* [PATCH bpf-next v3 1/4] bpf: sockmap: enable map_update_elem from bpf_iter
2020-09-29 9:30 [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Lorenz Bauer
@ 2020-09-29 9:30 ` Lorenz Bauer
2020-09-29 9:30 ` [PATCH bpf-next v3 2/4] selftests: bpf: Add helper to compare socket cookies Lorenz Bauer
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Lorenz Bauer @ 2020-09-29 9:30 UTC (permalink / raw)
To: kafai, Alexei Starovoitov, Daniel Borkmann, John Fastabend,
Jakub Sitnicki, Lorenz Bauer, David S. Miller, Jakub Kicinski
Cc: kernel-team, netdev, bpf, linux-kernel
Allow passing a pointer to a BTF struct sock_common* when updating
a sockmap or sockhash. Since BTF pointers can fault and therefore be
NULL at runtime we need to add an additional !sk check to
sock_map_update_elem. Since we may be passed a request or timewait
socket we also need to check sk_fullsock. Doing this allows calling
map_update_elem on sockmap from bpf_iter context, which uses
BTF pointers.
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
kernel/bpf/verifier.c | 2 +-
net/core/sock_map.c | 3 +++
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b25ba989c2dc..cc9c90d74dc1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3943,7 +3943,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
case BPF_MAP_TYPE_SOCKMAP:
case BPF_MAP_TYPE_SOCKHASH:
if (*arg_type == ARG_PTR_TO_MAP_VALUE) {
- *arg_type = ARG_PTR_TO_SOCKET;
+ *arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON;
} else {
verbose(env, "invalid arg_type for sockmap/sockhash\n");
return -EINVAL;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index e1f05e3fa1d0..08bc86f51593 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -610,6 +610,9 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
struct sock *sk = (struct sock *)value;
int ret;
+ if (unlikely(!sk || !sk_fullsock(sk)))
+ return -EINVAL;
+
if (!sock_map_sk_is_suitable(sk))
return -EOPNOTSUPP;
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH bpf-next v3 2/4] selftests: bpf: Add helper to compare socket cookies
2020-09-29 9:30 [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Lorenz Bauer
2020-09-29 9:30 ` [PATCH bpf-next v3 1/4] bpf: sockmap: enable map_update_elem from bpf_iter Lorenz Bauer
@ 2020-09-29 9:30 ` Lorenz Bauer
2020-09-29 9:30 ` [PATCH bpf-next v3 3/4] selftests: bpf: remove shared header from sockmap iter test Lorenz Bauer
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Lorenz Bauer @ 2020-09-29 9:30 UTC (permalink / raw)
To: kafai, Shuah Khan, Alexei Starovoitov, Daniel Borkmann
Cc: kernel-team, Lorenz Bauer, linux-kselftest, netdev, bpf, linux-kernel
We compare socket cookies to ensure that insertion into a sockmap worked.
Pull this out into a helper function for use in other tests.
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
---
.../selftests/bpf/prog_tests/sockmap_basic.c | 50 +++++++++++++------
1 file changed, 36 insertions(+), 14 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 4b7a527e7e82..3596d3f3039f 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -50,6 +50,37 @@ static int connected_socket_v4(void)
return -1;
}
+static void compare_cookies(struct bpf_map *src, struct bpf_map *dst)
+{
+ __u32 i, max_entries = bpf_map__max_entries(src);
+ int err, duration = 0, src_fd, dst_fd;
+
+ src_fd = bpf_map__fd(src);
+ dst_fd = bpf_map__fd(dst);
+
+ for (i = 0; i < max_entries; i++) {
+ __u64 src_cookie, dst_cookie;
