* [PATCH net-next v6 1/6] bpf: Refactor cgroups code in prep for new type
2016-11-30 18:16 [PATCH net-next v6 0/6] net: Add bpf support for sockets David Ahern
@ 2016-11-30 18:16 ` David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 2/6] bpf: Add new cgroup attach type to enable sock modifications David Ahern
` (4 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: David Ahern @ 2016-11-30 18:16 UTC (permalink / raw)
To: netdev; +Cc: daniel, ast, daniel, maheshb, tgraf, David Ahern
Code move and rename only; no functional change intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v6, v5
- no change
v4
- dropped refactor of __cgroup_bpf_run_filter and renamed it
to __cgroup_bpf_run_filter_skb
v3
- dropped the rename
v2
- fix bpf_prog_run_clear_cb to bpf_prog_run_save_cb as caught by Daniel
- rename BPF_PROG_TYPE_CGROUP_SKB and its cg_skb functions to
BPF_PROG_TYPE_CGROUP and cgroup
include/linux/bpf-cgroup.h | 46 +++++++++++++++++++++++-----------------------
kernel/bpf/cgroup.c | 10 +++++-----
kernel/bpf/syscall.c | 28 +++++++++++++++-------------
3 files changed, 43 insertions(+), 41 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index ec80d0c0953e..7f0fc635b13e 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -37,31 +37,31 @@ void cgroup_bpf_update(struct cgroup *cgrp,
struct bpf_prog *prog,
enum bpf_attach_type type);
-int __cgroup_bpf_run_filter(struct sock *sk,
- struct sk_buff *skb,
- enum bpf_attach_type type);
-
-/* Wrappers for __cgroup_bpf_run_filter() guarded by cgroup_bpf_enabled. */
-#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) \
-({ \
- int __ret = 0; \
- if (cgroup_bpf_enabled) \
- __ret = __cgroup_bpf_run_filter(sk, skb, \
- BPF_CGROUP_INET_INGRESS); \
- \
- __ret; \
+int __cgroup_bpf_run_filter_skb(struct sock *sk,
+ struct sk_buff *skb,
+ enum bpf_attach_type type);
+
+/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
+#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \
+ BPF_CGROUP_INET_INGRESS); \
+ \
+ __ret; \
})
-#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) \
-({ \
- int __ret = 0; \
- if (cgroup_bpf_enabled && sk && sk == skb->sk) { \
- typeof(sk) __sk = sk_to_full_sk(sk); \
- if (sk_fullsock(__sk)) \
- __ret = __cgroup_bpf_run_filter(__sk, skb, \
- BPF_CGROUP_INET_EGRESS); \
- } \
- __ret; \
+#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled && sk && sk == skb->sk) { \
+ typeof(sk) __sk = sk_to_full_sk(sk); \
+ if (sk_fullsock(__sk)) \
+ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \
+ BPF_CGROUP_INET_EGRESS); \
+ } \
+ __ret; \
})
#else
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 8c784f8c67cd..8fe55ffd109d 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -118,7 +118,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
}
/**
- * __cgroup_bpf_run_filter() - Run a program for packet filtering
+ * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socken sending or receiving traffic
* @skb: The skb that is being sent or received
* @type: The type of program to be exectuted
@@ -132,9 +132,9 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
* This function will return %-EPERM if any if an attached program was found
* and if it returned != 1 during execution. In all other cases, 0 is returned.
*/
-int __cgroup_bpf_run_filter(struct sock *sk,
- struct sk_buff *skb,
- enum bpf_attach_type type)
+int __cgroup_bpf_run_filter_skb(struct sock *sk,
+ struct sk_buff *skb,
+ enum bpf_attach_type type)
{
struct bpf_prog *prog;
struct cgroup *cgrp;
@@ -164,4 +164,4 @@ int __cgroup_bpf_run_filter(struct sock *sk,
return ret;
}
-EXPORT_SYMBOL(__cgroup_bpf_run_filter);
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4caa18e6860a..5518a6839ab1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -856,6 +856,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
{
struct bpf_prog *prog;
struct cgroup *cgrp;
+ enum bpf_prog_type ptype;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -866,25 +867,26 @@ static int bpf_prog_attach(const union bpf_attr *attr)
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
- prog = bpf_prog_get_type(attr->attach_bpf_fd,
- BPF_PROG_TYPE_CGROUP_SKB);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
-
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
- }
-
- cgroup_bpf_update(cgrp, prog, attr->attach_type);
- cgroup_put(cgrp);
+ ptype = BPF_PROG_TYPE_CGROUP_SKB;
break;
default:
return -EINVAL;
}
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp)) {
+ bpf_prog_put(prog);
+ return PTR_ERR(cgrp);
+ }
+
+ cgroup_bpf_update(cgrp, prog, attr->attach_type);
+ cgroup_put(cgrp);
+
return 0;
}
--
2.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH net-next v6 2/6] bpf: Add new cgroup attach type to enable sock modifications
2016-11-30 18:16 [PATCH net-next v6 0/6] net: Add bpf support for sockets David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 1/6] bpf: Refactor cgroups code in prep for new type David Ahern
@ 2016-11-30 18:16 ` David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 3/6] samples: bpf: add userspace example for modifying sk_bound_dev_if David Ahern
` (3 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: David Ahern @ 2016-11-30 18:16 UTC (permalink / raw)
To: netdev; +Cc: daniel, ast, daniel, maheshb, tgraf, David Ahern
Add new cgroup based program type, BPF_PROG_TYPE_CGROUP_SOCK. Similar to
BPF_PROG_TYPE_CGROUP_SKB programs can be attached to a cgroup and run
any time a process in the cgroup opens an AF_INET or AF_INET6 socket.
