* [RFC PATCH bpf-next v2 5/6] selftests/bpf: test BPF_MAP_DUMP command on a bpf hashmap
From: Brian Vazquez @ 2019-06-27 20:24 UTC (permalink / raw)
To: Brian Vazquez, Alexei Starovoitov, Daniel Borkmann,
David S . Miller
Cc: Stanislav Fomichev, Willem de Bruijn, Petar Penkov, linux-kernel,
netdev, bpf, Brian Vazquez
In-Reply-To: <20190627202417.33370-1-brianvv@google.com>
This tests exercise the new command on a bpf hashmap and make sure it
works as expected.
Signed-off-by: Brian Vazquez <brianvv@google.com>
---
tools/testing/selftests/bpf/test_maps.c | 70 ++++++++++++++++++++++++-
1 file changed, 68 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index a3fbc571280a9..3df72b46fd1d9 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -309,6 +309,73 @@ static void test_hashmap_walk(unsigned int task, void *data)
close(fd);
}
+static void test_hashmap_dump(void)
+{
+ int fd, i, max_entries = 3;
+ uint64_t keys[max_entries], values[max_entries];
+ uint64_t key, value, next_key;
+ bool next_key_valid = true;
+ void *buf, *elem, *prev_key;
+ u32 buf_len;
+ const int elem_size = sizeof(key) + sizeof(value);
+
+ fd = helper_fill_hashmap(max_entries);
+
+ // Get the elements in the hashmap, and store them in that order
+ assert(bpf_map_get_next_key(fd, NULL, &key) == 0);
+ i = 0;
+ keys[i] = key;
+ for (i = 1; next_key_valid; i++) {
+ next_key_valid = bpf_map_get_next_key(fd, &key, &next_key) == 0;
+ assert(bpf_map_lookup_elem(fd, &key, &values[i - 1]) == 0);
+ keys[i-1] = key;
+ key = next_key;
+ }
+
+ // Alloc memory for the whole table
+ buf = malloc(elem_size * max_entries);
+ assert(buf != NULL);
+
+ // Check that buf_len < elem_size returns EINVAL
+ buf_len = elem_size-1;
+ errno = 0;
+ assert(bpf_map_dump(fd, NULL, buf, &buf_len) == -1 && errno == EINVAL);
+
+ // Check that it returns the first two elements
+ errno = 0;
+ buf_len = elem_size * 2;
+ prev_key = NULL;
+ i = 0;
+ assert(bpf_map_dump(fd, prev_key, buf, &buf_len) == 0 &&
+ buf_len == 2*elem_size);
+ elem = buf;
+ assert((*(uint64_t *)elem) == keys[i] &&
+ (*(uint64_t *)(elem + sizeof(key))) == values[i]);
+ elem = buf + elem_size;
+ i++;
+ assert((*(uint64_t *)elem) == keys[i] &&
+ (*(uint64_t *)(elem + sizeof(key))) == values[i]);
+ i++;
+
+ /* Continue reading from map and verify buf_len only contains 1 element
+ * even though buf_len is 2 elem_size.
+ */
+ prev_key = elem;
+ assert(bpf_map_dump(fd, prev_key, buf, &buf_len) == 0 &&
+ buf_len == elem_size);
+ elem = buf;
+ assert((*(uint64_t *)elem) == keys[i] &&
+ (*(uint64_t *)(elem + sizeof(key))) == values[i]);
+
+ // Check that there are no more entries after last_key
+ prev_key = &keys[i];
+ assert(bpf_map_dump(fd, prev_key, buf, &buf_len) == -1 &&
+ errno == ENOENT);
+
+ free(buf);
+ close(fd);
+}
+
static void test_hashmap_zero_seed(void)
{
int i, first, second, old_flags;
@@ -1668,6 +1735,7 @@ static void run_all_tests(void)
test_hashmap_percpu(0, NULL);
test_hashmap_walk(0, NULL);
test_hashmap_zero_seed();
+ test_hashmap_dump();
test_arraymap(0, NULL);
test_arraymap_percpu(0, NULL);
@@ -1705,11 +1773,9 @@ int main(void)
map_flags = BPF_F_NO_PREALLOC;
run_all_tests();
-
#define CALL
#include <map_tests/tests.h>
#undef CALL
-
printf("test_maps: OK, %d SKIPPED\n", skips);
return 0;
}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [RFC PATCH bpf-next v2 3/6] bpf: keep bpf.h in sync with tools/
From: Brian Vazquez @ 2019-06-27 20:24 UTC (permalink / raw)
To: Brian Vazquez, Alexei Starovoitov, Daniel Borkmann,
David S . Miller
Cc: Stanislav Fomichev, Willem de Bruijn, Petar Penkov, linux-kernel,
netdev, bpf, Brian Vazquez
In-Reply-To: <20190627202417.33370-1-brianvv@google.com>
Adds bpf_attr.dump structure to libbpf.
Suggested-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
---
tools/include/uapi/linux/bpf.h | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b077507efa3f3..1d753958874df 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -106,6 +106,7 @@ enum bpf_cmd {
BPF_TASK_FD_QUERY,
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
BPF_MAP_FREEZE,
+ BPF_MAP_DUMP,
};
enum bpf_map_type {
@@ -385,6 +386,14 @@ union bpf_attr {
__u64 flags;
};
+ struct { /* struct used by BPF_MAP_DUMP command */
+ __u32 map_fd;
+ __aligned_u64 prev_key;
+ __aligned_u64 buf;
+ __aligned_u64 buf_len; /* input/output: len of buf */
+ __u64 flags;
+ } dump;
+
struct { /* anonymous struct used by BPF_PROG_LOAD command */
__u32 prog_type; /* one of enum bpf_prog_type */
__u32 insn_cnt;
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 0/9] bpf: getsockopt and setsockopt hooks
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf; +Cc: davem, ast, daniel, Stanislav Fomichev
This series implements two new per-cgroup hooks: getsockopt and
setsockopt along with a new sockopt program type. The idea is pretty
similar to recently introduced cgroup sysctl hooks, but
implementation is simpler (no need to convert to/from strings).
What this can be applied to:
* move business logic of what tos/priority/etc can be set by
containers (either pass or reject)
* handle existing options (or introduce new ones) differently by
propagating some information in cgroup/socket local storage
Compared to a simple syscall/{g,s}etsockopt tracepoint, those
hooks are context aware. Meaning, they can access underlying socket
and use cgroup and socket local storage.
v9:
* allow overwriting setsocktop arguments (Alexei Starovoitov)
(see individual changes for more changelog details)
Stanislav Fomichev (9):
bpf: implement getsockopt and setsockopt hooks
bpf: sync bpf.h to tools/
libbpf: support sockopt hooks
selftests/bpf: test sockopt section name
selftests/bpf: add sockopt test
selftests/bpf: add sockopt test that exercises sk helpers
selftests/bpf: add sockopt test that exercises BPF_F_ALLOW_MULTI
bpf: add sockopt documentation
bpftool: support cgroup sockopt
Documentation/bpf/index.rst | 1 +
Documentation/bpf/prog_cgroup_sockopt.rst | 93 ++
include/linux/bpf-cgroup.h | 45 +
include/linux/bpf.h | 2 +
include/linux/bpf_types.h | 1 +
include/linux/filter.h | 10 +
include/uapi/linux/bpf.h | 14 +
kernel/bpf/cgroup.c | 333 ++++++
kernel/bpf/core.c | 9 +
kernel/bpf/syscall.c | 19 +
kernel/bpf/verifier.c | 8 +
net/core/filter.c | 2 +-
net/socket.c | 30 +
.../bpftool/Documentation/bpftool-cgroup.rst | 7 +-
.../bpftool/Documentation/bpftool-prog.rst | 3 +-
tools/bpf/bpftool/bash-completion/bpftool | 9 +-
tools/bpf/bpftool/cgroup.c | 5 +-
tools/bpf/bpftool/main.h | 1 +
tools/bpf/bpftool/prog.c | 3 +-
tools/include/uapi/linux/bpf.h | 14 +
tools/lib/bpf/libbpf.c | 5 +
tools/lib/bpf/libbpf_probes.c | 1 +
tools/testing/selftests/bpf/.gitignore | 3 +
tools/testing/selftests/bpf/Makefile | 6 +-
.../selftests/bpf/progs/sockopt_multi.c | 71 ++
.../testing/selftests/bpf/progs/sockopt_sk.c | 111 ++
.../selftests/bpf/test_section_names.c | 10 +
tools/testing/selftests/bpf/test_sockopt.c | 1021 +++++++++++++++++
.../selftests/bpf/test_sockopt_multi.c | 374 ++++++
tools/testing/selftests/bpf/test_sockopt_sk.c | 214 ++++
30 files changed, 2415 insertions(+), 10 deletions(-)
create mode 100644 Documentation/bpf/prog_cgroup_sockopt.rst
create mode 100644 tools/testing/selftests/bpf/progs/sockopt_multi.c
create mode 100644 tools/testing/selftests/bpf/progs/sockopt_sk.c
create mode 100644 tools/testing/selftests/bpf/test_sockopt.c
create mode 100644 tools/testing/selftests/bpf/test_sockopt_multi.c
create mode 100644 tools/testing/selftests/bpf/test_sockopt_sk.c
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply
* [PATCH bpf-next v9 1/9] bpf: implement getsockopt and setsockopt hooks
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.
BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before
passing them down to the kernel or bypass kernel completely.
BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that
kernel returns.
Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure.
The buffer memory is pre-allocated (because I don't think there is
a precedent for working with __user memory from bpf). This might be
slow to do for each {s,g}etsockopt call, that's why I've added
__cgroup_bpf_prog_array_is_empty that exits early if there is nothing
attached to a cgroup. Note, however, that there is a race between
__cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup
program layout might have changed; this should not be a problem
because in general there is a race between multiple calls to
{s,g}etsocktop and user adding/removing bpf progs from a cgroup.
The return code of the BPF program is handled as follows:
* 0: EPERM
* 1: success, continue with next BPF program in the cgroup chain
v9:
* allow overwriting setsockopt arguments (Alexei Starovoitov):
* use set_fs (same as kernel_setsockopt)
* buffer is always kzalloc'd (no small on-stack buffer)
v8:
* use s32 for optlen (Andrii Nakryiko)
v7:
* return only 0 or 1 (Alexei Starovoitov)
* always run all progs (Alexei Starovoitov)
* use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov)
(decided to use optval=-1 instead, optval=0 might be a valid input)
* call getsockopt hook after kernel handlers (Alexei Starovoitov)
v6:
* rework cgroup chaining; stop as soon as bpf program returns
0 or 2; see patch with the documentation for the details
* drop Andrii's and Martin's Acked-by (not sure they are comfortable
with the new state of things)
v5:
* skip copy_to_user() and put_user() when ret == 0 (Martin Lau)
v4:
* don't export bpf_sk_fullsock helper (Martin Lau)
* size != sizeof(__u64) for uapi pointers (Martin Lau)
* offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau)
v3:
* typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko)
* reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii
Nakryiko)
* use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau)
* use BPF_FIELD_SIZEOF() for consistency (Martin Lau)
* new CG_SOCKOPT_ACCESS macro to wrap repeated parts
v2:
* moved bpf_sockopt_kern fields around to remove a hole (Martin Lau)
* aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau)
* bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau)
* added [0,2] return code check to verifier (Martin Lau)
* dropped unused buf[64] from the stack (Martin Lau)
* use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau)
* dropped bpf_target_off from ctx rewrites (Martin Lau)
* use return code for kernel bypass (Martin Lau & Andrii Nakryiko)
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
include/linux/bpf-cgroup.h | 45 +++++
include/linux/bpf.h | 2 +
include/linux/bpf_types.h | 1 +
include/linux/filter.h | 10 ++
include/uapi/linux/bpf.h | 14 ++
kernel/bpf/cgroup.c | 333 +++++++++++++++++++++++++++++++++++++
kernel/bpf/core.c | 9 +
kernel/bpf/syscall.c | 19 +++
kernel/bpf/verifier.c | 8 +
net/core/filter.c | 2 +-
net/socket.c | 30 ++++
11 files changed, 472 insertions(+), 1 deletion(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index bd79ae32909a..169fd25f6bc2 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
loff_t *ppos, void **new_buf,
enum bpf_attach_type type);
+int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
+ int *optname, char __user *optval,
+ int *optlen, char **kernel_optval);
+int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
+ int optname, char __user *optval,
+ int __user *optlen, int max_optlen,
+ int retval);
+
static inline enum bpf_cgroup_storage_type cgroup_storage_type(
struct bpf_map *map)
{
@@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
__ret; \
})
+#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
+ kernel_optval) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \
+ optname, optval, \
+ optlen, \
+ kernel_optval); \
+ __ret; \
+})
+
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ get_user(__ret, optlen); \
+ __ret; \
+})
+
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \
+ max_optlen, retval) \
+({ \
+ int __ret = retval; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \
+ optname, optval, \
+ optlen, max_optlen, \
+ retval); \
+ __ret; \
+})
+
int cgroup_bpf_prog_attach(const union bpf_attr *attr,
enum bpf_prog_type ptype, struct bpf_prog *prog);
int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
+ optlen, max_optlen, retval) ({ retval; })
+#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
+ kernel_optval) ({ 0; })
#define for_each_cgroup_storage_type(stype) for (; false; )
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a62e7889b0b6..18f4cc2c6acd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -518,6 +518,7 @@ struct bpf_prog_array {
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
void bpf_prog_array_free(struct bpf_prog_array *progs);
int bpf_prog_array_length(struct bpf_prog_array *progs);
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
__u32 __user *prog_ids, u32 cnt);
@@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto;
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;
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5a9975678d6f..eec5aeeeaf92 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
#ifdef CONFIG_CGROUP_BPF
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt)
#endif
#ifdef CONFIG_BPF_LIRC_MODE2
BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 43b45d6db36d..340f7d648974 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1199,4 +1199,14 @@ struct bpf_sysctl_kern {
u64 tmp_reg;
};
+struct bpf_sockopt_kern {
+ struct sock *sk;
+ u8 *optval;
+ u8 *optval_end;
+ s32 level;
+ s32 optname;
+ s32 optlen;
+ s32 retval;
+};
+
#endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b077507efa3f..a396b516a2b2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -170,6 +170,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_FLOW_DISSECTOR,
BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+ BPF_PROG_TYPE_CGROUP_SOCKOPT,
};
enum bpf_attach_type {
@@ -194,6 +195,8 @@ enum bpf_attach_type {
BPF_CGROUP_SYSCTL,
BPF_CGROUP_UDP4_RECVMSG,
BPF_CGROUP_UDP6_RECVMSG,
+ BPF_CGROUP_GETSOCKOPT,
+ BPF_CGROUP_SETSOCKOPT,
__MAX_BPF_ATTACH_TYPE
};
@@ -3541,4 +3544,15 @@ struct bpf_sysctl {
*/
};
+struct bpf_sockopt {
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(void *, optval);
+ __bpf_md_ptr(void *, optval_end);
+
+ __s32 level;
+ __s32 optname;
+ __s32 optlen;
+ __s32 retval;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 077ed3a19848..76fa0076f20d 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -15,6 +15,7 @@
#include <linux/bpf.h>
#include <linux/bpf-cgroup.h>
#include <net/sock.h>
+#include <net/bpf_sk_storage.h>
#include "../cgroup/cgroup-internal.h"
@@ -938,6 +939,188 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
+static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
+ enum bpf_attach_type attach_type)
+{
+ struct bpf_prog_array *prog_array;
+ bool empty;
+
+ rcu_read_lock();
+ prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]);
+ empty = bpf_prog_array_is_empty(prog_array);
+ rcu_read_unlock();
+
+ return empty;
+}
+
+static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
+{
+ if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
+ return -EINVAL;
+
+ ctx->optval = kzalloc(max_optlen, GFP_USER);
+ if (!ctx->optval)
+ return -ENOMEM;
+
+ ctx->optval_end = ctx->optval + max_optlen;
+ ctx->optlen = max_optlen;
+
+ return 0;
+}
+
+static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
+{
+ kfree(ctx->optval);
+}
+
+int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
+ int *optname, char __user *optval,
+ int *optlen, char **kernel_optval)
+{
+ struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+ struct bpf_sockopt_kern ctx = {
+ .sk = sk,
+ .level = *level,
+ .optname = *optname,
+ };
+ int ret;
+
+ /* Opportunistic check to see whether we have any BPF program
+ * attached to the hook so we don't waste time allocating
+ * memory and locking the socket.