+
+ err = bpf_map_lookup_elem(src_fd, &i, &src_cookie);
+ if (err && errno == ENOENT) {
+ err = bpf_map_lookup_elem(dst_fd, &i, &dst_cookie);
+ CHECK(!err, "map_lookup_elem(dst)", "element %u not deleted\n", i);
+ CHECK(err && errno != ENOENT, "map_lookup_elem(dst)", "%s\n",
+ strerror(errno));
+ continue;
+ }
+ if (CHECK(err, "lookup_elem(src)", "%s\n", strerror(errno)))
+ continue;
+
+ err = bpf_map_lookup_elem(dst_fd, &i, &dst_cookie);
+ if (CHECK(err, "lookup_elem(dst)", "%s\n", strerror(errno)))
+ continue;
+
+ CHECK(dst_cookie != src_cookie, "cookie mismatch",
+ "%llu != %llu (pos %u)\n", dst_cookie, src_cookie, i);
+ }
+}
+
/* Create a map, populate it with one socket, and free the map. */
static void test_sockmap_create_update_free(enum bpf_map_type map_type)
{
@@ -109,9 +140,9 @@ static void test_skmsg_helpers(enum bpf_map_type map_type)
static void test_sockmap_update(enum bpf_map_type map_type)
{
struct bpf_prog_test_run_attr tattr;
- int err, prog, src, dst, duration = 0;
+ int err, prog, src, duration = 0;
struct test_sockmap_update *skel;
- __u64 src_cookie, dst_cookie;
+ struct bpf_map *dst_map;
const __u32 zero = 0;
char dummy[14] = {0};
__s64 sk;
@@ -127,18 +158,14 @@ static void test_sockmap_update(enum bpf_map_type map_type)
prog = bpf_program__fd(skel->progs.copy_sock_map);
src = bpf_map__fd(skel->maps.src);
if (map_type == BPF_MAP_TYPE_SOCKMAP)
- dst = bpf_map__fd(skel->maps.dst_sock_map);
+ dst_map = skel->maps.dst_sock_map;
else
- dst = bpf_map__fd(skel->maps.dst_sock_hash);
+ dst_map = skel->maps.dst_sock_hash;
err = bpf_map_update_elem(src, &zero, &sk, BPF_NOEXIST);
if (CHECK(err, "update_elem(src)", "errno=%u\n", errno))
goto out;
- err = bpf_map_lookup_elem(src, &zero, &src_cookie);
- if (CHECK(err, "lookup_elem(src, cookie)", "errno=%u\n", errno))
- goto out;
-
tattr = (struct bpf_prog_test_run_attr){
.prog_fd = prog,
.repeat = 1,
@@ -151,12 +178,7 @@ static void test_sockmap_update(enum bpf_map_type map_type)
"errno=%u retval=%u\n", errno, tattr.retval))
goto out;
- err = bpf_map_lookup_elem(dst, &zero, &dst_cookie);
- if (CHECK(err, "lookup_elem(dst, cookie)", "errno=%u\n", errno))
- goto out;
-
- CHECK(dst_cookie != src_cookie, "cookie mismatch", "%llu != %llu\n",
- dst_cookie, src_cookie);
+ compare_cookies(skel->maps.src, dst_map);
out:
test_sockmap_update__destroy(skel);
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH bpf-next v3 3/4] selftests: bpf: remove shared header from sockmap iter test
2020-09-29 9:30 [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Lorenz Bauer
2020-09-29 9:30 ` [PATCH bpf-next v3 1/4] bpf: sockmap: enable map_update_elem from bpf_iter Lorenz Bauer
2020-09-29 9:30 ` [PATCH bpf-next v3 2/4] selftests: bpf: Add helper to compare socket cookies Lorenz Bauer
@ 2020-09-29 9:30 ` Lorenz Bauer
2020-09-29 9:30 ` [PATCH bpf-next v3 4/4] selftest: bpf: Test copying a sockmap and sockhash Lorenz Bauer
2020-09-29 15:53 ` [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Alexei Starovoitov
4 siblings, 0 replies; 6+ messages in thread
From: Lorenz Bauer @ 2020-09-29 9:30 UTC (permalink / raw)
To: kafai, Shuah Khan, Alexei Starovoitov, Daniel Borkmann
Cc: kernel-team, Lorenz Bauer, Yonghong Song, linux-kernel,
linux-kselftest, netdev, bpf
The shared header to define SOCKMAP_MAX_ENTRIES is a bit overkill.
Dynamically allocate the sock_fd array based on bpf_map__max_entries
instead.