Currently only sk_bound_dev_if is exported to userspace for modification
by a bpf program.
This allows a cgroup to be configured such that AF_INET{6} sockets opened
by processes are automatically bound to a specific device. In turn, this
enables the running of programs that do not support SO_BINDTODEVICE in a
specific VRF context / L3 domain.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v6
- added size check to sock_filter_is_valid_access; accesses must be u32
v5
- no change
v4
- dropped tweak to bpf_func signature
- dropped cg_sock_func_proto in favor of sk_filter_func_proto
- new __cgroup_bpf_run_filter_sk versus overloading __cgroup_bpf_run_filter
- reverted BPF_CGROUP_INET_SOCK to BPF_CGROUP_INET_SOCK_CREATE
v3
- reverted to new prog type BPF_PROG_TYPE_CGROUP_SOCK
- dropped the subtype
v2
- dropped the bpf_sock_store_u32 helper
- dropped the new prog type BPF_PROG_TYPE_CGROUP_SOCK
- moved valid access and context conversion to use subtype
- dropped CREATE from BPF_CGROUP_INET_SOCK and related function names
- moved running of filter from sk_alloc to inet{6}_create
include/linux/bpf-cgroup.h | 14 +++++++++++
include/uapi/linux/bpf.h | 6 +++++
kernel/bpf/cgroup.c | 33 ++++++++++++++++++++++++
kernel/bpf/syscall.c | 5 +++-
net/core/filter.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++
net/ipv4/af_inet.c | 12 ++++++++-
net/ipv6/af_inet6.c | 8 ++++++
7 files changed, 138 insertions(+), 2 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 7f0fc635b13e..7de376e37c5c 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -41,6 +41,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
struct sk_buff *skb,
enum bpf_attach_type type);
+int __cgroup_bpf_run_filter_sk(struct sock *sk,
+ enum bpf_attach_type type);
+
/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
({ \
@@ -64,6 +67,16 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
__ret; \
})
+#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled && sk) { \
+ __ret = __cgroup_bpf_run_filter_sk(sk, \
+ BPF_CGROUP_INET_SOCK_CREATE); \
+ } \
+ __ret; \
+})
+
#else
struct cgroup_bpf {};
@@ -73,6 +86,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
#endif /* CONFIG_CGROUP_BPF */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1370a9d1456f..75964e00d947 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -101,11 +101,13 @@ enum bpf_prog_type {
BPF_PROG_TYPE_XDP,
BPF_PROG_TYPE_PERF_EVENT,
BPF_PROG_TYPE_CGROUP_SKB,
+ BPF_PROG_TYPE_CGROUP_SOCK,
};
enum bpf_attach_type {
BPF_CGROUP_INET_INGRESS,
BPF_CGROUP_INET_EGRESS,
+ BPF_CGROUP_INET_SOCK_CREATE,
__MAX_BPF_ATTACH_TYPE
};
@@ -537,6 +539,10 @@ struct bpf_tunnel_key {
__u32 tunnel_label;
};
+struct bpf_sock {
+ __u32 bound_dev_if;
+};
+
/* User return codes for XDP prog type.
* A valid XDP program must return one of these defined values. All other
* return codes are reserved for future use. Unknown return codes will result
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 8fe55ffd109d..a515f7b007c6 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -165,3 +165,36 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
+
+/**
+ * __cgroup_bpf_run_filter_sk() - Run a program on a sock
+ * @sk: sock structure to manipulate
+ * @type: The type of program to be exectuted
+ *
+ * socket is passed is expected to be of type INET or INET6.