+ */
+ if (!cgroup_bpf_enabled ||
+ __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
+ return 0;
+
+ ret = sockopt_alloc_buf(&ctx, *optlen);
+ if (ret)
+ return ret;
+
+ if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ lock_sock(sk);
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT],
+ &ctx, BPF_PROG_RUN);
+ release_sock(sk);
+
+ if (!ret) {
+ ret = -EPERM;
+ goto out;
+ }
+
+ if (ctx.optlen == -1) {
+ /* optlen set to -1, bypass kernel */
+ ret = 1;
+ } else if (ctx.optlen > *optlen || ctx.optlen < -1) {
+ /* optlen is out of bounds */
+ ret = -EFAULT;
+ } else {
+ /* optlen within bounds, run kernel handler */
+ ret = 0;
+
+ /* export any potential modifications */
+ *level = ctx.level;
+ *optname = ctx.optname;
+ *optlen = ctx.optlen;
+ *kernel_optval = ctx.optval;
+ }
+
+out:
+ if (ret)
+ sockopt_free_buf(&ctx);
+ return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt);
+
+int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
+ int optname, char __user *optval,
+ int __user *optlen, int max_optlen,
+ int retval)
+{
+ struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+ struct bpf_sockopt_kern ctx = {
+ .sk = sk,
+ .level = level,
+ .optname = optname,
+ .retval = retval,
+ };
+ int ret;
+
+ /* Opportunistic check to see whether we have any BPF program
+ * attached to the hook so we don't waste time allocating
+ * memory and locking the socket.
+ */
+ if (!cgroup_bpf_enabled ||
+ __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
+ return retval;
+
+ ret = sockopt_alloc_buf(&ctx, max_optlen);
+ if (ret)
+ return ret;
+
+ if (!retval) {
+ /* If kernel getsockopt finished successfully,
+ * copy whatever was returned to the user back
+ * into our temporary buffer. Set optlen to the
+ * one that kernel returned as well to let
+ * BPF programs inspect the value.
+ */
+
+ if (get_user(ctx.optlen, optlen)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (ctx.optlen > max_optlen)
+ ctx.optlen = max_optlen;
+
+ if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ lock_sock(sk);
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT],
+ &ctx, BPF_PROG_RUN);
+ release_sock(sk);
+
+ if (!ret) {
+ ret = -EPERM;
+ goto out;
+ }
+
+ if (ctx.optlen > max_optlen) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ /* BPF programs only allowed to set retval to 0, not some
+ * arbitrary value.
+ */
+ if (ctx.retval != 0 && ctx.retval != retval) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
+ put_user(ctx.optlen, optlen)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret = ctx.retval;
+
+out:
+ sockopt_free_buf(&ctx);
+ return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+
static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
size_t *lenp)
{
@@ -1198,3 +1381,153 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
const struct bpf_prog_ops cg_sysctl_prog_ops = {
};
+
+static const struct bpf_func_proto *
+cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_sk_storage_get:
+ return &bpf_sk_storage_get_proto;
+ case BPF_FUNC_sk_storage_delete:
+ return &bpf_sk_storage_delete_proto;
+#ifdef CONFIG_INET
+ case BPF_FUNC_tcp_sock:
+ return &bpf_tcp_sock_proto;
+#endif
+ default:
+ return cgroup_base_func_proto(func_id, prog);
+ }
+}
+
+static bool cg_sockopt_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ const int size_default = sizeof(__u32);
+
+ if (off < 0 || off >= sizeof(struct bpf_sockopt))
+ return false;
+
+ if (off % size != 0)
+ return false;
+
+ if (type == BPF_WRITE) {
+ switch (off) {
+ case offsetof(struct bpf_sockopt, retval):
+ if (size != size_default)
+ return false;
+ return prog->expected_attach_type ==
+ BPF_CGROUP_GETSOCKOPT;
+ case offsetof(struct bpf_sockopt, optname):
+ /* fallthrough */
+ case offsetof(struct bpf_sockopt, level):
+ if (size != size_default)
+ return false;
+ return prog->expected_attach_type ==
+ BPF_CGROUP_SETSOCKOPT;
+ case offsetof(struct bpf_sockopt, optlen):
+ return size == size_default;
+ default:
+ return false;
+ }
+ }
+
+ switch (off) {
+ case offsetof(struct bpf_sockopt, sk):
+ if (size != sizeof(__u64))
+ return false;
+ info->reg_type = PTR_TO_SOCKET;
+ break;
+ case offsetof(struct bpf_sockopt, optval):
+ if (size != sizeof(__u64))
+ return false;
+ info->reg_type = PTR_TO_PACKET;
+ break;
+ case offsetof(struct bpf_sockopt, optval_end):
+ if (size != sizeof(__u64))
+ return false;
+ info->reg_type = PTR_TO_PACKET_END;
+ break;
+ case offsetof(struct bpf_sockopt, retval):
+ if (size != size_default)
+ return false;
+ return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT;
+ default:
+ if (size != size_default)
+ return false;
+ break;
+ }
+ return true;
+}
+
+#define CG_SOCKOPT_ACCESS_FIELD(T, F) \
+ T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \
+ si->dst_reg, si->src_reg, \
+ offsetof(struct bpf_sockopt_kern, F))
+
+static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type,
+ const struct bpf_insn *si,
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog,
+ u32 *target_size)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ switch (si->off) {
+ case offsetof(struct bpf_sockopt, sk):
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk);
+ break;
+ case offsetof(struct bpf_sockopt, level):
+ if (type == BPF_WRITE)
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level);
+ else
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level);
+ break;
+ case offsetof(struct bpf_sockopt, optname):
+ if (type == BPF_WRITE)
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname);
+ else
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname);
+ break;
+ case offsetof(struct bpf_sockopt, optlen):
+ if (type == BPF_WRITE)
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen);
+ else
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
+ break;
+ case offsetof(struct bpf_sockopt, retval):
+ if (type == BPF_WRITE)
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval);
+ else
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval);
+ break;
+ case offsetof(struct bpf_sockopt, optval):
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
+ break;
+ case offsetof(struct bpf_sockopt, optval_end):
+ *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end);
+ break;
+ }
+
+ return insn - insn_buf;
+}
+
+static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf,
+ bool direct_write,
+ const struct bpf_prog *prog)
+{
+ /* Nothing to do for sockopt argument. The data is kzalloc'ated.
+ */
+ return 0;
+}
+
+const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
+ .get_func_proto = cg_sockopt_func_proto,
+ .is_valid_access = cg_sockopt_is_valid_access,
+ .convert_ctx_access = cg_sockopt_convert_ctx_access,
+ .gen_prologue = cg_sockopt_get_prologue,
+};
+
+const struct bpf_prog_ops cg_sockopt_prog_ops = {
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 561ed07d3007..e2c1b43728da 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1809,6 +1809,15 @@ int bpf_prog_array_length(struct bpf_prog_array *array)
return cnt;
}
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
+{
+ struct bpf_prog_array_item *item;
+
+ for (item = array->items; item->prog; item++)
+ if (item->prog != &dummy_bpf_prog.prog)
+ return false;
+ return true;
+}
static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
u32 *prog_ids,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7713cf39795a..b0f545e07425 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1590,6 +1590,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
default:
return -EINVAL;
}
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ switch (expected_attach_type) {
+ case BPF_CGROUP_SETSOCKOPT:
+ case BPF_CGROUP_GETSOCKOPT:
+ return 0;
+ default:
+ return -EINVAL;
+ }
default:
return 0;
}
@@ -1840,6 +1848,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
switch (prog->type) {
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
case BPF_PROG_TYPE_CGROUP_SKB:
return prog->enforce_expected_attach_type &&
@@ -1912,6 +1921,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_SYSCTL:
ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
break;
+ case BPF_CGROUP_GETSOCKOPT:
+ case BPF_CGROUP_SETSOCKOPT:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+ break;
default:
return -EINVAL;
}
@@ -1995,6 +2008,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_CGROUP_SYSCTL:
ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
break;
+ case BPF_CGROUP_GETSOCKOPT:
+ case BPF_CGROUP_SETSOCKOPT:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+ break;
default:
return -EINVAL;
}
@@ -2031,6 +2048,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
case BPF_CGROUP_SYSCTL:
+ case BPF_CGROUP_GETSOCKOPT:
+ case BPF_CGROUP_SETSOCKOPT:
break;
case BPF_LIRC_MODE2:
return lirc_prog_query(attr, uattr);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0e079b2298f8..6b5623d320f9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2215,6 +2215,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
env->seen_direct_write = true;
return true;
+
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ if (t == BPF_WRITE)
+ env->seen_direct_write = true;
+
+ return true;
+
default:
return false;
}
@@ -6066,6 +6073,7 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
break;
default:
return 0;
diff --git a/net/core/filter.c b/net/core/filter.c
index 2014d76e0d2a..dc8534be12fc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5651,7 +5651,7 @@ BPF_CALL_1(bpf_tcp_sock, struct sock *, sk)
return (unsigned long)NULL;
}
-static const struct bpf_func_proto bpf_tcp_sock_proto = {
+const struct bpf_func_proto bpf_tcp_sock_proto = {
.func = bpf_tcp_sock,
.gpl_only = false,
.ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL,
diff --git a/net/socket.c b/net/socket.c
index 963df5dbdd54..0ddfbfb761d9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2051,6 +2051,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
static int __sys_setsockopt(int fd, int level, int optname,
char __user *optval, int optlen)
{
+ mm_segment_t oldfs = get_fs();
+ char *kernel_optval = NULL;
int err, fput_needed;
struct socket *sock;
@@ -2063,6 +2065,22 @@ static int __sys_setsockopt(int fd, int level, int optname,
if (err)
goto out_put;
+ err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level,
+ &optname, optval, &optlen,
+ &kernel_optval);
+
+ if (err < 0) {
+ goto out_put;
+ } else if (err > 0) {
+ err = 0;
+ goto out_put;
+ }
+
+ if (kernel_optval) {
+ set_fs(KERNEL_DS);
+ optval = (char __user __force *)kernel_optval;
+ }
+
if (level == SOL_SOCKET)
err =
sock_setsockopt(sock, level, optname, optval,
@@ -2071,6 +2089,11 @@ static int __sys_setsockopt(int fd, int level, int optname,
err =
sock->ops->setsockopt(sock, level, optname, optval,
optlen);
+
+ if (kernel_optval) {
+ set_fs(oldfs);
+ kfree(kernel_optval);
+ }
out_put:
fput_light(sock->file, fput_needed);
}
@@ -2093,6 +2116,7 @@ static int __sys_getsockopt(int fd, int level, int optname,
{
int err, fput_needed;
struct socket *sock;
+ int max_optlen;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock != NULL) {
@@ -2100,6 +2124,8 @@ static int __sys_getsockopt(int fd, int level, int optname,
if (err)
goto out_put;
+ max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
+
if (level == SOL_SOCKET)
err =
sock_getsockopt(sock, level, optname, optval,
@@ -2108,6 +2134,10 @@ static int __sys_getsockopt(int fd, int level, int optname,
err =
sock->ops->getsockopt(sock, level, optname, optval,
optlen);
+
+ err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
+ optval, optlen,
+ max_optlen, err);
out_put:
fput_light(sock->file, fput_needed);
}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 2/9] bpf: sync bpf.h to tools/
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Export new prog type and hook points to the libbpf.
