux/elf.h>
 #include <linux/pagemap.h>
 #include <linux/irq_work.h>
+#include <linux/btf_ids.h>
 #include "percpu_freelist.h"
 
 #define STACK_CREATE_FLAG_MASK					\
@@ -576,7 +577,9 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	return __bpf_get_stack(regs, task, buf, size, flags);
 }
 
-static int bpf_get_task_stack_btf_ids[5];
+BTF_ID_LIST(bpf_get_task_stack_btf_ids)
+BTF_ID(struct, task_struct)
+
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e0b7775039ab..e178e8e32b33 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -13,6 +13,7 @@
 #include <linux/kprobes.h>
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
+#include <linux/btf_ids.h>
 
 #include <asm/tlb.h>
 
@@ -710,7 +711,9 @@ out:
 	return err;
 }
 
-static int bpf_seq_printf_btf_ids[5];
+BTF_ID_LIST(bpf_seq_printf_btf_ids)
+BTF_ID(struct, seq_file)
+
 static const struct bpf_func_proto bpf_seq_printf_proto = {
 	.func		= bpf_seq_printf,
 	.gpl_only	= true,
@@ -728,7 +731,9 @@ BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
 	return seq_write(m, data, len) ? -EOVERFLOW : 0;
 }
 
-static int bpf_seq_write_btf_ids[5];
+BTF_ID_LIST(bpf_seq_write_btf_ids)
+BTF_ID(struct, seq_file)
+
 static const struct bpf_func_proto bpf_seq_write_proto = {
 	.func		= bpf_seq_write,
 	.gpl_only	= true,
diff --git a/net/core/filter.c b/net/core/filter.c
index ddcc0d6209e1..4e572441e64a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -75,6 +75,7 @@
 #include <net/ipv6_stubs.h>
 #include <net/bpf_sk_storage.h>
 #include <net/transp_v6.h>
+#include <linux/btf_ids.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -3779,7 +3780,9 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-static int bpf_skb_output_btf_ids[5];
+BTF_ID_LIST(bpf_skb_output_btf_ids)
+BTF_ID(struct, sk_buff)
+
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
@@ -4173,7 +4176,9 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-static int bpf_xdp_output_btf_ids[5];
+BTF_ID_LIST(bpf_xdp_output_btf_ids)
+BTF_ID(struct, xdp_buff)
+
 const struct bpf_func_proto bpf_xdp_output_proto = {
 	.func		= bpf_xdp_event_output,
 	.gpl_only	= true,
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 92dd745906f4..e26f02dbedee 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -336,6 +336,12 @@ fi
 
 vmlinux_link vmlinux "${kallsymso}" ${btf_vmlinux_bin_o}
 
+# fill in BTF IDs
+if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
+info BTFIDS vmlinux
+${RESOLVE_BTFIDS} vmlinux
+fi
+
 if [ -n "${CONFIG_BUILDTIME_TABLE_SORT}" ]; then
 	info SORTTAB vmlinux
 	if ! sorttable vmlinux; then
-- 
cgit v1.3-18-gd494


From ac5a72ea5c8989871e61f6bb0852e0f91de51ebe Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 13 Jul 2020 12:52:33 +0100
Subject: bpf: Use dedicated bpf_trace_printk event instead of trace_printk()

The bpf helper bpf_trace_printk() uses trace_printk() under the hood.
This leads to an alarming warning message originating from trace
buffer allocation which occurs the first time a program using
bpf_trace_printk() is loaded.

We can instead create a trace event for bpf_trace_printk() and enable
it in-kernel when/if we encounter a program using the
bpf_trace_printk() helper.  With this approach, trace_printk()
is not used directly and no warning message appears.

This work was started by Steven (see Link) and finished by Alan; added
Steven's Signed-off-by with his permission.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/r/20200628194334.6238b933@oasis.local.home
Link: https://lore.kernel.org/bpf/1594641154-18897-2-git-send-email-alan.maguire@oracle.com
---
 kernel/trace/Makefile    |  2 ++
 kernel/trace/bpf_trace.c | 42 +++++++++++++++++++++++++++++++++++++-----
 kernel/trace/bpf_trace.h | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 73 insertions(+), 5 deletions(-)
 create mode 100644 kernel/trace/bpf_trace.h

(limited to 'kernel/trace')

diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 6575bb0a0434..aeba5ee7325a 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,6 +31,8 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
 GCOV_PROFILE := y
 endif
 
+CFLAGS_bpf_trace.o := -I$(src)
+
 CFLAGS_trace_benchmark.o := -I$(src)
 CFLAGS_trace_events_filter.o := -I$(src)
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e178e8e32b33..3cc0dcb60ca2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -11,6 +11,7 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/kprobes.h>
+#include <linux/spinlock.h>
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
@@ -20,6 +21,9 @@
 #include "trace_probe.h"
 #include "trace.h"
 
+#define CREATE_TRACE_POINTS
+#include "bpf_trace.h"
+
 #define bpf_event_rcu_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
 
@@ -375,6 +379,30 @@ static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
 	}
 }
 