+ *
+ * The program type passed in via @type must be suitable for sock
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sk(struct sock *sk,
+ enum bpf_attach_type type)
+{
+ struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+ struct bpf_prog *prog;
+ int ret = 0;
+
+
+ rcu_read_lock();
+
+ prog = rcu_dereference(cgrp->bpf.effective[type]);
+ if (prog)
+ ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM;
+
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5518a6839ab1..85af86c496cd 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -869,7 +869,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_INET_EGRESS:
ptype = BPF_PROG_TYPE_CGROUP_SKB;
break;
-
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+ break;
default:
return -EINVAL;
}
@@ -905,6 +907,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
+ case BPF_CGROUP_INET_SOCK_CREATE:
cgrp = cgroup_get_from_fd(attr->target_fd);
if (IS_ERR(cgrp))
return PTR_ERR(cgrp);
diff --git a/net/core/filter.c b/net/core/filter.c
index 698a262b8ebb..5ee722dc097d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2676,6 +2676,32 @@ static bool sk_filter_is_valid_access(int off, int size,
return __is_valid_access(off, size, type);
}
+static bool sock_filter_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
+{
+ if (type == BPF_WRITE) {
+ switch (off) {
+ case offsetof(struct bpf_sock, bound_dev_if):
+ break;
+ default:
+ return false;
+ }
+ }
+
+ if (off < 0 || off + size > sizeof(struct bpf_sock))
+ return false;
+
+ /* The verifier guarantees that size > 0. */
+ if (off % size != 0)
+ return false;
+
+ if (size != sizeof(__u32))
+ return false;
+
+ return true;
+}
+
static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
const struct bpf_prog *prog)
{
@@ -2934,6 +2960,30 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
return insn - insn_buf;
}
+static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
+ int dst_reg, int src_reg,
+ int ctx_off,
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ switch (ctx_off) {
+ case offsetof(struct bpf_sock, bound_dev_if):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4);
+
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sock, sk_bound_dev_if));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sock, sk_bound_dev_if));
+ break;
+ }
+
+ return insn - insn_buf;
+}
+
static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
struct bpf_insn *insn_buf,
@@ -3007,6 +3057,12 @@ static const struct bpf_verifier_ops cg_skb_ops = {
.convert_ctx_access = sk_filter_convert_ctx_access,
};
+static const struct bpf_verifier_ops cg_sock_ops = {
+ .get_func_proto = sk_filter_func_proto,
+ .is_valid_access = sock_filter_is_valid_access,
+ .convert_ctx_access = sock_filter_convert_ctx_access,
+};
+
static struct bpf_prog_type_list sk_filter_type __read_mostly = {
.ops = &sk_filter_ops,
.type = BPF_PROG_TYPE_SOCKET_FILTER,
@@ -3032,6 +3088,11 @@ static struct bpf_prog_type_list cg_skb_type __read_mostly = {
.type = BPF_PROG_TYPE_CGROUP_SKB,
};
+static struct bpf_prog_type_list cg_sock_type __read_mostly = {
+ .ops = &cg_sock_ops,
+ .type = BPF_PROG_TYPE_CGROUP_SOCK
+};
+
static int __init register_sk_filter_ops(void)
{
bpf_register_prog_type(&sk_filter_type);
@@ -3039,6 +3100,7 @@ static int __init register_sk_filter_ops(void)
bpf_register_prog_type(&sched_act_type);
bpf_register_prog_type(&xdp_type);
bpf_register_prog_type(&cg_skb_type);
+ bpf_register_prog_type(&cg_sock_type);
return 0;
}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5ddf5cda07f4..24d2550492ee 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -374,8 +374,18 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
- if (err)
+ if (err) {
+ sk_common_release(sk);
+ goto out;
+ }
+ }
+
+ if (!kern) {
+ err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
+ if (err) {
sk_common_release(sk);
+ goto out;
+ }
}
out:
return err;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d424f3a3737a..237e654ba717 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -258,6 +258,14 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
goto out;
}
}
+
+ if (!kern) {
+ err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
+ if (err) {
+ sk_common_release(sk);
+ goto out;
+ }
+ }
out:
return err;
out_rcu_unlock:
--
2.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH net-next v6 3/6] samples: bpf: add userspace example for modifying sk_bound_dev_if
2016-11-30 18:16 [PATCH net-next v6 0/6] net: Add bpf support for sockets David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 1/6] bpf: Refactor cgroups code in prep for new type David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 2/6] bpf: Add new cgroup attach type to enable sock modifications David Ahern
@ 2016-11-30 18:16 ` David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 4/6] bpf: Add support for reading socket family, type, protocol David Ahern
` (2 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: David Ahern @ 2016-11-30 18:16 UTC (permalink / raw)
To: netdev; +Cc: daniel, ast, daniel, maheshb, tgraf, David Ahern
Add a simple program to demonstrate the ability to attach a bpf program
to a cgroup that sets sk_bound_dev_if for AF_INET{6} sockets when they
are created.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v6
- added conversion from device name to index in test program
v5
- changed BPF_CGROUP_INET_SOCK to BPF_CGROUP_INET_SOCK_CREATE
v4
- added test_cgrp2_sock.sh for an automated test
v3
- revert to BPF_PROG_TYPE_CGROUP_SOCK prog type
v2
- removed bpf_sock_store_u32 references
- changed BPF_CGROUP_INET_SOCK_CREATE to BPF_CGROUP_INET_SOCK
- remove BPF_PROG_TYPE_CGROUP_SOCK prog type and add prog_subtype
samples/bpf/Makefile | 2 +
samples/bpf/test_cgrp2_sock.c | 83 ++++++++++++++++++++++++++++++++++++++++++
samples/bpf/test_cgrp2_sock.sh | 47 ++++++++++++++++++++++++
3 files changed, 132 insertions(+)
create mode 100644 samples/bpf/test_cgrp2_sock.c
create mode 100755 samples/bpf/test_cgrp2_sock.sh
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 3ceb5a9d86df..a335b218198e 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -23,6 +23,7 @@ hostprogs-y += map_perf_test
hostprogs-y += test_overhead
hostprogs-y += test_cgrp2_array_pin
hostprogs-y += test_cgrp2_attach
+hostprogs-y += test_cgrp2_sock
hostprogs-y += xdp1
hostprogs-y += xdp2
hostprogs-y += test_current_task_under_cgroup
@@ -51,6 +52,7 @@ map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o
+test_cgrp2_sock-objs := libbpf.o test_cgrp2_sock.o
xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
# reuse xdp1 source intentionally
xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c
new file mode 100644
index 000000000000..d467b3c1c55c
--- /dev/null
+++ b/samples/bpf/test_cgrp2_sock.c
@@ -0,0 +1,83 @@
+/* eBPF example program:
+ *
+ * - Loads eBPF program
+ *
+ * The eBPF program sets the sk_bound_dev_if index in new AF_INET{6}
+ * sockets opened by processes in the cgroup.