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/include/uapi/linux/bpf.h | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b077507efa3f..a396b516a2b2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -170,6 +170,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_FLOW_DISSECTOR,
BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+ BPF_PROG_TYPE_CGROUP_SOCKOPT,
};
enum bpf_attach_type {
@@ -194,6 +195,8 @@ enum bpf_attach_type {
BPF_CGROUP_SYSCTL,
BPF_CGROUP_UDP4_RECVMSG,
BPF_CGROUP_UDP6_RECVMSG,
+ BPF_CGROUP_GETSOCKOPT,
+ BPF_CGROUP_SETSOCKOPT,
__MAX_BPF_ATTACH_TYPE
};
@@ -3541,4 +3544,15 @@ struct bpf_sysctl {
*/
};
+struct bpf_sockopt {
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(void *, optval);
+ __bpf_md_ptr(void *, optval_end);
+
+ __s32 level;
+ __s32 optname;
+ __s32 optlen;
+ __s32 retval;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 3/9] libbpf: support sockopt hooks
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Make libbpf aware of new sockopt hooks so it can derive prog type
and hook point from the section names.
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/lib/bpf/libbpf.c | 5 +++++
tools/lib/bpf/libbpf_probes.c | 1 +
2 files changed, 6 insertions(+)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5186b7710430..6e6ebef11ba3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2646,6 +2646,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
case BPF_PROG_TYPE_PERF_EVENT:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
return false;
case BPF_PROG_TYPE_KPROBE:
default:
@@ -3604,6 +3605,10 @@ static const struct {
BPF_CGROUP_UDP6_RECVMSG),
BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_CGROUP_SYSCTL),
+ BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_CGROUP_GETSOCKOPT),
+ BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_CGROUP_SETSOCKOPT),
};
#undef BPF_PROG_SEC_IMPL
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 6635a31a7a16..ace1a0708d99 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -101,6 +101,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_SK_REUSEPORT:
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
default:
break;
}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 4/9] selftests/bpf: test sockopt section name
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Add tests that make sure libbpf section detection works.
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/testing/selftests/bpf/test_section_names.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/tools/testing/selftests/bpf/test_section_names.c b/tools/testing/selftests/bpf/test_section_names.c
index dee2f2eceb0f..29833aeaf0de 100644
--- a/tools/testing/selftests/bpf/test_section_names.c
+++ b/tools/testing/selftests/bpf/test_section_names.c
@@ -134,6 +134,16 @@ static struct sec_name_test tests[] = {
{0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL},
{0, BPF_CGROUP_SYSCTL},
},
+ {
+ "cgroup/getsockopt",
+ {0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT},
+ {0, BPF_CGROUP_GETSOCKOPT},
+ },
+ {
+ "cgroup/setsockopt",
+ {0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT},
+ {0, BPF_CGROUP_SETSOCKOPT},
+ },
};
static int test_prog_type_by_name(const struct sec_name_test *test)
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 5/9] selftests/bpf: add sockopt test
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Add sockopt selftests:
* require proper expected_attach_type
* enforce context field read/write access
* test bpf_sockopt_handled handler
* test EPERM
* test limiting optlen from getsockopt
* test out-of-bounds access
v9:
* add tests for setsockopt argument mangling
v7:
* remove return 2; test retval=0 and optlen=-1
v3:
* use DW for optval{,_end} loads
v2:
* use return code 2 for kernel bypass
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/test_sockopt.c | 1021 ++++++++++++++++++++
3 files changed, 1024 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_sockopt.c
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 7470327edcfe..3fe92601223d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -39,3 +39,4 @@ libbpf.so.*
test_hashmap
test_btf_dump
xdping
+test_sockopt
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index faeb8220daa2..7f2210402e57 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -26,7 +26,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
test_cgroup_storage test_select_reuseport test_section_names \
test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
- test_btf_dump test_cgroup_attach xdping
+ test_btf_dump test_cgroup_attach xdping test_sockopt
BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
TEST_GEN_FILES = $(BPF_OBJ_FILES)
@@ -103,6 +103,7 @@ $(OUTPUT)/test_netcnt: cgroup_helpers.c
$(OUTPUT)/test_sock_fields: cgroup_helpers.c
$(OUTPUT)/test_sysctl: cgroup_helpers.c
$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c
+$(OUTPUT)/test_sockopt: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/test_sockopt.c b/tools/testing/selftests/bpf/test_sockopt.c
new file mode 100644
index 000000000000..23bd0819382d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockopt.c
@@ -0,0 +1,1021 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include <linux/filter.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#define CG_PATH "/sockopt"
+
+static char bpf_log_buf[4096];
+static bool verbose;
+
+enum sockopt_test_error {
+ OK = 0,
+ DENY_LOAD,
+ DENY_ATTACH,
+ EPERM_GETSOCKOPT,
+ EFAULT_GETSOCKOPT,
+ EPERM_SETSOCKOPT,
+ EFAULT_SETSOCKOPT,
+};
+
+static struct sockopt_test {
+ const char *descr;
+ const struct bpf_insn insns[64];
+ enum bpf_attach_type attach_type;
+ enum bpf_attach_type expected_attach_type;
+
+ int set_optname;
+ int set_level;
+ const char set_optval[64];
+ socklen_t set_optlen;
+
+ int get_optname;
+ int get_level;
+ const char get_optval[64];
+ socklen_t get_optlen;
+ socklen_t get_optlen_ret;
+
+ enum sockopt_test_error error;
+} tests[] = {
+
+ /* ==================== getsockopt ==================== */
+
+ {
+ .descr = "getsockopt: no expected_attach_type",
+ .insns = {
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = 0,
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "getsockopt: wrong expected_attach_type",
+ .insns = {
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+ .error = DENY_ATTACH,
+ },
+ {
+ .descr = "getsockopt: bypass bpf hook",
+ .insns = {
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = SOL_IP,
+
+ .get_optname = IP_TOS,
+ .set_optname = IP_TOS,
+
+ .set_optval = { 1 << 3 },
+ .set_optlen = 1,
+
+ .get_optval = { 1 << 3 },
+ .get_optlen = 1,
+ },
+ {
+ .descr = "getsockopt: return EPERM from bpf hook",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .get_optname = IP_TOS,
+
+ .get_optlen = 1,
+ .error = EPERM_GETSOCKOPT,
+ },
+ {
+ .descr = "getsockopt: no optval bounds check, deny loading",
+ .insns = {
+ /* r6 = ctx->optval */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval)),
+
+ /* ctx->optval[0] = 0x80 */
+ BPF_MOV64_IMM(BPF_REG_0, 0x80),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_0, 0),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "getsockopt: read ctx->level",
+ .insns = {
+ /* r6 = ctx->level */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, level)),
+
+ /* if (ctx->level == 123) { */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4),
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } else { */
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_level = 123,
+
+ .get_optlen = 1,
+ },
+ {
+ .descr = "getsockopt: deny writing to ctx->level",
+ .insns = {
+ /* ctx->level = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, level)),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "getsockopt: read ctx->optname",
+ .insns = {
+ /* r6 = ctx->optname */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optname)),
+
+ /* if (ctx->optname == 123) { */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4),
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } else { */
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_optname = 123,
+
+ .get_optlen = 1,
+ },
+ {
+ .descr = "getsockopt: read ctx->retval",
+ .insns = {
+ /* r6 = ctx->retval */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, retval)),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .get_optname = IP_TOS,
+ .get_optlen = 1,
+ },
+ {
+ .descr = "getsockopt: deny writing to ctx->optname",
+ .insns = {
+ /* ctx->optname = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optname)),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "getsockopt: read ctx->optlen",
+ .insns = {
+ /* r6 = ctx->optlen */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optlen)),
+
+ /* if (ctx->optlen == 64) { */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 64, 4),
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } else { */
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_optlen = 64,
+ },
+ {
+ .descr = "getsockopt: deny bigger ctx->optlen",
+ .insns = {
+ /* ctx->optlen = 65 */
+ BPF_MOV64_IMM(BPF_REG_0, 65),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_optlen = 64,
+
+ .error = EFAULT_GETSOCKOPT,
+ },
+ {
+ .descr = "getsockopt: deny arbitrary ctx->retval",
+ .insns = {
+ /* ctx->retval = 123 */
+ BPF_MOV64_IMM(BPF_REG_0, 123),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_optlen = 64,
+
+ .error = EFAULT_GETSOCKOPT,
+ },
+ {
+ .descr = "getsockopt: support smaller ctx->optlen",
+ .insns = {
+ /* ctx->optlen = 32 */
+ BPF_MOV64_IMM(BPF_REG_0, 32),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_optlen = 64,
+ .get_optlen_ret = 32,
+ },
+ {
+ .descr = "getsockopt: deny writing to ctx->optval",
+ .insns = {
+ /* ctx->optval = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optval)),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "getsockopt: deny writing to ctx->optval_end",
+ .insns = {
+ /* ctx->optval_end = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optval_end)),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "getsockopt: rewrite value",
+ .insns = {
+ /* r6 = ctx->optval */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval)),
+ /* r2 = ctx->optval */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+ /* r6 = ctx->optval + 1 */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
+
+ /* r7 = ctx->optval_end */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval_end)),
+
+ /* if (ctx->optval + 1 <= ctx->optval_end) { */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
+ /* ctx->optval[0] = 0xF0 */
+ BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0),
+ /* } */
+
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+
+ /* return 1*/
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_GETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .get_optname = IP_TOS,
+
+ .get_optval = { 0xF0 },
+ .get_optlen = 1,
+ },
+
+ /* ==================== setsockopt ==================== */
+
+ {
+ .descr = "setsockopt: no expected_attach_type",
+ .insns = {
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = 0,
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "setsockopt: wrong expected_attach_type",
+ .insns = {
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+ .error = DENY_ATTACH,
+ },
+ {
+ .descr = "setsockopt: bypass bpf hook",
+ .insns = {
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = SOL_IP,
+
+ .get_optname = IP_TOS,
+ .set_optname = IP_TOS,
+
+ .set_optval = { 1 << 3 },
+ .set_optlen = 1,
+
+ .get_optval = { 1 << 3 },
+ .get_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: return EPERM from bpf hook",
+ .insns = {
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_level = SOL_IP,
+ .set_optname = IP_TOS,
+
+ .set_optlen = 1,
+ .error = EPERM_SETSOCKOPT,
+ },
+ {
+ .descr = "setsockopt: no optval bounds check, deny loading",
+ .insns = {
+ /* r6 = ctx->optval */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval)),
+
+ /* r0 = ctx->optval[0] */
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "setsockopt: read ctx->level",
+ .insns = {
+ /* r6 = ctx->level */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, level)),
+
+ /* if (ctx->level == 123) { */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4),
+ /* ctx->optlen = -1 */
+ BPF_MOV64_IMM(BPF_REG_0, -1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } else { */
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_level = 123,
+
+ .set_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: allow changing ctx->level",
+ .insns = {
+ /* ctx->level = SOL_IP */
+ BPF_MOV64_IMM(BPF_REG_0, SOL_IP),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, level)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = 234, /* should be rewritten to SOL_IP */
+
+ .get_optname = IP_TOS,
+ .set_optname = IP_TOS,
+
+ .set_optval = { 1 << 3 },
+ .set_optlen = 1,
+ .get_optval = { 1 << 3 },
+ .get_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: read ctx->optname",
+ .insns = {
+ /* r6 = ctx->optname */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optname)),
+
+ /* if (ctx->optname == 123) { */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4),
+ /* ctx->optlen = -1 */
+ BPF_MOV64_IMM(BPF_REG_0, -1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } else { */
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_optname = 123,
+
+ .set_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: allow changing ctx->optname",
