netdev - [PATCH v6 bpf-next 1/3] bpf: add bpf_descendant

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190710180025.94726-2-javierhonduco@fb.com>
Date:   Wed, 10 Jul 2019 11:00:23 -0700
From:   Javier Honduvilla Coto <javierhonduco@...com>
To:     <netdev@...r.kernel.org>
CC:     <yhs@...com>, <kernel-team@...com>, <jonhaslam@...com>
Subject: [PATCH v6 bpf-next 1/3] bpf: add bpf_descendant_of helper

This patch adds the bpf_descendant_of helper which accepts a PID and
returns 1 if the PID of the process currently being executed is a
descendant of it or if it's itself. Returns 0 otherwise. The passed
PID should be the one as seen from the "global" pid namespace as the
processes' PIDs in the hierarchy are resolved using the context of said
initial namespace.

This is very useful in tracing programs when we want to filter by a
given PID and all the children it might spawn. The current workarounds
most people implement for this purpose have issues:

- Attaching to process spawning syscalls and dynamically add those PIDs
  to some bpf map that would be used to filter is cumbersome and
potentially racy.
- Unrolling some loop to perform what this helper is doing consumes lots
  of instructions. That and the impossibility to jump backwards makes it
really hard to be correct in really large process chains.

Signed-off-by: Javier Honduvilla Coto <javierhonduco@...com>
---
 include/linux/bpf.h      |  1 +
 include/uapi/linux/bpf.h | 20 +++++++++++++++++++-
 kernel/bpf/core.c        |  1 +
 kernel/bpf/helpers.c     | 27 +++++++++++++++++++++++++++
 kernel/trace/bpf_trace.c |  2 ++
 5 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 18f4cc2c6acd..4e861138887d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1053,6 +1053,7 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto;
 extern const struct bpf_func_proto bpf_strtol_proto;
 extern const struct bpf_func_proto bpf_strtoul_proto;
 extern const struct bpf_func_proto bpf_tcp_sock_proto;
+extern const struct bpf_func_proto bpf_descendant_of_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5695ab53e354..7e8c2bd654f5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2713,6 +2713,23 @@ union bpf_attr {
  *		**-EPERM** if no permission to send the *sig*.
  *
  *		**-EAGAIN** if bpf program can try again.
+ *
+ * int bpf_descendant_of(pid_t pid)
+ *     Description
+ *             Determine if the process identified by *pid* is an ancestor
+ *             (or equal) of the user process executed in this tracing
+ *             context. This is useful when filtering events happening
+ *             to a process and all of its descendants.
+ *
+ *             Note that *pid* must be the pid from the global namespace
+ *             as the pids of the process chain will be resolved using the
+ *             initial pid namespace viewer context.
+ *     Return
+ *             * 1 if the process identified by *pid* is an ancestor, or equal,
+ *             of the currently executing process within the global pid
+ *             namespace
+ *
+ *             * 0 otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2824,7 +2841,8 @@ union bpf_attr {
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
-	FN(send_signal),
+	FN(send_signal),		\
+	FN(descendant_of),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 16079550db6d..8f7f0ec8cded 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2039,6 +2039,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
 const struct bpf_func_proto bpf_get_current_comm_proto __weak;
 const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
+const struct bpf_func_proto bpf_descendant_of_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5e28718928ca..2214194e5f49 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -11,6 +11,7 @@
 #include <linux/uidgid.h>
 #include <linux/filter.h>
 #include <linux/ctype.h>
+#include <linux/init_task.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -487,3 +488,29 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 	.arg4_type	= ARG_PTR_TO_LONG,
 };
 #endif
+
+BPF_CALL_1(bpf_descendant_of, pid_t, pid)
+{
+	int result = 0;
+	struct task_struct *task = current;
+
+	if (pid == 0)
+		return 1;
+
+	while (task != &init_task) {
+		if (task->pid == pid) {
+			result = 1;
+			break;
+		}
+		task = rcu_dereference(task->real_parent);
+	}
+
+	return result;
+}
+
+const struct bpf_func_proto bpf_descendant_of_proto = {
+	.func		= bpf_descendant_of,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ca1255d14576..797d7b4a8e9a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -703,6 +703,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_probe_read_str:
 		return &bpf_probe_read_str_proto;
+	case BPF_FUNC_descendant_of:
+		return &bpf_descendant_of_proto;
 #ifdef CONFIG_CGROUPS
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;
-- 
2.17.1