+ *
+ * - Attaches the new program to a cgroup using BPF_PROG_ATTACH
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+#include <unistd.h>
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <net/if.h>
+#include <linux/bpf.h>
+
+#include "libbpf.h"
+
+static int prog_load(int idx)
+{
+ struct bpf_insn prog[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_3, idx),
+ BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, bound_dev_if)),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, bound_dev_if)),
+ BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */
+ BPF_EXIT_INSN(),
+ };
+
+ return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, prog, sizeof(prog),
+ "GPL", 0);
+}
+
+static int usage(const char *argv0)
+{
+ printf("Usage: %s cg-path device-index\n", argv0);
+ return EXIT_FAILURE;
+}
+
+int main(int argc, char **argv)
+{
+ int cg_fd, prog_fd, ret;
+ unsigned int idx;
+
+ if (argc < 2)
+ return usage(argv[0]);
+
+ idx = if_nametoindex(argv[2]);
+ if (!idx) {
+ printf("Invalid device name\n");
+ return EXIT_FAILURE;
+ }
+
+ cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY);
+ if (cg_fd < 0) {
+ printf("Failed to open cgroup path: '%s'\n", strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ prog_fd = prog_load(idx);
+ printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf);
+
+ if (prog_fd < 0) {
+ printf("Failed to load prog: '%s'\n", strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE);
+ if (ret < 0) {
+ printf("Failed to attach prog to cgroup: '%s'\n",
+ strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ return EXIT_SUCCESS;
+}
diff --git a/samples/bpf/test_cgrp2_sock.sh b/samples/bpf/test_cgrp2_sock.sh
new file mode 100755
index 000000000000..925fd467c7cc
--- /dev/null
+++ b/samples/bpf/test_cgrp2_sock.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+
+function config_device {
+ ip netns add at_ns0
+ ip link add veth0 type veth peer name veth0b
+ ip link set veth0b up
+ ip link set veth0 netns at_ns0
+ ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
+ ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip link add foo type vrf table 1234
+ ip link set foo up
+ ip addr add 172.16.1.101/24 dev veth0b
+ ip addr add 2401:db00::2/64 dev veth0b nodad
+ ip link set veth0b master foo
+}
+
+function attach_bpf {
+ rm -rf /tmp/cgroupv2
+ mkdir -p /tmp/cgroupv2
+ mount -t cgroup2 none /tmp/cgroupv2
+ mkdir -p /tmp/cgroupv2/foo
+ test_cgrp2_sock /tmp/cgroupv2/foo foo
+ echo $$ >> /tmp/cgroupv2/foo/cgroup.procs
+}
+
+function cleanup {
+ set +ex
+ ip netns delete at_ns0
+ ip link del veth0
+ ip link del foo
+ umount /tmp/cgroupv2
+ rm -rf /tmp/cgroupv2
+ set -ex
+}
+
+function do_test {
+ ping -c1 -w1 172.16.1.100
+ ping6 -c1 -w1 2401:db00::1
+}
+
+cleanup 2>/dev/null
+config_device
+attach_bpf
+do_test
+cleanup
+echo "*** PASS ***"
--
2.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH net-next v6 4/6] bpf: Add support for reading socket family, type, protocol
2016-11-30 18:16 [PATCH net-next v6 0/6] net: Add bpf support for sockets David Ahern
` (2 preceding siblings ...)
2016-11-30 18:16 ` [PATCH net-next v6 3/6] samples: bpf: add userspace example for modifying sk_bound_dev_if David Ahern
@ 2016-11-30 18:16 ` David Ahern
2016-12-01 5:53 ` Alexei Starovoitov
2016-11-30 18:16 ` [PATCH net-next v6 5/6] samples/bpf: Update bpf loader for cgroup section names David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets David Ahern
5 siblings, 1 reply; 12+ messages in thread
From: David Ahern @ 2016-11-30 18:16 UTC (permalink / raw)
To: netdev; +Cc: daniel, ast, daniel, maheshb, tgraf, David Ahern
Add socket family, type and protocol to bpf_sock allowing bpf programs
read-only access.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v6
- new patch for version 6 of set
include/net/sock.h | 15 +++++++++++++++
include/uapi/linux/bpf.h | 3 +++
net/core/filter.c | 42 ++++++++++++++++++++++++++++++++++++++++++
3 files changed, 60 insertions(+)
diff --git a/include/net/sock.h b/include/net/sock.h
index 442cbb118a07..69afda6bea15 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -389,6 +389,21 @@ struct sock {
* Because of non atomicity rules, all
* changes are protected by socket lock.