+ .insns = {
+ /* ctx->optname = IP_TOS */
+ BPF_MOV64_IMM(BPF_REG_0, IP_TOS),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optname)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = SOL_IP,
+
+ .get_optname = IP_TOS,
+ .set_optname = 456, /* should be rewritten to IP_TOS */
+
+ .set_optval = { 1 << 3 },
+ .set_optlen = 1,
+ .get_optval = { 1 << 3 },
+ .get_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: read ctx->optlen",
+ .insns = {
+ /* r6 = ctx->optlen */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optlen)),
+
+ /* if (ctx->optlen == 64) { */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 64, 4),
+ /* ctx->optlen = -1 */
+ BPF_MOV64_IMM(BPF_REG_0, -1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } else { */
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_optlen = 64,
+ },
+ {
+ .descr = "setsockopt: ctx->optlen == -1 is ok",
+ .insns = {
+ /* ctx->optlen = -1 */
+ BPF_MOV64_IMM(BPF_REG_0, -1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_optlen = 64,
+ },
+ {
+ .descr = "setsockopt: deny ctx->optlen < 0 (except -1)",
+ .insns = {
+ /* ctx->optlen = -2 */
+ BPF_MOV64_IMM(BPF_REG_0, -2),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_optlen = 4,
+
+ .error = EFAULT_SETSOCKOPT,
+ },
+ {
+ .descr = "setsockopt: deny ctx->optlen > input optlen",
+ .insns = {
+ /* ctx->optlen = 65 */
+ BPF_MOV64_IMM(BPF_REG_0, 65),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .set_optlen = 64,
+
+ .error = EFAULT_SETSOCKOPT,
+ },
+ {
+ .descr = "setsockopt: allow changing ctx->optlen within bounds",
+ .insns = {
+ /* r6 = ctx->optval */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval)),
+ /* r2 = ctx->optval */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+ /* r6 = ctx->optval + 1 */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
+
+ /* r7 = ctx->optval_end */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval_end)),
+
+ /* if (ctx->optval + 1 <= ctx->optval_end) { */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
+ /* ctx->optval[0] = 1 << 3 */
+ BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 1 << 3),
+ /* } */
+
+ /* ctx->optlen = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optlen)),
+
+ /* return 1*/
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = SOL_IP,
+
+ .get_optname = IP_TOS,
+ .set_optname = IP_TOS,
+
+ .set_optval = { 1, 1, 1, 1 },
+ .set_optlen = 4,
+ .get_optval = { 1 << 3 },
+ .get_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: deny write ctx->retval",
+ .insns = {
+ /* ctx->retval = 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, retval)),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "setsockopt: deny read ctx->retval",
+ .insns = {
+ /* r6 = ctx->retval */
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, retval)),
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "setsockopt: deny writing to ctx->optval",
+ .insns = {
+ /* ctx->optval = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optval)),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "setsockopt: deny writing to ctx->optval_end",
+ .insns = {
+ /* ctx->optval_end = 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sockopt, optval_end)),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .error = DENY_LOAD,
+ },
+ {
+ .descr = "setsockopt: allow IP_TOS <= 128",
+ .insns = {
+ /* r6 = ctx->optval */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval)),
+ /* r7 = ctx->optval + 1 */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1),
+
+ /* r8 = ctx->optval_end */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval_end)),
+
+ /* if (ctx->optval + 1 <= ctx->optval_end) { */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 4),
+
+ /* r9 = ctx->optval[0] */
+ BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_6, 0),
+
+ /* if (ctx->optval[0] < 128) */
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_9, 128, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } */
+
+ /* } else { */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = SOL_IP,
+
+ .get_optname = IP_TOS,
+ .set_optname = IP_TOS,
+
+ .set_optval = { 0x80 },
+ .set_optlen = 1,
+ .get_optval = { 0x80 },
+ .get_optlen = 1,
+ },
+ {
+ .descr = "setsockopt: deny IP_TOS > 128",
+ .insns = {
+ /* r6 = ctx->optval */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval)),
+ /* r7 = ctx->optval + 1 */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1),
+
+ /* r8 = ctx->optval_end */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_1,
+ offsetof(struct bpf_sockopt, optval_end)),
+
+ /* if (ctx->optval + 1 <= ctx->optval_end) { */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 4),
+
+ /* r9 = ctx->optval[0] */
+ BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_6, 0),
+
+ /* if (ctx->optval[0] < 128) */
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_9, 128, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+ /* } */
+
+ /* } else { */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ /* } */
+
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SETSOCKOPT,
+ .expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+ .get_level = SOL_IP,
+ .set_level = SOL_IP,
+
+ .get_optname = IP_TOS,
+ .set_optname = IP_TOS,
+
+ .set_optval = { 0x81 },
+ .set_optlen = 1,
+ .get_optval = { 0x00 },
+ .get_optlen = 1,
+
+ .error = EPERM_SETSOCKOPT,
+ },
+};
+
+static int load_prog(const struct bpf_insn *insns,
+ enum bpf_attach_type expected_attach_type)
+{
+ struct bpf_load_program_attr attr = {
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ .expected_attach_type = expected_attach_type,
+ .insns = insns,
+ .license = "GPL",
+ .log_level = 2,
+ };
+ int fd;
+
+ for (;
+ insns[attr.insns_cnt].code != (BPF_JMP | BPF_EXIT);
+ attr.insns_cnt++) {
+ }
+ attr.insns_cnt++;
+
+ fd = bpf_load_program_xattr(&attr, bpf_log_buf, sizeof(bpf_log_buf));
+ if (verbose && fd < 0)
+ fprintf(stderr, "%s\n", bpf_log_buf);
+
+ return fd;
+}
+
+static int run_test(int cgroup_fd, struct sockopt_test *test)
+{
+ int sock_fd, err, prog_fd;
+ void *optval = NULL;
+ int ret = 0;
+
+ prog_fd = load_prog(test->insns, test->expected_attach_type);
+ if (prog_fd < 0) {
+ if (test->error == DENY_LOAD)
+ return 0;
+
+ log_err("Failed to load BPF program");
+ return -1;
+ }
+
+ err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0);
+ if (err < 0) {
+ if (test->error == DENY_ATTACH)
+ goto close_prog_fd;
+
+ log_err("Failed to attach BPF program");
+ ret = -1;
+ goto close_prog_fd;
+ }
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (sock_fd < 0) {
+ log_err("Failed to create AF_INET socket");
+ ret = -1;
+ goto detach_prog;
+ }
+
+ if (test->set_optlen) {
+ err = setsockopt(sock_fd, test->set_level, test->set_optname,
+ test->set_optval, test->set_optlen);
+ if (err) {
+ if (errno == EPERM && test->error == EPERM_SETSOCKOPT)
+ goto close_sock_fd;
+ if (errno == EFAULT && test->error == EFAULT_SETSOCKOPT)
+ goto free_optval;
+
+ log_err("Failed to call setsockopt");
+ ret = -1;
+ goto close_sock_fd;
+ }
+ }
+
+ if (test->get_optlen) {
+ optval = malloc(test->get_optlen);
+ socklen_t optlen = test->get_optlen;
+ socklen_t expected_get_optlen = test->get_optlen_ret ?:
+ test->get_optlen;
+
+ err = getsockopt(sock_fd, test->get_level, test->get_optname,
+ optval, &optlen);
+ if (err) {
+ if (errno == EPERM && test->error == EPERM_GETSOCKOPT)
+ goto free_optval;
+ if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT)
+ goto free_optval;
+
+ log_err("Failed to call getsockopt");
+ ret = -1;
+ goto free_optval;
+ }
+
+ if (optlen != expected_get_optlen) {
+ errno = 0;
+ log_err("getsockopt returned unexpected optlen");
+ ret = -1;
+ goto free_optval;
+ }
+
+ if (memcmp(optval, test->get_optval, optlen) != 0) {
+ errno = 0;
+ log_err("getsockopt returned unexpected optval");
+ ret = -1;
+ goto free_optval;
+ }
+ }
+
+ ret = test->error != OK;
+
+free_optval:
+ free(optval);
+close_sock_fd:
+ close(sock_fd);
+detach_prog:
+ bpf_prog_detach2(prog_fd, cgroup_fd, test->attach_type);
+close_prog_fd:
+ close(prog_fd);
+ return ret;
+}
+
+int main(int args, char **argv)
+{
+ int err = EXIT_FAILURE, error_cnt = 0;
+ int cgroup_fd, i;
+
+ if (setup_cgroup_environment())
+ goto cleanup_obj;
+
+ cgroup_fd = create_and_get_cgroup(CG_PATH);
+ if (cgroup_fd < 0)
+ goto cleanup_cgroup_env;
+
+ if (join_cgroup(CG_PATH))
+ goto cleanup_cgroup;
+
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ int err = run_test(cgroup_fd, &tests[i]);
+
+ if (err)
+ error_cnt++;
+
+ printf("#%d %s: %s\n", i, err ? "FAIL" : "PASS",
+ tests[i].descr);
+ }
+
+ printf("Summary: %ld PASSED, %d FAILED\n",
+ ARRAY_SIZE(tests) - error_cnt, error_cnt);
+ err = error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
+
+cleanup_cgroup:
+ close(cgroup_fd);
+cleanup_cgroup_env:
+ cleanup_cgroup_environment();
+cleanup_obj:
+ return err;
+}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 6/9] selftests/bpf: add sockopt test that exercises sk helpers
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
socktop test that introduces new SOL_CUSTOM sockopt level and
stores whatever users sets in sk storage. Whenever getsockopt
is called, the original value is retrieved.
v9:
* SO_SNDBUF example to override user-supplied buffer
v7:
* use retval=0 and optlen-1
v6:
* test 'ret=1' use-case as well (Alexei Starovoitov)
v4:
* don't call bpf_sk_fullsock helper
v3:
* drop (__u8 *)(long) casts for optval{,_end}
v2:
* new test
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 3 +-
.../testing/selftests/bpf/progs/sockopt_sk.c | 111 +++++++++
tools/testing/selftests/bpf/test_sockopt_sk.c | 214 ++++++++++++++++++
4 files changed, 328 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/progs/sockopt_sk.c
create mode 100644 tools/testing/selftests/bpf/test_sockopt_sk.c
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 3fe92601223d..8ac076c311d4 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -40,3 +40,4 @@ test_hashmap
test_btf_dump
xdping
test_sockopt
+test_sockopt_sk
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7f2210402e57..57ae4e168ace 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -26,7 +26,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
test_cgroup_storage test_select_reuseport test_section_names \
test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
- test_btf_dump test_cgroup_attach xdping test_sockopt
+ test_btf_dump test_cgroup_attach xdping test_sockopt test_sockopt_sk
BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
TEST_GEN_FILES = $(BPF_OBJ_FILES)
@@ -104,6 +104,7 @@ $(OUTPUT)/test_sock_fields: cgroup_helpers.c
$(OUTPUT)/test_sysctl: cgroup_helpers.c
$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c
$(OUTPUT)/test_sockopt: cgroup_helpers.c
+$(OUTPUT)/test_sockopt_sk: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
new file mode 100644
index 000000000000..076122c898e9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <netinet/in.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
+
+#define SOL_CUSTOM 0xdeadbeef
+
+struct sockopt_sk {
+ __u8 val;
+};
+
+struct bpf_map_def SEC("maps") socket_storage_map = {
+ .type = BPF_MAP_TYPE_SK_STORAGE,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct sockopt_sk),
+ .map_flags = BPF_F_NO_PREALLOC,
+};
+BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct sockopt_sk);
+
+SEC("cgroup/getsockopt")
+int _getsockopt(struct bpf_sockopt *ctx)
+{
+ __u8 *optval_end = ctx->optval_end;
+ __u8 *optval = ctx->optval;
+ struct sockopt_sk *storage;
+
+ if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+ /* Not interested in SOL_IP:IP_TOS;
+ * let next BPF program in the cgroup chain or kernel
+ * handle it.
+ */
+ return 1;
+
+ if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
+ /* Not interested in SOL_SOCKET:SO_SNDBUF;
+ * let next BPF program in the cgroup chain or kernel
+ * handle it.
+ */
+ return 1;
+ }
+
+ if (ctx->level != SOL_CUSTOM)
+ return 0; /* EPERM, deny everything except custom level */
+
+ if (optval + 1 > optval_end)
+ return 0; /* EPERM, bounds check */
+
+ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return 0; /* EPERM, couldn't get sk storage */
+
+ if (!ctx->retval)
+ return 0; /* EPERM, kernel should not have handled
+ * SOL_CUSTOM, something is wrong!
+ */
+ ctx->retval = 0; /* Reset system call return value to zero */
+
+ optval[0] = storage->val;
+ ctx->optlen = 1;
+
+ return 1;
+}
+
+SEC("cgroup/setsockopt")
+int _setsockopt(struct bpf_sockopt *ctx)
+{
+ __u8 *optval_end = ctx->optval_end;
+ __u8 *optval = ctx->optval;
+ struct sockopt_sk *storage;
+
+ if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+ /* Not interested in SOL_IP:IP_TOS;
+ * let next BPF program in the cgroup chain or kernel
+ * handle it.
+ */
+ return 1;
+
+ if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
+ /* Overwrite SO_SNDBUF value */
+
+ if (optval + sizeof(__u32) > optval_end)
+ return 0; /* EPERM, bounds check */
+
+ *(__u32 *)optval = 0x55AA;
+ ctx->optlen = 4;
+
+ return 1;
+ }
+
+ if (ctx->level != SOL_CUSTOM)
+ return 0; /* EPERM, deny everything except custom level */
+
+ if (optval + 1 > optval_end)
+ return 0; /* EPERM, bounds check */
+
+ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return 0; /* EPERM, couldn't get sk storage */
+
+ storage->val = optval[0];
+ ctx->optlen = -1; /* BPF has consumed this option, don't call kernel
+ * setsockopt handler.