Suggested-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Acked-by: Yonghong Song <yhs@fb.com>
---
.../selftests/bpf/prog_tests/sockmap_basic.c | 36 +++++++++----------
.../selftests/bpf/progs/bpf_iter_sockmap.c | 5 ++-
.../selftests/bpf/progs/bpf_iter_sockmap.h | 3 --
3 files changed, 20 insertions(+), 24 deletions(-)
delete mode 100644 tools/testing/selftests/bpf/progs/bpf_iter_sockmap.h
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 3596d3f3039f..316c4e271b36 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -8,8 +8,6 @@
#include "test_sockmap_invalid_update.skel.h"
#include "bpf_iter_sockmap.skel.h"
-#include "progs/bpf_iter_sockmap.h"
-
#define TCP_REPAIR 19 /* TCP sock is under repair right now */
#define TCP_REPAIR_ON 1
@@ -201,9 +199,9 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
int err, len, src_fd, iter_fd, duration = 0;
union bpf_iter_link_info linfo = {0};
- __s64 sock_fd[SOCKMAP_MAX_ENTRIES];
- __u32 i, num_sockets, max_elems;
+ __u32 i, num_sockets, num_elems;
struct bpf_iter_sockmap *skel;
+ __s64 *sock_fd = NULL;
struct bpf_link *link;
struct bpf_map *src;
char buf[64];
@@ -212,22 +210,23 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
if (CHECK(!skel, "bpf_iter_sockmap__open_and_load", "skeleton open_and_load failed\n"))
return;
- for (i = 0; i < ARRAY_SIZE(sock_fd); i++)
- sock_fd[i] = -1;
-
- /* Make sure we have at least one "empty" entry to test iteration of
- * an empty slot.
- */
- num_sockets = ARRAY_SIZE(sock_fd) - 1;
-
if (map_type == BPF_MAP_TYPE_SOCKMAP) {
src = skel->maps.sockmap;
- max_elems = bpf_map__max_entries(src);
+ num_elems = bpf_map__max_entries(src);
+ num_sockets = num_elems - 1;
} else {
src = skel->maps.sockhash;
- max_elems = num_sockets;
+ num_elems = bpf_map__max_entries(src) - 1;
+ num_sockets = num_elems;
}
+ sock_fd = calloc(num_sockets, sizeof(*sock_fd));
+ if (CHECK(!sock_fd, "calloc(sock_fd)", "failed to allocate\n"))
+ goto out;
+
+ for (i = 0; i < num_sockets; i++)
+ sock_fd[i] = -1;
+
src_fd = bpf_map__fd(src);
for (i = 0; i < num_sockets; i++) {
@@ -258,8 +257,8 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
goto close_iter;
/* test results */
- if (CHECK(skel->bss->elems != max_elems, "elems", "got %u expected %u\n",
- skel->bss->elems, max_elems))
+ if (CHECK(skel->bss->elems != num_elems, "elems", "got %u expected %u\n",
+ skel->bss->elems, num_elems))
goto close_iter;
if (CHECK(skel->bss->socks != num_sockets, "socks", "got %u expected %u\n",
@@ -271,10 +270,11 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
free_link:
bpf_link__destroy(link);
out:
- for (i = 0; i < num_sockets; i++) {
+ for (i = 0; sock_fd && i < num_sockets; i++)
if (sock_fd[i] >= 0)
close(sock_fd[i]);
- }
+ if (sock_fd)
+ free(sock_fd);
bpf_iter_sockmap__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
index 0e27f73dd803..1af7555f6057 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
@@ -2,7 +2,6 @@
/* Copyright (c) 2020 Cloudflare */
#include "bpf_iter.h"
#include "bpf_tracing_net.h"
-#include "bpf_iter_sockmap.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <errno.h>
@@ -11,14 +10,14 @@ char _license[] SEC("license") = "GPL";
struct {
__uint(type, BPF_MAP_TYPE_SOCKMAP);
- __uint(max_entries, SOCKMAP_MAX_ENTRIES);
+ __uint(max_entries, 64);
__type(key, __u32);
__type(value, __u64);
} sockmap SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_SOCKHASH);
- __uint(max_entries, SOCKMAP_MAX_ENTRIES);
+ __uint(max_entries, 64);
__type(key, __u32);
__type(value, __u64);
} sockhash SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.h b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.h
deleted file mode 100644
index 35a675d13c0f..000000000000
--- a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#define SOCKMAP_MAX_ENTRIES (64)
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH bpf-next v3 4/4] selftest: bpf: Test copying a sockmap and sockhash
2020-09-29 9:30 [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Lorenz Bauer
` (2 preceding siblings ...)
2020-09-29 9:30 ` [PATCH bpf-next v3 3/4] selftests: bpf: remove shared header from sockmap iter test Lorenz Bauer
@ 2020-09-29 9:30 ` Lorenz Bauer
2020-09-29 15:53 ` [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Alexei Starovoitov
4 siblings, 0 replies; 6+ messages in thread
From: Lorenz Bauer @ 2020-09-29 9:30 UTC (permalink / raw)
To: kafai, Shuah Khan, Alexei Starovoitov, Daniel Borkmann
Cc: kernel-team, Lorenz Bauer, linux-kselftest, netdev, bpf, linux-kernel
Since we can now call map_update_elem(sockmap) from bpf_iter context
it's possible to copy a sockmap or sockhash in the kernel. Add a
selftest which exercises this.
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
---
.../selftests/bpf/prog_tests/sockmap_basic.c | 14 +++++-----
.../selftests/bpf/progs/bpf_iter_sockmap.c | 27 +++++++++++++++----
2 files changed, 30 insertions(+), 11 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 316c4e271b36..4c4224e3e10a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -194,7 +194,7 @@ static void test_sockmap_invalid_update(void)
test_sockmap_invalid_update__destroy(skel);
}
-static void test_sockmap_iter(enum bpf_map_type map_type)
+static void test_sockmap_copy(enum bpf_map_type map_type)
{
DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
int err, len, src_fd, iter_fd, duration = 0;
@@ -242,7 +242,7 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
linfo.map.map_fd = src_fd;
opts.link_info = &linfo;
opts.link_info_len = sizeof(linfo);
- link = bpf_program__attach_iter(skel->progs.count_elems, &opts);
+ link = bpf_program__attach_iter(skel->progs.copy, &opts);
if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
goto out;
@@ -265,6 +265,8 @@ static void test_sockmap_iter(enum bpf_map_type map_type)
skel->bss->socks, num_sockets))
goto close_iter;
+ compare_cookies(src, skel->maps.dst);
+
close_iter:
close(iter_fd);
free_link:
@@ -294,8 +296,8 @@ void test_sockmap_basic(void)
test_sockmap_update(BPF_MAP_TYPE_SOCKHASH);
if (test__start_subtest("sockmap update in unsafe context"))
test_sockmap_invalid_update();
- if (test__start_subtest("sockmap iter"))
- test_sockmap_iter(BPF_MAP_TYPE_SOCKMAP);
- if (test__start_subtest("sockhash iter"))
- test_sockmap_iter(BPF_MAP_TYPE_SOCKHASH);
+ if (test__start_subtest("sockmap copy"))
+ test_sockmap_copy(BPF_MAP_TYPE_SOCKMAP);
+ if (test__start_subtest("sockhash copy"))
+ test_sockmap_copy(BPF_MAP_TYPE_SOCKHASH);
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
index 1af7555f6057..f3af0e30cead 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
@@ -22,21 +22,38 @@ struct {
__type(value, __u64);
} sockhash SEC(".maps");
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKHASH);
+ __uint(max_entries, 64);
+ __type(key, __u32);
+ __type(value, __u64);
+} dst SEC(".maps");
+
__u32 elems = 0;
__u32 socks = 0;
SEC("iter/sockmap")
-int count_elems(struct bpf_iter__sockmap *ctx)
+int copy(struct bpf_iter__sockmap *ctx)
{
struct sock *sk = ctx->sk;
__u32 tmp, *key = ctx->key;
int ret;
- if (key)
- elems++;
+ if (!key)
+ return 0;
- if (sk)
+ elems++;
+
+ /* We need a temporary buffer on the stack, since the verifier doesn't
+ * let us use the pointer from the context as an argument to the helper.
+ */
+ tmp = *key;
+
+ if (sk) {
socks++;
+ return bpf_map_update_elem(&dst, &tmp, sk, 0) != 0;
+ }
- return 0;
+ ret = bpf_map_delete_elem(&dst, &tmp);
+ return ret && ret != -ENOENT;
}
--
2.25.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* Re: [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying
2020-09-29 9:30 [PATCH bpf-next v3 0/4] [PATCH bpf-next v2 0/4] Sockmap copying Lorenz Bauer
` (3 preceding siblings ...)
2020-09-29 9:30 ` [PATCH bpf-next v3 4/4] selftest: bpf: Test copying a sockmap and sockhash Lorenz Bauer
@ 2020-09-29 15:53 ` Alexei Starovoitov
4 siblings, 0 replies; 6+ messages in thread
From: Alexei Starovoitov @ 2020-09-29 15:53 UTC (permalink / raw)
To: Lorenz Bauer
Cc: Martin KaFai Lau, Alexei Starovoitov, Daniel Borkmann,
kernel-team, Network Development, bpf
On Tue, Sep 29, 2020 at 2:31 AM Lorenz Bauer <lmb@cloudflare.com> wrote:
>
> Changes in v3:
> - Initialize duration to 0 in selftests (Martin)
Clearly you didn't rebase.
^ permalink raw reply [flat|nested] 6+ messages in thread