*/
+ unsigned int __sk_flags_offset[0];
+#ifdef __BIG_ENDIAN_BITFIELD
+#define SK_FL_PROTO_SHIFT 16
+#define SK_FL_PROTO_MASK 0x00ff0000
+
+#define SK_FL_TYPE_SHIFT 0
+#define SK_FL_TYPE_MASK 0x0000ffff
+#else
+#define SK_FL_PROTO_SHIFT 8
+#define SK_FL_PROTO_MASK 0x0000ff00
+
+#define SK_FL_TYPE_SHIFT 16
+#define SK_FL_TYPE_MASK 0xffff0000
+#endif
+
kmemcheck_bitfield_begin(flags);
unsigned int sk_padding : 2,
sk_no_check_tx : 1,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 75964e00d947..b47ffd117fd6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -541,6 +541,9 @@ struct bpf_tunnel_key {
struct bpf_sock {
__u32 bound_dev_if;
+ __u32 family;
+ __u32 type;
+ __u32 protocol;
};
/* User return codes for XDP prog type.
diff --git a/net/core/filter.c b/net/core/filter.c
index 5ee722dc097d..ddc86efe1911 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2960,6 +2960,33 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
return insn - insn_buf;
}
+#define SOCKF_AD_TYPE 1
+#define SOCKF_AD_PROTOCOL 2
+
+static u32 convert_sock_access(int sock_field, int dst_reg, int src_reg,
+ struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ switch (sock_field) {
+ case SOCKF_AD_TYPE:
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sock, __sk_flags_offset));
+ *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_TYPE_MASK);
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_TYPE_SHIFT);
+ break;
+
+ case SOCKF_AD_PROTOCOL:
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sock, __sk_flags_offset));
+ *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_PROTO_MASK);
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_PROTO_SHIFT);
+ break;
+ }
+
+ return insn - insn_buf;
+}
+
static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
int dst_reg, int src_reg,
int ctx_off,
@@ -2979,6 +3006,21 @@ static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
offsetof(struct sock, sk_bound_dev_if));
break;
+
+ case offsetof(struct bpf_sock, family):
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2);
+
+ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg,
+ offsetof(struct sock, sk_family));
+ break;
+
+ case offsetof(struct bpf_sock, type):
+ return convert_sock_access(SOCKF_AD_TYPE, dst_reg, src_reg,
+ insn_buf);
+
+ case offsetof(struct bpf_sock, protocol):
+ return convert_sock_access(SOCKF_AD_PROTOCOL, dst_reg, src_reg,
+ insn_buf);
}
return insn - insn_buf;
--
2.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* Re: [PATCH net-next v6 4/6] bpf: Add support for reading socket family, type, protocol
2016-11-30 18:16 ` [PATCH net-next v6 4/6] bpf: Add support for reading socket family, type, protocol David Ahern
@ 2016-12-01 5:53 ` Alexei Starovoitov
0 siblings, 0 replies; 12+ messages in thread
From: Alexei Starovoitov @ 2016-12-01 5:53 UTC (permalink / raw)
To: David Ahern; +Cc: netdev, daniel, ast, daniel, maheshb, tgraf
On Wed, Nov 30, 2016 at 10:16:48AM -0800, David Ahern wrote:
> Add socket family, type and protocol to bpf_sock allowing bpf programs
> read-only access.
>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
...
> +static u32 convert_sock_access(int sock_field, int dst_reg, int src_reg,
> + struct bpf_insn *insn_buf)
> +{
> + struct bpf_insn *insn = insn_buf;
> +
> + switch (sock_field) {
> + case SOCKF_AD_TYPE:
> + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
> + offsetof(struct sock, __sk_flags_offset));
> + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, SK_FL_TYPE_MASK);
> + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, SK_FL_TYPE_SHIFT);
> + break;
Wasn't that complex after all? ;)
This part looks good.
> + case offsetof(struct bpf_sock, type):
> + return convert_sock_access(SOCKF_AD_TYPE, dst_reg, src_reg,
> + insn_buf);
my only request-for-change is to place the above 3 lines of *insn++ here
instead of adding new helper function for it.
In case of skb it was a helper, because it was called from different places.
Here this is the only place where it ever be needed, so extra helper
only confuses the reader.
The rest of the patches look good to me.
I'm not Ack-ing them yet, since you didn't carry over my Ack
from the first patch and I had to re-review it again this time.
Thanks.
^ permalink raw reply [flat|nested] 12+ messages in thread
* [PATCH net-next v6 5/6] samples/bpf: Update bpf loader for cgroup section names
2016-11-30 18:16 [PATCH net-next v6 0/6] net: Add bpf support for sockets David Ahern
` (3 preceding siblings ...)