+ */
+
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/test_sockopt_sk.c b/tools/testing/selftests/bpf/test_sockopt_sk.c
new file mode 100644
index 000000000000..12e79ed075ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockopt_sk.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include <linux/filter.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#define CG_PATH "/sockopt"
+
+#define SOL_CUSTOM 0xdeadbeef
+
+static int getsetsockopt(void)
+{
+ int fd, err;
+ char buf[4] = {};
+ socklen_t optlen;
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (fd < 0) {
+ log_err("Failed to create socket");
+ return -1;
+ }
+
+ /* IP_TOS - BPF bypass */
+
+ buf[0] = 0x08;
+ err = setsockopt(fd, SOL_IP, IP_TOS, buf, 1);
+ if (err) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto err;
+ }
+
+ buf[0] = 0x00;
+ optlen = 1;
+ err = getsockopt(fd, SOL_IP, IP_TOS, buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto err;
+ }
+
+ if (buf[0] != 0x08) {
+ log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08",
+ buf[0]);
+ goto err;
+ }
+
+ /* IP_TTL - EPERM */
+
+ buf[0] = 1;
+ err = setsockopt(fd, SOL_IP, IP_TTL, buf, 1);
+ if (!err || errno != EPERM) {
+ log_err("Unexpected success from setsockopt(IP_TTL)");
+ goto err;
+ }
+
+ /* SOL_CUSTOM - handled by BPF */
+
+ buf[0] = 0x01;
+ err = setsockopt(fd, SOL_CUSTOM, 0, buf, 1);
+ if (err) {
+ log_err("Failed to call setsockopt");
+ goto err;
+ }
+
+ buf[0] = 0x00;
+ optlen = 4;
+ err = getsockopt(fd, SOL_CUSTOM, 0, buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt");
+ goto err;
+ }
+
+ if (optlen != 1) {
+ log_err("Unexpected optlen %d != 1", optlen);
+ goto err;
+ }
+ if (buf[0] != 0x01) {
+ log_err("Unexpected buf[0] 0x%02x != 0x01", buf[0]);
+ goto err;
+ }
+
+ /* SO_SNDBUF is overwritten */
+
+ buf[0] = 0x01;
+ buf[1] = 0x01;
+ buf[2] = 0x01;
+ buf[3] = 0x01;
+ err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, buf, 4);
+ if (err) {
+ log_err("Failed to call setsockopt(SO_SNDBUF)");
+ goto err;
+ }
+
+ buf[0] = 0x00;
+ buf[1] = 0x00;
+ buf[2] = 0x00;
+ buf[3] = 0x00;
+ optlen = 4;
+ err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(SO_SNDBUF)");
+ goto err;
+ }
+
+ if (*(__u32 *)buf != 0x55AA*2) {
+ log_err("Unexpected getsockopt(SO_SNDBUF) 0x%x != 0x55AA*2",
+ *(__u32 *)buf);
+ goto err;
+ }
+
+ close(fd);
+ return 0;
+err:
+ close(fd);
+ return -1;
+}
+
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+{
+ enum bpf_attach_type attach_type;
+ enum bpf_prog_type prog_type;
+ struct bpf_program *prog;
+ int err;
+
+ err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
+ if (err) {
+ log_err("Failed to deduct types for %s BPF program", title);
+ return -1;
+ }
+
+ prog = bpf_object__find_program_by_title(obj, title);
+ if (!prog) {
+ log_err("Failed to find %s BPF program", title);
+ return -1;
+ }
+
+ err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
+ attach_type, 0);
+ if (err) {
+ log_err("Failed to attach %s BPF program", title);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int run_test(int cgroup_fd)
+{
+ struct bpf_prog_load_attr attr = {
+ .file = "./sockopt_sk.o",
+ };
+ struct bpf_object *obj;
+ int ignored;
+ int err;
+
+ err = bpf_prog_load_xattr(&attr, &obj, &ignored);
+ if (err) {
+ log_err("Failed to load BPF object");
+ return -1;
+ }
+
+ err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
+ if (err)
+ goto close_bpf_object;
+
+ err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt");
+ if (err)
+ goto close_bpf_object;
+
+ err = getsetsockopt();
+
+close_bpf_object:
+ bpf_object__close(obj);
+ return err;
+}
+
+int main(int args, char **argv)
+{
+ int cgroup_fd;
+ int err = EXIT_SUCCESS;
+
+ if (setup_cgroup_environment())
+ goto cleanup_obj;
+
+ cgroup_fd = create_and_get_cgroup(CG_PATH);
+ if (cgroup_fd < 0)
+ goto cleanup_cgroup_env;
+
+ if (join_cgroup(CG_PATH))
+ goto cleanup_cgroup;
+
+ if (run_test(cgroup_fd))
+ err = EXIT_FAILURE;
+
+ printf("test_sockopt_sk: %s\n",
+ err == EXIT_SUCCESS ? "PASSED" : "FAILED");
+
+cleanup_cgroup:
+ close(cgroup_fd);
+cleanup_cgroup_env:
+ cleanup_cgroup_environment();
+cleanup_obj:
+ return err;
+}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 7/9] selftests/bpf: add sockopt test that exercises BPF_F_ALLOW_MULTI
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
sockopt test that verifies chaining behavior.
v9:
* setsockopt chaining example
v7:
* rework the test to verify cgroup getsockopt chaining
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 4 +-
.../selftests/bpf/progs/sockopt_multi.c | 71 ++++
.../selftests/bpf/test_sockopt_multi.c | 374 ++++++++++++++++++
4 files changed, 449 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/progs/sockopt_multi.c
create mode 100644 tools/testing/selftests/bpf/test_sockopt_multi.c
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 8ac076c311d4..a2f7f79c7908 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -41,3 +41,4 @@ test_btf_dump
xdping
test_sockopt
test_sockopt_sk
+test_sockopt_multi
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 57ae4e168ace..de1754a8f5fe 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -26,7 +26,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
test_cgroup_storage test_select_reuseport test_section_names \
test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
- test_btf_dump test_cgroup_attach xdping test_sockopt test_sockopt_sk
+ test_btf_dump test_cgroup_attach xdping test_sockopt test_sockopt_sk \
+ test_sockopt_multi
BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
TEST_GEN_FILES = $(BPF_OBJ_FILES)
@@ -105,6 +106,7 @@ $(OUTPUT)/test_sysctl: cgroup_helpers.c
$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c
$(OUTPUT)/test_sockopt: cgroup_helpers.c
$(OUTPUT)/test_sockopt_sk: cgroup_helpers.c
+$(OUTPUT)/test_sockopt_multi: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
new file mode 100644
index 000000000000..4afd2595c08e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <netinet/in.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
+
+SEC("cgroup/getsockopt/child")
+int _getsockopt_child(struct bpf_sockopt *ctx)
+{
+ __u8 *optval_end = ctx->optval_end;
+ __u8 *optval = ctx->optval;
+
+ if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
+ return 1;
+
+ if (optval + 1 > optval_end)
+ return 0; /* EPERM, bounds check */
+
+ if (optval[0] != 0x80)
+ return 0; /* EPERM, unexpected optval from the kernel */
+
+ ctx->retval = 0; /* Reset system call return value to zero */
+
+ optval[0] = 0x90;
+ ctx->optlen = 1;
+
+ return 1;
+}
+
+SEC("cgroup/getsockopt/parent")
+int _getsockopt_parent(struct bpf_sockopt *ctx)
+{
+ __u8 *optval_end = ctx->optval_end;
+ __u8 *optval = ctx->optval;
+
+ if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
+ return 1;
+
+ if (optval + 1 > optval_end)
+ return 0; /* EPERM, bounds check */
+
+ if (optval[0] != 0x90)
+ return 0; /* EPERM, unexpected optval from the kernel */
+
+ ctx->retval = 0; /* Reset system call return value to zero */
+
+ optval[0] = 0xA0;
+ ctx->optlen = 1;
+
+ return 1;
+}
+
+SEC("cgroup/setsockopt")
+int _setsockopt(struct bpf_sockopt *ctx)
+{
+ __u8 *optval_end = ctx->optval_end;
+ __u8 *optval = ctx->optval;
+
+ if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
+ return 1;
+
+ if (optval + 1 > optval_end)
+ return 0; /* EPERM, bounds check */
+
+ optval[0] += 0x10;
+ ctx->optlen = 1;
+
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/test_sockopt_multi.c b/tools/testing/selftests/bpf/test_sockopt_multi.c
new file mode 100644
index 000000000000..4be3441db867
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockopt_multi.c
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <error.h>
+#include <errno.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include <linux/filter.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+{
+ enum bpf_attach_type attach_type;
+ enum bpf_prog_type prog_type;
+ struct bpf_program *prog;
+ int err;
+
+ err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
+ if (err) {
+ log_err("Failed to deduct types for %s BPF program", title);
+ return -1;
+ }
+
+ prog = bpf_object__find_program_by_title(obj, title);
+ if (!prog) {
+ log_err("Failed to find %s BPF program", title);
+ return -1;
+ }
+
+ err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
+ attach_type, BPF_F_ALLOW_MULTI);
+ if (err) {
+ log_err("Failed to attach %s BPF program", title);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title)
+{
+ enum bpf_attach_type attach_type;
+ enum bpf_prog_type prog_type;
+ struct bpf_program *prog;
+ int err;
+
+ err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
+ if (err)
+ return -1;
+
+ prog = bpf_object__find_program_by_title(obj, title);
+ if (!prog)
+ return -1;
+
+ err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd,
+ attach_type);
+ if (err)
+ return -1;
+
+ return 0;
+}
+
+static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
+ int cg_child, int sock_fd)
+{
+ socklen_t optlen;
+ __u8 buf;
+ int err;
+
+ /* Set IP_TOS to the expected value (0x80). */
+
+ buf = 0x80;
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0x80) {
+ log_err("Unexpected getsockopt 0x%x != 0x80 without BPF", buf);
+ err = -1;
+ goto detach;
+ }
+
+ /* Attach child program and make sure it returns new value:
+ * - kernel: -> 0x80
+ * - child: 0x80 -> 0x90
+ */
+
+ err = prog_attach(obj, cg_child, "cgroup/getsockopt/child");
+ if (err)
+ goto detach;
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0x90) {
+ log_err("Unexpected getsockopt 0x%x != 0x90", buf);
+ err = -1;
+ goto detach;
+ }
+
+ /* Attach parent program and make sure it returns new value:
+ * - kernel: -> 0x80
+ * - child: 0x80 -> 0x90
+ * - parent: 0x90 -> 0xA0
+ */
+
+ err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent");
+ if (err)
+ goto detach;
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0xA0) {
+ log_err("Unexpected getsockopt 0x%x != 0xA0", buf);
+ err = -1;
+ goto detach;
+ }
+
+ /* Setting unexpected initial sockopt should return EPERM:
+ * - kernel: -> 0x40
+ * - child: unexpected 0x40, EPERM
+ * - parent: unexpected 0x40, EPERM
+ */
+
+ buf = 0x40;
+ if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (!err) {
+ log_err("Unexpected success from getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ /* Detach child program and make sure we still get EPERM:
+ * - kernel: -> 0x40
+ * - parent: unexpected 0x40, EPERM
+ */
+
+ err = prog_detach(obj, cg_child, "cgroup/getsockopt/child");
+ if (err) {
+ log_err("Failed to detach child program");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (!err) {
+ log_err("Unexpected success from getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ /* Set initial value to the one the parent program expects:
+ * - kernel: -> 0x90
+ * - parent: 0x90 -> 0xA0
+ */
+
+ buf = 0x90;
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0xA0) {
+ log_err("Unexpected getsockopt 0x%x != 0xA0", buf);
+ err = -1;
+ goto detach;
+ }
+
+detach:
+ prog_detach(obj, cg_child, "cgroup/getsockopt/child");
+ prog_detach(obj, cg_parent, "cgroup/getsockopt/parent");
+
+ return err;
+}
+
+static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
+ int cg_child, int sock_fd)
+{
+ socklen_t optlen;
+ __u8 buf;
+ int err;
+
+ /* Set IP_TOS to the expected value (0x80). */
+
+ buf = 0x80;
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0x80) {
+ log_err("Unexpected getsockopt 0x%x != 0x80 without BPF", buf);
+ err = -1;
+ goto detach;
+ }
+
+ /* Attach child program and make sure it adds 0x10. */
+
+ err = prog_attach(obj, cg_child, "cgroup/setsockopt");
+ if (err)
+ goto detach;
+
+ buf = 0x80;
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0x80 + 0x10) {
+ log_err("Unexpected getsockopt 0x%x != 0x80 + 0x10", buf);
+ err = -1;
+ goto detach;
+ }
+
+ /* Attach parent program and make sure it adds another 0x10. */
+
+ err = prog_attach(obj, cg_parent, "cgroup/setsockopt");
+ if (err)
+ goto detach;
+
+ buf = 0x80;
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
+ log_err("Failed to call setsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ buf = 0x00;
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (err) {
+ log_err("Failed to call getsockopt(IP_TOS)");
+ goto detach;
+ }
+
+ if (buf != 0x80 + 2 * 0x10) {
+ log_err("Unexpected getsockopt 0x%x != 0x80 + 2 * 0x10", buf);
+ err = -1;
+ goto detach;
+ }
+
+detach:
+ prog_detach(obj, cg_child, "cgroup/setsockopt");
+ prog_detach(obj, cg_parent, "cgroup/setsockopt");
+
+ return err;
+}
+
+int main(int argc, char **argv)
+{
+ struct bpf_prog_load_attr attr = {
+ .file = "./sockopt_multi.o",
+ };
+ int cg_parent = -1, cg_child = -1;
+ struct bpf_object *obj = NULL;
+ int sock_fd = -1;
+ int err = -1;
+ int ignored;
+
+ if (setup_cgroup_environment()) {
+ log_err("Failed to setup cgroup environment\n");
+ goto out;
+ }
+
+ cg_parent = create_and_get_cgroup("/parent");
+ if (cg_parent < 0) {
+ log_err("Failed to create cgroup /parent\n");
+ goto out;
+ }
+
+ cg_child = create_and_get_cgroup("/parent/child");
+ if (cg_child < 0) {
+ log_err("Failed to create cgroup /parent/child\n");
+ goto out;
+ }
+
+ if (join_cgroup("/parent/child")) {
+ log_err("Failed to join cgroup /parent/child\n");
+ goto out;
+ }
+
+ err = bpf_prog_load_xattr(&attr, &obj, &ignored);
+ if (err) {
+ log_err("Failed to load BPF object");
+ goto out;
+ }
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (sock_fd < 0) {
+ log_err("Failed to create socket");
+ goto out;
+ }
+
+ if (run_getsockopt_test(obj, cg_parent, cg_child, sock_fd))
+ err = -1;
+ printf("test_sockopt_multi: getsockopt %s\n",
+ err ? "FAILED" : "PASSED");
+
+ if (run_setsockopt_test(obj, cg_parent, cg_child, sock_fd))
+ err = -1;
+ printf("test_sockopt_multi: setsockopt %s\n",
+ err ? "FAILED" : "PASSED");
+
+out:
+ close(sock_fd);
+ bpf_object__close(obj);
+ close(cg_child);
+ close(cg_parent);
+
+ printf("test_sockopt_multi: %s\n", err ? "FAILED" : "PASSED");
+ return err ? EXIT_FAILURE : EXIT_SUCCESS;
+}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 8/9] bpf: add sockopt documentation
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Provide user documentation about sockopt prog type and cgroup hooks.