+static DEFINE_RAW_SPINLOCK(trace_printk_lock);
+
+#define BPF_TRACE_PRINTK_SIZE   1024
+
+static inline __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	va_list ap;
+	int ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	va_start(ap, fmt);
+	ret = vsnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+	/* vsnprintf() will not append null for zero-length strings */
+	if (ret == 0)
+		buf[0] = '\0';
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	return ret;
+}
+
 /*
  * Only limited trace_printk() conversion specifiers allowed:
  * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
@@ -484,8 +512,7 @@ fmt_next:
  */
 #define __BPF_TP_EMIT()	__BPF_ARG3_TP()
 #define __BPF_TP(...)							\
-	__trace_printk(0 /* Fake ip */,					\
-		       fmt, ##__VA_ARGS__)
+	bpf_do_trace_printk(fmt, ##__VA_ARGS__)
 
 #define __BPF_ARG1_TP(...)						\
 	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
@@ -522,10 +549,15 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 {
 	/*
-	 * this program might be calling bpf_trace_printk,
-	 * so allocate per-cpu printk buffers
+	 * This program might be calling bpf_trace_printk,
+	 * so enable the associated bpf_trace/bpf_trace_printk event.
+	 * Repeat this each time as it is possible a user has
+	 * disabled bpf_trace_printk events.  By loading a program
+	 * calling bpf_trace_printk() however the user has expressed
+	 * the intent to see such events.
 	 */
-	trace_printk_init_buffers();
+	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
+		pr_warn_ratelimited("could not enable bpf_trace_printk events");
 
 	return &bpf_trace_printk_proto;
 }
diff --git a/kernel/trace/bpf_trace.h b/kernel/trace/bpf_trace.h
new file mode 100644
index 000000000000..9acbc11ac7bb
--- /dev/null
+++ b/kernel/trace/bpf_trace.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_trace
+
+#if !defined(_TRACE_BPF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_BPF_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(bpf_trace_printk,
+
+	TP_PROTO(const char *bpf_string),
+
+	TP_ARGS(bpf_string),
+
+	TP_STRUCT__entry(
+		__string(bpf_string, bpf_string)
+	),
+
+	TP_fast_assign(
+		__assign_str(bpf_string, bpf_string);
+	),
+
+	TP_printk("%s", __get_str(bpf_string))
+);
+
+#endif /* _TRACE_BPF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_trace
+
+#include <trace/define_trace.h>
-- 
cgit v1.3-18-gd494


From 7b04d6d60fcfb5b2200ffebb9cfb90927bdfeec7 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 23 Jul 2020 11:06:44 -0700
Subject: bpf: Separate bpf_get_[stack|stackid] for perf events BPF

Calling get_perf_callchain() on perf_events from PEBS entries may cause
unwinder errors. To fix this issue, the callchain is fetched early. Such
perf_events are marked with __PERF_SAMPLE_CALLCHAIN_EARLY.

Similarly, calling bpf_get_[stack|stackid] on perf_events from PEBS may
also cause unwinder errors. To fix this, add separate version of these
two helpers, bpf_get_[stack|stackid]_pe. These two hepers use callchain in
bpf_perf_event_data_kern->data->callchain.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723180648.1429892-2-songliubraving@fb.com
---
 include/linux/bpf.h      |   2 +
 kernel/bpf/stackmap.c    | 184 ++++++++++++++++++++++++++++++++++++++++++-----
 kernel/trace/bpf_trace.c |   4 +-
 3 files changed, 170 insertions(+), 20 deletions(-)

(limited to 'kernel/trace')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4175cf1f4665..8357be349133 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1675,6 +1675,8 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
 extern const struct bpf_func_proto bpf_get_task_stack_proto;
+extern const struct bpf_func_proto bpf_get_stackid_proto_pe;
+extern const struct bpf_func_proto bpf_get_stack_proto_pe;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 48d8e739975f..5beb2f8c23da 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
 #include <linux/elf.h>
@@ -387,11 +388,10 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
 #endif
 }
 
-BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
-	   u64, flags)
+static long __bpf_get_stackid(struct bpf_map *map,
+			      struct perf_callchain_entry *trace, u64 flags)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
-	struct perf_callchain_entry *trace;
 	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
 	u32 max_depth = map->value_size / stack_map_data_size(map);
 	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
@@ -399,21 +399,9 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	u32 hash, id, trace_nr, trace_len;
 	bool user = flags & BPF_F_USER_STACK;
-	bool kernel = !user;
 	u64 *ips;
 	bool hash_matches;
 
-	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
-			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
-		return -EINVAL;
-
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
-
-	if (unlikely(!trace))
-		/* couldn't fetch the stack trace */
-		return -EFAULT;
-
 	/* get_perf_callchain() guarantees that trace->nr >= init_nr
 	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
 	 */
@@ -478,6 +466,30 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	return id;
 }
 
+BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
+	   u64, flags)
+{
+	u32 max_depth = map->value_size / stack_map_data_size(map);
+	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
+	bool user = flags & BPF_F_USER_STACK;
+	struct perf_callchain_entry *trace;
+	bool kernel = !user;
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
+
+	if (unlikely(!trace))
+		/* couldn't fetch the stack trace */
+		return -EFAULT;
+
+	return __bpf_get_stackid(map, trace, flags);
+}
+
 const struct bpf_func_proto bpf_get_stackid_proto = {
 	.func		= bpf_get_stackid,
 	.gpl_only	= true,
@@ -487,7 +499,77 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+static __u64 count_kernel_ip(struct perf_callchain_entry *trace)
+{
+	__u64 nr_kernel = 0;
+
+	while (nr_kernel < trace->nr) {
+		if (trace->ip[nr_kernel] == PERF_CONTEXT_USER)
+			break;
+		nr_kernel++;
+	}
+	return nr_kernel;
+}
+
+BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_map *, map, u64, flags)
+{
+	struct perf_event *event = ctx->event;
+	struct perf_callchain_entry *trace;
+	bool kernel, user;
+	__u64 nr_kernel;
+	int ret;
+
+	/* perf_sample_data doesn't have callchain, use bpf_get_stackid */
+	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+		return bpf_get_stackid((unsigned long)(ctx->regs),
+				       (unsigned long) map, flags, 0, 0);
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	user = flags & BPF_F_USER_STACK;
+	kernel = !user;
+
+	trace = ctx->data->callchain;
+	if (unlikely(!trace))
+		return -EFAULT;
+
+	nr_kernel = count_kernel_ip(trace);
+
+	if (kernel) {
+		__u64 nr = trace->nr;
+
+		trace->nr = nr_kernel;
+		ret = __bpf_get_stackid(map, trace, flags);
+
+		/* restore nr */
+		trace->nr = nr;
+	} else { /* user */
+		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
+
+		skip += nr_kernel;
+		if (skip > BPF_F_SKIP_FIELD_MASK)
+			return -EFAULT;
+
+		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
+		ret = __bpf_get_stackid(map, trace, flags);
+	}
+	return ret;
+}
+
+const struct bpf_func_proto bpf_get_stackid_proto_pe = {
+	.func		= bpf_get_stackid_pe,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
+			    struct perf_callchain_entry *trace_in,
 			    void *buf, u32 size, u64 flags)
 {
 	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
@@ -520,7 +602,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else
 		init_nr = sysctl_perf_event_max_stack - num_elem;
 
-	if (kernel && task)
+	if (trace_in)
+		trace = trace_in;
+	else if (kernel && task)
 		trace = get_callchain_entry_for_task(task, init_nr);
 	else
 		trace = get_perf_callchain(regs, init_nr, kernel, user,
@@ -556,7 +640,7 @@ clear:
 BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	   u64, flags)
 {
-	return __bpf_get_stack(regs, NULL, buf, size, flags);
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
 }
 
 const struct bpf_func_proto bpf_get_stack_proto = {
@@ -574,7 +658,7 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 {
 	struct pt_regs *regs = task_pt_regs(task);
 
-	return __bpf_get_stack(regs, task, buf, size, flags);
+	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
 }
 
 BTF_ID_LIST(bpf_get_task_stack_btf_ids)
@@ -591,6 +675,70 @@ const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.btf_id		= bpf_get_task_stack_btf_ids,
 };
 
+BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
+	   void *, buf, u32, size, u64, flags)
+{
+	struct perf_event *event = ctx->event;
+	struct perf_callchain_entry *trace;
+	bool kernel, user;
+	int err = -EINVAL;
+	__u64 nr_kernel;
+
+	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+		return __bpf_get_stack(ctx->regs, NULL, NULL, buf, size, flags);
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_USER_BUILD_ID)))
+		goto clear;
+
+	user = flags & BPF_F_USER_STACK;
+	kernel = !user;
+
+	err = -EFAULT;
+	trace = ctx->data->callchain;
+	if (unlikely(!trace))
+		goto clear;
+
+	nr_kernel = count_kernel_ip(trace);
+
+	if (kernel) {
+		__u64 nr = trace->nr;
+
+		trace->nr = nr_kernel;
+		err = __bpf_get_stack(ctx->regs, NULL, trace, buf,
+				      size, flags);
+
+		/* restore nr */
+		trace->nr = nr;
+	} else { /* user */
+		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
+
+		skip += nr_kernel;
+		if (skip > BPF_F_SKIP_FIELD_MASK)
+			goto clear;
+
+		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
+		err = __bpf_get_stack(ctx->regs, NULL, trace, buf,
+				      size, flags);
+	}
+	return err;
+
+clear:
+	memset(buf, 0, size);
+	return err;
+
+}
+
+const struct bpf_func_proto bpf_get_stack_proto_pe = {
+	.func		= bpf_get_stack_pe,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3cc0dcb60ca2..cb91ef902cc4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1411,9 +1411,9 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
-		return &bpf_get_stackid_proto_tp;
+		return &bpf_get_stackid_proto_pe;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto_tp;
+		return &bpf_get_stack_proto_pe;
 	case BPF_FUNC_perf_prog_read_value:
 		return &bpf_perf_prog_read_value_proto;
 	case BPF_FUNC_read_branch_records:
-- 
cgit v1.3-18-gd494