2016-11-30 18:16 ` [PATCH net-next v6 4/6] bpf: Add support for reading socket family, type, protocol David Ahern
@ 2016-11-30 18:16 ` David Ahern
2016-11-30 18:16 ` [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets David Ahern
5 siblings, 0 replies; 12+ messages in thread
From: David Ahern @ 2016-11-30 18:16 UTC (permalink / raw)
To: netdev; +Cc: daniel, ast, daniel, maheshb, tgraf, David Ahern
Add support for section names starting with cgroup/skb and cgroup/sock.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v6
- new patch for version 6
samples/bpf/bpf_load.c | 14 +++++++++++---
samples/bpf/bpf_load.h | 1 +
2 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 62f54d6eb8bf..49b45ccbe153 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -52,6 +52,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0;
bool is_xdp = strncmp(event, "xdp", 3) == 0;
bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
+ bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
+ bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
enum bpf_prog_type prog_type;
char buf[256];
int fd, efd, err, id;
@@ -72,6 +74,10 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
prog_type = BPF_PROG_TYPE_XDP;
} else if (is_perf_event) {
prog_type = BPF_PROG_TYPE_PERF_EVENT;
+ } else if (is_cgroup_skb) {
+ prog_type = BPF_PROG_TYPE_CGROUP_SKB;
+ } else if (is_cgroup_sk) {
+ prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
} else {
printf("Unknown event '%s'\n", event);
return -1;
@@ -85,7 +91,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
prog_fd[prog_cnt++] = fd;
- if (is_xdp || is_perf_event)
+ if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk)
return 0;
if (is_socket) {
@@ -334,7 +340,8 @@ int load_bpf_file(char *path)
memcmp(shname_prog, "tracepoint/", 11) == 0 ||
memcmp(shname_prog, "xdp", 3) == 0 ||
memcmp(shname_prog, "perf_event", 10) == 0 ||
- memcmp(shname_prog, "socket", 6) == 0)
+ memcmp(shname_prog, "socket", 6) == 0 ||
+ memcmp(shname_prog, "cgroup/", 7) == 0)
load_and_attach(shname_prog, insns, data_prog->d_size);
}
}
@@ -353,7 +360,8 @@ int load_bpf_file(char *path)
memcmp(shname, "tracepoint/", 11) == 0 ||
memcmp(shname, "xdp", 3) == 0 ||
memcmp(shname, "perf_event", 10) == 0 ||
- memcmp(shname, "socket", 6) == 0)
+ memcmp(shname, "socket", 6) == 0 ||
+ memcmp(shname, "cgroup/", 7) == 0)
load_and_attach(shname, data->d_buf, data->d_size);
}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index dfa57fe65c8e..4adeeef53ad6 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -7,6 +7,7 @@
extern int map_fd[MAX_MAPS];
extern int prog_fd[MAX_PROGS];
extern int event_fd[MAX_PROGS];
+extern int prog_cnt;
/* parses elf file compiled by llvm .c->.o
* . parses 'maps' section and creates maps via BPF syscall
--
2.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets
2016-11-30 18:16 [PATCH net-next v6 0/6] net: Add bpf support for sockets David Ahern
` (4 preceding siblings ...)
2016-11-30 18:16 ` [PATCH net-next v6 5/6] samples/bpf: Update bpf loader for cgroup section names David Ahern
@ 2016-11-30 18:16 ` David Ahern
2016-12-01 5:59 ` Alexei Starovoitov
5 siblings, 1 reply; 12+ messages in thread
From: David Ahern @ 2016-11-30 18:16 UTC (permalink / raw)
To: netdev; +Cc: daniel, ast, daniel, maheshb, tgraf, David Ahern
Add examples preventing a process in a cgroup from opening a socket
based family, protocol and type.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v6
- new patch for version 6
samples/bpf/Makefile | 4 ++
samples/bpf/sock_flags_kern.c | 37 +++++++++++++++++++
samples/bpf/test_cgrp2_sock2.c | 66 +++++++++++++++++++++++++++++++++
samples/bpf/test_cgrp2_sock2.sh | 81 +++++++++++++++++++++++++++++++++++++++++
4 files changed, 188 insertions(+)
create mode 100644 samples/bpf/sock_flags_kern.c
create mode 100644 samples/bpf/test_cgrp2_sock2.c
create mode 100755 samples/bpf/test_cgrp2_sock2.sh
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index a335b218198e..8df12f9429dc 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -24,6 +24,7 @@ hostprogs-y += test_overhead
hostprogs-y += test_cgrp2_array_pin
hostprogs-y += test_cgrp2_attach
hostprogs-y += test_cgrp2_sock
+hostprogs-y += test_cgrp2_sock2
hostprogs-y += xdp1
hostprogs-y += xdp2
hostprogs-y += test_current_task_under_cgroup
@@ -53,6 +54,7 @@ test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o
test_cgrp2_sock-objs := libbpf.o test_cgrp2_sock.o
+test_cgrp2_sock2-objs := bpf_load.o libbpf.o test_cgrp2_sock2.o
xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
# reuse xdp1 source intentionally
xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
@@ -73,6 +75,7 @@ always += tracex3_kern.o
always += tracex4_kern.o
always += tracex5_kern.o
always += tracex6_kern.o
+always += sock_flags_kern.o
always += test_probe_write_user_kern.o
always += trace_output_kern.o
always += tcbpf1_kern.o
@@ -106,6 +109,7 @@ HOSTLOADLIBES_tracex3 += -lelf
HOSTLOADLIBES_tracex4 += -lelf -lrt
HOSTLOADLIBES_tracex5 += -lelf
HOSTLOADLIBES_tracex6 += -lelf
+HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
HOSTLOADLIBES_test_probe_write_user += -lelf
HOSTLOADLIBES_trace_output += -lelf -lrt
HOSTLOADLIBES_lathist += -lelf
diff --git a/samples/bpf/sock_flags_kern.c b/samples/bpf/sock_flags_kern.c
new file mode 100644
index 000000000000..d6a7f0013a5d
--- /dev/null
+++ b/samples/bpf/sock_flags_kern.c
@@ -0,0 +1,37 @@
+#include <uapi/linux/bpf.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+
+SEC("cgroup/sock1")
+int bpf_prog1(struct bpf_sock *sk)
+{
+ char fmt[] = "socket: family %d type %d protocol %d\n";
+
+ bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol);
+
+ /* block PF_INET6, SOCK_RAW, IPPROTO_ICMPV6 sockets
+ * ie., make ping6 fail
+ */
+ if (sk->family == PF_INET6 && sk->type == 3 && sk->protocol == 58)
+ return 0;
+
+ return 1;
+}
+
+SEC("cgroup/sock2")
+int bpf_prog2(struct bpf_sock *sk)
+{
+ char fmt[] = "socket: family %d type %d protocol %d\n";
+
+ bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol);
+
+ /* block PF_INET, SOCK_RAW, IPPROTO_ICMP sockets
+ * ie., make ping fail
+ */
+ if (sk->family == PF_INET && sk->type == 3 && sk->protocol == 1)
+ return 0;
+
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c
new file mode 100644
index 000000000000..455ef0d06e93
--- /dev/null
+++ b/samples/bpf/test_cgrp2_sock2.c
@@ -0,0 +1,66 @@
+/* eBPF example program:
+ *
+ * - Loads eBPF program
+ *
+ * The eBPF program loads a filter from file and attaches the
+ * program to a cgroup using BPF_PROG_ATTACH
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+#include <unistd.h>
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <net/if.h>
+#include <linux/bpf.h>
+
+#include "libbpf.h"
+#include "bpf_load.h"
+
+static int usage(const char *argv0)
+{
+ printf("Usage: %s cg-path filter-path [filter-id]\n", argv0);
+ return EXIT_FAILURE;
+}
+
+int main(int argc, char **argv)
+{
+ int cg_fd, ret, filter_id = 0;
+
+ if (argc < 3)
+ return usage(argv[0]);
+
+ cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY);
+ if (cg_fd < 0) {
+ printf("Failed to open cgroup path: '%s'\n", strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ if (load_bpf_file(argv[2]))
+ return EXIT_FAILURE;
+
+ printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf);
+
+ if (argc > 3)
+ filter_id = atoi(argv[3]);
+
+ if (filter_id > prog_cnt) {
+ printf("Invalid program id; program not found in file\n");
+ return EXIT_FAILURE;
+ }
+
+ ret = bpf_prog_attach(prog_fd[filter_id], cg_fd,
+ BPF_CGROUP_INET_SOCK_CREATE);
+ if (ret < 0) {
+ printf("Failed to attach prog to cgroup: '%s'\n",
+ strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ return EXIT_SUCCESS;
+}
diff --git a/samples/bpf/test_cgrp2_sock2.sh b/samples/bpf/test_cgrp2_sock2.sh
new file mode 100755
index 000000000000..891f12a0e26f
--- /dev/null
+++ b/samples/bpf/test_cgrp2_sock2.sh
@@ -0,0 +1,81 @@
+#!/bin/bash
+
+function config_device {
+ ip netns add at_ns0
+ ip link add veth0 type veth peer name veth0b
+ ip link set veth0b up
+ ip link set veth0 netns at_ns0
+ ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
+ ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add 172.16.1.101/24 dev veth0b
+ ip addr add 2401:db00::2/64 dev veth0b nodad
+}
+
+function config_cgroup {
+ rm -rf /tmp/cgroupv2
+ mkdir -p /tmp/cgroupv2
+ mount -t cgroup2 none /tmp/cgroupv2
+ mkdir -p /tmp/cgroupv2/foo
+ echo $$ >> /tmp/cgroupv2/foo/cgroup.procs
+}
+
+
+function attach_bpf {
+ test_cgrp2_sock2 /tmp/cgroupv2/foo sock_flags_kern.o $1
+ [ $? -ne 0 ] && exit 1
+}
+
+function cleanup {
+ ip link del veth0b
+ ip netns delete at_ns0
+ umount /tmp/cgroupv2
+ rm -rf /tmp/cgroupv2
+}
+
+cleanup 2>/dev/null
+
+set -e
+config_device
+config_cgroup
+set +e
+
+#
+# Test 1 - fail ping6
+#
+attach_bpf 0
+ping -c1 -w1 172.16.1.100
+if [ $? -ne 0 ]; then
+ echo "ping failed when it should succeed"
+ cleanup
+ exit 1
+fi
+
+ping6 -c1 -w1 2401:db00::1
+if [ $? -eq 0 ]; then
+ echo "ping6 succeeded when it should not"
+ cleanup
+ exit 1
+fi
+
+#
+# Test 2 - fail ping
+#
+attach_bpf 1
+ping6 -c1 -w1 2401:db00::1
+if [ $? -ne 0 ]; then
+ echo "ping6 failed when it should succeed"
+ cleanup
+ exit 1
+fi
+
+ping -c1 -w1 172.16.1.100
+if [ $? -eq 0 ]; then
+ echo "ping succeeded when it should not"
+ cleanup
+ exit 1
+fi
+
+cleanup
+echo
+echo "*** PASS ***"
--
2.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* Re: [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets
2016-11-30 18:16 ` [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets David Ahern
@ 2016-12-01 5:59 ` Alexei Starovoitov
2016-12-01 15:13 ` David Ahern
0 siblings, 1 reply; 12+ messages in thread
From: Alexei Starovoitov @ 2016-12-01 5:59 UTC (permalink / raw)
To: David Ahern; +Cc: netdev, daniel, ast, daniel, maheshb, tgraf
On Wed, Nov 30, 2016 at 10:16:50AM -0800, David Ahern wrote:
> Add examples preventing a process in a cgroup from opening a socket
> based family, protocol and type.
>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
...
> +++ b/samples/bpf/sock_flags_kern.c
> @@ -0,0 +1,37 @@
> +#include <uapi/linux/bpf.h>
> +#include <linux/socket.h>
> +#include "bpf_helpers.h"
> +
> +SEC("cgroup/sock1")
> +int bpf_prog1(struct bpf_sock *sk)
> +{
> + char fmt[] = "socket: family %d type %d protocol %d\n";
> +
> + bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol);
> +
> + /* block PF_INET6, SOCK_RAW, IPPROTO_ICMPV6 sockets
> + * ie., make ping6 fail
> + */
> + if (sk->family == PF_INET6 && sk->type == 3 && sk->protocol == 58)
> + return 0;
why not to use SOCK_RAW and IPPROTO_ICMPV6 instead of constants?
Thanks for the test!
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets
2016-12-01 5:59 ` Alexei Starovoitov
@ 2016-12-01 15:13 ` David Ahern
2016-12-05 10:51 ` David Laight
0 siblings, 1 reply; 12+ messages in thread
From: David Ahern @ 2016-12-01 15:13 UTC (permalink / raw)
To: Alexei Starovoitov; +Cc: netdev, daniel, ast, daniel, maheshb, tgraf
On 11/30/16 10:59 PM, Alexei Starovoitov wrote:
> On Wed, Nov 30, 2016 at 10:16:50AM -0800, David Ahern wrote:
>> Add examples preventing a process in a cgroup from opening a socket
>> based family, protocol and type.
>>
>> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ...
>> +++ b/samples/bpf/sock_flags_kern.c
>> @@ -0,0 +1,37 @@
>> +#include <uapi/linux/bpf.h>
>> +#include <linux/socket.h>
>> +#include "bpf_helpers.h"
>> +
>> +SEC("cgroup/sock1")
>> +int bpf_prog1(struct bpf_sock *sk)
>> +{
>> + char fmt[] = "socket: family %d type %d protocol %d\n";
>> +
>> + bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol);
>> +
>> + /* block PF_INET6, SOCK_RAW, IPPROTO_ICMPV6 sockets
>> + * ie., make ping6 fail
>> + */
>> + if (sk->family == PF_INET6 && sk->type == 3 && sk->protocol == 58)
>> + return 0;
>
> why not to use SOCK_RAW and IPPROTO_ICMPV6 instead of constants?
header file hell.
^ permalink raw reply [flat|nested] 12+ messages in thread* RE: [PATCH net-next v6 6/6] samples/bpf: add userspace example for prohibiting sockets
2016-12-01 15:13 ` David Ahern
@ 2016-12-05 10:51 ` David Laight
2016-12-05 14:31 ` David Ahern
0 siblings, 1 reply; 12+ messages in thread
From: David Laight @ 2016-12-05 10:51 UTC (permalink / raw)
To: 'David Ahern', Alexei Starovoitov
Cc: netdev@vger.kernel.org, daniel@zonque.org, ast@fb.com,
daniel@iogearbox.net, maheshb@google.com, tgraf@suug.ch
From: David Ahern
> Sent: 01 December 2016 15:14
> On 11/30/16 10:59 PM, Alexei Starovoitov wrote:
> > On Wed, Nov 30, 2016 at 10:16:50AM -0800, David Ahern wrote:
> >> Add examples preventing a process in a cgroup from opening a socket
> >> based family, protocol and type.
> >>
> >> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> > ...
> >> +++ b/samples/bpf/sock_flags_kern.c
> >> @@ -0,0 +1,37 @@
> >> +#include <uapi/linux/bpf.h>
> >> +#include <linux/socket.h>
> >> +#include "bpf_helpers.h"
> >> +
> >> +SEC("cgroup/sock1")
> >> +int bpf_prog1(struct bpf_sock *sk)
> >> +{
> >> + char fmt[] = "socket: family %d type %d protocol %d\n";
> >> +
> >> + bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol);
> >> +
> >> + /* block PF_INET6, SOCK_RAW, IPPROTO_ICMPV6 sockets
> >> + * ie., make ping6 fail
> >> + */
> >> + if (sk->family == PF_INET6 && sk->type == 3 && sk->protocol == 58)
> >> + return 0;
> >
> > why not to use SOCK_RAW and IPPROTO_ICMPV6 instead of constants?
>
> header file hell.
You can at least improve the comment.
Or add:
#ifndef SOCK_RAW
#define SPCK_RAW 3
#endif
(etc) at the top of the file.
David
^ permalink raw reply [flat|nested] 12+ messages in thread