v9:
* add details about setsockopt context and inheritance
v7:
* add description for retval=0 and optlen=-1
v6:
* describe cgroup chaining, add example
v2:
* use return code 2 for kernel bypass
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
Documentation/bpf/index.rst | 1 +
Documentation/bpf/prog_cgroup_sockopt.rst | 93 +++++++++++++++++++++++
2 files changed, 94 insertions(+)
create mode 100644 Documentation/bpf/prog_cgroup_sockopt.rst
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index d3fe4cac0c90..801a6ed3f2e5 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -42,6 +42,7 @@ Program types
.. toctree::
:maxdepth: 1
+ prog_cgroup_sockopt
prog_cgroup_sysctl
prog_flow_dissector
diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst
new file mode 100644
index 000000000000..c47d974629ae
--- /dev/null
+++ b/Documentation/bpf/prog_cgroup_sockopt.rst
@@ -0,0 +1,93 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+BPF_PROG_TYPE_CGROUP_SOCKOPT
+============================
+
+``BPF_PROG_TYPE_CGROUP_SOCKOPT`` program type can be attached to two
+cgroup hooks:
+
+* ``BPF_CGROUP_GETSOCKOPT`` - called every time process executes ``getsockopt``
+ system call.
+* ``BPF_CGROUP_SETSOCKOPT`` - called every time process executes ``setsockopt``
+ system call.
+
+The context (``struct bpf_sockopt``) has associated socket (``sk``) and
+all input arguments: ``level``, ``optname``, ``optval`` and ``optlen``.
+
+BPF_CGROUP_SETSOCKOPT
+=====================
+
+``BPF_CGROUP_SETSOCKOPT`` is triggered *before* the kernel handling of
+sockopt and it has writable context: it can modify the supplied arguments
+before passing them down to the kernel. This hook has access to the cgroup
+and socket local storage.
+
+If BPF program sets ``optlen`` to -1, the control will be returned
+back to the userspace after all other BPF programs in the cgroup
+chain finish (i.e. kernel ``setsockopt`` handling will *not* be executed).
+
+Note, that ``optlen`` can not be increased beyond the user-supplied
+value. It can only be decreased or set to -1. Any other value will
+trigger ``EFAULT``.
+
+Return Type
+-----------
+
+* ``0`` - reject the syscall, ``EPERM`` will be returned to the userspace.
+* ``1`` - success, continue with next BPF program in the cgroup chain.
+
+BPF_CGROUP_GETSOCKOPT
+=====================
+
+``BPF_CGROUP_GETSOCKOPT`` is triggered *after* the kernel handing of
+sockopt. The BPF hook can observe ``optval``, ``optlen`` and ``retval``
+if it's interested in whatever kernel has returned. BPF hook can override
+the values above, adjust ``optlen`` and reset ``retval`` to 0. If ``optlen``
+has been increased above initial ``getsockopt`` value (i.e. userspace
+buffer is too small), ``EFAULT`` is returned.
+
+This hook has access to the cgroup and socket local storage.
+
+Note, that the only acceptable value to set to ``retval`` is 0 and the
+original value that the kernel returned. Any other value will trigger
+``EFAULT``.
+
+Return Type
+-----------
+
+* ``0`` - reject the syscall, ``EPERM`` will be returned to the userspace.
+* ``1`` - success: copy ``optval`` and ``optlen`` to userspace, return
+ ``retval`` from the syscall (note that this can be overwritten by
+ the BPF program from the parent cgroup).
+
+Cgroup Inheritance
+==================
+
+Suppose, there is the following cgroup hierarchy where each cgroup
+has ``BPF_CGROUP_GETSOCKOPT`` attached at each level with
+``BPF_F_ALLOW_MULTI`` flag::
+
+ A (root, parent)
+ \
+ B (child)
+
+When the application calls ``getsockopt`` syscall from the cgroup B,
+the programs are executed from the bottom up: B, A. First program
+(B) sees the result of kernel's ``getsockopt``. It can optionally
+adjust ``optval``, ``optlen`` and reset ``retval`` to 0. After that
+control will be passed to the second (A) program which will see the
+same context as B including any potential modifications.
+
+Same for ``BPF_CGROUP_SETSOCKOPT``: if the program is attached to
+A and B, the trigger order is B, then A. If B does any changes
+to the input arguments (``level``, ``optname``, ``optval``, ``optlen``),
+then the next program in the chain (A) will see those changes,
+*not* the original input ``setsockopt`` arguments. The potentially
+modified values will be then passed down to the kernel.
+
+Example
+=======
+
+See ``tools/testing/selftests/bpf/progs/sockopt_sk.c`` for an example
+of BPF program that handles socket options.
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH bpf-next v9 9/9] bpftool: support cgroup sockopt
From: Stanislav Fomichev @ 2019-06-27 20:38 UTC (permalink / raw)
To: netdev, bpf
Cc: davem, ast, daniel, Stanislav Fomichev, Andrii Nakryiko,
Martin Lau, Jakub Kicinski
In-Reply-To: <20190627203855.10515-1-sdf@google.com>
Support sockopt prog type and cgroup hooks in the bpftool.
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 7 +++++--
tools/bpf/bpftool/Documentation/bpftool-prog.rst | 3 ++-
tools/bpf/bpftool/bash-completion/bpftool | 9 ++++++---
tools/bpf/bpftool/cgroup.c | 5 ++++-
tools/bpf/bpftool/main.h | 1 +
tools/bpf/bpftool/prog.c | 3 ++-
6 files changed, 20 insertions(+), 8 deletions(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index d80fdde79c22..585f270c2d25 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -29,7 +29,8 @@ CGROUP COMMANDS
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** |
| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** |
-| **sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** }
+| **sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** |
+| **getsockopt** | **setsockopt** }
| *ATTACH_FLAGS* := { **multi** | **override** }
DESCRIPTION
@@ -90,7 +91,9 @@ DESCRIPTION
an unconnected udp4 socket (since 5.2);
**recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
an unconnected udp6 socket (since 5.2);
- **sysctl** sysctl access (since 5.2).
+ **sysctl** sysctl access (since 5.2);
+ **getsockopt** call to getsockopt (since 5.3);
+ **setsockopt** call to setsockopt (since 5.3).
**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
Detach *PROG* from the cgroup *CGROUP* and attach type
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 55dd06517a3b..1df637f85f94 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -40,7 +40,8 @@ PROG COMMANDS
| **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
| **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
-| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl**
+| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** |
+| **cgroup/getsockopt** | **cgroup/setsockopt**
| }
| *ATTACH_TYPE* := {
| **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector**
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index a17e84c67498..ba37095e1f62 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -379,7 +379,8 @@ _bpftool()
cgroup/sendmsg4 cgroup/sendmsg6 \
cgroup/recvmsg4 cgroup/recvmsg6 \
cgroup/post_bind4 cgroup/post_bind6 \
- cgroup/sysctl" -- \
+ cgroup/sysctl cgroup/getsockopt \
+ cgroup/setsockopt" -- \
"$cur" ) )
return 0
;;
@@ -689,7 +690,8 @@ _bpftool()
attach|detach)
local ATTACH_TYPES='ingress egress sock_create sock_ops \
device bind4 bind6 post_bind4 post_bind6 connect4 \
- connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl'
+ connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \
+ getsockopt setsockopt'
local ATTACH_FLAGS='multi override'
local PROG_TYPE='id pinned tag'
case $prev in
@@ -699,7 +701,8 @@ _bpftool()
;;
ingress|egress|sock_create|sock_ops|device|bind4|bind6|\
post_bind4|post_bind6|connect4|connect6|sendmsg4|\
- sendmsg6|recvmsg4|recvmsg6|sysctl)
+ sendmsg6|recvmsg4|recvmsg6|sysctl|getsockopt|\
+ setsockopt)
COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
"$cur" ) )
return 0
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 73ec8ea33fb4..390b89a224f1 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -26,7 +26,8 @@
" sock_ops | device | bind4 | bind6 |\n" \
" post_bind4 | post_bind6 | connect4 |\n" \
" connect6 | sendmsg4 | sendmsg6 |\n" \
- " recvmsg4 | recvmsg6 | sysctl }"
+ " recvmsg4 | recvmsg6 | sysctl |\n" \
+ " getsockopt | setsockopt }"
static const char * const attach_type_strings[] = {
[BPF_CGROUP_INET_INGRESS] = "ingress",
@@ -45,6 +46,8 @@ static const char * const attach_type_strings[] = {
[BPF_CGROUP_SYSCTL] = "sysctl",
[BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4",
[BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6",
+ [BPF_CGROUP_GETSOCKOPT] = "getsockopt",
+ [BPF_CGROUP_SETSOCKOPT] = "setsockopt",
[__MAX_BPF_ATTACH_TYPE] = NULL,
};
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28a2a5857e14..9c5d9c80f71e 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport",
[BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector",
[BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl",
+ [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt",
};
extern const char * const map_type_name[];
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index f1a831f05010..9b0db5d14e31 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1071,7 +1071,8 @@ static int do_help(int argc, char **argv)
" cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
" cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
" cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n"
- " cgroup/recvmsg6 }\n"
+ " cgroup/recvmsg6 | cgroup/getsockopt |\n"
+ " cgroup/setsockopt }\n"
" ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
" flow_dissector }\n"
" " HELP_SPEC_OPTIONS "\n"
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* Re: [PATCH 8/9] keys: Network namespace domain tag [ver #4]
From: Willem de Bruijn @ 2019-06-27 20:55 UTC (permalink / raw)
To: David Howells
Cc: Eric W. Biederman, keyrings, linux-cifs, linux-nfs,
Network Development, linux-afs, dwalsh, vgoyal,
linux-security-module, linux-fsdevel, LKML
In-Reply-To: <156096287188.28733.15342608110117616221.stgit@warthog.procyon.org.uk>
On Wed, Jun 19, 2019 at 12:49 PM David Howells <dhowells@redhat.com> wrote:
>
> Create key domain tags for network namespaces and make it possible to
> automatically tag keys that are used by networked services (e.g. AF_RXRPC,
> AFS, DNS) with the default network namespace if not set by the caller.
>
> This allows keys with the same description but in different namespaces to
> coexist within a keyring.
>
> Signed-off-by: David Howells <dhowells@redhat.com>
> cc: netdev@vger.kernel.org
> cc: linux-nfs@vger.kernel.org
> cc: linux-cifs@vger.kernel.org
> cc: linux-afs@lists.infradead.org
> ---
> diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
> index 711b161505ac..076a75c73c9e 100644
> --- a/net/core/net_namespace.c
> +++ b/net/core/net_namespace.c
> @@ -38,9 +38,16 @@ EXPORT_SYMBOL_GPL(net_namespace_list);
> DECLARE_RWSEM(net_rwsem);
> EXPORT_SYMBOL_GPL(net_rwsem);
>
> +#ifdef CONFIG_KEYS
> +static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
> +#endif
> +
> struct net init_net = {
> .count = REFCOUNT_INIT(1),
> .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
> +#ifdef CONFIG_KEYS
> + .key_domain = &init_net_key_domain,
> +#endif
> };
> EXPORT_SYMBOL(init_net);
>
> @@ -386,10 +393,21 @@ static struct net *net_alloc(void)
> if (!net)
> goto out_free;
>
> +#ifdef CONFIG_KEYS
> + net->key_domain = kzalloc(sizeof(struct key_tag), GFP_KERNEL);
> + if (!net->key_domain)
> + goto out_free_2;
> + refcount_set(&net->key_domain->usage, 1);
> +#endif
> +
> rcu_assign_pointer(net->gen, ng);
> out:
> return net;
>
> +#ifdef CONFIG_KEYS
> +out_free_2:
> + kmem_cache_free(net_cachep, net);
needs
net = NULL;
to signal failure
> +#endif
> out_free:
> kfree(ng);
> goto out;
Reported-by: syzbot <syzkaller@googlegroups.com>
BUG: KASAN: use-after-free in atomic_set
include/asm-generic/atomic-instrumented.h:44 [inline]
BUG: KASAN: use-after-free in refcount_set include/linux/refcount.h:32 [inline]
BUG: KASAN: use-after-free in copy_net_ns+0x1e8/0x431
net/core/net_namespace.c:466
Write of size 4 at addr ffff88809c9de080 by task syz-executor.1/12624
CPU: 1 PID: 12624 Comm: syz-executor.1 Not tainted 5.2.0-rc6-next-20190626 #23
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x172/0x1f0 lib/dump_stack.c:113
print_address_description.cold+0xd4/0x306 mm/kasan/report.c:351
__kasan_report.cold+0x1b/0x36 mm/kasan/report.c:482
kasan_report+0x12/0x17 mm/kasan/common.c:614
check_memory_region_inline mm/kasan/generic.c:185 [inline]
check_memory_region+0x123/0x190 mm/kasan/generic.c:191
kasan_check_write+0x14/0x20 mm/kasan/common.c:100
atomic_set include/asm-generic/atomic-instrumented.h:44 [inline]
refcount_set include/linux/refcount.h:32 [inline]
copy_net_ns+0x1e8/0x431 net/core/net_namespace.c:466
create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:103
unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:202
ksys_unshare+0x444/0x980 kernel/fork.c:2828
__do_sys_unshare kernel/fork.c:2896 [inline]
__se_sys_unshare kernel/fork.c:2894 [inline]
__x64_sys_unshare+0x31/0x40 kernel/fork.c:2894
do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:301
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x459519
Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48
89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d
01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f2202261c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000110
RAX: ffffffffffffffda RBX: 00007f2202261c90 RCX: 0000000000459519
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000040000000
RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f22022626d4
R13: 00000000004c8a2c R14: 00000000004df7d0 R15: 0000000000000006
Allocated by task 12624:
save_stack+0x23/0x90 mm/kasan/common.c:71
set_track mm/kasan/common.c:79 [inline]
__kasan_kmalloc mm/kasan/common.c:489 [inline]
__kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497
slab_post_alloc_hook mm/slab.h:520 [inline]
slab_alloc mm/slab.c:3320 [inline]
kmem_cache_alloc+0x121/0x710 mm/slab.c:3484
kmem_cache_zalloc include/linux/slab.h:737 [inline]
net_alloc net/core/net_namespace.c:410 [inline]
copy_net_ns+0xf1/0x431 net/core/net_namespace.c:461
create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:103
unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:202
ksys_unshare+0x444/0x980 kernel/fork.c:2828
__do_sys_unshare kernel/fork.c:2896 [inline]
__se_sys_unshare kernel/fork.c:2894 [inline]
__x64_sys_unshare+0x31/0x40 kernel/fork.c:2894
do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:301
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Freed by task 12624:
save_stack+0x23/0x90 mm/kasan/common.c:71
set_track mm/kasan/common.c:79 [inline]
__kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
__cache_free mm/slab.c:3426 [inline]
kmem_cache_free+0x86/0x320 mm/slab.c:3694
net_alloc net/core/net_namespace.c:427 [inline]
copy_net_ns+0x3b1/0x431 net/core/net_namespace.c:461
create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:103
unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:202
ksys_unshare+0x444/0x980 kernel/fork.c:2828
__do_sys_unshare kernel/fork.c:2896 [inline]
__se_sys_unshare kernel/fork.c:2894 [inline]
__x64_sys_unshare+0x31/0x40 kernel/fork.c:2894
do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:301
entry_SYSCALL_64_after_hwframe+0x49/0xbe
^ permalink raw reply
* Re: [PATCH net] net/ibmvnic: Report last valid speed and duplex values to ethtool
From: Thomas Falcon @ 2019-06-27 20:56 UTC (permalink / raw)
To: Andrew Lunn; +Cc: netdev, linuxppc-dev, bjking1, pradeep, dnbanerg
In-Reply-To: <20190627175715.GP27733@lunn.ch>
On 6/27/19 12:57 PM, Andrew Lunn wrote:
> On Thu, Jun 27, 2019 at 12:09:13PM -0500, Thomas Falcon wrote:
>> This patch resolves an issue with sensitive bonding modes
>> that require valid speed and duplex settings to function
>> properly. Currently, the adapter will report that device
>> speed and duplex is unknown if the communication link
>> with firmware is unavailable.
> Dumb question. If you cannot communicate with the firmware, isn't the
> device FUBAR? So setting the LACP port to disabled is the correct
> things to do.
>
> Andrew
>
Yes, I think that is correct too. The problem is that the link is only
down temporarily. In this case - we are testing with a pseries logical
partition - the partition is migrated to another server. The driver must
wait for a signal from the hypervisor to resume operation with the new
device. Once it resumes, we see that the device reboots and gets
correct speed settings, but the port flag (AD_LACP_PORT_ENABLED) is
still cleared.
Tom
^ permalink raw reply
* Re: [PATCH v2 bpf-next 1/3] libbpf: add perf buffer API
From: Daniel Borkmann @ 2019-06-27 21:04 UTC (permalink / raw)
To: Andrii Nakryiko, andrii.nakryiko, ast, bpf, netdev, kernel-team
In-Reply-To: <20190626061235.602633-2-andriin@fb.com>
On 06/26/2019 08:12 AM, Andrii Nakryiko wrote:
> BPF_MAP_TYPE_PERF_EVENT_ARRAY map is often used to send data from BPF program
> to user space for additional processing. libbpf already has very low-level API
> to read single CPU perf buffer, bpf_perf_event_read_simple(), but it's hard to
> use and requires a lot of code to set everything up. This patch adds
> perf_buffer abstraction on top of it, abstracting setting up and polling
> per-CPU logic into simple and convenient API, similar to what BCC provides.
>
> perf_buffer__new() sets up per-CPU ring buffers and updates corresponding BPF
> map entries. It accepts two user-provided callbacks: one for handling raw
> samples and one for get notifications of lost samples due to buffer overflow.
>
> perf_buffer__poll() is used to fetch ring buffer data across all CPUs,
> utilizing epoll instance.
>
> perf_buffer__free() does corresponding clean up and unsets FDs from BPF map.
>
> All APIs are not thread-safe. User should ensure proper locking/coordination if
> used in multi-threaded set up.
>
> Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Aside from current feedback, this series generally looks great! Two small things:
> diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
> index 2382fbda4cbb..10f48103110a 100644
> --- a/tools/lib/bpf/libbpf.map
> +++ b/tools/lib/bpf/libbpf.map
> @@ -170,13 +170,16 @@ LIBBPF_0.0.4 {
> btf_dump__dump_type;
> btf_dump__free;
> btf_dump__new;
> - btf__parse_elf;
> bpf_object__load_xattr;
> bpf_program__attach_kprobe;
> bpf_program__attach_perf_event;
> bpf_program__attach_raw_tracepoint;
> bpf_program__attach_tracepoint;
> bpf_program__attach_uprobe;
> + btf__parse_elf;
> libbpf_num_possible_cpus;
> libbpf_perf_event_disable_and_close;
> + perf_buffer__free;
> + perf_buffer__new;
> + perf_buffer__poll;
We should prefix with libbpf_* given it's not strictly BPF-only and rather
helper function.
Also, we should convert bpftool (tools/bpf/bpftool/map_perf_ring.c) to make
use of these new helpers instead of open-coding there.
Thanks,
Daniel
^ permalink raw reply
* [PATCH net-next] r8169: improve handling VLAN tag
From: Heiner Kallweit @ 2019-06-27 21:06 UTC (permalink / raw)
To: Realtek linux nic maintainers, David Miller; +Cc: netdev@vger.kernel.org
The VLAN tag is stored in the descriptor in network byte order.
Using swab16 works on little endian host systems only. Better play safe
and use ntohs or htons respectively.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
drivers/net/ethernet/realtek/r8169_main.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 48b8a90f7..b4df66bef 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1528,7 +1528,7 @@ static int rtl8169_set_features(struct net_device *dev,
static inline u32 rtl8169_tx_vlan_tag(struct sk_buff *skb)
{
return (skb_vlan_tag_present(skb)) ?
- TxVlanTag | swab16(skb_vlan_tag_get(skb)) : 0x00;
+ TxVlanTag | htons(skb_vlan_tag_get(skb)) : 0x00;
}
static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
@@ -1536,7 +1536,8 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
u32 opts2 = le32_to_cpu(desc->opts2);
if (opts2 & RxVlanTag)
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+ ntohs(opts2 & 0xffff));
}
static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs,
--
2.22.0
^ permalink raw reply related
* [PATCH net-next] r8169: consider that 32 Bit DMA is the default
From: Heiner Kallweit @ 2019-06-27 21:12 UTC (permalink / raw)
To: Realtek linux nic maintainers, David Miller; +Cc: netdev@vger.kernel.org
Documentation/DMA-API-HOWTO.txt states:
By default, the kernel assumes that your device can address 32-bits of
DMA addressing. For a 64-bit capable device, this needs to be increased,
and for a device with limitations, it needs to be decreased.
Therefore we don't need the 32 Bit DMA fallback configuration and can
remove it.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
drivers/net/ethernet/realtek/r8169_main.c | 9 +--------
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b4df66bef..1b5f125e1 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -6724,15 +6724,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
tp->cp_cmd = RTL_R16(tp, CPlusCmd);
if (sizeof(dma_addr_t) > 4 && tp->mac_version >= RTL_GIGA_MAC_VER_18 &&
- !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
+ !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
dev->features |= NETIF_F_HIGHDMA;
- } else {
- rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
- if (rc < 0) {
- dev_err(&pdev->dev, "DMA configuration failed\n");
- return rc;
- }
- }
rtl_init_rxcfg(tp);
--
2.22.0
^ permalink raw reply related
* Re: [PATCH v2 bpf-next 3/7] libbpf: add kprobe/uprobe attach API
From: Daniel Borkmann @ 2019-06-27 21:16 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: Andrii Nakryiko, Alexei Starovoitov, Stanislav Fomichev, bpf,
Networking, Kernel Team
In-Reply-To: <CAEf4BzYy4Eorj0VxzArZg+V4muJCvDTX_VVfoouzZUcrBwTa1w@mail.gmail.com>
On 06/27/2019 12:15 AM, Andrii Nakryiko wrote:
> On Wed, Jun 26, 2019 at 7:25 AM Daniel Borkmann <daniel@iogearbox.net> wrote:
[...]
>> What this boils down to is that this should get a proper abstraction, e.g. as
>> in struct libbpf_event which holds the event object. There should be helper
>> functions like libbpf_event_create_{kprobe,uprobe,tracepoint,raw_tracepoint} returning
>> such an struct libbpf_event object on success, and a single libbpf_event_destroy()
>> that does the event specific teardown. bpf_program__attach_event() can then take
>> care of only attaching the program to it. Having an object for this is also more
>> extensible than just a fd number. Nice thing is that this can also be completely
>> internal to libbpf.c as with struct bpf_program and other abstractions where we
>> don't expose the internals in the public header.
>
> Yeah, I totally agree, I think this is a great idea! I don't
> particularly like "event" name, that seems very overloaded term. Do
> you mind if I call this "bpf_hook" instead of "libbpf_event"? I've
> always thought about these different points in the system to which one
> can attach BPF program as hooks exposed from kernel :)
>
> Would it also make sense to do attaching to non-tracing hooks using
> the same mechanism (e.g., all the per-cgroup stuff, sysctl, etc)? Not
> sure how people do that today, will check to see how it's done, but I
> think nothing should conceptually prevent doing that using the same
> abstract bpf_hook way, right?
I think if we abstract it this way, then absolutely. If I grok the naming conventions
from the README right, then this would be under 'bpf_hook__' prefix. :)
Thanks,
Daniel
^ permalink raw reply
* [PATCH net-next] r8169: remove not needed call to dma_sync_single_for_device
From: Heiner Kallweit @ 2019-06-27 21:19 UTC (permalink / raw)
To: Realtek linux nic maintainers, David Miller; +Cc: netdev@vger.kernel.org
DMA_API_HOWTO.txt includes an example explaining when
dma_sync_single_for_device() is not needed, and that example matches
our use case. The buffer isn't changed by the CPU and direction is
DMA_FROM_DEVICE, so we can remove the call to
dma_sync_single_for_device().
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
drivers/net/ethernet/realtek/r8169_main.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 1b5f125e1..a73f25321 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5785,7 +5785,6 @@ static struct sk_buff *rtl8169_try_rx_copy(void *data,
skb = napi_alloc_skb(&tp->napi, pkt_size);
if (skb)
skb_copy_to_linear_data(skb, data, pkt_size);
- dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE);
return skb;
}
--
2.22.0
^ permalink raw reply related
* Re: [PATCH 00/11] XDP unaligned chunk placement support
From: Jakub Kicinski @ 2019-06-27 21:25 UTC (permalink / raw)
To: Laatz, Kevin
Cc: Jonathan Lemon, netdev, ast, daniel, bjorn.topel, magnus.karlsson,
bpf, intel-wired-lan, bruce.richardson, ciara.loftus
In-Reply-To: <ef7e9469-e7be-647b-8bb1-da29bc01fa2e@intel.com>
On Thu, 27 Jun 2019 12:14:50 +0100, Laatz, Kevin wrote:
> On the application side (xdpsock), we don't have to worry about the user
> defined headroom, since it is 0, so we only need to account for the
> XDP_PACKET_HEADROOM when computing the original address (in the default
> scenario).
That assumes specific layout for the data inside the buffer. Some NICs
will prepend information like timestamp to the packet, meaning the
packet would start at offset XDP_PACKET_HEADROOM + metadata len..
I think that's very limiting. What is the challenge in providing
aligned addresses, exactly?
^ permalink raw reply
* [Patch net] netrom: fix a memory leak in nr_rx_frame()
From: Cong Wang @ 2019-06-27 21:30 UTC (permalink / raw)
To: netdev; +Cc: Cong Wang, syzbot+d6636a36d3c34bd88938
When the skb is associated with a new sock, just assigning
it to skb->sk is not sufficient, we have to set its destructor
to free the sock properly too.
Reported-by: syzbot+d6636a36d3c34bd88938@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
net/netrom/af_netrom.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 86b87925ef34..96740d389377 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -869,7 +869,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
unsigned short frametype, flags, window, timeout;
int ret;
- skb->sk = NULL; /* Initially we don't know who it's for */
+ skb_orphan(skb);
/*
* skb->data points to the netrom frame start
@@ -968,6 +968,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
window = skb->data[20];
skb->sk = make;
+ skb->destructor = sock_efree;
make->sk_state = TCP_ESTABLISHED;
/* Fill in his circuit details */
--
2.21.0
^ permalink raw reply related
* Re: [PATCH v2 bpf-next 3/7] libbpf: add kprobe/uprobe attach API
From: Andrii Nakryiko @ 2019-06-27 21:42 UTC (permalink / raw)
To: Daniel Borkmann
Cc: Andrii Nakryiko, Alexei Starovoitov, Stanislav Fomichev, bpf,
Networking, Kernel Team
In-Reply-To: <44d3b02d-b0fb-b0cb-a0d3-e7dd4bde0b92@iogearbox.net>
On Thu, Jun 27, 2019 at 2:16 PM Daniel Borkmann <daniel@iogearbox.net> wrote:
>
> On 06/27/2019 12:15 AM, Andrii Nakryiko wrote:
> > On Wed, Jun 26, 2019 at 7:25 AM Daniel Borkmann <daniel@iogearbox.net> wrote:
> [...]
> >> What this boils down to is that this should get a proper abstraction, e.g. as
> >> in struct libbpf_event which holds the event object. There should be helper
> >> functions like libbpf_event_create_{kprobe,uprobe,tracepoint,raw_tracepoint} returning
> >> such an struct libbpf_event object on success, and a single libbpf_event_destroy()
> >> that does the event specific teardown. bpf_program__attach_event() can then take
> >> care of only attaching the program to it. Having an object for this is also more
> >> extensible than just a fd number. Nice thing is that this can also be completely
> >> internal to libbpf.c as with struct bpf_program and other abstractions where we
> >> don't expose the internals in the public header.
> >
> > Yeah, I totally agree, I think this is a great idea! I don't
> > particularly like "event" name, that seems very overloaded term. Do
> > you mind if I call this "bpf_hook" instead of "libbpf_event"? I've
> > always thought about these different points in the system to which one
> > can attach BPF program as hooks exposed from kernel :)
> >
> > Would it also make sense to do attaching to non-tracing hooks using
> > the same mechanism (e.g., all the per-cgroup stuff, sysctl, etc)? Not
> > sure how people do that today, will check to see how it's done, but I
> > think nothing should conceptually prevent doing that using the same
> > abstract bpf_hook way, right?
>
> I think if we abstract it this way, then absolutely. If I grok the naming conventions
> from the README right, then this would be under 'bpf_hook__' prefix. :)
Yeah, so this is what I had, API-wise:
struct bpf_hook;
LIBBPF_API struct bpf_hook *bpf_hook__new_perf_event(int pfd);
LIBBPF_API struct bpf_hook *bpf_hook__new_kprobe(bool retprobe,
const char *func_name);
LIBBPF_API struct bpf_hook *bpf_hook__new_uprobe(bool retprobe, pid_t pid,
const char *binary_path,
size_t func_offset);
LIBBPF_API struct bpf_hook *bpf_hook__new_tracepoint(const char *tp_category,
const char *tp_name);
LIBBPF_API struct bpf_hook *bpf_hook__new_raw_tracepoint(const char *tp_name);
LIBBPF_API int bpf_hook__attach_program(struct bpf_hook *hook,
struct bpf_program *prog);
LIBBPF_API int bpf_hook__free(struct bpf_hook *hook);
You'd use bpf_hook_new_xxx to create struct bpf_hook, which then get's
attached using generic bpf_hook__attach_program and detached/freed
with generic bpf_hook__free.
But once I converted selftests, I realized that this generic
bpf_hook__attach_program is kind of unnecessary and is just a
boiler-plate extra function that everyone has to call. So now I'm
leaning towards a hybrid approach:
- bpf_program__attach_xxx will create some specific struct bpf_hook
*and* attach bpf_program to it;
- bpf_hook__free(struct bpf_hook *) would still be used to detach/free
resources, abstracting away specifics of detaching.
There are few benefits to this, I think:
1. Less error checking and clean up from caller: attach either
succeeds (and you'll have to eventually do bpf_hook__free) or not, and
then nothing needs to be cleaned up. With separate create/attach, if
create succeeds, but attach fails, you'll have to do extra
bpf_hook__free call. This bundling of create/attach does prevent
theoretical use case of having hook creation in one place and then
pass this generically into another place for attachment, but it seems
like a bit far-fetched corner use case, which can be implemented at
application level, if necessary.
2. bpf_program__attach has more context for helpful log messages, if
something goes wrong. E.g.,
bpf_program__attach_tracepoint(tp_category, tp_name), once it created
perf event FD for tracepoint, can discard tp_category and tp_name and
use only FD for attachment. But if attachment fails, we don't really
know which tracepoint failed to attach. To facilitate that, you'd need
to allocate/copy tp_category/tp_name (just in case for logging), which
is PITA. With bundled attach, you can log nice error with context
right there with no overhead.
This still allows to do cgroup/flow/sysctl/etc attachment in similar
uniform way (but that's for another set of patches).
Also, I renamed bpf_hook to bpf_link as it seems to convey connection
between connection point (hook) and bpf_program better. Alternative
might be bpf_assoc, I'll mention that as well in cover letter.
Anyways, I think it's better usability without losing anything
(realistically) in terms of flexibility for users. I'll post v2 later
today.
>
> Thanks,
> Daniel
^ permalink raw reply
* Re: [PATCH v2 bpf-next 1/3] libbpf: add perf buffer API
From: Andrii Nakryiko @ 2019-06-27 21:45 UTC (permalink / raw)
To: Daniel Borkmann
Cc: Andrii Nakryiko, Alexei Starovoitov, bpf, Networking, Kernel Team
In-Reply-To: <7de14b2b-a663-eed9-8f70-fb6bd5ea84d8@iogearbox.net>
On Thu, Jun 27, 2019 at 2:04 PM Daniel Borkmann <daniel@iogearbox.net> wrote:
>
> On 06/26/2019 08:12 AM, Andrii Nakryiko wrote:
> > BPF_MAP_TYPE_PERF_EVENT_ARRAY map is often used to send data from BPF program
> > to user space for additional processing. libbpf already has very low-level API
> > to read single CPU perf buffer, bpf_perf_event_read_simple(), but it's hard to
> > use and requires a lot of code to set everything up. This patch adds
> > perf_buffer abstraction on top of it, abstracting setting up and polling
> > per-CPU logic into simple and convenient API, similar to what BCC provides.
> >
> > perf_buffer__new() sets up per-CPU ring buffers and updates corresponding BPF
> > map entries. It accepts two user-provided callbacks: one for handling raw
> > samples and one for get notifications of lost samples due to buffer overflow.
> >
> > perf_buffer__poll() is used to fetch ring buffer data across all CPUs,
> > utilizing epoll instance.
> >
> > perf_buffer__free() does corresponding clean up and unsets FDs from BPF map.
> >
> > All APIs are not thread-safe. User should ensure proper locking/coordination if
> > used in multi-threaded set up.
> >
> > Signed-off-by: Andrii Nakryiko <andriin@fb.com>
>
> Aside from current feedback, this series generally looks great! Two small things:
>
> > diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
> > index 2382fbda4cbb..10f48103110a 100644
> > --- a/tools/lib/bpf/libbpf.map
> > +++ b/tools/lib/bpf/libbpf.map
> > @@ -170,13 +170,16 @@ LIBBPF_0.0.4 {
> > btf_dump__dump_type;
> > btf_dump__free;
> > btf_dump__new;
> > - btf__parse_elf;
> > bpf_object__load_xattr;
> > bpf_program__attach_kprobe;
> > bpf_program__attach_perf_event;
> > bpf_program__attach_raw_tracepoint;
> > bpf_program__attach_tracepoint;
> > bpf_program__attach_uprobe;
> > + btf__parse_elf;
> > libbpf_num_possible_cpus;
> > libbpf_perf_event_disable_and_close;
> > + perf_buffer__free;
> > + perf_buffer__new;
> > + perf_buffer__poll;
>
> We should prefix with libbpf_* given it's not strictly BPF-only and rather
> helper function.
Well, perf_buffer is an object similar to `struct btf`, `struct
bpf_program`, etc. So it seems appropriate to follow this
"<object>__<method>" convention. Also, `struct libbpf_perf_buffer` and
`libbpf_perf_buffer__new` looks verbose and pretty ugly, IMO.
>
> Also, we should convert bpftool (tools/bpf/bpftool/map_perf_ring.c) to make
> use of these new helpers instead of open-coding there.
Yep, absolutely, will do that as well, thanks for pointing me there!
>
> Thanks,
> Daniel
^ permalink raw reply
* [PATCH v2 net-next 0/3] Better PHYLINK compliance for SJA1105 DSA
From: Vladimir Oltean @ 2019-06-27 21:46 UTC (permalink / raw)
To: linux, f.fainelli, vivien.didelot, andrew, davem; +Cc: netdev, Vladimir Oltean
After discussing with Russell King, it appears this driver is making a
few confusions and not performing some checks for consistent operation.
Changes in v2:
- Removed redundant print in the phylink_validate callback (in 2/3).
Vladimir Oltean (3):
net: dsa: sja1105: Don't check state->link in phylink_mac_config
net: dsa: sja1105: Check for PHY mode mismatches with what PHYLINK
reports
net: dsa: sja1105: Mark in-band AN modes not supported for PHYLINK
drivers/net/dsa/sja1105/sja1105_main.c | 56 +++++++++++++++++++++++++-
1 file changed, 54 insertions(+), 2 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH v2 net-next 1/3] net: dsa: sja1105: Don't check state->link in phylink_mac_config
From: Vladimir Oltean @ 2019-06-27 21:46 UTC (permalink / raw)
To: linux, f.fainelli, vivien.didelot, andrew, davem
Cc: netdev, Vladimir Oltean, Russell King
In-Reply-To: <20190627214637.22366-1-olteanv@gmail.com>
It has been pointed out that PHYLINK can call mac_config only to update
the phy_interface_type and without knowing what the AN results are.
Experimentally, when this was observed to happen, state->link was also
unset, and therefore was used as a proxy to ignore this call. However it
is also suggested that state->link is undefined for this callback and
should not be relied upon.
So let the previously-dead codepath for SPEED_UNKNOWN be called, and
update the comment to make sure the MAC's behavior is sane.
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
---
drivers/net/dsa/sja1105/sja1105_main.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index caebf76eaa3e..da1736093b06 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -715,7 +715,13 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
switch (speed_mbps) {
case SPEED_UNKNOWN:
- /* No speed update requested */
+ /* PHYLINK called sja1105_mac_config() to inform us about
+ * the state->interface, but AN has not completed and the
+ * speed is not yet valid. UM10944.pdf says that setting
+ * SJA1105_SPEED_AUTO at runtime disables the port, so that is
+ * ok for power consumption in case AN will never complete -
+ * otherwise PHYLINK should come back with a new update.
+ */
speed = SJA1105_SPEED_AUTO;
break;
case SPEED_10:
@@ -766,9 +772,6 @@ static void sja1105_mac_config(struct dsa_switch *ds, int port,
{
struct sja1105_private *priv = ds->priv;
- if (!state->link)
- return;
-
sja1105_adjust_port_config(priv, port, state->speed);
}
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox