summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/prog_tests
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/bpf/prog_tests')
-rw-r--r--tools/testing/selftests/bpf/prog_tests/align.c178
-rw-r--r--tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c27
-rw-r--r--tools/testing/selftests/bpf/prog_tests/atomics.c10
-rw-r--r--tools/testing/selftests/bpf/prog_tests/attach_probe.c112
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_cookie.c53
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_iter.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_nf.c6
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c231
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c101
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dump.c120
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_split.c58
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_sysfs.c81
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c617
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c77
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c72
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c71
-rw-r--r--tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c285
-rw-r--r--tools/testing/selftests/bpf/prog_tests/dynptr.c33
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fd_array.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c192
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fentry_fexit.c15
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fentry_test.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_test.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fill_link_info.c18
-rw-r--r--tools/testing/selftests/bpf/prog_tests/for_each.c37
-rw-r--r--tools/testing/selftests/bpf/prog_tests/free_timer.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kernel_flag.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c247
-rw-r--r--tools/testing/selftests/bpf/prog_tests/linked_list.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/log_buf.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/map_excl.c54
-rw-r--r--tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/module_attach.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c50
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pinning_htab.c36
-rw-r--r--tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c125
-rw-r--r--tools/testing/selftests/bpf/prog_tests/rbtree.c6
-rw-r--r--tools/testing/selftests/bpf/prog_tests/recursive_attach.c67
-rw-r--r--tools/testing/selftests/bpf/prog_tests/reg_bounds.c18
-rw-r--r--tools/testing/selftests/bpf/prog_tests/res_spin_lock.c23
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sha256.c52
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sk_assign.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/snprintf.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c885
-rw-r--r--tools/testing/selftests/bpf/prog_tests/socket_helpers.h84
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h25
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c389
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c459
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_redir.c465
-rw-r--r--tools/testing/selftests/bpf/prog_tests/spin_lock.c12
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map.c71
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stream.c108
-rw-r--r--tools/testing/selftests/bpf/prog_tests/string_kfuncs.c66
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tailcalls.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/task_local_data.h386
-rw-r--r--tools/testing/selftests/bpf/prog_tests/task_work_stress.c130
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_helpers.h28
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_redirect.c11
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_btf_ext.c64
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c74
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_sysctl.c1612
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_task_local_data.c297
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_task_work.c157
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_veristat.c156
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer.c38
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_crash.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_lockup.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_mim.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/token.c85
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tracing_failure.c52
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tracing_struct.c29
-rw-r--r--tools/testing/selftests/bpf/prog_tests/uprobe.c156
-rw-r--r--tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c486
-rw-r--r--tools/testing/selftests/bpf/prog_tests/usdt.c135
-rw-r--r--tools/testing/selftests/bpf/prog_tests/user_ringbuf.c10
-rw-r--r--tools/testing/selftests/bpf/prog_tests/verifier.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c114
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c222
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c31
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c13
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_metadata.c22
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c179
92 files changed, 9101 insertions, 1134 deletions
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 1d53a8561ee2..24c509ce4e5b 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -42,11 +42,11 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "2"},
- {1, "R3_w", "4"},
- {2, "R3_w", "8"},
- {3, "R3_w", "16"},
- {4, "R3_w", "32"},
+ {0, "R3", "2"},
+ {1, "R3", "4"},
+ {2, "R3", "8"},
+ {3, "R3", "16"},
+ {4, "R3", "32"},
},
},
{
@@ -70,17 +70,17 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "1"},
- {1, "R3_w", "2"},
- {2, "R3_w", "4"},
- {3, "R3_w", "8"},
- {4, "R3_w", "16"},
- {5, "R3_w", "1"},
- {6, "R4_w", "32"},
- {7, "R4_w", "16"},
- {8, "R4_w", "8"},
- {9, "R4_w", "4"},
- {10, "R4_w", "2"},
+ {0, "R3", "1"},
+ {1, "R3", "2"},
+ {2, "R3", "4"},
+ {3, "R3", "8"},
+ {4, "R3", "16"},
+ {5, "R3", "1"},
+ {6, "R4", "32"},
+ {7, "R4", "16"},
+ {8, "R4", "8"},
+ {9, "R4", "4"},
+ {10, "R4", "2"},
},
},
{
@@ -99,12 +99,12 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "4"},
- {1, "R3_w", "8"},
- {2, "R3_w", "10"},
- {3, "R4_w", "8"},
- {4, "R4_w", "12"},
- {5, "R4_w", "14"},
+ {0, "R3", "4"},
+ {1, "R3", "8"},
+ {2, "R3", "10"},
+ {3, "R4", "8"},
+ {4, "R4", "12"},
+ {5, "R4", "14"},
},
},
{
@@ -121,10 +121,10 @@ static struct bpf_align_test tests[] = {
.matches = {
{0, "R1", "ctx()"},
{0, "R10", "fp0"},
- {0, "R3_w", "7"},
- {1, "R3_w", "7"},
- {2, "R3_w", "14"},
- {3, "R3_w", "56"},
+ {0, "R3", "7"},
+ {1, "R3", "7"},
+ {2, "R3", "14"},
+ {3, "R3", "56"},
},
},
@@ -162,19 +162,19 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {6, "R0_w", "pkt(off=8,r=8)"},
- {6, "R3_w", "var_off=(0x0; 0xff)"},
- {7, "R3_w", "var_off=(0x0; 0x1fe)"},
- {8, "R3_w", "var_off=(0x0; 0x3fc)"},
- {9, "R3_w", "var_off=(0x0; 0x7f8)"},
- {10, "R3_w", "var_off=(0x0; 0xff0)"},
- {12, "R3_w", "pkt_end()"},
- {17, "R4_w", "var_off=(0x0; 0xff)"},
- {18, "R4_w", "var_off=(0x0; 0x1fe0)"},
- {19, "R4_w", "var_off=(0x0; 0xff0)"},
- {20, "R4_w", "var_off=(0x0; 0x7f8)"},
- {21, "R4_w", "var_off=(0x0; 0x3fc)"},
- {22, "R4_w", "var_off=(0x0; 0x1fe)"},
+ {6, "R0", "pkt(off=8,r=8)"},
+ {6, "R3", "var_off=(0x0; 0xff)"},
+ {7, "R3", "var_off=(0x0; 0x1fe)"},
+ {8, "R3", "var_off=(0x0; 0x3fc)"},
+ {9, "R3", "var_off=(0x0; 0x7f8)"},
+ {10, "R3", "var_off=(0x0; 0xff0)"},
+ {12, "R3", "pkt_end()"},
+ {17, "R4", "var_off=(0x0; 0xff)"},
+ {18, "R4", "var_off=(0x0; 0x1fe0)"},
+ {19, "R4", "var_off=(0x0; 0xff0)"},
+ {20, "R4", "var_off=(0x0; 0x7f8)"},
+ {21, "R4", "var_off=(0x0; 0x3fc)"},
+ {22, "R4", "var_off=(0x0; 0x1fe)"},
},
},
{
@@ -195,16 +195,16 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {6, "R3_w", "var_off=(0x0; 0xff)"},
- {7, "R4_w", "var_off=(0x0; 0xff)"},
- {8, "R4_w", "var_off=(0x0; 0xff)"},
- {9, "R4_w", "var_off=(0x0; 0xff)"},
- {10, "R4_w", "var_off=(0x0; 0x1fe)"},
- {11, "R4_w", "var_off=(0x0; 0xff)"},
- {12, "R4_w", "var_off=(0x0; 0x3fc)"},
- {13, "R4_w", "var_off=(0x0; 0xff)"},
- {14, "R4_w", "var_off=(0x0; 0x7f8)"},
- {15, "R4_w", "var_off=(0x0; 0xff0)"},
+ {6, "R3", "var_off=(0x0; 0xff)"},
+ {7, "R4", "var_off=(0x0; 0xff)"},
+ {8, "R4", "var_off=(0x0; 0xff)"},
+ {9, "R4", "var_off=(0x0; 0xff)"},
+ {10, "R4", "var_off=(0x0; 0x1fe)"},
+ {11, "R4", "var_off=(0x0; 0xff)"},
+ {12, "R4", "var_off=(0x0; 0x3fc)"},
+ {13, "R4", "var_off=(0x0; 0xff)"},
+ {14, "R4", "var_off=(0x0; 0x7f8)"},
+ {15, "R4", "var_off=(0x0; 0xff0)"},
},
},
{
@@ -235,14 +235,14 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {2, "R5_w", "pkt(r=0)"},
- {4, "R5_w", "pkt(off=14,r=0)"},
- {5, "R4_w", "pkt(off=14,r=0)"},
+ {2, "R5", "pkt(r=0)"},
+ {4, "R5", "pkt(off=14,r=0)"},
+ {5, "R4", "pkt(off=14,r=0)"},
{9, "R2", "pkt(r=18)"},
{10, "R5", "pkt(off=14,r=18)"},
- {10, "R4_w", "var_off=(0x0; 0xff)"},
- {13, "R4_w", "var_off=(0x0; 0xffff)"},
- {14, "R4_w", "var_off=(0x0; 0xffff)"},
+ {10, "R4", "var_off=(0x0; 0xff)"},
+ {13, "R4", "var_off=(0x0; 0xffff)"},
+ {14, "R4", "var_off=(0x0; 0xffff)"},
},
},
{
@@ -299,12 +299,12 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {7, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {6, "R2", "pkt(r=8)"},
+ {7, "R6", "var_off=(0x0; 0x3fc)"},
/* Offset is added to packet pointer R5, resulting in
* known fixed offset, and variable offset from R6.
*/
- {11, "R5_w", "pkt(id=1,off=14,"},
+ {11, "R5", "pkt(id=1,off=14,"},
/* At the time the word size load is performed from R5,
* it's total offset is NET_IP_ALIGN + reg->off (0) +
* reg->aux_off (14) which is 16. Then the variable
@@ -320,12 +320,12 @@ static struct bpf_align_test tests[] = {
* instruction to validate R5 state. We also check
* that R4 is what it should be in such case.
*/
- {18, "R4_w", "var_off=(0x0; 0x3fc)"},
- {18, "R5_w", "var_off=(0x0; 0x3fc)"},
+ {18, "R4", "var_off=(0x0; 0x3fc)"},
+ {18, "R5", "var_off=(0x0; 0x3fc)"},
/* Constant offset is added to R5, resulting in
* reg->off of 14.
*/
- {19, "R5_w", "pkt(id=2,off=14,"},
+ {19, "R5", "pkt(id=2,off=14,"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off
* (14) which is 16. Then the variable offset is 4-byte
@@ -337,21 +337,21 @@ static struct bpf_align_test tests[] = {
/* Constant offset is added to R5 packet pointer,
* resulting in reg->off value of 14.
*/
- {26, "R5_w", "pkt(off=14,r=8)"},
+ {26, "R5", "pkt(off=14,r=8)"},
/* Variable offset is added to R5, resulting in a
* variable offset of (4n). See comment for insn #18
* for R4 = R5 trick.
*/
- {28, "R4_w", "var_off=(0x0; 0x3fc)"},
- {28, "R5_w", "var_off=(0x0; 0x3fc)"},
+ {28, "R4", "var_off=(0x0; 0x3fc)"},
+ {28, "R5", "var_off=(0x0; 0x3fc)"},
/* Constant is added to R5 again, setting reg->off to 18. */
- {29, "R5_w", "pkt(id=3,off=18,"},
+ {29, "R5", "pkt(id=3,off=18,"},
/* And once more we add a variable; resulting var_off
* is still (4n), fixed offset is not changed.
* Also, we create a new reg->id.
*/
- {31, "R4_w", "var_off=(0x0; 0x7fc)"},
- {31, "R5_w", "var_off=(0x0; 0x7fc)"},
+ {31, "R4", "var_off=(0x0; 0x7fc)"},
+ {31, "R5", "var_off=(0x0; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (18)
* which is 20. Then the variable offset is (4n), so
@@ -397,12 +397,12 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {7, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {6, "R2", "pkt(r=8)"},
+ {7, "R6", "var_off=(0x0; 0x3fc)"},
/* Adding 14 makes R6 be (4n+2) */
- {8, "R6_w", "var_off=(0x2; 0x7fc)"},
+ {8, "R6", "var_off=(0x2; 0x7fc)"},
/* Packet pointer has (4n+2) offset */
- {11, "R5_w", "var_off=(0x2; 0x7fc)"},
+ {11, "R5", "var_off=(0x2; 0x7fc)"},
{12, "R4", "var_off=(0x2; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
@@ -414,11 +414,11 @@ static struct bpf_align_test tests[] = {
/* Newly read value in R6 was shifted left by 2, so has
* known alignment of 4.
*/
- {17, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {17, "R6", "var_off=(0x0; 0x3fc)"},
/* Added (4n) to packet pointer's (4n+2) var_off, giving
* another (4n+2).
*/
- {19, "R5_w", "var_off=(0x2; 0xffc)"},
+ {19, "R5", "var_off=(0x2; 0xffc)"},
{20, "R4", "var_off=(0x2; 0xffc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
@@ -459,18 +459,18 @@ static struct bpf_align_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.matches = {
- {3, "R5_w", "pkt_end()"},
+ {3, "R5", "pkt_end()"},
/* (ptr - ptr) << 2 == unknown, (4n) */
- {5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"},
+ {5, "R5", "var_off=(0x0; 0xfffffffffffffffc)"},
/* (4n) + 14 == (4n+2). We blow our bounds, because
* the add could overflow.
*/
- {6, "R5_w", "var_off=(0x2; 0xfffffffffffffffc)"},
+ {6, "R5", "var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>=0 */
{9, "R5", "var_off=(0x2; 0x7ffffffffffffffc)"},
/* packet pointer + nonnegative (4n+2) */
- {11, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
- {12, "R4_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
+ {11, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"},
+ {12, "R4", "var_off=(0x2; 0x7ffffffffffffffc)"},
/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
* We checked the bounds, but it might have been able
* to overflow if the packet pointer started in the
@@ -478,7 +478,7 @@ static struct bpf_align_test tests[] = {
* So we did not get a 'range' on R6, and the access
* attempt will fail.
*/
- {15, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"},
+ {15, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"},
}
},
{
@@ -513,12 +513,12 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {8, "R6_w", "var_off=(0x0; 0x3fc)"},
+ {6, "R2", "pkt(r=8)"},
+ {8, "R6", "var_off=(0x0; 0x3fc)"},
/* Adding 14 makes R6 be (4n+2) */
- {9, "R6_w", "var_off=(0x2; 0x7fc)"},
+ {9, "R6", "var_off=(0x2; 0x7fc)"},
/* New unknown value in R7 is (4n) */
- {10, "R7_w", "var_off=(0x0; 0x3fc)"},
+ {10, "R7", "var_off=(0x0; 0x3fc)"},
/* Subtracting it from R6 blows our unsigned bounds */
{11, "R6", "var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>= 0 */
@@ -566,16 +566,16 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {6, "R2_w", "pkt(r=8)"},
- {9, "R6_w", "var_off=(0x0; 0x3c)"},
+ {6, "R2", "pkt(r=8)"},
+ {9, "R6", "var_off=(0x0; 0x3c)"},
/* Adding 14 makes R6 be (4n+2) */
- {10, "R6_w", "var_off=(0x2; 0x7c)"},
+ {10, "R6", "var_off=(0x2; 0x7c)"},
/* Subtracting from packet pointer overflows ubounds */
- {13, "R5_w", "var_off=(0xffffffffffffff82; 0x7c)"},
+ {13, "R5", "var_off=(0xffffffffffffff82; 0x7c)"},
/* New unknown value in R7 is (4n), >= 76 */
- {14, "R7_w", "var_off=(0x0; 0x7fc)"},
+ {14, "R7", "var_off=(0x0; 0x7fc)"},
/* Adding it to packet pointer gives nice bounds again */
- {16, "R5_w", "var_off=(0x2; 0x7fc)"},
+ {16, "R5", "var_off=(0x2; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
index 7565fc7690c2..693fd86fbde6 100644
--- a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
@@ -40,8 +40,13 @@ static void *spin_lock_thread(void *arg)
err = bpf_prog_test_run_opts(prog_fd, &topts);
ASSERT_OK(err, "test_run err");
+
+ if (topts.retval == -EOPNOTSUPP)
+ goto end;
+
ASSERT_EQ((int)topts.retval, 0, "test_run retval");
+end:
pthread_exit(arg);
}
@@ -51,9 +56,11 @@ static void test_arena_spin_lock_size(int size)
struct arena_spin_lock *skel;
pthread_t thread_id[16];
int prog_fd, i, err;
+ int nthreads;
void *ret;
- if (get_nprocs() < 2) {
+ nthreads = MIN(get_nprocs(), ARRAY_SIZE(thread_id));
+ if (nthreads < 2) {
test__skip();
return;
}
@@ -61,30 +68,38 @@ static void test_arena_spin_lock_size(int size)
skel = arena_spin_lock__open_and_load();
if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load"))
return;
+
if (skel->data->test_skip == 2) {
test__skip();
goto end;
}
skel->bss->cs_count = size;
- skel->bss->limit = repeat * 16;
+ skel->bss->limit = repeat * nthreads;
- ASSERT_OK(pthread_barrier_init(&barrier, NULL, 16), "barrier init");
+ ASSERT_OK(pthread_barrier_init(&barrier, NULL, nthreads), "barrier init");
prog_fd = bpf_program__fd(skel->progs.prog);
- for (i = 0; i < 16; i++) {
+ for (i = 0; i < nthreads; i++) {
err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd);
if (!ASSERT_OK(err, "pthread_create"))
goto end_barrier;
}
- for (i = 0; i < 16; i++) {
+ for (i = 0; i < nthreads; i++) {
if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join"))
goto end_barrier;
if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd"))
goto end_barrier;
}
- ASSERT_EQ(skel->bss->counter, repeat * 16, "check counter value");
+ if (skel->data->test_skip == 3) {
+ printf("%s:SKIP: CONFIG_NR_CPUS exceed the maximum supported by arena spinlock\n",
+ __func__);
+ test__skip();
+ goto end_barrier;
+ }
+
+ ASSERT_EQ(skel->bss->counter, repeat * nthreads, "check counter value");
end_barrier:
pthread_barrier_destroy(&barrier);
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index 13e101f370a1..92b5f378bfb8 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -165,11 +165,17 @@ static void test_xchg(struct atomics_lskel *skel)
void test_atomics(void)
{
struct atomics_lskel *skel;
+ int err;
- skel = atomics_lskel__open_and_load();
- if (!ASSERT_OK_PTR(skel, "atomics skeleton load"))
+ skel = atomics_lskel__open();
+ if (!ASSERT_OK_PTR(skel, "atomics skeleton open"))
return;
+ skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = atomics_lskel__load(skel);
+ if (!ASSERT_OK(err, "atomics skeleton load"))
+ goto cleanup;
+
if (skel->data->skip_tests) {
printf("%s:SKIP:no ENABLE_ATOMICS_TESTS (missing Clang BPF atomics support)",
__func__);
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 329c7862b52d..9e77e5da7097 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -3,6 +3,7 @@
#include "test_attach_kprobe_sleepable.skel.h"
#include "test_attach_probe_manual.skel.h"
#include "test_attach_probe.skel.h"
+#include "kprobe_write_ctx.skel.h"
/* this is how USDT semaphore is actually defined, except volatile modifier */
volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
@@ -122,6 +123,110 @@ cleanup:
test_attach_probe_manual__destroy(skel);
}
+/* attach uprobe/uretprobe long event name testings */
+static void test_attach_uprobe_long_event_name(void)
+{
+ DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+ struct bpf_link *uprobe_link, *uretprobe_link;
+ struct test_attach_probe_manual *skel;
+ ssize_t uprobe_offset;
+ char path[PATH_MAX] = {0};
+
+ skel = test_attach_probe_manual__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load"))
+ return;
+
+ uprobe_offset = get_uprobe_offset(&trigger_func);
+ if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset"))
+ goto cleanup;
+
+ if (!ASSERT_GT(readlink("/proc/self/exe", path, PATH_MAX - 1), 0, "readlink"))
+ goto cleanup;
+
+ /* manual-attach uprobe/uretprobe */
+ uprobe_opts.attach_mode = PROBE_ATTACH_MODE_LEGACY;
+ uprobe_opts.ref_ctr_offset = 0;
+ uprobe_opts.retprobe = false;
+ uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe,
+ 0 /* self pid */,
+ path,
+ uprobe_offset,
+ &uprobe_opts);
+ if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe_long_event_name"))
+ goto cleanup;
+ skel->links.handle_uprobe = uprobe_link;
+
+ uprobe_opts.retprobe = true;
+ uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe,
+ -1 /* any pid */,
+ path,
+ uprobe_offset, &uprobe_opts);
+ if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe_long_event_name"))
+ goto cleanup;
+ skel->links.handle_uretprobe = uretprobe_link;
+
+cleanup:
+ test_attach_probe_manual__destroy(skel);
+}
+
+/* attach kprobe/kretprobe long event name testings */
+static void test_attach_kprobe_long_event_name(void)
+{
+ DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts);
+ struct bpf_link *kprobe_link, *kretprobe_link;
+ struct test_attach_probe_manual *skel;
+
+ skel = test_attach_probe_manual__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load"))
+ return;
+
+ /* manual-attach kprobe/kretprobe */
+ kprobe_opts.attach_mode = PROBE_ATTACH_MODE_LEGACY;
+ kprobe_opts.retprobe = false;
+ kprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+ "bpf_testmod_looooooooooooooooooooooooooooooong_name",
+ &kprobe_opts);
+ if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe_long_event_name"))
+ goto cleanup;
+ skel->links.handle_kprobe = kprobe_link;
+
+ kprobe_opts.retprobe = true;
+ kretprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+ "bpf_testmod_looooooooooooooooooooooooooooooong_name",
+ &kprobe_opts);
+ if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe_long_event_name"))
+ goto cleanup;
+ skel->links.handle_kretprobe = kretprobe_link;
+
+cleanup:
+ test_attach_probe_manual__destroy(skel);
+}
+
+#ifdef __x86_64__
+/* attach kprobe/kretprobe long event name testings */
+static void test_attach_kprobe_write_ctx(void)
+{
+ struct kprobe_write_ctx *skel = NULL;
+ struct bpf_link *link = NULL;
+
+ skel = kprobe_write_ctx__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load"))
+ return;
+
+ link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_write_ctx,
+ "bpf_fentry_test1", NULL);
+ if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts"))
+ bpf_link__destroy(link);
+
+ kprobe_write_ctx__destroy(skel);
+}
+#else
+static void test_attach_kprobe_write_ctx(void)
+{
+ test__skip();
+}
+#endif
+
static void test_attach_probe_auto(struct test_attach_probe *skel)
{
struct bpf_link *uprobe_err_link;
@@ -323,6 +428,13 @@ void test_attach_probe(void)
if (test__start_subtest("uprobe-ref_ctr"))
test_uprobe_ref_ctr(skel);
+ if (test__start_subtest("uprobe-long_name"))
+ test_attach_uprobe_long_event_name();
+ if (test__start_subtest("kprobe-long_name"))
+ test_attach_kprobe_long_event_name();
+ if (test__start_subtest("kprobe-write-ctx"))
+ test_attach_kprobe_write_ctx();
+
cleanup:
test_attach_probe__destroy(skel);
ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_cleanup");
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
index 67557cda2208..42b49870e520 100644
--- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -13,7 +13,7 @@
static void test_fail_cases(void)
{
LIBBPF_OPTS(bpf_map_create_opts, opts);
- __u32 value;
+ __u32 value = 0;
int fd, err;
/* Invalid key size */
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 6befa870434b..75f4dff7d042 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -450,8 +450,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
attr.size = sizeof(attr);
attr.type = PERF_TYPE_SOFTWARE;
attr.config = PERF_COUNT_SW_CPU_CLOCK;
- attr.freq = 1;
- attr.sample_freq = 10000;
+ attr.sample_period = 100000;
pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
if (!ASSERT_GE(pfd, 0, "perf_fd"))
goto cleanup;
@@ -489,10 +488,28 @@ cleanup:
bpf_link__destroy(link);
}
+static int verify_tracing_link_info(int fd, u64 cookie)
+{
+ struct bpf_link_info info;
+ int err;
+ u32 len = sizeof(info);
+
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ if (!ASSERT_OK(err, "get_link_info"))
+ return -1;
+
+ if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING, "link_type"))
+ return -1;
+
+ ASSERT_EQ(info.tracing.cookie, cookie, "tracing_cookie");
+
+ return 0;
+}
+
static void tracing_subtest(struct test_bpf_cookie *skel)
{
__u64 cookie;
- int prog_fd;
+ int prog_fd, err;
int fentry_fd = -1, fexit_fd = -1, fmod_ret_fd = -1;
LIBBPF_OPTS(bpf_test_run_opts, opts);
LIBBPF_OPTS(bpf_link_create_opts, link_opts);
@@ -507,6 +524,10 @@ static void tracing_subtest(struct test_bpf_cookie *skel)
if (!ASSERT_GE(fentry_fd, 0, "fentry.link_create"))
goto cleanup;
+ err = verify_tracing_link_info(fentry_fd, cookie);
+ if (!ASSERT_OK(err, "verify_tracing_link_info"))
+ goto cleanup;
+
cookie = 0x20000000000000L;
prog_fd = bpf_program__fd(skel->progs.fexit_test1);
link_opts.tracing.cookie = cookie;
@@ -635,10 +656,29 @@ cleanup:
bpf_link__destroy(link);
}
+static int verify_raw_tp_link_info(int fd, u64 cookie)
+{
+ struct bpf_link_info info;
+ int err;
+ u32 len = sizeof(info);
+
+ memset(&info, 0, sizeof(info));
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ if (!ASSERT_OK(err, "get_link_info"))
+ return -1;
+
+ if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type"))
+ return -1;
+
+ ASSERT_EQ(info.raw_tracepoint.cookie, cookie, "raw_tp_cookie");
+
+ return 0;
+}
+
static void raw_tp_subtest(struct test_bpf_cookie *skel)
{
__u64 cookie;
- int prog_fd, link_fd = -1;
+ int err, prog_fd, link_fd = -1;
struct bpf_link *link = NULL;
LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts);
LIBBPF_OPTS(bpf_raw_tracepoint_opts, opts);
@@ -656,6 +696,11 @@ static void raw_tp_subtest(struct test_bpf_cookie *skel)
goto cleanup;
usleep(1); /* trigger */
+
+ err = verify_raw_tp_link_info(link_fd, cookie);
+ if (!ASSERT_OK(err, "verify_raw_tp_link_info"))
+ goto cleanup;
+
close(link_fd); /* detach */
link_fd = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index add4a18c33bd..5225d69bf79b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -323,7 +323,7 @@ static void test_task_pidfd(void)
static void test_task_sleepable(void)
{
struct bpf_iter_tasks *skel;
- int pid, status, err, data_pipe[2], finish_pipe[2], c;
+ int pid, status, err, data_pipe[2], finish_pipe[2], c = 0;
char *test_data = NULL;
char *test_data_long = NULL;
char *data[2];
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
index fe2c502e5089..ecc3d47919ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
@@ -78,7 +78,7 @@ static int test_setup_uffd(void *fault_addr)
}
uffd_register.range.start = (unsigned long)fault_addr;
- uffd_register.range.len = 4096;
+ uffd_register.range.len = getpagesize();
uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING;
if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) {
close(uffd);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index dbd13f8e42a7..dd6512fa652b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -63,6 +63,12 @@ static void test_bpf_nf_ct(int mode)
.repeat = 1,
);
+ if (SYS_NOFAIL("iptables-legacy --version")) {
+ fprintf(stdout, "Missing required iptables-legacy tool\n");
+ test__skip();
+ return;
+ }
+
skel = test_bpf_nf__open_and_load();
if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
new file mode 100644
index 000000000000..730357cd0c9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pkt_sched.h>
+#include <linux/rtnetlink.h>
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "bpf_qdisc_fifo.skel.h"
+#include "bpf_qdisc_fq.skel.h"
+#include "bpf_qdisc_fail__incompl_ops.skel.h"
+
+#define LO_IFINDEX 1
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+
+static void do_test(char *qdisc)
+{
+ DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+ .attach_point = BPF_TC_QDISC,
+ .parent = TC_H_ROOT,
+ .handle = 0x8000000,
+ .qdisc = qdisc);
+ int srv_fd = -1, cli_fd = -1;
+ int err;
+
+ err = bpf_tc_hook_create(&hook);
+ if (!ASSERT_OK(err, "attach qdisc"))
+ return;
+
+ srv_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+ if (!ASSERT_OK_FD(srv_fd, "start server"))
+ goto done;
+
+ cli_fd = connect_to_fd(srv_fd, 0);
+ if (!ASSERT_OK_FD(cli_fd, "connect to client"))
+ goto done;
+
+ err = send_recv_data(srv_fd, cli_fd, total_bytes);
+ ASSERT_OK(err, "send_recv_data");
+
+done:
+ if (srv_fd != -1)
+ close(srv_fd);
+ if (cli_fd != -1)
+ close(cli_fd);
+
+ bpf_tc_hook_destroy(&hook);
+}
+
+static void test_fifo(void)
+{
+ struct bpf_qdisc_fifo *fifo_skel;
+
+ fifo_skel = bpf_qdisc_fifo__open_and_load();
+ if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+ return;
+
+ if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+ goto out;
+
+ do_test("bpf_fifo");
+out:
+ bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_fq(void)
+{
+ struct bpf_qdisc_fq *fq_skel;
+
+ fq_skel = bpf_qdisc_fq__open_and_load();
+ if (!ASSERT_OK_PTR(fq_skel, "bpf_qdisc_fq__open_and_load"))
+ return;
+
+ if (!ASSERT_OK(bpf_qdisc_fq__attach(fq_skel), "bpf_qdisc_fq__attach"))
+ goto out;
+
+ do_test("bpf_fq");
+out:
+ bpf_qdisc_fq__destroy(fq_skel);
+}
+
+static void test_qdisc_attach_to_mq(void)
+{
+ DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook,
+ .attach_point = BPF_TC_QDISC,
+ .parent = TC_H_MAKE(1 << 16, 1),
+ .handle = 0x11 << 16,
+ .qdisc = "bpf_fifo");
+ struct bpf_qdisc_fifo *fifo_skel;
+ int err;
+
+ fifo_skel = bpf_qdisc_fifo__open_and_load();
+ if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+ return;
+
+ if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+ goto out;
+
+ SYS(out, "ip link add veth0 type veth peer veth1");
+ hook.ifindex = if_nametoindex("veth0");
+ SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+ err = bpf_tc_hook_create(&hook);
+ ASSERT_OK(err, "attach qdisc");
+
+ bpf_tc_hook_destroy(&hook);
+
+ SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+ bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_qdisc_attach_to_non_root(void)
+{
+ DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+ .attach_point = BPF_TC_QDISC,
+ .parent = TC_H_MAKE(1 << 16, 1),
+ .handle = 0x11 << 16,
+ .qdisc = "bpf_fifo");
+ struct bpf_qdisc_fifo *fifo_skel;
+ int err;
+
+ fifo_skel = bpf_qdisc_fifo__open_and_load();
+ if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+ return;
+
+ if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+ goto out;
+
+ SYS(out, "tc qdisc add dev lo root handle 1: htb");
+ SYS(out_del_htb, "tc class add dev lo parent 1: classid 1:1 htb rate 75Kbit");
+
+ err = bpf_tc_hook_create(&hook);
+ if (!ASSERT_ERR(err, "attach qdisc"))
+ bpf_tc_hook_destroy(&hook);
+
+out_del_htb:
+ SYS(out, "tc qdisc delete dev lo root htb");
+out:
+ bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_incompl_ops(void)
+{
+ struct bpf_qdisc_fail__incompl_ops *skel;
+ struct bpf_link *link;
+
+ skel = bpf_qdisc_fail__incompl_ops__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "bpf_qdisc_fifo__open_and_load"))
+ return;
+
+ link = bpf_map__attach_struct_ops(skel->maps.test);
+ if (!ASSERT_ERR_PTR(link, "bpf_map__attach_struct_ops"))
+ bpf_link__destroy(link);
+
+ bpf_qdisc_fail__incompl_ops__destroy(skel);
+}
+
+static int get_default_qdisc(char *qdisc_name)
+{
+ FILE *f;
+ int num;
+
+ f = fopen("/proc/sys/net/core/default_qdisc", "r");
+ if (!f)
+ return -errno;
+
+ num = fscanf(f, "%s", qdisc_name);
+ fclose(f);
+
+ return num == 1 ? 0 : -EFAULT;
+}
+
+static void test_default_qdisc_attach_to_mq(void)
+{
+ char default_qdisc[IFNAMSIZ] = {};
+ struct bpf_qdisc_fifo *fifo_skel;
+ struct netns_obj *netns = NULL;
+ int err;
+
+ fifo_skel = bpf_qdisc_fifo__open_and_load();
+ if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+ return;
+
+ if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+ goto out;
+
+ err = get_default_qdisc(default_qdisc);
+ if (!ASSERT_OK(err, "read sysctl net.core.default_qdisc"))
+ goto out;
+
+ err = write_sysctl("/proc/sys/net/core/default_qdisc", "bpf_fifo");
+ if (!ASSERT_OK(err, "write sysctl net.core.default_qdisc"))
+ goto out;
+
+ netns = netns_new("bpf_qdisc_ns", true);
+ if (!ASSERT_OK_PTR(netns, "netns_new"))
+ goto out;
+
+ SYS(out, "ip link add veth0 type veth peer veth1");
+ SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+ ASSERT_EQ(fifo_skel->bss->init_called, true, "init_called");
+
+ SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+ netns_free(netns);
+ if (default_qdisc[0])
+ write_sysctl("/proc/sys/net/core/default_qdisc", default_qdisc);
+
+ bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+void test_ns_bpf_qdisc(void)
+{
+ if (test__start_subtest("fifo"))
+ test_fifo();
+ if (test__start_subtest("fq"))
+ test_fq();
+ if (test__start_subtest("attach to mq"))
+ test_qdisc_attach_to_mq();
+ if (test__start_subtest("attach to non root"))
+ test_qdisc_attach_to_non_root();
+ if (test__start_subtest("incompl_ops"))
+ test_incompl_ops();
+}
+
+void serial_test_bpf_qdisc_default(void)
+{
+ test_default_qdisc_attach_to_mq();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
index d9024c7a892a..5bc15bb6b7ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
@@ -440,6 +440,105 @@ cleanup:
btf__free(btf1);
}
+/* Ensure module split BTF dedup worked correctly; when dedup fails badly
+ * core kernel types are in split BTF also, so ensure that references to
+ * such types point at base - not split - BTF.
+ *
+ * bpf_testmod_test_write() has multiple core kernel type parameters;
+ *
+ * ssize_t
+ * bpf_testmod_test_write(struct file *file, struct kobject *kobj,
+ * struct bin_attribute *bin_attr,
+ * char *buf, loff_t off, size_t len);
+ *
+ * Ensure each of the FUNC_PROTO params is a core kernel type.
+ *
+ * Do the same for
+ *
+ * __bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk);
+ *
+ * ...and
+ *
+ * __bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb);
+ *
+ */
+const char *mod_funcs[] = {
+ "bpf_testmod_test_write",
+ "bpf_kfunc_call_test3",
+ "bpf_kfunc_call_test_pass_ctx"
+};
+
+static void test_split_module(void)
+{
+ struct btf *vmlinux_btf, *btf1 = NULL;
+ int i, nr_base_types;
+
+ vmlinux_btf = btf__load_vmlinux_btf();
+ if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux_btf"))
+ return;
+ nr_base_types = btf__type_cnt(vmlinux_btf);
+ if (!ASSERT_GT(nr_base_types, 0, "nr_base_types"))
+ goto cleanup;
+
+ btf1 = btf__parse_split("/sys/kernel/btf/bpf_testmod", vmlinux_btf);
+ if (!ASSERT_OK_PTR(btf1, "split_btf"))
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(mod_funcs); i++) {
+ const struct btf_param *p;
+ const struct btf_type *t;
+ __u16 vlen;
+ __u32 id;
+ int j;
+
+ id = btf__find_by_name_kind(btf1, mod_funcs[i], BTF_KIND_FUNC);
+ if (!ASSERT_GE(id, nr_base_types, "func_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf1, id);
+ if (!ASSERT_OK_PTR(t, "func_id_type"))
+ goto cleanup;
+ t = btf__type_by_id(btf1, t->type);
+ if (!ASSERT_OK_PTR(t, "func_proto_id_type"))
+ goto cleanup;
+ if (!ASSERT_EQ(btf_is_func_proto(t), true, "is_func_proto"))
+ goto cleanup;
+ vlen = btf_vlen(t);
+
+ for (j = 0, p = btf_params(t); j < vlen; j++, p++) {
+ /* bpf_testmod uses resilient split BTF, so any
+ * reference types will be added to split BTF and their
+ * associated targets will be base BTF types; for example
+ * for a "struct sock *" the PTR will be in split BTF
+ * while the "struct sock" will be in base.
+ *
+ * In some cases like loff_t we have to resolve
+ * multiple typedefs hence the while() loop below.
+ *
+ * Note that resilient split BTF generation depends
+ * on pahole version, so we do not assert that
+ * reference types are in split BTF, as if pahole
+ * does not support resilient split BTF they will
+ * also be base BTF types.
+ */
+ id = p->type;
+ do {
+ t = btf__type_by_id(btf1, id);
+ if (!ASSERT_OK_PTR(t, "param_ref_type"))
+ goto cleanup;
+ if (!btf_is_mod(t) && !btf_is_ptr(t) && !btf_is_typedef(t))
+ break;
+ id = t->type;
+ } while (true);
+
+ if (!ASSERT_LT(id, nr_base_types, "verify_base_type"))
+ goto cleanup;
+ }
+ }
+cleanup:
+ btf__free(btf1);
+ btf__free(vmlinux_btf);
+}
+
void test_btf_dedup_split()
{
if (test__start_subtest("split_simple"))
@@ -450,4 +549,6 @@ void test_btf_dedup_split()
test_split_fwd_resolve();
if (test__start_subtest("split_dup_struct_in_cu"))
test_split_dup_struct_in_cu();
+ if (test__start_subtest("split_module"))
+ test_split_module();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index c0a776feec23..10cba526d3e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -63,7 +63,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
/* tests with t->known_ptr_sz have no "long" or "unsigned long" type,
* so it's impossible to determine correct pointer size; but if they
- * do, it should be 8 regardless of host architecture, becaues BPF
+ * do, it should be 8 regardless of host architecture, because BPF
* target is always 64-bit
*/
if (!t->known_ptr_sz) {
@@ -879,6 +879,122 @@ static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
"static int bpf_cgrp_storage_busy = (int)2", 2);
}
+struct btf_dump_string_ctx {
+ struct btf *btf;
+ struct btf_dump *d;
+ char *str;
+ struct btf_dump_type_data_opts *opts;
+ int array_id;
+};
+
+static int btf_dump_one_string(struct btf_dump_string_ctx *ctx,
+ char *ptr, size_t ptr_sz,
+ const char *expected_val)
+{
+ size_t type_sz;
+ int ret;
+
+ ctx->str[0] = '\0';
+ type_sz = btf__resolve_size(ctx->btf, ctx->array_id);
+ ret = btf_dump__dump_type_data(ctx->d, ctx->array_id, ptr, ptr_sz, ctx->opts);
+ if (type_sz <= ptr_sz) {
+ if (!ASSERT_EQ(ret, type_sz, "failed/unexpected type_sz"))
+ return -EINVAL;
+ }
+ if (!ASSERT_STREQ(ctx->str, expected_val, "ensure expected/actual match"))
+ return -EFAULT;
+ return 0;
+}
+
+static void btf_dump_strings(struct btf_dump_string_ctx *ctx)
+{
+ struct btf_dump_type_data_opts *opts = ctx->opts;
+
+ opts->emit_strings = true;
+
+ opts->compact = true;
+ opts->emit_zeroes = false;
+
+ opts->skip_names = false;
+ btf_dump_one_string(ctx, "foo", 4, "(char[4])\"foo\"");
+
+ opts->skip_names = true;
+ btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+ /* This should have no effect. */
+ opts->emit_zeroes = false;
+ btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+ /* This should have no effect. */
+ opts->compact = false;
+ btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+ /* Non-printable characters come out as hex. */
+ btf_dump_one_string(ctx, "fo\xff", 4, "\"fo\\xff\"");
+ btf_dump_one_string(ctx, "fo\x7", 4, "\"fo\\x07\"");
+
+ /*
+ * Strings that are too long for the specified type ("char[4]")
+ * should fall back to the current behavior.
+ */
+ opts->compact = true;
+ btf_dump_one_string(ctx, "abcde", 6, "['a','b','c','d',]");
+
+ /*
+ * Strings that are too short for the specified type ("char[4]")
+ * should work normally.
+ */
+ btf_dump_one_string(ctx, "ab", 3, "\"ab\"");
+
+ /* Non-NUL-terminated arrays don't get printed as strings. */
+ char food[4] = { 'f', 'o', 'o', 'd' };
+ char bye[3] = { 'b', 'y', 'e' };
+
+ btf_dump_one_string(ctx, food, 4, "['f','o','o','d',]");
+ btf_dump_one_string(ctx, bye, 3, "['b','y','e',]");
+
+ /* The embedded NUL should terminate the string. */
+ char embed[4] = { 'f', 'o', '\0', 'd' };
+
+ btf_dump_one_string(ctx, embed, 4, "\"fo\"");
+}
+
+static void test_btf_dump_string_data(void)
+{
+ struct test_ctx t = {};
+ char str[STRSIZE];
+ struct btf_dump *d;
+ DECLARE_LIBBPF_OPTS(btf_dump_type_data_opts, opts);
+ struct btf_dump_string_ctx ctx;
+ int char_id, int_id, array_id;
+
+ if (test_ctx__init(&t))
+ return;
+
+ d = btf_dump__new(t.btf, btf_dump_snprintf, str, NULL);
+ if (!ASSERT_OK_PTR(d, "could not create BTF dump"))
+ return;
+
+ /* Generate BTF for a four-element char array. */
+ char_id = btf__add_int(t.btf, "char", 1, BTF_INT_CHAR);
+ ASSERT_EQ(char_id, 1, "char_id");
+ int_id = btf__add_int(t.btf, "int", 4, BTF_INT_SIGNED);
+ ASSERT_EQ(int_id, 2, "int_id");
+ array_id = btf__add_array(t.btf, int_id, char_id, 4);
+ ASSERT_EQ(array_id, 3, "array_id");
+
+ ctx.btf = t.btf;
+ ctx.d = d;
+ ctx.str = str;
+ ctx.opts = &opts;
+ ctx.array_id = array_id;
+
+ btf_dump_strings(&ctx);
+
+ btf_dump__free(d);
+ test_ctx__free(&t);
+}
+
static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str,
const char *name, const char *expected_val,
void *data, size_t data_sz)
@@ -970,6 +1086,8 @@ void test_btf_dump() {
test_btf_dump_struct_data(btf, d, str);
if (test__start_subtest("btf_dump: var_data"))
test_btf_dump_var_data(btf, d, str);
+ if (test__start_subtest("btf_dump: string_data"))
+ test_btf_dump_string_data();
btf_dump__free(d);
btf__free(btf);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c
index eef1158676ed..3696fb9a05ed 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c
@@ -12,10 +12,11 @@ static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
vfprintf(ctx, fmt, args);
}
-void test_btf_split() {
+static void __test_btf_split(bool multi)
+{
struct btf_dump *d = NULL;
const struct btf_type *t;
- struct btf *btf1, *btf2;
+ struct btf *btf1, *btf2, *btf3 = NULL;
int str_off, i, err;
btf1 = btf__new_empty();
@@ -63,14 +64,46 @@ void test_btf_split() {
ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen");
ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name");
+ if (multi) {
+ btf3 = btf__new_empty_split(btf2);
+ if (!ASSERT_OK_PTR(btf3, "multi_split_btf"))
+ goto cleanup;
+ } else {
+ btf3 = btf2;
+ }
+
+ btf__add_union(btf3, "u1", 16); /* [5] union u1 { */
+ btf__add_field(btf3, "f1", 4, 0, 0); /* struct s2 f1; */
+ btf__add_field(btf3, "uf2", 1, 0, 0); /* int f2; */
+ /* } */
+
+ if (multi) {
+ t = btf__type_by_id(btf2, 5);
+ ASSERT_NULL(t, "multisplit_type_in_first_split");
+ }
+
+ t = btf__type_by_id(btf3, 5);
+ if (!ASSERT_OK_PTR(t, "split_union_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_union(t), true, "split_union_kind");
+ ASSERT_EQ(btf_vlen(t), 2, "split_union_vlen");
+ ASSERT_STREQ(btf__str_by_offset(btf3, t->name_off), "u1", "split_union_name");
+ ASSERT_EQ(btf__type_cnt(btf3), 6, "split_type_cnt");
+
+ t = btf__type_by_id(btf3, 1);
+ if (!ASSERT_OK_PTR(t, "split_base_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_int(t), true, "split_base_int");
+ ASSERT_STREQ(btf__str_by_offset(btf3, t->name_off), "int", "split_base_type_name");
+
/* BTF-to-C dump of split BTF */
dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
return;
- d = btf_dump__new(btf2, btf_dump_printf, dump_buf_file, NULL);
+ d = btf_dump__new(btf3, btf_dump_printf, dump_buf_file, NULL);
if (!ASSERT_OK_PTR(d, "btf_dump__new"))
goto cleanup;
- for (i = 1; i < btf__type_cnt(btf2); i++) {
+ for (i = 1; i < btf__type_cnt(btf3); i++) {
err = btf_dump__dump_type(d, i);
ASSERT_OK(err, "dump_type_ok");
}
@@ -79,12 +112,15 @@ void test_btf_split() {
ASSERT_STREQ(dump_buf,
"struct s1 {\n"
" int f1;\n"
-"};\n"
-"\n"
+"};\n\n"
"struct s2 {\n"
" struct s1 f1;\n"
" int f2;\n"
" int *f3;\n"
+"};\n\n"
+"union u1 {\n"
+" struct s2 f1;\n"
+" int uf2;\n"
"};\n\n", "c_dump");
cleanup:
@@ -94,4 +130,14 @@ cleanup:
btf_dump__free(d);
btf__free(btf1);
btf__free(btf2);
+ if (btf2 != btf3)
+ btf__free(btf3);
+}
+
+void test_btf_split(void)
+{
+ if (test__start_subtest("single_split"))
+ __test_btf_split(false);
+ if (test__start_subtest("multi_split"))
+ __test_btf_split(true);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c b/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c
new file mode 100644
index 000000000000..3923e64c4c1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright (c) 2025 Isovalent */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+static void test_btf_mmap_sysfs(const char *path, struct btf *base)
+{
+ struct stat st;
+ __u64 btf_size, end;
+ void *raw_data = NULL;
+ int fd = -1;
+ long page_size;
+ struct btf *btf = NULL;
+
+ page_size = sysconf(_SC_PAGESIZE);
+ if (!ASSERT_GE(page_size, 0, "get_page_size"))
+ goto cleanup;
+
+ if (!ASSERT_OK(stat(path, &st), "stat_btf"))
+ goto cleanup;
+
+ btf_size = st.st_size;
+ end = (btf_size + page_size - 1) / page_size * page_size;
+
+ fd = open(path, O_RDONLY);
+ if (!ASSERT_GE(fd, 0, "open_btf"))
+ goto cleanup;
+
+ raw_data = mmap(NULL, btf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+ if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_writable"))
+ goto cleanup;
+
+ raw_data = mmap(NULL, btf_size, PROT_READ, MAP_SHARED, fd, 0);
+ if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_shared"))
+ goto cleanup;
+
+ raw_data = mmap(NULL, end + 1, PROT_READ, MAP_PRIVATE, fd, 0);
+ if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_invalid_size"))
+ goto cleanup;
+
+ raw_data = mmap(NULL, end, PROT_READ, MAP_PRIVATE, fd, 0);
+ if (!ASSERT_OK_PTR(raw_data, "mmap_btf"))
+ goto cleanup;
+
+ if (!ASSERT_EQ(mprotect(raw_data, btf_size, PROT_READ | PROT_WRITE), -1,
+ "mprotect_writable"))
+ goto cleanup;
+
+ if (!ASSERT_EQ(mprotect(raw_data, btf_size, PROT_READ | PROT_EXEC), -1,
+ "mprotect_executable"))
+ goto cleanup;
+
+ /* Check padding is zeroed */
+ for (int i = btf_size; i < end; i++) {
+ if (((__u8 *)raw_data)[i] != 0) {
+ PRINT_FAIL("tail of BTF is not zero at page offset %d\n", i);
+ goto cleanup;
+ }
+ }
+
+ btf = btf__new_split(raw_data, btf_size, base);
+ if (!ASSERT_OK_PTR(btf, "parse_btf"))
+ goto cleanup;
+
+cleanup:
+ btf__free(btf);
+ if (raw_data && raw_data != MAP_FAILED)
+ munmap(raw_data, btf_size);
+ if (fd >= 0)
+ close(fd);
+}
+
+void test_btf_sysfs(void)
+{
+ test_btf_mmap_sysfs("/sys/kernel/btf/vmlinux", NULL);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c
new file mode 100644
index 000000000000..bb60704a3ef9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c
@@ -0,0 +1,617 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_mprog.skel.h"
+
+static void assert_mprog_count(int cg, int atype, int expected)
+{
+ __u32 count = 0, attach_flags = 0;
+ int err;
+
+ err = bpf_prog_query(cg, atype, 0, &attach_flags,
+ NULL, &count);
+ ASSERT_EQ(count, expected, "count");
+ ASSERT_EQ(err, 0, "prog_query");
+}
+
+static void test_prog_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+ LIBBPF_OPTS(bpf_prog_query_opts, optq);
+ __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+ struct cgroup_mprog *skel;
+ __u32 prog_ids[10];
+ int cg, err;
+
+ cg = test__join_cgroup("/prog_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /prog_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+ fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+ fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+ id1 = id_from_prog_fd(fd1);
+ id2 = id_from_prog_fd(fd2);
+ id3 = id_from_prog_fd(fd3);
+ id4 = id_from_prog_fd(fd4);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE,
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd2, fd1] */
+ err = bpf_prog_attach_opts(fd2, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd2, fd3, fd1] */
+ err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ err = bpf_prog_attach_opts(fd4, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ /* retrieve optq.prog_cnt */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ /* optq.prog_cnt will be used in below query */
+ memset(prog_ids, 0, sizeof(prog_ids));
+ optq.prog_ids = prog_ids;
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ ASSERT_EQ(optq.count, 4, "count");
+ ASSERT_EQ(optq.revision, 5, "revision");
+ ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+ ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+ ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]");
+ ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+ ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+ ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+cleanup4:
+ optd.expected_revision = 5;
+ err = bpf_prog_detach_opts(fd4, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ LIBBPF_OPTS_RESET(optd);
+ err = bpf_prog_detach_opts(fd3, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 2);
+
+ /* Check revision after two detach operations */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ ASSERT_OK(err, "prog_query");
+ ASSERT_EQ(optq.revision, 7, "revision");
+
+cleanup2:
+ err = bpf_prog_detach_opts(fd2, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ err = bpf_prog_detach_opts(fd1, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_link_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_cgroup_opts, opta);
+ LIBBPF_OPTS(bpf_cgroup_opts, optd);
+ LIBBPF_OPTS(bpf_prog_query_opts, optq);
+ struct bpf_link *link1, *link2, *link3, *link4;
+ __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+ struct cgroup_mprog *skel;
+ __u32 prog_ids[10];
+ int cg, err;
+
+ cg = test__join_cgroup("/link_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /link_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+ fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+ fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+ id1 = id_from_prog_fd(fd1);
+ id2 = id_from_prog_fd(fd2);
+ id3 = id_from_prog_fd(fd3);
+ id4 = id_from_prog_fd(fd4);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta);
+ if (!ASSERT_OK_PTR(link1, "link_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_BEFORE | BPF_F_LINK,
+ .relative_id = id_from_link_fd(bpf_link__fd(link1)),
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd2, fd1] */
+ link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta);
+ if (!ASSERT_OK_PTR(link2, "link_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_AFTER | BPF_F_LINK,
+ .relative_fd = bpf_link__fd(link2),
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd2, fd3, fd1] */
+ link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+ if (!ASSERT_OK_PTR(link3, "link_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta);
+ if (!ASSERT_OK_PTR(link4, "link_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ /* retrieve optq.prog_cnt */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ /* optq.prog_cnt will be used in below query */
+ memset(prog_ids, 0, sizeof(prog_ids));
+ optq.prog_ids = prog_ids;
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ ASSERT_EQ(optq.count, 4, "count");
+ ASSERT_EQ(optq.revision, 5, "revision");
+ ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+ ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+ ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]");
+ ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+ ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+ ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+cleanup4:
+ bpf_link__destroy(link4);
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ bpf_link__destroy(link3);
+ assert_mprog_count(cg, atype, 2);
+
+ /* Check revision after two detach operations */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ ASSERT_OK(err, "prog_query");
+ ASSERT_EQ(optq.revision, 7, "revision");
+
+cleanup2:
+ bpf_link__destroy(link2);
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ bpf_link__destroy(link1);
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_preorder_prog_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+ __u32 fd1, fd2, fd3, fd4;
+ struct cgroup_mprog *skel;
+ int cg, err;
+
+ cg = test__join_cgroup("/preorder_prog_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_prog_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+ fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+ fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER,
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd1, fd2] */
+ err = bpf_prog_attach_opts(fd2, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+ if (!ASSERT_EQ(err, -EINVAL, "prog_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_PREORDER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd1, fd2, fd3] */
+ err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ err = bpf_prog_attach_opts(fd4, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ err = bpf_prog_detach_opts(fd4, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ err = bpf_prog_detach_opts(fd3, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 2);
+
+cleanup2:
+ err = bpf_prog_detach_opts(fd2, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ err = bpf_prog_detach_opts(fd1, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_preorder_link_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_cgroup_opts, opta);
+ struct bpf_link *link1, *link2, *link3, *link4;
+ struct cgroup_mprog *skel;
+ __u32 fd2;
+ int cg;
+
+ cg = test__join_cgroup("/preorder_link_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_link_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta);
+ if (!ASSERT_OK_PTR(link1, "link_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_PREORDER,
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd1, fd2] */
+ link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta);
+ if (!ASSERT_OK_PTR(link2, "link_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_AFTER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+ if (!ASSERT_ERR_PTR(link3, "link_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_AFTER | BPF_F_PREORDER | BPF_F_LINK,
+ .relative_fd = bpf_link__fd(link2),
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd1, fd2, fd3] */
+ link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+ if (!ASSERT_OK_PTR(link3, "link_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta);
+ if (!ASSERT_OK_PTR(link4, "prog_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ bpf_link__destroy(link4);
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ bpf_link__destroy(link3);
+ assert_mprog_count(cg, atype, 2);
+
+cleanup2:
+ bpf_link__destroy(link2);
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ bpf_link__destroy(link1);
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_invalid_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ __u32 fd1, fd2, id2;
+ struct cgroup_mprog *skel;
+ int cg, err;
+
+ cg = test__join_cgroup("/invalid_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /invalid_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+
+ id2 = id_from_prog_fd(fd2);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_ID,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_ID,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_LINK,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE,
+ .relative_fd = fd1,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ .relative_fd = fd1,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup;
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE | BPF_F_AFTER,
+ .replace_prog_fd = fd1,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 1);
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+void test_cgroup_mprog_opts(void)
+{
+ if (test__start_subtest("prog_attach_detach"))
+ test_prog_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("link_attach_detach"))
+ test_link_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("preorder_prog_attach_detach"))
+ test_preorder_prog_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("preorder_link_attach_detach"))
+ test_preorder_link_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("invalid_attach_detach"))
+ test_invalid_attach_detach(BPF_CGROUP_GETSOCKOPT);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c
new file mode 100644
index 000000000000..a36d2e968bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_preorder.skel.h"
+
+static int run_getsockopt_test(int cg_parent, int sock_fd, bool has_relative_fd)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opts);
+ enum bpf_attach_type prog_p_atype, prog_p2_atype;
+ int prog_p_fd, prog_p2_fd;
+ struct cgroup_preorder *skel = NULL;
+ struct bpf_program *prog;
+ __u8 *result, buf;
+ socklen_t optlen = 1;
+ int err = 0;
+
+ skel = cgroup_preorder__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load"))
+ return 0;
+
+ LIBBPF_OPTS_RESET(opts);
+ opts.flags = BPF_F_ALLOW_MULTI;
+ prog = skel->progs.parent;
+ prog_p_fd = bpf_program__fd(prog);
+ prog_p_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent"))
+ goto close_skel;
+
+ opts.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE;
+ if (has_relative_fd)
+ opts.relative_fd = prog_p_fd;
+ prog = skel->progs.parent_2;
+ prog_p2_fd = bpf_program__fd(prog);
+ prog_p2_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2"))
+ goto detach_parent;
+
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (!ASSERT_OK(err, "getsockopt"))
+ goto detach_parent_2;
+
+ result = skel->bss->result;
+ ASSERT_TRUE(result[0] == 4 && result[1] == 3, "result values");
+
+detach_parent_2:
+ ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype),
+ "bpf_prog_detach2-parent_2");
+detach_parent:
+ ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype),
+ "bpf_prog_detach2-parent");
+close_skel:
+ cgroup_preorder__destroy(skel);
+ return err;
+}
+
+void test_cgroup_mprog_ordering(void)
+{
+ int cg_parent = -1, sock_fd = -1;
+
+ cg_parent = test__join_cgroup("/parent");
+ if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
+ goto out;
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (!ASSERT_GE(sock_fd, 0, "socket"))
+ goto out;
+
+ ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, false), "getsockopt_test_1");
+ ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, true), "getsockopt_test_2");
+
+out:
+ close(sock_fd);
+ close(cg_parent);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
new file mode 100644
index 000000000000..5ad904e9d15d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+
+#include "read_cgroupfs_xattr.skel.h"
+#include "cgroup_read_xattr.skel.h"
+
+#define CGROUP_FS_PARENT "foo/"
+#define CGROUP_FS_CHILD CGROUP_FS_PARENT "bar/"
+#define TMP_FILE "/tmp/selftests_cgroup_xattr"
+
+static const char xattr_value_a[] = "bpf_selftest_value_a";
+static const char xattr_value_b[] = "bpf_selftest_value_b";
+static const char xattr_name[] = "user.bpf_test";
+
+static void test_read_cgroup_xattr(void)
+{
+ int tmp_fd, parent_cgroup_fd = -1, child_cgroup_fd = -1;
+ struct read_cgroupfs_xattr *skel = NULL;
+
+ parent_cgroup_fd = test__join_cgroup(CGROUP_FS_PARENT);
+ if (!ASSERT_OK_FD(parent_cgroup_fd, "create parent cgroup"))
+ return;
+ if (!ASSERT_OK(set_cgroup_xattr(CGROUP_FS_PARENT, xattr_name, xattr_value_a),
+ "set parent xattr"))
+ goto out;
+
+ child_cgroup_fd = test__join_cgroup(CGROUP_FS_CHILD);
+ if (!ASSERT_OK_FD(child_cgroup_fd, "create child cgroup"))
+ goto out;
+ if (!ASSERT_OK(set_cgroup_xattr(CGROUP_FS_CHILD, xattr_name, xattr_value_b),
+ "set child xattr"))
+ goto out;
+
+ skel = read_cgroupfs_xattr__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "read_cgroupfs_xattr__open_and_load"))
+ goto out;
+
+ skel->bss->target_pid = sys_gettid();
+
+ if (!ASSERT_OK(read_cgroupfs_xattr__attach(skel), "read_cgroupfs_xattr__attach"))
+ goto out;
+
+ tmp_fd = open(TMP_FILE, O_RDONLY | O_CREAT);
+ ASSERT_OK_FD(tmp_fd, "open tmp file");
+ close(tmp_fd);
+
+ ASSERT_TRUE(skel->bss->found_value_a, "found_value_a");
+ ASSERT_TRUE(skel->bss->found_value_b, "found_value_b");
+
+out:
+ close(child_cgroup_fd);
+ close(parent_cgroup_fd);
+ read_cgroupfs_xattr__destroy(skel);
+ unlink(TMP_FILE);
+}
+
+void test_cgroup_xattr(void)
+{
+ RUN_TESTS(cgroup_read_xattr);
+
+ if (test__start_subtest("read_cgroupfs_xattr"))
+ test_read_cgroup_xattr();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
index adda85f97058..4b42fbc96efc 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
@@ -4,6 +4,8 @@
#define _GNU_SOURCE
#include <cgroup_helpers.h>
#include <test_progs.h>
+#include <sched.h>
+#include <sys/wait.h>
#include "cgrp_kfunc_failure.skel.h"
#include "cgrp_kfunc_success.skel.h"
@@ -87,6 +89,72 @@ static const char * const success_tests[] = {
"test_cgrp_from_id",
};
+static void test_cgrp_from_id_ns(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ struct cgrp_kfunc_success *skel;
+ struct bpf_program *prog;
+ int pid, pipe_fd[2];
+
+ skel = open_load_cgrp_kfunc_skel();
+ if (!ASSERT_OK_PTR(skel, "open_load_skel"))
+ return;
+
+ if (!ASSERT_OK(skel->bss->err, "pre_mkdir_err"))
+ goto cleanup;
+
+ prog = skel->progs.test_cgrp_from_id_ns;
+
+ if (!ASSERT_OK(pipe(pipe_fd), "pipe"))
+ goto cleanup;
+
+ pid = fork();
+ if (!ASSERT_GE(pid, 0, "fork result")) {
+ close(pipe_fd[0]);
+ close(pipe_fd[1]);
+ goto cleanup;
+ }
+
+ if (pid == 0) {
+ int ret = 0;
+
+ close(pipe_fd[0]);
+
+ if (!ASSERT_GE(cgroup_setup_and_join("cgrp_from_id_ns"), 0, "join cgroup"))
+ exit(1);
+
+ if (!ASSERT_OK(unshare(CLONE_NEWCGROUP), "unshare cgns"))
+ exit(1);
+
+ ret = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts);
+ if (!ASSERT_OK(ret, "test run ret"))
+ exit(1);
+
+ if (!ASSERT_OK(opts.retval, "test run retval"))
+ exit(1);
+
+ if (!ASSERT_EQ(write(pipe_fd[1], &ret, sizeof(ret)), sizeof(ret), "write pipe"))
+ exit(1);
+
+ exit(0);
+ } else {
+ int res;
+
+ close(pipe_fd[1]);
+
+ ASSERT_EQ(read(pipe_fd[0], &res, sizeof(res)), sizeof(res), "read res");
+ ASSERT_EQ(waitpid(pid, NULL, 0), pid, "wait on child");
+
+ remove_cgroup_pid("cgrp_from_id_ns", pid);
+
+ ASSERT_OK(res, "result from run");
+ }
+
+ close(pipe_fd[0]);
+cleanup:
+ cgrp_kfunc_success__destroy(skel);
+}
+
void test_cgrp_kfunc(void)
{
int i, err;
@@ -102,6 +170,9 @@ void test_cgrp_kfunc(void)
run_success_test(success_tests[i]);
}
+ if (test__start_subtest("test_cgrp_from_id_ns"))
+ test_cgrp_from_id_ns();
+
RUN_TESTS(cgrp_kfunc_failure);
cleanup:
diff --git a/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
new file mode 100644
index 000000000000..6c2b0c3dbcd8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "dmabuf_iter.skel.h"
+
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/udmabuf.h>
+
+static int udmabuf = -1;
+static const char udmabuf_test_buffer_name[DMA_BUF_NAME_LEN] = "udmabuf_test_buffer_for_iter";
+static size_t udmabuf_test_buffer_size;
+static int sysheap_dmabuf = -1;
+static const char sysheap_test_buffer_name[DMA_BUF_NAME_LEN] = "sysheap_test_buffer_for_iter";
+static size_t sysheap_test_buffer_size;
+
+static int create_udmabuf(void)
+{
+ struct udmabuf_create create;
+ int dev_udmabuf, memfd, local_udmabuf;
+
+ udmabuf_test_buffer_size = 10 * getpagesize();
+
+ if (!ASSERT_LE(sizeof(udmabuf_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG"))
+ return -1;
+
+ memfd = memfd_create("memfd_test", MFD_ALLOW_SEALING);
+ if (!ASSERT_OK_FD(memfd, "memfd_create"))
+ return -1;
+
+ if (!ASSERT_OK(ftruncate(memfd, udmabuf_test_buffer_size), "ftruncate"))
+ goto close_memfd;
+
+ if (!ASSERT_OK(fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK), "seal"))
+ goto close_memfd;
+
+ dev_udmabuf = open("/dev/udmabuf", O_RDONLY);
+ if (!ASSERT_OK_FD(dev_udmabuf, "open udmabuf"))
+ goto close_memfd;
+
+ memset(&create, 0, sizeof(create));
+ create.memfd = memfd;
+ create.flags = UDMABUF_FLAGS_CLOEXEC;
+ create.offset = 0;
+ create.size = udmabuf_test_buffer_size;
+
+ local_udmabuf = ioctl(dev_udmabuf, UDMABUF_CREATE, &create);
+ close(dev_udmabuf);
+ if (!ASSERT_OK_FD(local_udmabuf, "udmabuf_create"))
+ goto close_memfd;
+
+ if (!ASSERT_OK(ioctl(local_udmabuf, DMA_BUF_SET_NAME_B, udmabuf_test_buffer_name), "name"))
+ goto close_udmabuf;
+
+ return local_udmabuf;
+
+close_udmabuf:
+ close(local_udmabuf);
+close_memfd:
+ close(memfd);
+ return -1;
+}
+
+static int create_sys_heap_dmabuf(void)
+{
+ sysheap_test_buffer_size = 20 * getpagesize();
+
+ struct dma_heap_allocation_data data = {
+ .len = sysheap_test_buffer_size,
+ .fd = 0,
+ .fd_flags = O_RDWR | O_CLOEXEC,
+ .heap_flags = 0,
+ };
+ int heap_fd, ret;
+
+ if (!ASSERT_LE(sizeof(sysheap_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG"))
+ return -1;
+
+ heap_fd = open("/dev/dma_heap/system", O_RDONLY);
+ if (!ASSERT_OK_FD(heap_fd, "open dma heap"))
+ return -1;
+
+ ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, &data);
+ close(heap_fd);
+ if (!ASSERT_OK(ret, "syheap alloc"))
+ return -1;
+
+ if (!ASSERT_OK(ioctl(data.fd, DMA_BUF_SET_NAME_B, sysheap_test_buffer_name), "name"))
+ goto close_sysheap_dmabuf;
+
+ return data.fd;
+
+close_sysheap_dmabuf:
+ close(data.fd);
+ return -1;
+}
+
+static int create_test_buffers(void)
+{
+ udmabuf = create_udmabuf();
+ sysheap_dmabuf = create_sys_heap_dmabuf();
+
+ if (udmabuf < 0 || sysheap_dmabuf < 0)
+ return -1;
+
+ return 0;
+}
+
+static void destroy_test_buffers(void)
+{
+ close(udmabuf);
+ udmabuf = -1;
+
+ close(sysheap_dmabuf);
+ sysheap_dmabuf = -1;
+}
+
+enum Fields { INODE, SIZE, NAME, EXPORTER, FIELD_COUNT };
+struct DmabufInfo {
+ unsigned long inode;
+ unsigned long size;
+ char name[DMA_BUF_NAME_LEN];
+ char exporter[32];
+};
+
+static bool check_dmabuf_info(const struct DmabufInfo *bufinfo,
+ unsigned long size,
+ const char *name, const char *exporter)
+{
+ return size == bufinfo->size &&
+ !strcmp(name, bufinfo->name) &&
+ !strcmp(exporter, bufinfo->exporter);
+}
+
+static void subtest_dmabuf_iter_check_no_infinite_reads(struct dmabuf_iter *skel)
+{
+ int iter_fd;
+ char buf[256];
+
+ iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
+ if (!ASSERT_OK_FD(iter_fd, "iter_create"))
+ return;
+
+ while (read(iter_fd, buf, sizeof(buf)) > 0)
+ ; /* Read out all contents */
+
+ /* Next reads should return 0 */
+ ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
+
+ close(iter_fd);
+}
+
+static void subtest_dmabuf_iter_check_default_iter(struct dmabuf_iter *skel)
+{
+ bool found_test_sysheap_dmabuf = false;
+ bool found_test_udmabuf = false;
+ struct DmabufInfo bufinfo;
+ size_t linesize = 0;
+ char *line = NULL;
+ FILE *iter_file;
+ int iter_fd, f = INODE;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
+ if (!ASSERT_OK_FD(iter_fd, "iter_create"))
+ return;
+
+ iter_file = fdopen(iter_fd, "r");
+ if (!ASSERT_OK_PTR(iter_file, "fdopen"))
+ goto close_iter_fd;
+
+ while (getline(&line, &linesize, iter_file) != -1) {
+ if (f % FIELD_COUNT == INODE) {
+ ASSERT_EQ(sscanf(line, "%ld", &bufinfo.inode), 1,
+ "read inode");
+ } else if (f % FIELD_COUNT == SIZE) {
+ ASSERT_EQ(sscanf(line, "%ld", &bufinfo.size), 1,
+ "read size");
+ } else if (f % FIELD_COUNT == NAME) {
+ ASSERT_EQ(sscanf(line, "%s", bufinfo.name), 1,
+ "read name");
+ } else if (f % FIELD_COUNT == EXPORTER) {
+ ASSERT_EQ(sscanf(line, "%31s", bufinfo.exporter), 1,
+ "read exporter");
+
+ if (check_dmabuf_info(&bufinfo,
+ sysheap_test_buffer_size,
+ sysheap_test_buffer_name,
+ "system"))
+ found_test_sysheap_dmabuf = true;
+ else if (check_dmabuf_info(&bufinfo,
+ udmabuf_test_buffer_size,
+ udmabuf_test_buffer_name,
+ "udmabuf"))
+ found_test_udmabuf = true;
+ }
+ ++f;
+ }
+
+ ASSERT_EQ(f % FIELD_COUNT, INODE, "number of fields");
+
+ ASSERT_TRUE(found_test_sysheap_dmabuf, "found_test_sysheap_dmabuf");
+ ASSERT_TRUE(found_test_udmabuf, "found_test_udmabuf");
+
+ free(line);
+ fclose(iter_file);
+close_iter_fd:
+ close(iter_fd);
+}
+
+static void subtest_dmabuf_iter_check_open_coded(struct dmabuf_iter *skel, int map_fd)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ char key[DMA_BUF_NAME_LEN];
+ int err, fd;
+ bool found;
+
+ /* No need to attach it, just run it directly */
+ fd = bpf_program__fd(skel->progs.iter_dmabuf_for_each);
+
+ err = bpf_prog_test_run_opts(fd, &topts);
+ if (!ASSERT_OK(err, "test_run_opts err"))
+ return;
+ if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+ return;
+
+ if (!ASSERT_OK(bpf_map_get_next_key(map_fd, NULL, key), "get next key"))
+ return;
+
+ do {
+ ASSERT_OK(bpf_map_lookup_elem(map_fd, key, &found), "lookup");
+ ASSERT_TRUE(found, "found test buffer");
+ } while (bpf_map_get_next_key(map_fd, key, key));
+}
+
+void test_dmabuf_iter(void)
+{
+ struct dmabuf_iter *skel = NULL;
+ int map_fd;
+ const bool f = false;
+
+ skel = dmabuf_iter__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "dmabuf_iter__open_and_load"))
+ return;
+
+ map_fd = bpf_map__fd(skel->maps.testbuf_hash);
+ if (!ASSERT_OK_FD(map_fd, "map_fd"))
+ goto destroy_skel;
+
+ if (!ASSERT_OK(bpf_map_update_elem(map_fd, udmabuf_test_buffer_name, &f, BPF_ANY),
+ "insert udmabuf"))
+ goto destroy_skel;
+ if (!ASSERT_OK(bpf_map_update_elem(map_fd, sysheap_test_buffer_name, &f, BPF_ANY),
+ "insert sysheap buffer"))
+ goto destroy_skel;
+
+ if (!ASSERT_OK(create_test_buffers(), "create_test_buffers"))
+ goto destroy;
+
+ if (!ASSERT_OK(dmabuf_iter__attach(skel), "skel_attach"))
+ goto destroy;
+
+ if (test__start_subtest("no_infinite_reads"))
+ subtest_dmabuf_iter_check_no_infinite_reads(skel);
+ if (test__start_subtest("default_iter"))
+ subtest_dmabuf_iter_check_default_iter(skel);
+ if (test__start_subtest("open_coded"))
+ subtest_dmabuf_iter_check_open_coded(skel, map_fd);
+
+destroy:
+ destroy_test_buffers();
+destroy_skel:
+ dmabuf_iter__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index e29cc16124c2..b9f86cb91e81 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -21,9 +21,19 @@ static struct {
{"test_dynptr_data", SETUP_SYSCALL_SLEEP},
{"test_dynptr_copy", SETUP_SYSCALL_SLEEP},
{"test_dynptr_copy_xdp", SETUP_XDP_PROG},
+ {"test_dynptr_memset_zero", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_memset_notzero", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_memset_zero_offset", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_memset_zero_adjusted", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_memset_overflow", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_memset_overflow_offset", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_memset_readonly", SETUP_SKB_PROG},
+ {"test_dynptr_memset_xdp_chunks", SETUP_XDP_PROG},
{"test_ringbuf", SETUP_SYSCALL_SLEEP},
{"test_skb_readonly", SETUP_SKB_PROG},
{"test_dynptr_skb_data", SETUP_SKB_PROG},
+ {"test_dynptr_skb_meta_data", SETUP_SKB_PROG},
+ {"test_dynptr_skb_meta_flags", SETUP_SKB_PROG},
{"test_adjust", SETUP_SYSCALL_SLEEP},
{"test_adjust_err", SETUP_SYSCALL_SLEEP},
{"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP},
@@ -33,10 +43,21 @@ static struct {
{"test_dynptr_skb_no_buff", SETUP_SKB_PROG},
{"test_dynptr_skb_strcmp", SETUP_SKB_PROG},
{"test_dynptr_skb_tp_btf", SETUP_SKB_PROG_TP},
+ {"test_probe_read_user_dynptr", SETUP_XDP_PROG},
+ {"test_probe_read_kernel_dynptr", SETUP_XDP_PROG},
+ {"test_probe_read_user_str_dynptr", SETUP_XDP_PROG},
+ {"test_probe_read_kernel_str_dynptr", SETUP_XDP_PROG},
+ {"test_copy_from_user_dynptr", SETUP_SYSCALL_SLEEP},
+ {"test_copy_from_user_str_dynptr", SETUP_SYSCALL_SLEEP},
+ {"test_copy_from_user_task_dynptr", SETUP_SYSCALL_SLEEP},
+ {"test_copy_from_user_task_str_dynptr", SETUP_SYSCALL_SLEEP},
};
+#define PAGE_SIZE_64K 65536
+
static void verify_success(const char *prog_name, enum test_setup_type setup_type)
{
+ char user_data[384] = {[0 ... 382] = 'a', '\0'};
struct dynptr_success *skel;
struct bpf_program *prog;
struct bpf_link *link;
@@ -58,6 +79,10 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
if (!ASSERT_OK(err, "dynptr_success__load"))
goto cleanup;
+ skel->bss->user_ptr = user_data;
+ skel->data->test_len[0] = sizeof(user_data);
+ memcpy(skel->bss->expected_str, user_data, sizeof(user_data));
+
switch (setup_type) {
case SETUP_SYSCALL_SLEEP:
link = bpf_program__attach(prog);
@@ -125,14 +150,18 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
}
case SETUP_XDP_PROG:
{
- char data[5000];
+ char data[90000];
int err, prog_fd;
LIBBPF_OPTS(bpf_test_run_opts, opts,
.data_in = &data,
- .data_size_in = sizeof(data),
.repeat = 1,
);
+ if (getpagesize() == PAGE_SIZE_64K)
+ opts.data_size_in = sizeof(data);
+ else
+ opts.data_size_in = 5000;
+
prog_fd = bpf_program__fd(prog);
err = bpf_prog_test_run_opts(prog_fd, &opts);
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index 9add890c2d37..c534b4d5f9da 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -293,7 +293,7 @@ static int get_btf_id_by_fd(int btf_fd, __u32 *id)
* 1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1
* 2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2
* 3) Close the btf_fd, now refcnt=1
- * Wait and check that BTF stil exists.
+ * Wait and check that BTF still exists.
*/
static void check_fd_array_cnt__referenced_btfs(void)
{
@@ -312,7 +312,7 @@ static void check_fd_array_cnt__referenced_btfs(void)
/* btf should still exist when original file descriptor is closed */
err = get_btf_id_by_fd(extra_fds[0], &btf_id);
- if (!ASSERT_GE(err, 0, "get_btf_id_by_fd"))
+ if (!ASSERT_EQ(err, 0, "get_btf_id_by_fd"))
goto cleanup;
Close(extra_fds[0]);
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c b/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c
new file mode 100644
index 000000000000..ca46fdd6e1ae
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <test_progs.h>
+#include "fd_htab_lookup.skel.h"
+
+struct htab_op_ctx {
+ int fd;
+ int loop;
+ unsigned int entries;
+ bool stop;
+};
+
+#define ERR_TO_RETVAL(where, err) ((void *)(long)(((where) << 12) | (-err)))
+
+static void *htab_lookup_fn(void *arg)
+{
+ struct htab_op_ctx *ctx = arg;
+ int i = 0;
+
+ while (i++ < ctx->loop && !ctx->stop) {
+ unsigned int j;
+
+ for (j = 0; j < ctx->entries; j++) {
+ unsigned int key = j, zero = 0, value;
+ int inner_fd, err;
+
+ err = bpf_map_lookup_elem(ctx->fd, &key, &value);
+ if (err) {
+ ctx->stop = true;
+ return ERR_TO_RETVAL(1, err);
+ }
+
+ inner_fd = bpf_map_get_fd_by_id(value);
+ if (inner_fd < 0) {
+ /* The old map has been freed */
+ if (inner_fd == -ENOENT)
+ continue;
+ ctx->stop = true;
+ return ERR_TO_RETVAL(2, inner_fd);
+ }
+
+ err = bpf_map_lookup_elem(inner_fd, &zero, &value);
+ if (err) {
+ close(inner_fd);
+ ctx->stop = true;
+ return ERR_TO_RETVAL(3, err);
+ }
+ close(inner_fd);
+
+ if (value != key) {
+ ctx->stop = true;
+ return ERR_TO_RETVAL(4, -EINVAL);
+ }
+ }
+ }
+
+ return NULL;
+}
+
+static void *htab_update_fn(void *arg)
+{
+ struct htab_op_ctx *ctx = arg;
+ int i = 0;
+
+ while (i++ < ctx->loop && !ctx->stop) {
+ unsigned int j;
+
+ for (j = 0; j < ctx->entries; j++) {
+ unsigned int key = j, zero = 0;
+ int inner_fd, err;
+
+ inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+ if (inner_fd < 0) {
+ ctx->stop = true;
+ return ERR_TO_RETVAL(1, inner_fd);
+ }
+
+ err = bpf_map_update_elem(inner_fd, &zero, &key, 0);
+ if (err) {
+ close(inner_fd);
+ ctx->stop = true;
+ return ERR_TO_RETVAL(2, err);
+ }
+
+ err = bpf_map_update_elem(ctx->fd, &key, &inner_fd, BPF_EXIST);
+ if (err) {
+ close(inner_fd);
+ ctx->stop = true;
+ return ERR_TO_RETVAL(3, err);
+ }
+ close(inner_fd);
+ }
+ }
+
+ return NULL;
+}
+
+static int setup_htab(int fd, unsigned int entries)
+{
+ unsigned int i;
+
+ for (i = 0; i < entries; i++) {
+ unsigned int key = i, zero = 0;
+ int inner_fd, err;
+
+ inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+ if (!ASSERT_OK_FD(inner_fd, "new array"))
+ return -1;
+
+ err = bpf_map_update_elem(inner_fd, &zero, &key, 0);
+ if (!ASSERT_OK(err, "init array")) {
+ close(inner_fd);
+ return -1;
+ }
+
+ err = bpf_map_update_elem(fd, &key, &inner_fd, 0);
+ if (!ASSERT_OK(err, "init outer")) {
+ close(inner_fd);
+ return -1;
+ }
+ close(inner_fd);
+ }
+
+ return 0;
+}
+
+static int get_int_from_env(const char *name, int dft)
+{
+ const char *value;
+
+ value = getenv(name);
+ if (!value)
+ return dft;
+
+ return atoi(value);
+}
+
+void test_fd_htab_lookup(void)
+{
+ unsigned int i, wr_nr = 8, rd_nr = 16;
+ pthread_t tids[wr_nr + rd_nr];
+ struct fd_htab_lookup *skel;
+ struct htab_op_ctx ctx;
+ int err;
+
+ skel = fd_htab_lookup__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "fd_htab_lookup__open_and_load"))
+ return;
+
+ ctx.fd = bpf_map__fd(skel->maps.outer_map);
+ ctx.loop = get_int_from_env("FD_HTAB_LOOP_NR", 5);
+ ctx.stop = false;
+ ctx.entries = 8;
+
+ err = setup_htab(ctx.fd, ctx.entries);
+ if (err)
+ goto destroy;
+
+ memset(tids, 0, sizeof(tids));
+ for (i = 0; i < wr_nr; i++) {
+ err = pthread_create(&tids[i], NULL, htab_update_fn, &ctx);
+ if (!ASSERT_OK(err, "pthread_create")) {
+ ctx.stop = true;
+ goto reap;
+ }
+ }
+ for (i = 0; i < rd_nr; i++) {
+ err = pthread_create(&tids[i + wr_nr], NULL, htab_lookup_fn, &ctx);
+ if (!ASSERT_OK(err, "pthread_create")) {
+ ctx.stop = true;
+ goto reap;
+ }
+ }
+
+reap:
+ for (i = 0; i < wr_nr + rd_nr; i++) {
+ void *ret = NULL;
+ char desc[32];
+
+ if (!tids[i])
+ continue;
+
+ snprintf(desc, sizeof(desc), "thread %u", i + 1);
+ err = pthread_join(tids[i], &ret);
+ ASSERT_OK(err, desc);
+ ASSERT_EQ(ret, NULL, desc);
+ }
+destroy:
+ fd_htab_lookup__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 130f5b82d2e6..5ef1804e44df 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -12,13 +12,24 @@ void test_fentry_fexit(void)
int err, prog_fd, i;
LIBBPF_OPTS(bpf_test_run_opts, topts);
- fentry_skel = fentry_test_lskel__open_and_load();
+ fentry_skel = fentry_test_lskel__open();
if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
goto close_prog;
- fexit_skel = fexit_test_lskel__open_and_load();
+
+ fentry_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fentry_test_lskel__load(fentry_skel);
+ if (!ASSERT_OK(err, "fentry_skel_load"))
+ goto close_prog;
+
+ fexit_skel = fexit_test_lskel__open();
if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
goto close_prog;
+ fexit_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fexit_test_lskel__load(fexit_skel);
+ if (!ASSERT_OK(err, "fexit_skel_load"))
+ goto close_prog;
+
err = fentry_test_lskel__attach(fentry_skel);
if (!ASSERT_OK(err, "fentry_attach"))
goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index aee1bc77a17f..ec882328eb59 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -43,8 +43,13 @@ static void fentry_test(void)
struct fentry_test_lskel *fentry_skel = NULL;
int err;
- fentry_skel = fentry_test_lskel__open_and_load();
- if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
+ fentry_skel = fentry_test_lskel__open();
+ if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_open"))
+ goto cleanup;
+
+ fentry_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fentry_test_lskel__load(fentry_skel);
+ if (!ASSERT_OK(err, "fentry_skel_load"))
goto cleanup;
err = fentry_test_common(fentry_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c b/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c
deleted file mode 100644
index 568d3aa48a78..000000000000
--- a/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c
+++ /dev/null
@@ -1,9 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <test_progs.h>
-#include "fexit_noreturns.skel.h"
-
-void test_fexit_noreturns(void)
-{
- RUN_TESTS(fexit_noreturns);
-}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 1c13007e37dd..94eed753560c 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -43,8 +43,13 @@ static void fexit_test(void)
struct fexit_test_lskel *fexit_skel = NULL;
int err;
- fexit_skel = fexit_test_lskel__open_and_load();
- if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
+ fexit_skel = fexit_test_lskel__open();
+ if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_open"))
+ goto cleanup;
+
+ fexit_skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+ err = fexit_test_lskel__load(fexit_skel);
+ if (!ASSERT_OK(err, "fexit_skel_load"))
goto cleanup;
err = fexit_test_common(fexit_skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index e59af2aa6601..e40114620751 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -37,6 +37,7 @@ static noinline void uprobe_func(void)
static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr,
ssize_t offset, ssize_t entry_offset)
{
+ ssize_t ref_ctr_offset = entry_offset /* ref_ctr_offset for uprobes */;
struct bpf_link_info info;
__u32 len = sizeof(info);
char buf[PATH_MAX];
@@ -97,6 +98,7 @@ again:
case BPF_PERF_EVENT_UPROBE:
case BPF_PERF_EVENT_URETPROBE:
ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset");
+ ASSERT_EQ(info.perf_event.uprobe.ref_ctr_offset, ref_ctr_offset, "uprobe_ref_ctr_offset");
ASSERT_EQ(info.perf_event.uprobe.name_len, strlen(UPROBE_FILE) + 1,
"name_len");
@@ -241,20 +243,32 @@ static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
.retprobe = type == BPF_PERF_EVENT_URETPROBE,
.bpf_cookie = PERF_EVENT_COOKIE,
);
+ const char *sema[1] = {
+ "uprobe_link_info_sema_1",
+ };
+ __u64 *ref_ctr_offset;
struct bpf_link *link;
int link_fd, err;
+ err = elf_resolve_syms_offsets("/proc/self/exe", 1, sema,
+ (unsigned long **) &ref_ctr_offset, STT_OBJECT);
+ if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object"))
+ return;
+
+ opts.ref_ctr_offset = *ref_ctr_offset;
link = bpf_program__attach_uprobe_opts(skel->progs.uprobe_run,
0, /* self pid */
UPROBE_FILE, uprobe_offset,
&opts);
if (!ASSERT_OK_PTR(link, "attach_uprobe"))
- return;
+ goto out;
link_fd = bpf_link__fd(link);
- err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0);
+ err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, *ref_ctr_offset);
ASSERT_OK(err, "verify_perf_link_info");
bpf_link__destroy(link);
+out:
+ free(ref_ctr_offset);
}
static int verify_kmulti_link_info(int fd, bool retprobe, bool has_cookies)
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 09f6487f58b9..5fea3209566e 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -6,6 +6,7 @@
#include "for_each_array_map_elem.skel.h"
#include "for_each_map_elem_write_key.skel.h"
#include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
static unsigned int duration;
@@ -203,6 +204,40 @@ out:
for_each_multi_maps__destroy(skel);
}
+static void test_hash_modify(void)
+{
+ struct for_each_hash_modify *skel;
+ int max_entries, i, err;
+ __u64 key, val;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1
+ );
+
+ skel = for_each_hash_modify__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+ return;
+
+ max_entries = bpf_map__max_entries(skel->maps.hashmap);
+ for (i = 0; i < max_entries; i++) {
+ key = i;
+ val = i;
+ err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+ &val, sizeof(val), BPF_ANY);
+ if (!ASSERT_OK(err, "map_update"))
+ goto out;
+ }
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+ ASSERT_OK(topts.retval, "retval");
+
+out:
+ for_each_hash_modify__destroy(skel);
+}
+
void test_for_each(void)
{
if (test__start_subtest("hash_map"))
@@ -213,4 +248,6 @@ void test_for_each(void)
test_write_map_key();
if (test__start_subtest("multi_maps"))
test_multi_maps();
+ if (test__start_subtest("hash_modify"))
+ test_hash_modify();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
index b7b77a6b2979..0de8facca4c5 100644
--- a/tools/testing/selftests/bpf/prog_tests/free_timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -124,6 +124,10 @@ void test_free_timer(void)
int err;
skel = free_timer__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "open_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
index a133354ac9bc..97b00c7efe94 100644
--- a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
+++ b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
@@ -16,7 +16,7 @@ void test_kernel_flag(void)
if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel"))
return;
- lsm_skel->bss->monitored_tid = gettid();
+ lsm_skel->bss->monitored_tid = sys_gettid();
ret = test_kernel_flag__attach(lsm_skel);
if (!ASSERT_OK(ret, "test_kernel_flag__attach"))
diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
index 8e13a3416a21..1de14b111931 100644
--- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
@@ -104,7 +104,7 @@ void test_kmem_cache_iter(void)
goto destroy;
memset(buf, 0, sizeof(buf));
- while (read(iter_fd, buf, sizeof(buf) > 0)) {
+ while (read(iter_fd, buf, sizeof(buf)) > 0) {
/* Read out all contents */
printf("%s", buf);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index e19ef509ebf8..6cfaa978bc9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -7,6 +7,7 @@
#include "kprobe_multi_session.skel.h"
#include "kprobe_multi_session_cookie.skel.h"
#include "kprobe_multi_verifier.skel.h"
+#include "kprobe_write_ctx.skel.h"
#include "bpf/libbpf_internal.h"
#include "bpf/hashmap.h"
@@ -422,220 +423,6 @@ static void test_unique_match(void)
kprobe_multi__destroy(skel);
}
-static size_t symbol_hash(long key, void *ctx __maybe_unused)
-{
- return str_hash((const char *) key);
-}
-
-static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
-{
- return strcmp((const char *) key1, (const char *) key2) == 0;
-}
-
-static bool is_invalid_entry(char *buf, bool kernel)
-{
- if (kernel && strchr(buf, '['))
- return true;
- if (!kernel && !strchr(buf, '['))
- return true;
- return false;
-}
-
-static bool skip_entry(char *name)
-{
- /*
- * We attach to almost all kernel functions and some of them
- * will cause 'suspicious RCU usage' when fprobe is attached
- * to them. Filter out the current culprits - arch_cpu_idle
- * default_idle and rcu_* functions.
- */
- if (!strcmp(name, "arch_cpu_idle"))
- return true;
- if (!strcmp(name, "default_idle"))
- return true;
- if (!strncmp(name, "rcu_", 4))
- return true;
- if (!strcmp(name, "bpf_dispatcher_xdp_func"))
- return true;
- if (!strncmp(name, "__ftrace_invalid_address__",
- sizeof("__ftrace_invalid_address__") - 1))
- return true;
- return false;
-}
-
-/* Do comparision by ignoring '.llvm.<hash>' suffixes. */
-static int compare_name(const char *name1, const char *name2)
-{
- const char *res1, *res2;
- int len1, len2;
-
- res1 = strstr(name1, ".llvm.");
- res2 = strstr(name2, ".llvm.");
- len1 = res1 ? res1 - name1 : strlen(name1);
- len2 = res2 ? res2 - name2 : strlen(name2);
-
- if (len1 == len2)
- return strncmp(name1, name2, len1);
- if (len1 < len2)
- return strncmp(name1, name2, len1) <= 0 ? -1 : 1;
- return strncmp(name1, name2, len2) >= 0 ? 1 : -1;
-}
-
-static int load_kallsyms_compare(const void *p1, const void *p2)
-{
- return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name);
-}
-
-static int search_kallsyms_compare(const void *p1, const struct ksym *p2)
-{
- return compare_name(p1, p2->name);
-}
-
-static int get_syms(char ***symsp, size_t *cntp, bool kernel)
-{
- size_t cap = 0, cnt = 0;
- char *name = NULL, *ksym_name, **syms = NULL;
- struct hashmap *map;
- struct ksyms *ksyms;
- struct ksym *ks;
- char buf[256];
- FILE *f;
- int err = 0;
-
- ksyms = load_kallsyms_custom_local(load_kallsyms_compare);
- if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_custom_local"))
- return -EINVAL;
-
- /*
- * The available_filter_functions contains many duplicates,
- * but other than that all symbols are usable in kprobe multi
- * interface.
- * Filtering out duplicates by using hashmap__add, which won't
- * add existing entry.
- */
-
- if (access("/sys/kernel/tracing/trace", F_OK) == 0)
- f = fopen("/sys/kernel/tracing/available_filter_functions", "r");
- else
- f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
-
- if (!f)
- return -EINVAL;
-
- map = hashmap__new(symbol_hash, symbol_equal, NULL);
- if (IS_ERR(map)) {
- err = libbpf_get_error(map);
- goto error;
- }
-
- while (fgets(buf, sizeof(buf), f)) {
- if (is_invalid_entry(buf, kernel))
- continue;
-
- free(name);
- if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1)
- continue;
- if (skip_entry(name))
- continue;
-
- ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare);
- if (!ks) {
- err = -EINVAL;
- goto error;
- }
-
- ksym_name = ks->name;
- err = hashmap__add(map, ksym_name, 0);
- if (err == -EEXIST) {
- err = 0;
- continue;
- }
- if (err)
- goto error;
-
- err = libbpf_ensure_mem((void **) &syms, &cap,
- sizeof(*syms), cnt + 1);
- if (err)
- goto error;
-
- syms[cnt++] = ksym_name;
- }
-
- *symsp = syms;
- *cntp = cnt;
-
-error:
- free(name);
- fclose(f);
- hashmap__free(map);
- if (err)
- free(syms);
- return err;
-}
-
-static int get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel)
-{
- unsigned long *addr, *addrs, *tmp_addrs;
- int err = 0, max_cnt, inc_cnt;
- char *name = NULL;
- size_t cnt = 0;
- char buf[256];
- FILE *f;
-
- if (access("/sys/kernel/tracing/trace", F_OK) == 0)
- f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r");
- else
- f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r");
-
- if (!f)
- return -ENOENT;
-
- /* In my local setup, the number of entries is 50k+ so Let us initially
- * allocate space to hold 64k entries. If 64k is not enough, incrementally
- * increase 1k each time.
- */
- max_cnt = 65536;
- inc_cnt = 1024;
- addrs = malloc(max_cnt * sizeof(long));
- if (addrs == NULL) {
- err = -ENOMEM;
- goto error;
- }
-
- while (fgets(buf, sizeof(buf), f)) {
- if (is_invalid_entry(buf, kernel))
- continue;
-
- free(name);
- if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2)
- continue;
- if (skip_entry(name))
- continue;
-
- if (cnt == max_cnt) {
- max_cnt += inc_cnt;
- tmp_addrs = realloc(addrs, max_cnt);
- if (!tmp_addrs) {
- err = -ENOMEM;
- goto error;
- }
- addrs = tmp_addrs;
- }
-
- addrs[cnt++] = (unsigned long)addr;
- }
-
- *addrsp = addrs;
- *cntp = cnt;
-
-error:
- free(name);
- fclose(f);
- if (err)
- free(addrs);
- return err;
-}
-
static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts)
{
long attach_start_ns, attach_end_ns;
@@ -670,7 +457,7 @@ static void test_kprobe_multi_bench_attach(bool kernel)
char **syms = NULL;
size_t cnt = 0;
- if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms"))
+ if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms"))
return;
skel = kprobe_multi_empty__open_and_load();
@@ -696,13 +483,13 @@ static void test_kprobe_multi_bench_attach_addr(bool kernel)
size_t cnt = 0;
int err;
- err = get_addrs(&addrs, &cnt, kernel);
+ err = bpf_get_addrs(&addrs, &cnt, kernel);
if (err == -ENOENT) {
test__skip();
return;
}
- if (!ASSERT_OK(err, "get_addrs"))
+ if (!ASSERT_OK(err, "bpf_get_addrs"))
return;
skel = kprobe_multi_empty__open_and_load();
@@ -753,6 +540,30 @@ cleanup:
kprobe_multi_override__destroy(skel);
}
+#ifdef __x86_64__
+static void test_attach_write_ctx(void)
+{
+ struct kprobe_write_ctx *skel = NULL;
+ struct bpf_link *link = NULL;
+
+ skel = kprobe_write_ctx__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load"))
+ return;
+
+ link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_multi_write_ctx,
+ "bpf_fentry_test1", NULL);
+ if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts"))
+ bpf_link__destroy(link);
+
+ kprobe_write_ctx__destroy(skel);
+}
+#else
+static void test_attach_write_ctx(void)
+{
+ test__skip();
+}
+#endif
+
void serial_test_kprobe_multi_bench_attach(void)
{
if (test__start_subtest("kernel"))
@@ -792,5 +603,7 @@ void test_kprobe_multi_test(void)
test_session_cookie_skel_api();
if (test__start_subtest("unique_match"))
test_unique_match();
+ if (test__start_subtest("attach_write_ctx"))
+ test_attach_write_ctx();
RUN_TESTS(kprobe_multi_verifier);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index 77d07e0a4a55..14c5a7ef0e87 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -7,6 +7,7 @@
#include "linked_list.skel.h"
#include "linked_list_fail.skel.h"
+#include "linked_list_peek.skel.h"
static char log_buf[1024 * 1024];
@@ -71,7 +72,7 @@ static struct {
{ "new_null_ret", "R0 invalid mem access 'ptr_or_null_'" },
{ "obj_new_acq", "Unreleased reference id=" },
{ "use_after_drop", "invalid mem access 'scalar'" },
- { "ptr_walk_scalar", "type=scalar expected=percpu_ptr_" },
+ { "ptr_walk_scalar", "type=rdonly_untrusted_mem expected=percpu_ptr_" },
{ "direct_read_lock", "direct access to bpf_spin_lock is disallowed" },
{ "direct_write_lock", "direct access to bpf_spin_lock is disallowed" },
{ "direct_read_head", "direct access to bpf_list_head is disallowed" },
@@ -805,3 +806,8 @@ void test_linked_list(void)
test_linked_list_success(LIST_IN_LIST, true);
test_linked_list_success(TEST_ALL, false);
}
+
+void test_linked_list_peek(void)
+{
+ RUN_TESTS(linked_list_peek);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index 169ce689b97c..d6f14a232002 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -7,6 +7,10 @@
#include "test_log_buf.skel.h"
#include "bpf_util.h"
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
+
static size_t libbpf_log_pos;
static char libbpf_log_buf[1024 * 1024];
static bool libbpf_log_error;
diff --git a/tools/testing/selftests/bpf/prog_tests/map_excl.c b/tools/testing/selftests/bpf/prog_tests/map_excl.c
new file mode 100644
index 000000000000..6bdc6d6de0da
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_excl.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Google LLC. */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+#include "map_excl.skel.h"
+
+static void test_map_excl_allowed(void)
+{
+ struct map_excl *skel = map_excl__open();
+ int err;
+
+ err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access);
+ if (!ASSERT_OK(err, "bpf_map__set_exclusive_program"))
+ goto out;
+
+ bpf_program__set_autoload(skel->progs.should_have_access, true);
+ bpf_program__set_autoload(skel->progs.should_not_have_access, false);
+
+ err = map_excl__load(skel);
+ ASSERT_OK(err, "map_excl__load");
+out:
+ map_excl__destroy(skel);
+}
+
+static void test_map_excl_denied(void)
+{
+ struct map_excl *skel = map_excl__open();
+ int err;
+
+ err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access);
+ if (!ASSERT_OK(err, "bpf_map__make_exclusive"))
+ goto out;
+
+ bpf_program__set_autoload(skel->progs.should_have_access, false);
+ bpf_program__set_autoload(skel->progs.should_not_have_access, true);
+
+ err = map_excl__load(skel);
+ ASSERT_EQ(err, -EACCES, "exclusive map access not denied\n");
+out:
+ map_excl__destroy(skel);
+
+}
+
+void test_map_excl(void)
+{
+ if (test__start_subtest("map_excl_allowed"))
+ test_map_excl_allowed();
+ if (test__start_subtest("map_excl_denied"))
+ test_map_excl_denied();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c
new file mode 100644
index 000000000000..40d4f687bd9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+#include "mem_rdonly_untrusted.skel.h"
+
+void test_mem_rdonly_untrusted(void)
+{
+ RUN_TESTS(mem_rdonly_untrusted);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 6d391d95f96e..70fa7ae93173 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -90,7 +90,7 @@ void test_module_attach(void)
test_module_attach__detach(skel);
- /* attach fentry/fexit and make sure it get's module reference */
+ /* attach fentry/fexit and make sure it gets module reference */
link = bpf_program__attach(skel->progs.handle_fentry);
if (!ASSERT_OK_PTR(link, "attach_fentry"))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c
new file mode 100644
index 000000000000..9ae49b587f3e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <test_progs.h>
+
+
+#include "test_pinning_devmap.skel.h"
+
+void test_pinning_devmap_reuse(void)
+{
+ const char *pinpath1 = "/sys/fs/bpf/pinmap1";
+ const char *pinpath2 = "/sys/fs/bpf/pinmap2";
+ struct test_pinning_devmap *skel1 = NULL, *skel2 = NULL;
+ int err;
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+ /* load the object a first time */
+ skel1 = test_pinning_devmap__open_and_load();
+ if (!ASSERT_OK_PTR(skel1, "skel_load1"))
+ goto out;
+
+ /* load the object a second time, re-using the pinned map */
+ skel2 = test_pinning_devmap__open_and_load();
+ if (!ASSERT_OK_PTR(skel2, "skel_load2"))
+ goto out;
+
+ /* we can close the reference safely without
+ * the map's refcount falling to 0
+ */
+ test_pinning_devmap__destroy(skel1);
+ skel1 = NULL;
+
+ /* now, swap the pins */
+ err = renameat2(0, pinpath1, 0, pinpath2, RENAME_EXCHANGE);
+ if (!ASSERT_OK(err, "swap pins"))
+ goto out;
+
+ /* load the object again, this time the re-use should fail */
+ skel1 = test_pinning_devmap__open_and_load();
+ if (!ASSERT_ERR_PTR(skel1, "skel_load3"))
+ goto out;
+
+out:
+ unlink(pinpath1);
+ unlink(pinpath2);
+ test_pinning_devmap__destroy(skel1);
+ test_pinning_devmap__destroy(skel2);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_htab.c b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c
new file mode 100644
index 000000000000..16bd74be3dbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_pinning_htab.skel.h"
+
+static void unpin_map(const char *map_name, const char *pin_path)
+{
+ struct test_pinning_htab *skel;
+ struct bpf_map *map;
+ int err;
+
+ skel = test_pinning_htab__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+ return;
+
+ map = bpf_object__find_map_by_name(skel->obj, map_name);
+ if (!ASSERT_OK_PTR(map, "bpf_object__find_map_by_name"))
+ goto out;
+
+ err = bpf_map__pin(map, pin_path);
+ if (!ASSERT_OK(err, "bpf_map__pin"))
+ goto out;
+
+ err = bpf_map__unpin(map, pin_path);
+ ASSERT_OK(err, "bpf_map__unpin");
+out:
+ test_pinning_htab__destroy(skel);
+}
+
+void test_pinning_htab(void)
+{
+ if (test__start_subtest("timer_prealloc"))
+ unpin_map("timer_prealloc", "/sys/fs/bpf/timer_prealloc");
+ if (test__start_subtest("timer_no_prealloc"))
+ unpin_map("timer_no_prealloc", "/sys/fs/bpf/timer_no_prealloc");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
index 14f2796076e0..7607cfc2408c 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
@@ -54,3 +54,128 @@ void test_prog_tests_framework(void)
return;
clear_test_state(state);
}
+
+static void dummy_emit(const char *buf, bool force) {}
+
+void test_prog_tests_framework_expected_msgs(void)
+{
+ struct expected_msgs msgs;
+ int i, j, error_cnt;
+ const struct {
+ const char *name;
+ const char *log;
+ const char *expected;
+ struct expect_msg *pats;
+ } cases[] = {
+ {
+ .name = "simple-ok",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "simple-fail",
+ .log = "aaabbbddd",
+ .expected = "MATCHED SUBSTR: 'aaa'\n"
+ "EXPECTED SUBSTR: 'ccc'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-ok-mid",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "foo", .negative = true },
+ { .substr = "bar", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-ok-tail",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "foo", .negative = true },
+ {}
+ }
+ },
+ {
+ .name = "negative-ok-head",
+ .log = "aaabbbccc",
+ .pats = (struct expect_msg[]) {
+ { .substr = "foo", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-head",
+ .log = "aaabbbccc",
+ .expected = "UNEXPECTED SUBSTR: 'aaa'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa", .negative = true },
+ { .substr = "bbb" },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-tail",
+ .log = "aaabbbccc",
+ .expected = "UNEXPECTED SUBSTR: 'ccc'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "bbb" },
+ { .substr = "ccc", .negative = true },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-mid-1",
+ .log = "aaabbbccc",
+ .expected = "UNEXPECTED SUBSTR: 'bbb'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "bbb", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ },
+ {
+ .name = "negative-fail-mid-2",
+ .log = "aaabbb222ccc",
+ .expected = "UNEXPECTED SUBSTR: '222'\n",
+ .pats = (struct expect_msg[]) {
+ { .substr = "aaa" },
+ { .substr = "222", .negative = true },
+ { .substr = "bbb", .negative = true },
+ { .substr = "ccc" },
+ {}
+ }
+ }
+ };
+
+ for (i = 0; i < ARRAY_SIZE(cases); i++) {
+ if (test__start_subtest(cases[i].name)) {
+ error_cnt = env.subtest_state->error_cnt;
+ msgs.patterns = cases[i].pats;
+ msgs.cnt = 0;
+ for (j = 0; cases[i].pats[j].substr; j++)
+ msgs.cnt++;
+ validate_msgs(cases[i].log, &msgs, dummy_emit);
+ fflush(stderr);
+ env.subtest_state->error_cnt = error_cnt;
+ if (cases[i].expected)
+ ASSERT_HAS_SUBSTR(env.subtest_state->log_buf, cases[i].expected, "expected output");
+ else
+ ASSERT_STREQ(env.subtest_state->log_buf, "", "expected no output");
+ test__end_subtest();
+ }
+ }
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/rbtree.c b/tools/testing/selftests/bpf/prog_tests/rbtree.c
index 9818f06c97c5..d8f3d7a45fe9 100644
--- a/tools/testing/selftests/bpf/prog_tests/rbtree.c
+++ b/tools/testing/selftests/bpf/prog_tests/rbtree.c
@@ -8,6 +8,7 @@
#include "rbtree_fail.skel.h"
#include "rbtree_btf_fail__wrong_node_type.skel.h"
#include "rbtree_btf_fail__add_wrong_type.skel.h"
+#include "rbtree_search.skel.h"
static void test_rbtree_add_nodes(void)
{
@@ -187,3 +188,8 @@ void test_rbtree_fail(void)
{
RUN_TESTS(rbtree_fail);
}
+
+void test_rbtree_search(void)
+{
+ RUN_TESTS(rbtree_search);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
index 8100509e561b..0ffa01d54ce2 100644
--- a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
@@ -149,3 +149,70 @@ close_prog:
fentry_recursive_target__destroy(target_skel);
fentry_recursive__destroy(tracing_skel);
}
+
+static void *fentry_target_test_run(void *arg)
+{
+ for (;;) {
+ int prog_fd = __atomic_load_n((int *)arg, __ATOMIC_SEQ_CST);
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ int err;
+
+ if (prog_fd == -1)
+ break;
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ if (!ASSERT_OK(err, "fentry_target test_run"))
+ break;
+ }
+
+ return NULL;
+}
+
+void test_fentry_attach_stress(void)
+{
+ struct fentry_recursive_target *target_skel = NULL;
+ struct fentry_recursive *tracing_skel = NULL;
+ struct bpf_program *prog;
+ int err, i, tgt_prog_fd;
+ pthread_t thread;
+
+ target_skel = fentry_recursive_target__open_and_load();
+ if (!ASSERT_OK_PTR(target_skel,
+ "fentry_recursive_target__open_and_load"))
+ goto close_prog;
+ tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target);
+ err = pthread_create(&thread, NULL,
+ fentry_target_test_run, &tgt_prog_fd);
+ if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+ goto close_prog;
+
+ for (i = 0; i < 1000; i++) {
+ tracing_skel = fentry_recursive__open();
+ if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open"))
+ goto stop_thread;
+
+ prog = tracing_skel->progs.recursive_attach;
+ err = bpf_program__set_attach_target(prog, tgt_prog_fd,
+ "fentry_target");
+ if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+ goto stop_thread;
+
+ err = fentry_recursive__load(tracing_skel);
+ if (!ASSERT_OK(err, "fentry_recursive__load"))
+ goto stop_thread;
+
+ err = fentry_recursive__attach(tracing_skel);
+ if (!ASSERT_OK(err, "fentry_recursive__attach"))
+ goto stop_thread;
+
+ fentry_recursive__destroy(tracing_skel);
+ tracing_skel = NULL;
+ }
+
+stop_thread:
+ __atomic_store_n(&tgt_prog_fd, -1, __ATOMIC_SEQ_CST);
+ err = pthread_join(thread, NULL);
+ ASSERT_OK(err, "pthread_join");
+close_prog:
+ fentry_recursive__destroy(tracing_skel);
+ fentry_recursive_target__destroy(target_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 39d42271cc46..d93a0c7b1786 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -465,6 +465,20 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
return range_improve(x_t, x, x_swap);
}
+ if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) {
+ if (x_t == S64 && x.a > x.b) {
+ if (x.b < y.a && x.a <= y.b)
+ return range(x_t, x.a, y.b);
+ if (x.a > y.b && x.b >= y.a)
+ return range(x_t, y.a, x.b);
+ } else if (x_t == U64 && y.a > y.b) {
+ if (y.b < x.a && y.a <= x.b)
+ return range(x_t, y.a, x.b);
+ if (y.a > x.b && y.b >= x.a)
+ return range(x_t, x.a, y.b);
+ }
+ }
+
/* otherwise, plain range cast and intersection works */
return range_improve(x_t, x, y_cast);
}
@@ -609,7 +623,7 @@ static void range_cond(enum num_t t, struct range x, struct range y,
*newx = range(t, x.a, x.b);
*newy = range(t, y.a + 1, y.b);
} else if (x.a == x.b && x.b == y.b) {
- /* X is a constant matching rigth side of Y */
+ /* X is a constant matching right side of Y */
*newx = range(t, x.a, x.b);
*newy = range(t, y.a, y.b - 1);
} else if (y.a == y.b && x.a == y.a) {
@@ -617,7 +631,7 @@ static void range_cond(enum num_t t, struct range x, struct range y,
*newx = range(t, x.a + 1, x.b);
*newy = range(t, y.a, y.b);
} else if (y.a == y.b && x.b == y.b) {
- /* Y is a constant matching rigth side of X */
+ /* Y is a constant matching right side of X */
*newx = range(t, x.a, x.b - 1);
*newy = range(t, y.a, y.b);
} else {
diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
index 115287ba441b..8c6c2043a432 100644
--- a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
@@ -25,8 +25,11 @@ static void *spin_lock_thread(void *arg)
while (!READ_ONCE(skip)) {
err = bpf_prog_test_run_opts(prog_fd, &topts);
- ASSERT_OK(err, "test_run");
- ASSERT_OK(topts.retval, "test_run retval");
+ if (err || topts.retval) {
+ ASSERT_OK(err, "test_run");
+ ASSERT_OK(topts.retval, "test_run retval");
+ break;
+ }
}
pthread_exit(arg);
}
@@ -96,3 +99,19 @@ end:
res_spin_lock__destroy(skel);
return;
}
+
+void serial_test_res_spin_lock_stress(void)
+{
+ if (libbpf_num_possible_cpus() < 3) {
+ test__skip();
+ return;
+ }
+
+ ASSERT_OK(load_module("bpf_test_rqspinlock.ko", false), "load module AA");
+ sleep(5);
+ unload_module("bpf_test_rqspinlock", false);
+
+ ASSERT_OK(load_module_params("bpf_test_rqspinlock.ko", "test_ab=1", false), "load module ABBA");
+ sleep(5);
+ unload_module("bpf_test_rqspinlock", false);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index da430df45aa4..d1e4cb28a72c 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -97,7 +97,7 @@ static void ringbuf_write_subtest(void)
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
- skel->maps.ringbuf.max_entries = 0x4000;
+ skel->maps.ringbuf.max_entries = 0x40000;
err = test_ringbuf_write_lskel__load(skel);
if (!ASSERT_OK(err, "skel_load"))
@@ -108,7 +108,7 @@ static void ringbuf_write_subtest(void)
mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0);
if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"))
goto cleanup;
- *mmap_ptr = 0x3000;
+ *mmap_ptr = 0x30000;
ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw");
skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/sha256.c b/tools/testing/selftests/bpf/prog_tests/sha256.c
new file mode 100644
index 000000000000..604a0b1423d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sha256.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2025 Google LLC */
+
+#include <test_progs.h>
+#include "bpf/libbpf_internal.h"
+
+#define MAX_LEN 4096
+
+/* Test libbpf_sha256() for all lengths from 0 to MAX_LEN inclusively. */
+void test_sha256(void)
+{
+ /*
+ * The correctness of this value was verified by running this test with
+ * libbpf_sha256() replaced by OpenSSL's SHA256().
+ */
+ static const __u8 expected_digest_of_digests[SHA256_DIGEST_LENGTH] = {
+ 0x62, 0x30, 0x0e, 0x1d, 0xea, 0x7f, 0xc4, 0x74,
+ 0xfd, 0x8e, 0x64, 0x0b, 0xd8, 0x5f, 0xea, 0x04,
+ 0xf3, 0xef, 0x77, 0x42, 0xc2, 0x01, 0xb8, 0x90,
+ 0x6e, 0x19, 0x91, 0x1b, 0xca, 0xb3, 0x28, 0x42,
+ };
+ __u64 seed = 0;
+ __u8 *data = NULL, *digests = NULL;
+ __u8 digest_of_digests[SHA256_DIGEST_LENGTH];
+ size_t i;
+
+ data = malloc(MAX_LEN);
+ if (!ASSERT_OK_PTR(data, "malloc"))
+ goto out;
+ digests = malloc((MAX_LEN + 1) * SHA256_DIGEST_LENGTH);
+ if (!ASSERT_OK_PTR(digests, "malloc"))
+ goto out;
+
+ /* Generate MAX_LEN bytes of "random" data deterministically. */
+ for (i = 0; i < MAX_LEN; i++) {
+ seed = (seed * 25214903917 + 11) & ((1ULL << 48) - 1);
+ data[i] = (__u8)(seed >> 16);
+ }
+
+ /* Calculate a digest for each length 0 through MAX_LEN inclusively. */
+ for (i = 0; i <= MAX_LEN; i++)
+ libbpf_sha256(data, i, &digests[i * SHA256_DIGEST_LENGTH]);
+
+ /* Calculate and verify the digest of all the digests. */
+ libbpf_sha256(digests, (MAX_LEN + 1) * SHA256_DIGEST_LENGTH,
+ digest_of_digests);
+ ASSERT_MEMEQ(digest_of_digests, expected_digest_of_digests,
+ SHA256_DIGEST_LENGTH, "digest_of_digests");
+out:
+ free(data);
+ free(digests);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
index 0b9bd1d6f7cc..10a0ab954b8a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -37,8 +37,10 @@ configure_stack(void)
tc = popen("tc -V", "r");
if (CHECK_FAIL(!tc))
return false;
- if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc)))
+ if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) {
+ pclose(tc);
return false;
+ }
if (strstr(tc_version, ", libbpf "))
prog = "test_sk_assign_libbpf.bpf.o";
else
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
index 4be6fdb78c6a..594441acb707 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -116,6 +116,8 @@ static void test_snprintf_negative(void)
ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7");
ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
+ ASSERT_ERR(load_single_snprintf("%p%"), "invalid specifier 8");
+ ASSERT_ERR(load_single_snprintf("%s%"), "invalid specifier 9");
}
void test_snprintf(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
index d56e18b25528..27781df8f2fb 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -1,20 +1,875 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2024 Meta
+#include <poll.h>
#include <test_progs.h>
#include "network_helpers.h"
#include "sock_iter_batch.skel.h"
#define TEST_NS "sock_iter_batch_netns"
+#define TEST_CHILD_NS "sock_iter_batch_child_netns"
+static const int init_batch_size = 16;
static const int nr_soreuse = 4;
+struct iter_out {
+ int idx;
+ __u64 cookie;
+} __packed;
+
+struct sock_count {
+ __u64 cookie;
+ int count;
+};
+
+static int insert(__u64 cookie, struct sock_count counts[], int counts_len)
+{
+ int insert = -1;
+ int i = 0;
+
+ for (; i < counts_len; i++) {
+ if (!counts[i].cookie) {
+ insert = i;
+ } else if (counts[i].cookie == cookie) {
+ insert = i;
+ break;
+ }
+ }
+ if (insert < 0)
+ return insert;
+
+ counts[insert].cookie = cookie;
+ counts[insert].count++;
+
+ return counts[insert].count;
+}
+
+static int read_n(int iter_fd, int n, struct sock_count counts[],
+ int counts_len)
+{
+ struct iter_out out;
+ int nread = 1;
+ int i = 0;
+
+ for (; nread > 0 && (n < 0 || i < n); i++) {
+ nread = read(iter_fd, &out, sizeof(out));
+ if (!nread || !ASSERT_EQ(nread, sizeof(out), "nread"))
+ break;
+ ASSERT_GE(insert(out.cookie, counts, counts_len), 0, "insert");
+ }
+
+ ASSERT_TRUE(n < 0 || i == n, "n < 0 || i == n");
+
+ return i;
+}
+
+static __u64 socket_cookie(int fd)
+{
+ __u64 cookie;
+ socklen_t cookie_len = sizeof(cookie);
+
+ if (!ASSERT_OK(getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie,
+ &cookie_len), "getsockopt(SO_COOKIE)"))
+ return 0;
+ return cookie;
+}
+
+static bool was_seen(int fd, struct sock_count counts[], int counts_len)
+{
+ __u64 cookie = socket_cookie(fd);
+ int i = 0;
+
+ for (; cookie && i < counts_len; i++)
+ if (cookie == counts[i].cookie)
+ return true;
+
+ return false;
+}
+
+static int get_seen_socket(int *fds, struct sock_count counts[], int n)
+{
+ int i = 0;
+
+ for (; i < n; i++)
+ if (was_seen(fds[i], counts, n))
+ return i;
+ return -1;
+}
+
+static int get_nth_socket(int *fds, int fds_len, struct bpf_link *link, int n)
+{
+ int i, nread, iter_fd;
+ int nth_sock_idx = -1;
+ struct iter_out out;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+ return -1;
+
+ for (; n >= 0; n--) {
+ nread = read(iter_fd, &out, sizeof(out));
+ if (!nread || !ASSERT_GE(nread, 1, "nread"))
+ goto done;
+ }
+
+ for (i = 0; i < fds_len && nth_sock_idx < 0; i++)
+ if (fds[i] >= 0 && socket_cookie(fds[i]) == out.cookie)
+ nth_sock_idx = i;
+done:
+ close(iter_fd);
+ return nth_sock_idx;
+}
+
+static void destroy(int fd)
+{
+ struct sock_iter_batch *skel = NULL;
+ __u64 cookie = socket_cookie(fd);
+ struct bpf_link *link = NULL;
+ int iter_fd = -1;
+ int nread;
+ __u64 out;
+
+ skel = sock_iter_batch__open();
+ if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+ goto done;
+
+ skel->rodata->destroy_cookie = cookie;
+
+ if (!ASSERT_OK(sock_iter_batch__load(skel), "sock_iter_batch__load"))
+ goto done;
+
+ link = bpf_program__attach_iter(skel->progs.iter_tcp_destroy, NULL);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+ goto done;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+ goto done;
+
+ /* Delete matching socket. */
+ nread = read(iter_fd, &out, sizeof(out));
+ ASSERT_GE(nread, 0, "nread");
+ if (nread)
+ ASSERT_EQ(out, cookie, "cookie matches");
+done:
+ if (iter_fd >= 0)
+ close(iter_fd);
+ bpf_link__destroy(link);
+ sock_iter_batch__destroy(skel);
+ close(fd);
+}
+
+static int get_seen_count(int fd, struct sock_count counts[], int n)
+{
+ __u64 cookie = socket_cookie(fd);
+ int count = 0;
+ int i = 0;
+
+ for (; cookie && !count && i < n; i++)
+ if (cookie == counts[i].cookie)
+ count = counts[i].count;
+
+ return count;
+}
+
+static void check_n_were_seen_once(int *fds, int fds_len, int n,
+ struct sock_count counts[], int counts_len)
+{
+ int seen_once = 0;
+ int seen_cnt;
+ int i = 0;
+
+ for (; i < fds_len; i++) {
+ /* Skip any sockets that were closed or that weren't seen
+ * exactly once.
+ */
+ if (fds[i] < 0)
+ continue;
+ seen_cnt = get_seen_count(fds[i], counts, counts_len);
+ if (seen_cnt && ASSERT_EQ(seen_cnt, 1, "seen_cnt"))
+ seen_once++;
+ }
+
+ ASSERT_EQ(seen_once, n, "seen_once");
+}
+
+static int accept_from_one(struct pollfd *server_poll_fds,
+ int server_poll_fds_len)
+{
+ static const int poll_timeout_ms = 5000; /* 5s */
+ int ret;
+ int i;
+
+ ret = poll(server_poll_fds, server_poll_fds_len, poll_timeout_ms);
+ if (!ASSERT_EQ(ret, 1, "poll"))
+ return -1;
+
+ for (i = 0; i < server_poll_fds_len; i++)
+ if (server_poll_fds[i].revents & POLLIN)
+ return accept(server_poll_fds[i].fd, NULL, NULL);
+
+ return -1;
+}
+
+static int *connect_to_server(int family, int sock_type, const char *addr,
+ __u16 port, int nr_connects, int *server_fds,
+ int server_fds_len)
+{
+ struct pollfd *server_poll_fds = NULL;
+ int *established_socks = NULL;
+ int i;
+
+ server_poll_fds = calloc(server_fds_len, sizeof(*server_poll_fds));
+ if (!ASSERT_OK_PTR(server_poll_fds, "server_poll_fds"))
+ return NULL;
+
+ for (i = 0; i < server_fds_len; i++) {
+ server_poll_fds[i].fd = server_fds[i];
+ server_poll_fds[i].events = POLLIN;
+ }
+
+ i = 0;
+
+ established_socks = malloc(sizeof(*established_socks) * nr_connects*2);
+ if (!ASSERT_OK_PTR(established_socks, "established_socks"))
+ goto error;
+
+ while (nr_connects--) {
+ established_socks[i] = connect_to_addr_str(family, sock_type,
+ addr, port, NULL);
+ if (!ASSERT_OK_FD(established_socks[i], "connect_to_addr_str"))
+ goto error;
+ i++;
+ established_socks[i] = accept_from_one(server_poll_fds,
+ server_fds_len);
+ if (!ASSERT_OK_FD(established_socks[i], "accept_from_one"))
+ goto error;
+ i++;
+ }
+
+ free(server_poll_fds);
+ return established_socks;
+error:
+ free_fds(established_socks, i);
+ free(server_poll_fds);
+ return NULL;
+}
+
+static void remove_seen(int family, int sock_type, const char *addr, __u16 port,
+ int *socks, int socks_len, int *established_socks,
+ int established_socks_len, struct sock_count *counts,
+ int counts_len, struct bpf_link *link, int iter_fd)
+{
+ int close_idx;
+
+ /* Iterate through the first socks_len - 1 sockets. */
+ read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+ /* Make sure we saw socks_len - 1 sockets exactly once. */
+ check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+ counts_len);
+
+ /* Close a socket we've already seen to remove it from the bucket. */
+ close_idx = get_seen_socket(socks, counts, counts_len);
+ if (!ASSERT_GE(close_idx, 0, "close_idx"))
+ return;
+ close(socks[close_idx]);
+ socks[close_idx] = -1;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure the last socket wasn't skipped and that there were no
+ * repeats.
+ */
+ check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+ counts_len);
+}
+
+static void remove_seen_established(int family, int sock_type, const char *addr,
+ __u16 port, int *listen_socks,
+ int listen_socks_len, int *established_socks,
+ int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ int close_idx;
+
+ /* Iterate through all listening sockets. */
+ read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+ /* Make sure we saw all listening sockets exactly once. */
+ check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+ counts, counts_len);
+
+ /* Leave one established socket. */
+ read_n(iter_fd, established_socks_len - 1, counts, counts_len);
+
+ /* Close a socket we've already seen to remove it from the bucket. */
+ close_idx = get_nth_socket(established_socks, established_socks_len,
+ link, listen_socks_len + 1);
+ if (!ASSERT_GE(close_idx, 0, "close_idx"))
+ return;
+ destroy(established_socks[close_idx]);
+ established_socks[close_idx] = -1;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure the last socket wasn't skipped and that there were no
+ * repeats.
+ */
+ check_n_were_seen_once(established_socks, established_socks_len,
+ established_socks_len - 1, counts, counts_len);
+}
+
+static void remove_unseen(int family, int sock_type, const char *addr,
+ __u16 port, int *socks, int socks_len,
+ int *established_socks, int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ int close_idx;
+
+ /* Iterate through the first socket. */
+ read_n(iter_fd, 1, counts, counts_len);
+
+ /* Make sure we saw a socket from fds. */
+ check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+ /* Close what would be the next socket in the bucket to exercise the
+ * condition where we need to skip past the first cookie we remembered.
+ */
+ close_idx = get_nth_socket(socks, socks_len, link, 1);
+ if (!ASSERT_GE(close_idx, 0, "close_idx"))
+ return;
+ close(socks[close_idx]);
+ socks[close_idx] = -1;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure the remaining sockets were seen exactly once and that we
+ * didn't repeat the socket that was already seen.
+ */
+ check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+ counts_len);
+}
+
+static void remove_unseen_established(int family, int sock_type,
+ const char *addr, __u16 port,
+ int *listen_socks, int listen_socks_len,
+ int *established_socks,
+ int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ int close_idx;
+
+ /* Iterate through all listening sockets. */
+ read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+ /* Make sure we saw all listening sockets exactly once. */
+ check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+ counts, counts_len);
+
+ /* Iterate through the first established socket. */
+ read_n(iter_fd, 1, counts, counts_len);
+
+ /* Make sure we saw one established socks. */
+ check_n_were_seen_once(established_socks, established_socks_len, 1,
+ counts, counts_len);
+
+ /* Close what would be the next socket in the bucket to exercise the
+ * condition where we need to skip past the first cookie we remembered.
+ */
+ close_idx = get_nth_socket(established_socks, established_socks_len,
+ link, listen_socks_len + 1);
+ if (!ASSERT_GE(close_idx, 0, "close_idx"))
+ return;
+
+ destroy(established_socks[close_idx]);
+ established_socks[close_idx] = -1;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure the remaining sockets were seen exactly once and that we
+ * didn't repeat the socket that was already seen.
+ */
+ check_n_were_seen_once(established_socks, established_socks_len,
+ established_socks_len - 1, counts, counts_len);
+}
+
+static void remove_all(int family, int sock_type, const char *addr,
+ __u16 port, int *socks, int socks_len,
+ int *established_socks, int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ int close_idx, i;
+
+ /* Iterate through the first socket. */
+ read_n(iter_fd, 1, counts, counts_len);
+
+ /* Make sure we saw a socket from fds. */
+ check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+ /* Close all remaining sockets to exhaust the list of saved cookies and
+ * exit without putting any sockets into the batch on the next read.
+ */
+ for (i = 0; i < socks_len - 1; i++) {
+ close_idx = get_nth_socket(socks, socks_len, link, 1);
+ if (!ASSERT_GE(close_idx, 0, "close_idx"))
+ return;
+ close(socks[close_idx]);
+ socks[close_idx] = -1;
+ }
+
+ /* Make sure there are no more sockets returned */
+ ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n");
+}
+
+static void remove_all_established(int family, int sock_type, const char *addr,
+ __u16 port, int *listen_socks,
+ int listen_socks_len, int *established_socks,
+ int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ int *close_idx = NULL;
+ int i;
+
+ /* Iterate through all listening sockets. */
+ read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+ /* Make sure we saw all listening sockets exactly once. */
+ check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+ counts, counts_len);
+
+ /* Iterate through the first established socket. */
+ read_n(iter_fd, 1, counts, counts_len);
+
+ /* Make sure we saw one established socks. */
+ check_n_were_seen_once(established_socks, established_socks_len, 1,
+ counts, counts_len);
+
+ /* Close all remaining sockets to exhaust the list of saved cookies and
+ * exit without putting any sockets into the batch on the next read.
+ */
+ close_idx = malloc(sizeof(int) * (established_socks_len - 1));
+ if (!ASSERT_OK_PTR(close_idx, "close_idx malloc"))
+ return;
+ for (i = 0; i < established_socks_len - 1; i++) {
+ close_idx[i] = get_nth_socket(established_socks,
+ established_socks_len, link,
+ listen_socks_len + i);
+ if (!ASSERT_GE(close_idx[i], 0, "close_idx"))
+ return;
+ }
+
+ for (i = 0; i < established_socks_len - 1; i++) {
+ destroy(established_socks[close_idx[i]]);
+ established_socks[close_idx[i]] = -1;
+ }
+
+ /* Make sure there are no more sockets returned */
+ ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n");
+ free(close_idx);
+}
+
+static void add_some(int family, int sock_type, const char *addr, __u16 port,
+ int *socks, int socks_len, int *established_socks,
+ int established_socks_len, struct sock_count *counts,
+ int counts_len, struct bpf_link *link, int iter_fd)
+{
+ int *new_socks = NULL;
+
+ /* Iterate through the first socks_len - 1 sockets. */
+ read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+ /* Make sure we saw socks_len - 1 sockets exactly once. */
+ check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+ counts_len);
+
+ /* Double the number of sockets in the bucket. */
+ new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+ socks_len);
+ if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+ goto done;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure each of the original sockets was seen exactly once. */
+ check_n_were_seen_once(socks, socks_len, socks_len, counts,
+ counts_len);
+done:
+ free_fds(new_socks, socks_len);
+}
+
+static void add_some_established(int family, int sock_type, const char *addr,
+ __u16 port, int *listen_socks,
+ int listen_socks_len, int *established_socks,
+ int established_socks_len,
+ struct sock_count *counts,
+ int counts_len, struct bpf_link *link,
+ int iter_fd)
+{
+ int *new_socks = NULL;
+
+ /* Iterate through all listening sockets. */
+ read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+ /* Make sure we saw all listening sockets exactly once. */
+ check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+ counts, counts_len);
+
+ /* Iterate through the first established_socks_len - 1 sockets. */
+ read_n(iter_fd, established_socks_len - 1, counts, counts_len);
+
+ /* Make sure we saw established_socks_len - 1 sockets exactly once. */
+ check_n_were_seen_once(established_socks, established_socks_len,
+ established_socks_len - 1, counts, counts_len);
+
+ /* Double the number of established sockets in the bucket. */
+ new_socks = connect_to_server(family, sock_type, addr, port,
+ established_socks_len / 2, listen_socks,
+ listen_socks_len);
+ if (!ASSERT_OK_PTR(new_socks, "connect_to_server"))
+ goto done;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure each of the original sockets was seen exactly once. */
+ check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+ counts, counts_len);
+ check_n_were_seen_once(established_socks, established_socks_len,
+ established_socks_len, counts, counts_len);
+done:
+ free_fds(new_socks, established_socks_len);
+}
+
+static void force_realloc(int family, int sock_type, const char *addr,
+ __u16 port, int *socks, int socks_len,
+ int *established_socks, int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ int *new_socks = NULL;
+
+ /* Iterate through the first socket just to initialize the batch. */
+ read_n(iter_fd, 1, counts, counts_len);
+
+ /* Double the number of sockets in the bucket to force a realloc on the
+ * next read.
+ */
+ new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+ socks_len);
+ if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+ goto done;
+
+ /* Iterate through the rest of the sockets. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure each socket from the first set was seen exactly once. */
+ check_n_were_seen_once(socks, socks_len, socks_len, counts,
+ counts_len);
+done:
+ free_fds(new_socks, socks_len);
+}
+
+static void force_realloc_established(int family, int sock_type,
+ const char *addr, __u16 port,
+ int *listen_socks, int listen_socks_len,
+ int *established_socks,
+ int established_socks_len,
+ struct sock_count *counts, int counts_len,
+ struct bpf_link *link, int iter_fd)
+{
+ /* Iterate through all sockets to trigger a realloc. */
+ read_n(iter_fd, -1, counts, counts_len);
+
+ /* Make sure each socket was seen exactly once. */
+ check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+ counts, counts_len);
+ check_n_were_seen_once(established_socks, established_socks_len,
+ established_socks_len, counts, counts_len);
+}
+
+struct test_case {
+ void (*test)(int family, int sock_type, const char *addr, __u16 port,
+ int *socks, int socks_len, int *established_socks,
+ int established_socks_len, struct sock_count *counts,
+ int counts_len, struct bpf_link *link, int iter_fd);
+ const char *description;
+ int ehash_buckets;
+ int connections;
+ int init_socks;
+ int max_socks;
+ int sock_type;
+ int family;
+};
+
+static struct test_case resume_tests[] = {
+ {
+ .description = "udp: resume after removing a seen socket",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_DGRAM,
+ .family = AF_INET6,
+ .test = remove_seen,
+ },
+ {
+ .description = "udp: resume after removing one unseen socket",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_DGRAM,
+ .family = AF_INET6,
+ .test = remove_unseen,
+ },
+ {
+ .description = "udp: resume after removing all unseen sockets",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_DGRAM,
+ .family = AF_INET6,
+ .test = remove_all,
+ },
+ {
+ .description = "udp: resume after adding a few sockets",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_DGRAM,
+ /* Use AF_INET so that new sockets are added to the head of the
+ * bucket's list.
+ */
+ .family = AF_INET,
+ .test = add_some,
+ },
+ {
+ .description = "udp: force a realloc to occur",
+ .init_socks = init_batch_size,
+ .max_socks = init_batch_size * 2,
+ .sock_type = SOCK_DGRAM,
+ /* Use AF_INET6 so that new sockets are added to the tail of the
+ * bucket's list, needing to be added to the next batch to force
+ * a realloc.
+ */
+ .family = AF_INET6,
+ .test = force_realloc,
+ },
+ {
+ .description = "tcp: resume after removing a seen socket (listening)",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = remove_seen,
+ },
+ {
+ .description = "tcp: resume after removing one unseen socket (listening)",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = remove_unseen,
+ },
+ {
+ .description = "tcp: resume after removing all unseen sockets (listening)",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = remove_all,
+ },
+ {
+ .description = "tcp: resume after adding a few sockets (listening)",
+ .init_socks = nr_soreuse,
+ .max_socks = nr_soreuse,
+ .sock_type = SOCK_STREAM,
+ /* Use AF_INET so that new sockets are added to the head of the
+ * bucket's list.
+ */
+ .family = AF_INET,
+ .test = add_some,
+ },
+ {
+ .description = "tcp: force a realloc to occur (listening)",
+ .init_socks = init_batch_size,
+ .max_socks = init_batch_size * 2,
+ .sock_type = SOCK_STREAM,
+ /* Use AF_INET6 so that new sockets are added to the tail of the
+ * bucket's list, needing to be added to the next batch to force
+ * a realloc.
+ */
+ .family = AF_INET6,
+ .test = force_realloc,
+ },
+ {
+ .description = "tcp: resume after removing a seen socket (established)",
+ /* Force all established sockets into one bucket */
+ .ehash_buckets = 1,
+ .connections = nr_soreuse,
+ .init_socks = nr_soreuse,
+ /* Room for connect()ed and accept()ed sockets */
+ .max_socks = nr_soreuse * 3,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = remove_seen_established,
+ },
+ {
+ .description = "tcp: resume after removing one unseen socket (established)",
+ /* Force all established sockets into one bucket */
+ .ehash_buckets = 1,
+ .connections = nr_soreuse,
+ .init_socks = nr_soreuse,
+ /* Room for connect()ed and accept()ed sockets */
+ .max_socks = nr_soreuse * 3,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = remove_unseen_established,
+ },
+ {
+ .description = "tcp: resume after removing all unseen sockets (established)",
+ /* Force all established sockets into one bucket */
+ .ehash_buckets = 1,
+ .connections = nr_soreuse,
+ .init_socks = nr_soreuse,
+ /* Room for connect()ed and accept()ed sockets */
+ .max_socks = nr_soreuse * 3,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = remove_all_established,
+ },
+ {
+ .description = "tcp: resume after adding a few sockets (established)",
+ /* Force all established sockets into one bucket */
+ .ehash_buckets = 1,
+ .connections = nr_soreuse,
+ .init_socks = nr_soreuse,
+ /* Room for connect()ed and accept()ed sockets */
+ .max_socks = nr_soreuse * 3,
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = add_some_established,
+ },
+ {
+ .description = "tcp: force a realloc to occur (established)",
+ /* Force all established sockets into one bucket */
+ .ehash_buckets = 1,
+ /* Bucket size will need to double when going from listening to
+ * established sockets.
+ */
+ .connections = init_batch_size,
+ .init_socks = nr_soreuse,
+ /* Room for connect()ed and accept()ed sockets */
+ .max_socks = nr_soreuse + (init_batch_size * 2),
+ .sock_type = SOCK_STREAM,
+ .family = AF_INET6,
+ .test = force_realloc_established,
+ },
+};
+
+static void do_resume_test(struct test_case *tc)
+{
+ struct sock_iter_batch *skel = NULL;
+ struct sock_count *counts = NULL;
+ static const __u16 port = 10001;
+ struct nstoken *nstoken = NULL;
+ struct bpf_link *link = NULL;
+ int *established_fds = NULL;
+ int err, iter_fd = -1;
+ const char *addr;
+ int *fds = NULL;
+
+ if (tc->ehash_buckets) {
+ SYS_NOFAIL("ip netns del " TEST_CHILD_NS);
+ SYS(done, "sysctl -wq net.ipv4.tcp_child_ehash_entries=%d",
+ tc->ehash_buckets);
+ SYS(done, "ip netns add %s", TEST_CHILD_NS);
+ SYS(done, "ip -net %s link set dev lo up", TEST_CHILD_NS);
+ nstoken = open_netns(TEST_CHILD_NS);
+ if (!ASSERT_OK_PTR(nstoken, "open_child_netns"))
+ goto done;
+ }
+
+ counts = calloc(tc->max_socks, sizeof(*counts));
+ if (!ASSERT_OK_PTR(counts, "counts"))
+ goto done;
+ skel = sock_iter_batch__open();
+ if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+ goto done;
+
+ /* Prepare a bucket of sockets in the kernel hashtable */
+ addr = tc->family == AF_INET6 ? "::1" : "127.0.0.1";
+ fds = start_reuseport_server(tc->family, tc->sock_type, addr, port, 0,
+ tc->init_socks);
+ if (!ASSERT_OK_PTR(fds, "start_reuseport_server"))
+ goto done;
+ if (tc->connections) {
+ established_fds = connect_to_server(tc->family, tc->sock_type,
+ addr, port,
+ tc->connections, fds,
+ tc->init_socks);
+ if (!ASSERT_OK_PTR(established_fds, "connect_to_server"))
+ goto done;
+ }
+ skel->rodata->ports[0] = 0;
+ skel->rodata->ports[1] = 0;
+ skel->rodata->sf = tc->family;
+ skel->rodata->ss = 0;
+
+ err = sock_iter_batch__load(skel);
+ if (!ASSERT_OK(err, "sock_iter_batch__load"))
+ goto done;
+
+ link = bpf_program__attach_iter(tc->sock_type == SOCK_STREAM ?
+ skel->progs.iter_tcp_soreuse :
+ skel->progs.iter_udp_soreuse,
+ NULL);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+ goto done;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+ goto done;
+
+ tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks,
+ established_fds, tc->connections*2, counts, tc->max_socks,
+ link, iter_fd);
+done:
+ close_netns(nstoken);
+ SYS_NOFAIL("ip netns del " TEST_CHILD_NS);
+ SYS_NOFAIL("sysctl -w net.ipv4.tcp_child_ehash_entries=0");
+ free(counts);
+ free_fds(fds, tc->init_socks);
+ free_fds(established_fds, tc->connections*2);
+ if (iter_fd >= 0)
+ close(iter_fd);
+ bpf_link__destroy(link);
+ sock_iter_batch__destroy(skel);
+}
+
+static void do_resume_tests(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(resume_tests); i++) {
+ if (test__start_subtest(resume_tests[i].description)) {
+ do_resume_test(&resume_tests[i]);
+ }
+ }
+}
+
static void do_test(int sock_type, bool onebyone)
{
int err, i, nread, to_read, total_read, iter_fd = -1;
- int first_idx, second_idx, indices[nr_soreuse];
+ struct iter_out outputs[nr_soreuse];
struct bpf_link *link = NULL;
struct sock_iter_batch *skel;
+ int first_idx, second_idx;
int *fds[2] = {};
skel = sock_iter_batch__open();
@@ -34,6 +889,9 @@ static void do_test(int sock_type, bool onebyone)
goto done;
skel->rodata->ports[i] = ntohs(local_port);
}
+ skel->rodata->sf = AF_INET6;
+ if (sock_type == SOCK_STREAM)
+ skel->rodata->ss = TCP_LISTEN;
err = sock_iter_batch__load(skel);
if (!ASSERT_OK(err, "sock_iter_batch__load"))
@@ -55,38 +913,38 @@ static void do_test(int sock_type, bool onebyone)
* from a bucket and leave one socket out from
* that bucket on purpose.
*/
- to_read = (nr_soreuse - 1) * sizeof(*indices);
+ to_read = (nr_soreuse - 1) * sizeof(*outputs);
total_read = 0;
first_idx = -1;
do {
- nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
- if (nread <= 0 || nread % sizeof(*indices))
+ nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+ if (nread <= 0 || nread % sizeof(*outputs))
break;
total_read += nread;
if (first_idx == -1)
- first_idx = indices[0];
- for (i = 0; i < nread / sizeof(*indices); i++)
- ASSERT_EQ(indices[i], first_idx, "first_idx");
+ first_idx = outputs[0].idx;
+ for (i = 0; i < nread / sizeof(*outputs); i++)
+ ASSERT_EQ(outputs[i].idx, first_idx, "first_idx");
} while (total_read < to_read);
- ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread");
+ ASSERT_EQ(nread, onebyone ? sizeof(*outputs) : to_read, "nread");
ASSERT_EQ(total_read, to_read, "total_read");
free_fds(fds[first_idx], nr_soreuse);
fds[first_idx] = NULL;
/* Read the "whole" second bucket */
- to_read = nr_soreuse * sizeof(*indices);
+ to_read = nr_soreuse * sizeof(*outputs);
total_read = 0;
second_idx = !first_idx;
do {
- nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
- if (nread <= 0 || nread % sizeof(*indices))
+ nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+ if (nread <= 0 || nread % sizeof(*outputs))
break;
total_read += nread;
- for (i = 0; i < nread / sizeof(*indices); i++)
- ASSERT_EQ(indices[i], second_idx, "second_idx");
+ for (i = 0; i < nread / sizeof(*outputs); i++)
+ ASSERT_EQ(outputs[i].idx, second_idx, "second_idx");
} while (total_read <= to_read);
ASSERT_EQ(nread, 0, "nread");
/* Both so_reuseport ports should be in different buckets, so
@@ -128,6 +986,7 @@ void test_sock_iter_batch(void)
do_test(SOCK_DGRAM, true);
do_test(SOCK_DGRAM, false);
}
+ do_resume_tests();
close_netns(nstoken);
done:
diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
index 1bdfb79ef009..e02cabcc814e 100644
--- a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
@@ -3,6 +3,7 @@
#ifndef __SOCKET_HELPERS__
#define __SOCKET_HELPERS__
+#include <sys/un.h>
#include <linux/vm_sockets.h>
/* include/linux/net.h */
@@ -169,6 +170,15 @@ static inline void init_addr_loopback6(struct sockaddr_storage *ss,
*len = sizeof(*addr6);
}
+static inline void init_addr_loopback_unix(struct sockaddr_storage *ss,
+ socklen_t *len)
+{
+ struct sockaddr_un *addr = memset(ss, 0, sizeof(*ss));
+
+ addr->sun_family = AF_UNIX;
+ *len = sizeof(sa_family_t);
+}
+
static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
socklen_t *len)
{
@@ -190,6 +200,9 @@ static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
case AF_INET6:
init_addr_loopback6(ss, len);
return;
+ case AF_UNIX:
+ init_addr_loopback_unix(ss, len);
+ return;
case AF_VSOCK:
init_addr_loopback_vsock(ss, len);
return;
@@ -315,21 +328,27 @@ static inline int create_pair(int family, int sotype, int *p0, int *p1)
{
__close_fd int s, c = -1, p = -1;
struct sockaddr_storage addr;
- socklen_t len = sizeof(addr);
+ socklen_t len;
int err;
s = socket_loopback(family, sotype);
if (s < 0)
return s;
- err = xgetsockname(s, sockaddr(&addr), &len);
- if (err)
- return err;
-
c = xsocket(family, sotype, 0);
if (c < 0)
return c;
+ init_addr_loopback(family, &addr, &len);
+ err = xbind(c, sockaddr(&addr), len);
+ if (err)
+ return err;
+
+ len = sizeof(addr);
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ return err;
+
err = connect(c, sockaddr(&addr), len);
if (err) {
if (errno != EINPROGRESS) {
@@ -391,4 +410,59 @@ static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
return err;
}
+static inline const char *socket_kind_to_str(int sock_fd)
+{
+ socklen_t opt_len;
+ int domain, type;
+
+ opt_len = sizeof(domain);
+ if (getsockopt(sock_fd, SOL_SOCKET, SO_DOMAIN, &domain, &opt_len))
+ FAIL_ERRNO("getsockopt(SO_DOMAIN)");
+
+ opt_len = sizeof(type);
+ if (getsockopt(sock_fd, SOL_SOCKET, SO_TYPE, &type, &opt_len))
+ FAIL_ERRNO("getsockopt(SO_TYPE)");
+
+ switch (domain) {
+ case AF_INET:
+ switch (type) {
+ case SOCK_STREAM:
+ return "tcp4";
+ case SOCK_DGRAM:
+ return "udp4";
+ }
+ break;
+ case AF_INET6:
+ switch (type) {
+ case SOCK_STREAM:
+ return "tcp6";
+ case SOCK_DGRAM:
+ return "udp6";
+ }
+ break;
+ case AF_UNIX:
+ switch (type) {
+ case SOCK_STREAM:
+ return "u_str";
+ case SOCK_DGRAM:
+ return "u_dgr";
+ case SOCK_SEQPACKET:
+ return "u_seq";
+ }
+ break;
+ case AF_VSOCK:
+ switch (type) {
+ case SOCK_STREAM:
+ return "v_str";
+ case SOCK_DGRAM:
+ return "v_dgr";
+ case SOCK_SEQPACKET:
+ return "v_seq";
+ }
+ break;
+ }
+
+ return "???";
+}
+
#endif // __SOCKET_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index 3e5571dd578d..d815efac52fd 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -5,12 +5,15 @@
#define MAX_TEST_NAME 80
+#define u32(v) ((u32){(v)})
+#define u64(v) ((u64){(v)})
+
#define __always_unused __attribute__((__unused__))
#define xbpf_map_delete_elem(fd, key) \
({ \
int __ret = bpf_map_delete_elem((fd), (key)); \
- if (__ret < 0) \
+ if (__ret < 0) \
FAIL_ERRNO("map_delete"); \
__ret; \
})
@@ -18,7 +21,7 @@
#define xbpf_map_lookup_elem(fd, key, val) \
({ \
int __ret = bpf_map_lookup_elem((fd), (key), (val)); \
- if (__ret < 0) \
+ if (__ret < 0) \
FAIL_ERRNO("map_lookup"); \
__ret; \
})
@@ -26,7 +29,7 @@
#define xbpf_map_update_elem(fd, key, val, flags) \
({ \
int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \
- if (__ret < 0) \
+ if (__ret < 0) \
FAIL_ERRNO("map_update"); \
__ret; \
})
@@ -35,7 +38,7 @@
({ \
int __ret = \
bpf_prog_attach((prog), (target), (type), (flags)); \
- if (__ret < 0) \
+ if (__ret < 0) \
FAIL_ERRNO("prog_attach(" #type ")"); \
__ret; \
})
@@ -43,7 +46,7 @@
#define xbpf_prog_detach2(prog, target, type) \
({ \
int __ret = bpf_prog_detach2((prog), (target), (type)); \
- if (__ret < 0) \
+ if (__ret < 0) \
FAIL_ERRNO("prog_detach2(" #type ")"); \
__ret; \
})
@@ -66,21 +69,15 @@
__ret; \
})
-static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
+static inline int add_to_sockmap(int mapfd, int fd1, int fd2)
{
- u64 value;
- u32 key;
int err;
- key = 0;
- value = fd1;
- err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ err = xbpf_map_update_elem(mapfd, &u32(0), &u64(fd1), BPF_NOEXIST);
if (err)
return err;
- key = 1;
- value = fd2;
- return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ return xbpf_map_update_elem(mapfd, &u32(1), &u64(fd2), BPF_NOEXIST);
}
#endif // __SOCKMAP_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 2d0796314862..b87e7f39e15a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -3,77 +3,62 @@
/*
* Tests for sockmap/sockhash holding kTLS sockets.
*/
-
+#include <error.h>
#include <netinet/tcp.h>
+#include <linux/tls.h>
#include "test_progs.h"
+#include "sockmap_helpers.h"
+#include "test_skmsg_load_helpers.skel.h"
+#include "test_sockmap_ktls.skel.h"
#define MAX_TEST_NAME 80
#define TCP_ULP 31
-static int tcp_server(int family)
+static int init_ktls_pairs(int c, int p)
{
- int err, s;
-
- s = socket(family, SOCK_STREAM, 0);
- if (!ASSERT_GE(s, 0, "socket"))
- return -1;
-
- err = listen(s, SOMAXCONN);
- if (!ASSERT_OK(err, "listen"))
- return -1;
-
- return s;
-}
+ int err;
+ struct tls12_crypto_info_aes_gcm_128 crypto_rx;
+ struct tls12_crypto_info_aes_gcm_128 crypto_tx;
-static int disconnect(int fd)
-{
- struct sockaddr unspec = { AF_UNSPEC };
+ err = setsockopt(c, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
+ if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
+ goto out;
- return connect(fd, &unspec, sizeof(unspec));
+ err = setsockopt(p, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
+ if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
+ goto out;
+
+ memset(&crypto_rx, 0, sizeof(crypto_rx));
+ memset(&crypto_tx, 0, sizeof(crypto_tx));
+ crypto_rx.info.version = TLS_1_2_VERSION;
+ crypto_tx.info.version = TLS_1_2_VERSION;
+ crypto_rx.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+ crypto_tx.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+ err = setsockopt(c, SOL_TLS, TLS_TX, &crypto_tx, sizeof(crypto_tx));
+ if (!ASSERT_OK(err, "setsockopt(TLS_TX)"))
+ goto out;
+
+ err = setsockopt(p, SOL_TLS, TLS_RX, &crypto_rx, sizeof(crypto_rx));
+ if (!ASSERT_OK(err, "setsockopt(TLS_RX)"))
+ goto out;
+ return 0;
+out:
+ return -1;
}
-/* Disconnect (unhash) a kTLS socket after removing it from sockmap. */
-static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
+static int create_ktls_pairs(int family, int sotype, int *c, int *p)
{
- struct sockaddr_storage addr = {0};
- socklen_t len = sizeof(addr);
- int err, cli, srv, zero = 0;
-
- srv = tcp_server(family);
- if (srv == -1)
- return;
-
- err = getsockname(srv, (struct sockaddr *)&addr, &len);
- if (!ASSERT_OK(err, "getsockopt"))
- goto close_srv;
-
- cli = socket(family, SOCK_STREAM, 0);
- if (!ASSERT_GE(cli, 0, "socket"))
- goto close_srv;
+ int err;
- err = connect(cli, (struct sockaddr *)&addr, len);
- if (!ASSERT_OK(err, "connect"))
- goto close_cli;
-
- err = bpf_map_update_elem(map, &zero, &cli, 0);
- if (!ASSERT_OK(err, "bpf_map_update_elem"))
- goto close_cli;
-
- err = setsockopt(cli, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
- if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
- goto close_cli;
-
- err = bpf_map_delete_elem(map, &zero);
- if (!ASSERT_OK(err, "bpf_map_delete_elem"))
- goto close_cli;
-
- err = disconnect(cli);
- ASSERT_OK(err, "disconnect");
+ err = create_pair(family, sotype, c, p);
+ if (!ASSERT_OK(err, "create_pair()"))
+ return -1;
-close_cli:
- close(cli);
-close_srv:
- close(srv);
+ err = init_ktls_pairs(*c, *p);
+ if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+ return -1;
+ return 0;
}
static void test_sockmap_ktls_update_fails_when_sock_has_ulp(int family, int map)
@@ -146,6 +131,278 @@ static const char *fmt_test_name(const char *subtest_name, int family,
return test_name;
}
+static void test_sockmap_ktls_offload(int family, int sotype)
+{
+ int err;
+ int c = 0, p = 0, sent, recvd;
+ char msg[12] = "hello world\0";
+ char rcv[13];
+
+ err = create_ktls_pairs(family, sotype, &c, &p);
+ if (!ASSERT_OK(err, "create_ktls_pairs()"))
+ goto out;
+
+ sent = send(c, msg, sizeof(msg), 0);
+ if (!ASSERT_OK(err, "send(msg)"))
+ goto out;
+
+ recvd = recv(p, rcv, sizeof(rcv), 0);
+ if (!ASSERT_OK(err, "recv(msg)") ||
+ !ASSERT_EQ(recvd, sent, "length mismatch"))
+ goto out;
+
+ ASSERT_OK(memcmp(msg, rcv, sizeof(msg)), "data mismatch");
+
+out:
+ if (c)
+ close(c);
+ if (p)
+ close(p);
+}
+
+static void test_sockmap_ktls_tx_cork(int family, int sotype, bool push)
+{
+ int err, off;
+ int i, j;
+ int start_push = 0, push_len = 0;
+ int c = 0, p = 0, one = 1, sent, recvd;
+ int prog_fd, map_fd;
+ char msg[12] = "hello world\0";
+ char rcv[20] = {0};
+ struct test_sockmap_ktls *skel;
+
+ skel = test_sockmap_ktls__open_and_load();
+ if (!ASSERT_TRUE(skel, "open ktls skel"))
+ return;
+
+ err = create_pair(family, sotype, &c, &p);
+ if (!ASSERT_OK(err, "create_pair()"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs.prog_sk_policy);
+ map_fd = bpf_map__fd(skel->maps.sock_map);
+
+ err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach sk msg"))
+ goto out;
+
+ err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(c)"))
+ goto out;
+
+ err = init_ktls_pairs(c, p);
+ if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+ goto out;
+
+ skel->bss->cork_byte = sizeof(msg);
+ if (push) {
+ start_push = 1;
+ push_len = 2;
+ }
+ skel->bss->push_start = start_push;
+ skel->bss->push_end = push_len;
+
+ off = sizeof(msg) / 2;
+ sent = send(c, msg, off, 0);
+ if (!ASSERT_EQ(sent, off, "send(msg)"))
+ goto out;
+
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+ if (!ASSERT_EQ(-1, recvd, "expected no data"))
+ goto out;
+
+ /* send remaining msg */
+ sent = send(c, msg + off, sizeof(msg) - off, 0);
+ if (!ASSERT_EQ(sent, sizeof(msg) - off, "send remaining data"))
+ goto out;
+
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+ if (!ASSERT_OK(err, "recv(msg)") ||
+ !ASSERT_EQ(recvd, sizeof(msg) + push_len, "check length mismatch"))
+ goto out;
+
+ for (i = 0, j = 0; i < recvd;) {
+ /* skip checking the data that has been pushed in */
+ if (i >= start_push && i <= start_push + push_len - 1) {
+ i++;
+ continue;
+ }
+ if (!ASSERT_EQ(rcv[i], msg[j], "data mismatch"))
+ goto out;
+ i++;
+ j++;
+ }
+out:
+ if (c)
+ close(c);
+ if (p)
+ close(p);
+ test_sockmap_ktls__destroy(skel);
+}
+
+static void test_sockmap_ktls_tx_no_buf(int family, int sotype, bool push)
+{
+ int c = -1, p = -1, one = 1, two = 2;
+ struct test_sockmap_ktls *skel;
+ unsigned char *data = NULL;
+ struct msghdr msg = {0};
+ struct iovec iov[2];
+ int prog_fd, map_fd;
+ int txrx_buf = 1024;
+ int iov_length = 8192;
+ int err;
+
+ skel = test_sockmap_ktls__open_and_load();
+ if (!ASSERT_TRUE(skel, "open ktls skel"))
+ return;
+
+ err = create_pair(family, sotype, &c, &p);
+ if (!ASSERT_OK(err, "create_pair()"))
+ goto out;
+
+ err = setsockopt(c, SOL_SOCKET, SO_RCVBUFFORCE, &txrx_buf, sizeof(int));
+ err |= setsockopt(p, SOL_SOCKET, SO_SNDBUFFORCE, &txrx_buf, sizeof(int));
+ if (!ASSERT_OK(err, "set buf limit"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs.prog_sk_policy_redir);
+ map_fd = bpf_map__fd(skel->maps.sock_map);
+
+ err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach sk msg"))
+ goto out;
+
+ err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(c)"))
+ goto out;
+
+ err = bpf_map_update_elem(map_fd, &two, &p, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+ goto out;
+
+ skel->bss->apply_bytes = 1024;
+
+ err = init_ktls_pairs(c, p);
+ if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+ goto out;
+
+ data = calloc(iov_length, sizeof(char));
+ if (!data)
+ goto out;
+
+ iov[0].iov_base = data;
+ iov[0].iov_len = iov_length;
+ iov[1].iov_base = data;
+ iov[1].iov_len = iov_length;
+ msg.msg_iov = iov;
+ msg.msg_iovlen = 2;
+
+ for (;;) {
+ err = sendmsg(c, &msg, MSG_DONTWAIT);
+ if (err <= 0)
+ break;
+ }
+
+out:
+ if (data)
+ free(data);
+ if (c != -1)
+ close(c);
+ if (p != -1)
+ close(p);
+
+ test_sockmap_ktls__destroy(skel);
+}
+
+static void test_sockmap_ktls_tx_pop(int family, int sotype)
+{
+ char msg[37] = "0123456789abcdefghijklmnopqrstuvwxyz\0";
+ int c = 0, p = 0, one = 1, sent, recvd;
+ struct test_sockmap_ktls *skel;
+ int prog_fd, map_fd;
+ char rcv[50] = {0};
+ int err;
+ int i, m, r;
+
+ skel = test_sockmap_ktls__open_and_load();
+ if (!ASSERT_TRUE(skel, "open ktls skel"))
+ return;
+
+ err = create_pair(family, sotype, &c, &p);
+ if (!ASSERT_OK(err, "create_pair()"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs.prog_sk_policy);
+ map_fd = bpf_map__fd(skel->maps.sock_map);
+
+ err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach sk msg"))
+ goto out;
+
+ err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(c)"))
+ goto out;
+
+ err = init_ktls_pairs(c, p);
+ if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+ goto out;
+
+ struct {
+ int pop_start;
+ int pop_len;
+ } pop_policy[] = {
+ /* trim the start */
+ {0, 2},
+ {0, 10},
+ {1, 2},
+ {1, 10},
+ /* trim the end */
+ {35, 2},
+ /* New entries should be added before this line */
+ {-1, -1},
+ };
+
+ i = 0;
+ while (pop_policy[i].pop_start >= 0) {
+ skel->bss->pop_start = pop_policy[i].pop_start;
+ skel->bss->pop_end = pop_policy[i].pop_len;
+
+ sent = send(c, msg, sizeof(msg), 0);
+ if (!ASSERT_EQ(sent, sizeof(msg), "send(msg)"))
+ goto out;
+
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+ if (!ASSERT_EQ(recvd, sizeof(msg) - pop_policy[i].pop_len, "pop len mismatch"))
+ goto out;
+
+ /* verify the data
+ * msg: 0123456789a bcdefghij klmnopqrstuvwxyz
+ * | |
+ * popped data
+ */
+ for (m = 0, r = 0; m < sizeof(msg);) {
+ /* skip checking the data that has been popped */
+ if (m >= pop_policy[i].pop_start &&
+ m <= pop_policy[i].pop_start + pop_policy[i].pop_len - 1) {
+ m++;
+ continue;
+ }
+
+ if (!ASSERT_EQ(msg[m], rcv[r], "data mismatch"))
+ goto out;
+ m++;
+ r++;
+ }
+ i++;
+ }
+out:
+ if (c)
+ close(c);
+ if (p)
+ close(p);
+ test_sockmap_ktls__destroy(skel);
+}
+
static void run_tests(int family, enum bpf_map_type map_type)
{
int map;
@@ -154,18 +411,32 @@ static void run_tests(int family, enum bpf_map_type map_type)
if (!ASSERT_GE(map, 0, "bpf_map_create"))
return;
- if (test__start_subtest(fmt_test_name("disconnect_after_delete", family, map_type)))
- test_sockmap_ktls_disconnect_after_delete(family, map);
if (test__start_subtest(fmt_test_name("update_fails_when_sock_has_ulp", family, map_type)))
test_sockmap_ktls_update_fails_when_sock_has_ulp(family, map);
close(map);
}
+static void run_ktls_test(int family, int sotype)
+{
+ if (test__start_subtest("tls simple offload"))
+ test_sockmap_ktls_offload(family, sotype);
+ if (test__start_subtest("tls tx cork"))
+ test_sockmap_ktls_tx_cork(family, sotype, false);
+ if (test__start_subtest("tls tx cork with push"))
+ test_sockmap_ktls_tx_cork(family, sotype, true);
+ if (test__start_subtest("tls tx egress with no buf"))
+ test_sockmap_ktls_tx_no_buf(family, sotype, true);
+ if (test__start_subtest("tls tx with pop"))
+ test_sockmap_ktls_tx_pop(family, sotype);
+}
+
void test_sockmap_ktls(void)
{
run_tests(AF_INET, BPF_MAP_TYPE_SOCKMAP);
run_tests(AF_INET, BPF_MAP_TYPE_SOCKHASH);
run_tests(AF_INET6, BPF_MAP_TYPE_SOCKMAP);
run_tests(AF_INET6, BPF_MAP_TYPE_SOCKHASH);
+ run_ktls_test(AF_INET, SOCK_STREAM);
+ run_ktls_test(AF_INET6, SOCK_STREAM);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 4ee1148d22be..f1bdccc7e4e7 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -924,6 +924,8 @@ static void redir_partial(int family, int sotype, int sock_map, int parser_map)
goto close;
n = xsend(c1, buf, sizeof(buf), 0);
+ if (n == -1)
+ goto close;
if (n < sizeof(buf))
FAIL("incomplete write");
@@ -1366,237 +1368,6 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
}
}
-static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
- int sock_mapfd, int nop_mapfd,
- int verd_mapfd, enum redir_mode mode,
- int send_flags)
-{
- const char *log_prefix = redir_mode_str(mode);
- unsigned int pass;
- int err, n;
- u32 key;
- char b;
-
- zero_verdict_count(verd_mapfd);
-
- err = add_to_sockmap(sock_mapfd, peer0, peer1);
- if (err)
- return;
-
- if (nop_mapfd >= 0) {
- err = add_to_sockmap(nop_mapfd, cli0, cli1);
- if (err)
- return;
- }
-
- /* Last byte is OOB data when send_flags has MSG_OOB bit set */
- n = xsend(cli1, "ab", 2, send_flags);
- if (n >= 0 && n < 2)
- FAIL("%s: incomplete send", log_prefix);
- if (n < 2)
- return;
-
- key = SK_PASS;
- err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
- if (err)
- return;
- if (pass != 1)
- FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
- n = recv_timeout(mode == REDIR_INGRESS ? peer0 : cli0, &b, 1, 0, IO_TIMEOUT_SEC);
- if (n < 0)
- FAIL_ERRNO("%s: recv_timeout", log_prefix);
- if (n == 0)
- FAIL("%s: incomplete recv", log_prefix);
-
- if (send_flags & MSG_OOB) {
- /* Check that we can't read OOB while in sockmap */
- errno = 0;
- n = recv(peer1, &b, 1, MSG_OOB | MSG_DONTWAIT);
- if (n != -1 || errno != EOPNOTSUPP)
- FAIL("%s: recv(MSG_OOB): expected EOPNOTSUPP: retval=%d errno=%d",
- log_prefix, n, errno);
-
- /* Remove peer1 from sockmap */
- xbpf_map_delete_elem(sock_mapfd, &(int){ 1 });
-
- /* Check that OOB was dropped on redirect */
- errno = 0;
- n = recv(peer1, &b, 1, MSG_OOB | MSG_DONTWAIT);
- if (n != -1 || errno != EINVAL)
- FAIL("%s: recv(MSG_OOB): expected EINVAL: retval=%d errno=%d",
- log_prefix, n, errno);
- }
-}
-
-static void unix_redir_to_connected(int sotype, int sock_mapfd,
- int verd_mapfd, enum redir_mode mode)
-{
- int c0, c1, p0, p1;
- int sfd[2];
-
- if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
- return;
- c0 = sfd[0], p0 = sfd[1];
-
- if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
- goto close0;
- c1 = sfd[0], p1 = sfd[1];
-
- pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd,
- mode, NO_FLAGS);
-
- xclose(c1);
- xclose(p1);
-close0:
- xclose(c0);
- xclose(p0);
-}
-
-static void unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
- struct bpf_map *inner_map, int sotype)
-{
- int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
- int verdict_map = bpf_map__fd(skel->maps.verdict_map);
- int sock_map = bpf_map__fd(inner_map);
- int err;
-
- err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
- if (err)
- return;
-
- skel->bss->test_ingress = false;
- unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_EGRESS);
- skel->bss->test_ingress = true;
- unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_INGRESS);
-
- xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
- int sotype)
-{
- const char *family_name, *map_name;
- char s[MAX_TEST_NAME];
-
- family_name = family_str(AF_UNIX);
- map_name = map_type_str(map);
- snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
- if (!test__start_subtest(s))
- return;
- unix_skb_redir_to_connected(skel, map, sotype);
-}
-
-/* Returns two connected loopback vsock sockets */
-static int vsock_socketpair_connectible(int sotype, int *v0, int *v1)
-{
- return create_pair(AF_VSOCK, sotype | SOCK_NONBLOCK, v0, v1);
-}
-
-static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd,
- enum redir_mode mode, int sotype)
-{
- const char *log_prefix = redir_mode_str(mode);
- char a = 'a', b = 'b';
- int u0, u1, v0, v1;
- int sfd[2];
- unsigned int pass;
- int err, n;
- u32 key;
-
- zero_verdict_count(verd_mapfd);
-
- if (socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0, sfd))
- return;
-
- u0 = sfd[0];
- u1 = sfd[1];
-
- err = vsock_socketpair_connectible(sotype, &v0, &v1);
- if (err) {
- FAIL("vsock_socketpair_connectible() failed");
- goto close_uds;
- }
-
- err = add_to_sockmap(sock_mapfd, u0, v0);
- if (err) {
- FAIL("add_to_sockmap failed");
- goto close_vsock;
- }
-
- n = write(v1, &a, sizeof(a));
- if (n < 0)
- FAIL_ERRNO("%s: write", log_prefix);
- if (n == 0)
- FAIL("%s: incomplete write", log_prefix);
- if (n < 1)
- goto out;
-
- n = xrecv_nonblock(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), 0);
- if (n < 0)
- FAIL("%s: recv() err, errno=%d", log_prefix, errno);
- if (n == 0)
- FAIL("%s: incomplete recv", log_prefix);
- if (b != a)
- FAIL("%s: vsock socket map failed, %c != %c", log_prefix, a, b);
-
- key = SK_PASS;
- err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
- if (err)
- goto out;
- if (pass != 1)
- FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-out:
- key = 0;
- bpf_map_delete_elem(sock_mapfd, &key);
- key = 1;
- bpf_map_delete_elem(sock_mapfd, &key);
-
-close_vsock:
- close(v0);
- close(v1);
-
-close_uds:
- close(u0);
- close(u1);
-}
-
-static void vsock_unix_skb_redir_connectible(struct test_sockmap_listen *skel,
- struct bpf_map *inner_map,
- int sotype)
-{
- int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
- int verdict_map = bpf_map__fd(skel->maps.verdict_map);
- int sock_map = bpf_map__fd(inner_map);
- int err;
-
- err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
- if (err)
- return;
-
- skel->bss->test_ingress = false;
- vsock_unix_redir_connectible(sock_map, verdict_map, REDIR_EGRESS, sotype);
- skel->bss->test_ingress = true;
- vsock_unix_redir_connectible(sock_map, verdict_map, REDIR_INGRESS, sotype);
-
- xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_vsock_redir(struct test_sockmap_listen *skel, struct bpf_map *map)
-{
- const char *family_name, *map_name;
- char s[MAX_TEST_NAME];
-
- family_name = family_str(AF_VSOCK);
- map_name = map_type_str(map);
- snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
- if (!test__start_subtest(s))
- return;
-
- vsock_unix_skb_redir_connectible(skel, map, SOCK_STREAM);
- vsock_unix_skb_redir_connectible(skel, map, SOCK_SEQPACKET);
-}
-
static void test_reuseport(struct test_sockmap_listen *skel,
struct bpf_map *map, int family, int sotype)
{
@@ -1637,224 +1408,6 @@ static void test_reuseport(struct test_sockmap_listen *skel,
}
}
-static int inet_socketpair(int family, int type, int *s, int *c)
-{
- return create_pair(family, type | SOCK_NONBLOCK, s, c);
-}
-
-static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
- enum redir_mode mode)
-{
- int c0, c1, p0, p1;
- int err;
-
- err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
- if (err)
- return;
- err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1);
- if (err)
- goto close_cli0;
-
- pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd,
- mode, NO_FLAGS);
-
- xclose(c1);
- xclose(p1);
-close_cli0:
- xclose(c0);
- xclose(p0);
-}
-
-static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
- struct bpf_map *inner_map, int family)
-{
- int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
- int verdict_map = bpf_map__fd(skel->maps.verdict_map);
- int sock_map = bpf_map__fd(inner_map);
- int err;
-
- err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
- if (err)
- return;
-
- skel->bss->test_ingress = false;
- udp_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
- skel->bss->test_ingress = true;
- udp_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
-
- xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
- int family)
-{
- const char *family_name, *map_name;
- char s[MAX_TEST_NAME];
-
- family_name = family_str(family);
- map_name = map_type_str(map);
- snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
- if (!test__start_subtest(s))
- return;
- udp_skb_redir_to_connected(skel, map, family);
-}
-
-static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
- int verd_mapfd, enum redir_mode mode)
-{
- int c0, c1, p0, p1;
- int sfd[2];
- int err;
-
- if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd))
- return;
- c0 = sfd[0], p0 = sfd[1];
-
- err = inet_socketpair(family, type, &p1, &c1);
- if (err)
- goto close;
-
- pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd,
- mode, NO_FLAGS);
-
- xclose(c1);
- xclose(p1);
-close:
- xclose(c0);
- xclose(p0);
-}
-
-static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
- struct bpf_map *inner_map, int family)
-{
- int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
- int verdict_map = bpf_map__fd(skel->maps.verdict_map);
- int sock_map = bpf_map__fd(inner_map);
- int err;
-
- err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
- if (err)
- return;
-
- skel->bss->test_ingress = false;
- inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
- REDIR_EGRESS);
- inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
- REDIR_EGRESS);
- skel->bss->test_ingress = true;
- inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
- REDIR_INGRESS);
- inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
- REDIR_INGRESS);
-
- xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
- int nop_mapfd, int verd_mapfd,
- enum redir_mode mode, int send_flags)
-{
- int c0, c1, p0, p1;
- int sfd[2];
- int err;
-
- err = inet_socketpair(family, type, &p0, &c0);
- if (err)
- return;
-
- if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd))
- goto close_cli0;
- c1 = sfd[0], p1 = sfd[1];
-
- pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, nop_mapfd,
- verd_mapfd, mode, send_flags);
-
- xclose(c1);
- xclose(p1);
-close_cli0:
- xclose(c0);
- xclose(p0);
-}
-
-static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
- struct bpf_map *inner_map, int family)
-{
- int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
- int nop_map = bpf_map__fd(skel->maps.nop_map);
- int verdict_map = bpf_map__fd(skel->maps.verdict_map);
- int sock_map = bpf_map__fd(inner_map);
- int err;
-
- err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
- if (err)
- return;
-
- skel->bss->test_ingress = false;
- unix_inet_redir_to_connected(family, SOCK_DGRAM,
- sock_map, -1, verdict_map,
- REDIR_EGRESS, NO_FLAGS);
- unix_inet_redir_to_connected(family, SOCK_STREAM,
- sock_map, -1, verdict_map,
- REDIR_EGRESS, NO_FLAGS);
-
- unix_inet_redir_to_connected(family, SOCK_DGRAM,
- sock_map, nop_map, verdict_map,
- REDIR_EGRESS, NO_FLAGS);
- unix_inet_redir_to_connected(family, SOCK_STREAM,
- sock_map, nop_map, verdict_map,
- REDIR_EGRESS, NO_FLAGS);
-
- /* MSG_OOB not supported by AF_UNIX SOCK_DGRAM */
- unix_inet_redir_to_connected(family, SOCK_STREAM,
- sock_map, nop_map, verdict_map,
- REDIR_EGRESS, MSG_OOB);
-
- skel->bss->test_ingress = true;
- unix_inet_redir_to_connected(family, SOCK_DGRAM,
- sock_map, -1, verdict_map,
- REDIR_INGRESS, NO_FLAGS);
- unix_inet_redir_to_connected(family, SOCK_STREAM,
- sock_map, -1, verdict_map,
- REDIR_INGRESS, NO_FLAGS);
-
- unix_inet_redir_to_connected(family, SOCK_DGRAM,
- sock_map, nop_map, verdict_map,
- REDIR_INGRESS, NO_FLAGS);
- unix_inet_redir_to_connected(family, SOCK_STREAM,
- sock_map, nop_map, verdict_map,
- REDIR_INGRESS, NO_FLAGS);
-
- /* MSG_OOB not supported by AF_UNIX SOCK_DGRAM */
- unix_inet_redir_to_connected(family, SOCK_STREAM,
- sock_map, nop_map, verdict_map,
- REDIR_INGRESS, MSG_OOB);
-
- xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
- int family)
-{
- const char *family_name, *map_name;
- struct netns_obj *netns;
- char s[MAX_TEST_NAME];
-
- family_name = family_str(family);
- map_name = map_type_str(map);
- snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
- if (!test__start_subtest(s))
- return;
-
- netns = netns_new("sockmap_listen", true);
- if (!ASSERT_OK_PTR(netns, "netns_new"))
- return;
-
- inet_unix_skb_redir_to_connected(skel, map, family);
- unix_inet_skb_redir_to_connected(skel, map, family);
-
- netns_free(netns);
-}
-
static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
int family)
{
@@ -1863,8 +1416,6 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
test_redir(skel, map, family, SOCK_STREAM);
test_reuseport(skel, map, family, SOCK_STREAM);
test_reuseport(skel, map, family, SOCK_DGRAM);
- test_udp_redir(skel, map, family);
- test_udp_unix_redir(skel, map, family);
}
void serial_test_sockmap_listen(void)
@@ -1880,16 +1431,10 @@ void serial_test_sockmap_listen(void)
skel->bss->test_sockmap = true;
run_tests(skel, skel->maps.sock_map, AF_INET);
run_tests(skel, skel->maps.sock_map, AF_INET6);
- test_unix_redir(skel, skel->maps.sock_map, SOCK_DGRAM);
- test_unix_redir(skel, skel->maps.sock_map, SOCK_STREAM);
- test_vsock_redir(skel, skel->maps.sock_map);
skel->bss->test_sockmap = false;
run_tests(skel, skel->maps.sock_hash, AF_INET);
run_tests(skel, skel->maps.sock_hash, AF_INET6);
- test_unix_redir(skel, skel->maps.sock_hash, SOCK_DGRAM);
- test_unix_redir(skel, skel->maps.sock_hash, SOCK_STREAM);
- test_vsock_redir(skel, skel->maps.sock_hash);
test_sockmap_listen__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c b/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c
new file mode 100644
index 000000000000..9c461d93113d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for sockmap/sockhash redirection.
+ *
+ * BPF_MAP_TYPE_SOCKMAP
+ * BPF_MAP_TYPE_SOCKHASH
+ * x
+ * sk_msg-to-egress
+ * sk_msg-to-ingress
+ * sk_skb-to-egress
+ * sk_skb-to-ingress
+ * x
+ * AF_INET, SOCK_STREAM
+ * AF_INET6, SOCK_STREAM
+ * AF_INET, SOCK_DGRAM
+ * AF_INET6, SOCK_DGRAM
+ * AF_UNIX, SOCK_STREAM
+ * AF_UNIX, SOCK_DGRAM
+ * AF_VSOCK, SOCK_STREAM
+ * AF_VSOCK, SOCK_SEQPACKET
+ */
+
+#include <errno.h>
+#include <error.h>
+#include <sched.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <linux/string.h>
+#include <linux/vm_sockets.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "linux/const.h"
+#include "test_progs.h"
+#include "sockmap_helpers.h"
+#include "test_sockmap_redir.skel.h"
+
+/* The meaning of SUPPORTED is "will redirect packet as expected".
+ */
+#define SUPPORTED _BITUL(0)
+
+/* Note on sk_skb-to-ingress ->af_vsock:
+ *
+ * Peer socket may receive the packet some time after the return from sendmsg().
+ * In a typical usage scenario, recvmsg() will block until the redirected packet
+ * appears in the destination queue, or timeout if the packet was dropped. By
+ * that point, the verdict map has already been updated to reflect what has
+ * happened.
+ *
+ * But sk_skb-to-ingress/af_vsock is an unsupported combination, so no recvmsg()
+ * takes place. Which means we may race the execution of the verdict logic and
+ * read map_verd before it has been updated, i.e. we might observe
+ * map_verd[SK_DROP]=0 instead of map_verd[SK_DROP]=1.
+ *
+ * This confuses the selftest logic: if there was no packet dropped, where's the
+ * packet? So here's a heuristic: on map_verd[SK_DROP]=map_verd[SK_PASS]=0
+ * (which implies the verdict program has not been ran) just re-read the verdict
+ * map again.
+ */
+#define UNSUPPORTED_RACY_VERD _BITUL(1)
+
+enum prog_type {
+ SK_MSG_EGRESS,
+ SK_MSG_INGRESS,
+ SK_SKB_EGRESS,
+ SK_SKB_INGRESS,
+};
+
+enum {
+ SEND_INNER = 0,
+ SEND_OUTER,
+};
+
+enum {
+ RECV_INNER = 0,
+ RECV_OUTER,
+};
+
+struct maps {
+ int in;
+ int out;
+ int verd;
+};
+
+struct combo_spec {
+ enum prog_type prog_type;
+ const char *in, *out;
+};
+
+struct redir_spec {
+ const char *name;
+ int idx_send;
+ int idx_recv;
+ enum prog_type prog_type;
+};
+
+struct socket_spec {
+ int family;
+ int sotype;
+ int send_flags;
+ int in[2];
+ int out[2];
+};
+
+static int socket_spec_pairs(struct socket_spec *s)
+{
+ return create_socket_pairs(s->family, s->sotype,
+ &s->in[0], &s->out[0],
+ &s->in[1], &s->out[1]);
+}
+
+static void socket_spec_close(struct socket_spec *s)
+{
+ xclose(s->in[0]);
+ xclose(s->in[1]);
+ xclose(s->out[0]);
+ xclose(s->out[1]);
+}
+
+static void get_redir_params(struct redir_spec *redir,
+ struct test_sockmap_redir *skel, int *prog_fd,
+ enum bpf_attach_type *attach_type,
+ int *redirect_flags)
+{
+ enum prog_type type = redir->prog_type;
+ struct bpf_program *prog;
+ bool sk_msg;
+
+ sk_msg = type == SK_MSG_INGRESS || type == SK_MSG_EGRESS;
+ prog = sk_msg ? skel->progs.prog_msg_verdict : skel->progs.prog_skb_verdict;
+
+ *prog_fd = bpf_program__fd(prog);
+ *attach_type = sk_msg ? BPF_SK_MSG_VERDICT : BPF_SK_SKB_VERDICT;
+
+ if (type == SK_MSG_INGRESS || type == SK_SKB_INGRESS)
+ *redirect_flags = BPF_F_INGRESS;
+ else
+ *redirect_flags = 0;
+}
+
+static void try_recv(const char *prefix, int fd, int flags, bool expect_success)
+{
+ ssize_t n;
+ char buf;
+
+ errno = 0;
+ n = recv(fd, &buf, 1, flags);
+ if (n < 0 && expect_success)
+ FAIL_ERRNO("%s: unexpected failure: retval=%zd", prefix, n);
+ if (!n && !expect_success)
+ FAIL("%s: expected failure: retval=%zd", prefix, n);
+}
+
+static void handle_unsupported(int sd_send, int sd_peer, int sd_in, int sd_out,
+ int sd_recv, int map_verd, int status)
+{
+ unsigned int drop, pass;
+ char recv_buf;
+ ssize_t n;
+
+get_verdict:
+ if (xbpf_map_lookup_elem(map_verd, &u32(SK_DROP), &drop) ||
+ xbpf_map_lookup_elem(map_verd, &u32(SK_PASS), &pass))
+ return;
+
+ if (pass == 0 && drop == 0 && (status & UNSUPPORTED_RACY_VERD)) {
+ sched_yield();
+ goto get_verdict;
+ }
+
+ if (pass != 0) {
+ FAIL("unsupported: wanted verdict pass 0, have %u", pass);
+ return;
+ }
+
+ /* If nothing was dropped, packet should have reached the peer */
+ if (drop == 0) {
+ errno = 0;
+ n = recv_timeout(sd_peer, &recv_buf, 1, 0, IO_TIMEOUT_SEC);
+ if (n != 1)
+ FAIL_ERRNO("unsupported: packet missing, retval=%zd", n);
+ }
+
+ /* Ensure queues are empty */
+ try_recv("bpf.recv(sd_send)", sd_send, MSG_DONTWAIT, false);
+ if (sd_in != sd_send)
+ try_recv("bpf.recv(sd_in)", sd_in, MSG_DONTWAIT, false);
+
+ try_recv("bpf.recv(sd_out)", sd_out, MSG_DONTWAIT, false);
+ if (sd_recv != sd_out)
+ try_recv("bpf.recv(sd_recv)", sd_recv, MSG_DONTWAIT, false);
+}
+
+static void test_send_redir_recv(int sd_send, int send_flags, int sd_peer,
+ int sd_in, int sd_out, int sd_recv,
+ struct maps *maps, int status)
+{
+ unsigned int drop, pass;
+ char *send_buf = "ab";
+ char recv_buf = '\0';
+ ssize_t n, len = 1;
+
+ /* Zero out the verdict map */
+ if (xbpf_map_update_elem(maps->verd, &u32(SK_DROP), &u32(0), BPF_ANY) ||
+ xbpf_map_update_elem(maps->verd, &u32(SK_PASS), &u32(0), BPF_ANY))
+ return;
+
+ if (xbpf_map_update_elem(maps->in, &u32(0), &u64(sd_in), BPF_NOEXIST))
+ return;
+
+ if (xbpf_map_update_elem(maps->out, &u32(0), &u64(sd_out), BPF_NOEXIST))
+ goto del_in;
+
+ /* Last byte is OOB data when send_flags has MSG_OOB bit set */
+ if (send_flags & MSG_OOB)
+ len++;
+ n = send(sd_send, send_buf, len, send_flags);
+ if (n >= 0 && n < len)
+ FAIL("incomplete send");
+ if (n < 0) {
+ /* sk_msg redirect combo not supported? */
+ if (status & SUPPORTED || errno != EACCES)
+ FAIL_ERRNO("send");
+ goto out;
+ }
+
+ if (!(status & SUPPORTED)) {
+ handle_unsupported(sd_send, sd_peer, sd_in, sd_out, sd_recv,
+ maps->verd, status);
+ goto out;
+ }
+
+ errno = 0;
+ n = recv_timeout(sd_recv, &recv_buf, 1, 0, IO_TIMEOUT_SEC);
+ if (n != 1) {
+ FAIL_ERRNO("recv_timeout()");
+ goto out;
+ }
+
+ /* Check verdict _after_ recv(); af_vsock may need time to catch up */
+ if (xbpf_map_lookup_elem(maps->verd, &u32(SK_DROP), &drop) ||
+ xbpf_map_lookup_elem(maps->verd, &u32(SK_PASS), &pass))
+ goto out;
+
+ if (drop != 0 || pass != 1)
+ FAIL("unexpected verdict drop/pass: wanted 0/1, have %u/%u",
+ drop, pass);
+
+ if (recv_buf != send_buf[0])
+ FAIL("recv(): payload check, %02x != %02x", recv_buf, send_buf[0]);
+
+ if (send_flags & MSG_OOB) {
+ /* Fail reading OOB while in sockmap */
+ try_recv("bpf.recv(sd_out, MSG_OOB)", sd_out,
+ MSG_OOB | MSG_DONTWAIT, false);
+
+ /* Remove sd_out from sockmap */
+ xbpf_map_delete_elem(maps->out, &u32(0));
+
+ /* Check that OOB was dropped on redirect */
+ try_recv("recv(sd_out, MSG_OOB)", sd_out,
+ MSG_OOB | MSG_DONTWAIT, false);
+
+ goto del_in;
+ }
+out:
+ xbpf_map_delete_elem(maps->out, &u32(0));
+del_in:
+ xbpf_map_delete_elem(maps->in, &u32(0));
+}
+
+static int is_redir_supported(enum prog_type type, const char *in,
+ const char *out)
+{
+ /* Matching based on strings returned by socket_kind_to_str():
+ * tcp4, udp4, tcp6, udp6, u_str, u_dgr, v_str, v_seq
+ * Plus a wildcard: any
+ * Not in use: u_seq, v_dgr
+ */
+ struct combo_spec *c, combos[] = {
+ /* Send to local: TCP -> any, but vsock */
+ { SK_MSG_INGRESS, "tcp", "tcp" },
+ { SK_MSG_INGRESS, "tcp", "udp" },
+ { SK_MSG_INGRESS, "tcp", "u_str" },
+ { SK_MSG_INGRESS, "tcp", "u_dgr" },
+
+ /* Send to egress: TCP -> TCP */
+ { SK_MSG_EGRESS, "tcp", "tcp" },
+
+ /* Ingress to egress: any -> any */
+ { SK_SKB_EGRESS, "any", "any" },
+
+ /* Ingress to local: any -> any, but vsock */
+ { SK_SKB_INGRESS, "any", "tcp" },
+ { SK_SKB_INGRESS, "any", "udp" },
+ { SK_SKB_INGRESS, "any", "u_str" },
+ { SK_SKB_INGRESS, "any", "u_dgr" },
+ };
+
+ for (c = combos; c < combos + ARRAY_SIZE(combos); c++) {
+ if (c->prog_type == type &&
+ (!strcmp(c->in, "any") || strstarts(in, c->in)) &&
+ (!strcmp(c->out, "any") || strstarts(out, c->out)))
+ return SUPPORTED;
+ }
+
+ return 0;
+}
+
+static int get_support_status(enum prog_type type, const char *in,
+ const char *out)
+{
+ int status = is_redir_supported(type, in, out);
+
+ if (type == SK_SKB_INGRESS && strstarts(out, "v_"))
+ status |= UNSUPPORTED_RACY_VERD;
+
+ return status;
+}
+
+static void test_socket(enum bpf_map_type type, struct redir_spec *redir,
+ struct maps *maps, struct socket_spec *s_in,
+ struct socket_spec *s_out)
+{
+ int fd_in, fd_out, fd_send, fd_peer, fd_recv, flags, status;
+ const char *in_str, *out_str;
+ char s[MAX_TEST_NAME];
+
+ fd_in = s_in->in[0];
+ fd_out = s_out->out[0];
+ fd_send = s_in->in[redir->idx_send];
+ fd_peer = s_in->in[redir->idx_send ^ 1];
+ fd_recv = s_out->out[redir->idx_recv];
+ flags = s_in->send_flags;
+
+ in_str = socket_kind_to_str(fd_in);
+ out_str = socket_kind_to_str(fd_out);
+ status = get_support_status(redir->prog_type, in_str, out_str);
+
+ snprintf(s, sizeof(s),
+ "%-4s %-17s %-5s %s %-5s%6s",
+ /* hash sk_skb-to-ingress u_str → v_str (OOB) */
+ type == BPF_MAP_TYPE_SOCKMAP ? "map" : "hash",
+ redir->name,
+ in_str,
+ status & SUPPORTED ? "→" : " ",
+ out_str,
+ (flags & MSG_OOB) ? "(OOB)" : "");
+
+ if (!test__start_subtest(s))
+ return;
+
+ test_send_redir_recv(fd_send, flags, fd_peer, fd_in, fd_out, fd_recv,
+ maps, status);
+}
+
+static void test_redir(enum bpf_map_type type, struct redir_spec *redir,
+ struct maps *maps)
+{
+ struct socket_spec *s, sockets[] = {
+ { AF_INET, SOCK_STREAM },
+ // { AF_INET, SOCK_STREAM, MSG_OOB }, /* Known to be broken */
+ { AF_INET6, SOCK_STREAM },
+ { AF_INET, SOCK_DGRAM },
+ { AF_INET6, SOCK_DGRAM },
+ { AF_UNIX, SOCK_STREAM },
+ { AF_UNIX, SOCK_STREAM, MSG_OOB },
+ { AF_UNIX, SOCK_DGRAM },
+ // { AF_UNIX, SOCK_SEQPACKET}, /* Unsupported BPF_MAP_UPDATE_ELEM */
+ { AF_VSOCK, SOCK_STREAM },
+ // { AF_VSOCK, SOCK_DGRAM }, /* Unsupported socket() */
+ { AF_VSOCK, SOCK_SEQPACKET },
+ };
+
+ for (s = sockets; s < sockets + ARRAY_SIZE(sockets); s++)
+ if (socket_spec_pairs(s))
+ goto out;
+
+ /* Intra-proto */
+ for (s = sockets; s < sockets + ARRAY_SIZE(sockets); s++)
+ test_socket(type, redir, maps, s, s);
+
+ /* Cross-proto */
+ for (int i = 0; i < ARRAY_SIZE(sockets); i++) {
+ for (int j = 0; j < ARRAY_SIZE(sockets); j++) {
+ struct socket_spec *out = &sockets[j];
+ struct socket_spec *in = &sockets[i];
+
+ /* Skip intra-proto and between variants */
+ if (out->send_flags ||
+ (in->family == out->family &&
+ in->sotype == out->sotype))
+ continue;
+
+ test_socket(type, redir, maps, in, out);
+ }
+ }
+out:
+ while (--s >= sockets)
+ socket_spec_close(s);
+}
+
+static void test_map(enum bpf_map_type type)
+{
+ struct redir_spec *r, redirs[] = {
+ { "sk_msg-to-ingress", SEND_INNER, RECV_INNER, SK_MSG_INGRESS },
+ { "sk_msg-to-egress", SEND_INNER, RECV_OUTER, SK_MSG_EGRESS },
+ { "sk_skb-to-egress", SEND_OUTER, RECV_OUTER, SK_SKB_EGRESS },
+ { "sk_skb-to-ingress", SEND_OUTER, RECV_INNER, SK_SKB_INGRESS },
+ };
+
+ for (r = redirs; r < redirs + ARRAY_SIZE(redirs); r++) {
+ enum bpf_attach_type attach_type;
+ struct test_sockmap_redir *skel;
+ struct maps maps;
+ int prog_fd;
+
+ skel = test_sockmap_redir__open_and_load();
+ if (!skel) {
+ FAIL("open_and_load");
+ return;
+ }
+
+ switch (type) {
+ case BPF_MAP_TYPE_SOCKMAP:
+ maps.in = bpf_map__fd(skel->maps.nop_map);
+ maps.out = bpf_map__fd(skel->maps.sock_map);
+ break;
+ case BPF_MAP_TYPE_SOCKHASH:
+ maps.in = bpf_map__fd(skel->maps.nop_hash);
+ maps.out = bpf_map__fd(skel->maps.sock_hash);
+ break;
+ default:
+ FAIL("Unsupported bpf_map_type");
+ return;
+ }
+
+ skel->bss->redirect_type = type;
+ maps.verd = bpf_map__fd(skel->maps.verdict_map);
+ get_redir_params(r, skel, &prog_fd, &attach_type,
+ &skel->bss->redirect_flags);
+
+ if (xbpf_prog_attach(prog_fd, maps.in, attach_type, 0))
+ return;
+
+ test_redir(type, r, &maps);
+
+ if (xbpf_prog_detach2(prog_fd, maps.in, attach_type))
+ return;
+
+ test_sockmap_redir__destroy(skel);
+ }
+}
+
+void serial_test_sockmap_redir(void)
+{
+ test_map(BPF_MAP_TYPE_SOCKMAP);
+ test_map(BPF_MAP_TYPE_SOCKHASH);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index e3ea5dc2f697..254fbfeab06a 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -13,22 +13,22 @@ static struct {
const char *err_msg;
} spin_lock_fail_tests[] = {
{ "lock_id_kptr_preserve",
- "5: (bf) r1 = r0 ; R0_w=ptr_foo(id=2,ref_obj_id=2) "
- "R1_w=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
+ "5: (bf) r1 = r0 ; R0=ptr_foo(id=2,ref_obj_id=2) "
+ "R1=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=ptr_ expected=percpu_ptr_" },
{ "lock_id_global_zero",
- "; R1_w=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
+ "; R1=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=map_value expected=percpu_ptr_" },
{ "lock_id_mapval_preserve",
"[0-9]\\+: (bf) r1 = r0 ;"
- " R0_w=map_value(id=1,map=array_map,ks=4,vs=8)"
- " R1_w=map_value(id=1,map=array_map,ks=4,vs=8)\n"
+ " R0=map_value(id=1,map=array_map,ks=4,vs=8)"
+ " R1=map_value(id=1,map=array_map,ks=4,vs=8)\n"
"[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=map_value expected=percpu_ptr_" },
{ "lock_id_innermapval_preserve",
"[0-9]\\+: (bf) r1 = r0 ;"
" R0=map_value(id=2,ks=4,vs=8)"
- " R1_w=map_value(id=2,ks=4,vs=8)\n"
+ " R1=map_value(id=2,ks=4,vs=8)\n"
"[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
"R1 type=map_value expected=percpu_ptr_" },
{ "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" },
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
index b7ba5cd47d96..271b5cc9fc01 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
@@ -39,7 +39,7 @@ retry:
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index 0832fd787457..b277dddd5af7 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -66,7 +66,7 @@ retry:
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
index df59e4ae2951..c23b97414813 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -1,46 +1,27 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include "stacktrace_map.skel.h"
void test_stacktrace_map(void)
{
+ struct stacktrace_map *skel;
int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
- const char *prog_name = "oncpu";
- int err, prog_fd, stack_trace_len;
- const char *file = "./test_stacktrace_map.bpf.o";
- __u32 key, val, duration = 0;
- struct bpf_program *prog;
- struct bpf_object *obj;
- struct bpf_link *link;
+ int err, stack_trace_len;
+ __u32 key, val, stack_id, duration = 0;
+ __u64 stack[PERF_MAX_STACK_DEPTH];
- err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
- if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+ skel = stacktrace_map__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
return;
- prog = bpf_object__find_program_by_name(obj, prog_name);
- if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
- goto close_prog;
-
- link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch");
- if (!ASSERT_OK_PTR(link, "attach_tp"))
- goto close_prog;
-
- /* find map fds */
- control_map_fd = bpf_find_map(__func__, obj, "control_map");
- if (CHECK_FAIL(control_map_fd < 0))
- goto disable_pmu;
-
- stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
- if (CHECK_FAIL(stackid_hmap_fd < 0))
- goto disable_pmu;
-
- stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
- if (CHECK_FAIL(stackmap_fd < 0))
- goto disable_pmu;
-
- stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
- if (CHECK_FAIL(stack_amap_fd < 0))
- goto disable_pmu;
+ control_map_fd = bpf_map__fd(skel->maps.control_map);
+ stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap);
+ stackmap_fd = bpf_map__fd(skel->maps.stackmap);
+ stack_amap_fd = bpf_map__fd(skel->maps.stack_amap);
+ err = stacktrace_map__attach(skel);
+ if (!ASSERT_OK(err, "skel_attach"))
+ goto out;
/* give some time for bpf program run */
sleep(1);
@@ -50,26 +31,32 @@ void test_stacktrace_map(void)
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
+ goto out;
err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
+ goto out;
stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
-
-disable_pmu:
- bpf_link__destroy(link);
-close_prog:
- bpf_object__close(obj);
+ goto out;
+
+ stack_id = skel->bss->stack_id;
+ err = bpf_map_lookup_and_delete_elem(stackmap_fd, &stack_id, stack);
+ if (!ASSERT_OK(err, "lookup and delete target stack_id"))
+ goto out;
+
+ err = bpf_map_lookup_elem(stackmap_fd, &stack_id, stack);
+ if (!ASSERT_EQ(err, -ENOENT, "lookup deleted stack_id"))
+ goto out;
+out:
+ stacktrace_map__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
index c6ef06f55cdb..e985d51d3d47 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -5,7 +5,7 @@ void test_stacktrace_map_raw_tp(void)
{
const char *prog_name = "oncpu";
int control_map_fd, stackid_hmap_fd, stackmap_fd;
- const char *file = "./test_stacktrace_map.bpf.o";
+ const char *file = "./stacktrace_map.bpf.o";
__u32 key, val, duration = 0;
int err, prog_fd;
struct bpf_program *prog;
@@ -46,7 +46,7 @@ void test_stacktrace_map_raw_tp(void)
bpf_map_update_elem(control_map_fd, &key, &val, 0);
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
index 1932b1e0685c..dc2ccf6a14d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
@@ -40,7 +40,7 @@ void test_stacktrace_map_skip(void)
skel->bss->control = 1;
/* for every element in stackid_hmap, we can find a corresponding one
- * in stackmap, and vise versa.
+ * in stackmap, and vice versa.
*/
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap"))
diff --git a/tools/testing/selftests/bpf/prog_tests/stream.c b/tools/testing/selftests/bpf/prog_tests/stream.c
new file mode 100644
index 000000000000..c3cce5c292bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/stream.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+
+#include "stream.skel.h"
+#include "stream_fail.skel.h"
+
+void test_stream_failure(void)
+{
+ RUN_TESTS(stream_fail);
+}
+
+void test_stream_success(void)
+{
+ RUN_TESTS(stream);
+ return;
+}
+
+void test_stream_syscall(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+ struct stream *skel;
+ int ret, prog_fd;
+ char buf[64];
+
+ skel = stream__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "stream__open_and_load"))
+ return;
+
+ prog_fd = bpf_program__fd(skel->progs.stream_syscall);
+ ret = bpf_prog_test_run_opts(prog_fd, &opts);
+ ASSERT_OK(ret, "ret");
+ ASSERT_OK(opts.retval, "retval");
+
+ ASSERT_LT(bpf_prog_stream_read(0, BPF_STREAM_STDOUT, buf, sizeof(buf), &ropts), 0, "error");
+ ret = -errno;
+ ASSERT_EQ(ret, -EINVAL, "bad prog_fd");
+
+ ASSERT_LT(bpf_prog_stream_read(prog_fd, 0, buf, sizeof(buf), &ropts), 0, "error");
+ ret = -errno;
+ ASSERT_EQ(ret, -ENOENT, "bad stream id");
+
+ ASSERT_LT(bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, NULL, sizeof(buf), NULL), 0, "error");
+ ret = -errno;
+ ASSERT_EQ(ret, -EFAULT, "bad stream buf");
+
+ ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 2, NULL);
+ ASSERT_EQ(ret, 2, "bytes");
+ ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 2, NULL);
+ ASSERT_EQ(ret, 1, "bytes");
+ ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 1, &ropts);
+ ASSERT_EQ(ret, 0, "no bytes stdout");
+ ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, 1, &ropts);
+ ASSERT_EQ(ret, 0, "no bytes stderr");
+
+ stream__destroy(skel);
+}
+
+static void test_address(struct bpf_program *prog, unsigned long *fault_addr_p)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+ int ret, prog_fd;
+ char fault_addr[64];
+ char buf[1024];
+
+ prog_fd = bpf_program__fd(prog);
+
+ ret = bpf_prog_test_run_opts(prog_fd, &opts);
+ ASSERT_OK(ret, "ret");
+ ASSERT_OK(opts.retval, "retval");
+
+ sprintf(fault_addr, "0x%lx", *fault_addr_p);
+
+ ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, sizeof(buf), &ropts);
+ ASSERT_GT(ret, 0, "stream read");
+ ASSERT_LE(ret, 1023, "len for buf");
+ buf[ret] = '\0';
+
+ if (!ASSERT_HAS_SUBSTR(buf, fault_addr, "fault_addr")) {
+ fprintf(stderr, "Output from stream:\n%s\n", buf);
+ fprintf(stderr, "Fault Addr: %s\n", fault_addr);
+ }
+}
+
+void test_stream_arena_fault_address(void)
+{
+ struct stream *skel;
+
+#if !defined(__x86_64__) && !defined(__aarch64__)
+ printf("%s:SKIP: arena fault reporting not supported\n", __func__);
+ test__skip();
+ return;
+#endif
+
+ skel = stream__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "stream__open_and_load"))
+ return;
+
+ if (test__start_subtest("read_fault"))
+ test_address(skel->progs.stream_arena_read_fault, &skel->bss->fault_addr);
+ if (test__start_subtest("write_fault"))
+ test_address(skel->progs.stream_arena_write_fault, &skel->bss->fault_addr);
+
+ stream__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
new file mode 100644
index 000000000000..4d66fad3c8bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include <test_progs.h>
+#include "string_kfuncs_success.skel.h"
+#include "string_kfuncs_failure1.skel.h"
+#include "string_kfuncs_failure2.skel.h"
+#include <sys/mman.h>
+
+static const char * const test_cases[] = {
+ "strcmp",
+ "strcasecmp",
+ "strchr",
+ "strchrnul",
+ "strnchr",
+ "strrchr",
+ "strlen",
+ "strnlen",
+ "strspn_str",
+ "strspn_accept",
+ "strcspn_str",
+ "strcspn_reject",
+ "strstr",
+ "strnstr",
+};
+
+void run_too_long_tests(void)
+{
+ struct string_kfuncs_failure2 *skel;
+ struct bpf_program *prog;
+ char test_name[256];
+ int err, i;
+
+ skel = string_kfuncs_failure2__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "string_kfuncs_failure2__open_and_load"))
+ return;
+
+ memset(skel->bss->long_str, 'a', sizeof(skel->bss->long_str));
+
+ for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+ sprintf(test_name, "test_%s_too_long", test_cases[i]);
+ if (!test__start_subtest(test_name))
+ continue;
+
+ prog = bpf_object__find_program_by_name(skel->obj, test_name);
+ if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+ goto cleanup;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+ if (!ASSERT_OK(err, "bpf_prog_test_run"))
+ goto cleanup;
+
+ ASSERT_EQ(topts.retval, -E2BIG, "reading too long string fails with -E2BIG");
+ }
+
+cleanup:
+ string_kfuncs_failure2__destroy(skel);
+}
+
+void test_string_kfuncs(void)
+{
+ RUN_TESTS(string_kfuncs_success);
+ RUN_TESTS(string_kfuncs_failure1);
+
+ run_too_long_tests();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 66a900327f91..0ab36503c3b2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1195,7 +1195,7 @@ static void test_tailcall_hierarchy_count(const char *which, bool test_fentry,
bool test_fexit,
bool test_fentry_entry)
{
- int err, map_fd, prog_fd, main_data_fd, fentry_data_fd, fexit_data_fd, i, val;
+ int err, map_fd, prog_fd, main_data_fd, fentry_data_fd = 0, fexit_data_fd = 0, i, val;
struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
struct bpf_program *prog, *fentry_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
new file mode 100644
index 000000000000..2de38776a2d4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TASK_LOCAL_DATA_H
+#define __TASK_LOCAL_DATA_H
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdatomic.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+#include <pthread.h>
+#endif
+
+#include <bpf/bpf.h>
+
+/*
+ * OPTIONS
+ *
+ * Define the option before including the header
+ *
+ * TLD_FREE_DATA_ON_THREAD_EXIT - Frees memory on thread exit automatically
+ *
+ * Thread-specific memory for storing TLD is allocated lazily on the first call to
+ * tld_get_data(). The thread that calls it must also call tld_free() on thread exit
+ * to prevent memory leak. Pthread will be included if the option is defined. A pthread
+ * key will be registered with a destructor that calls tld_free().
+ *
+ *
+ * TLD_DYN_DATA_SIZE - The maximum size of memory allocated for TLDs created dynamically
+ * (default: 64 bytes)
+ *
+ * A TLD can be defined statically using TLD_DEFINE_KEY() or created on the fly using
+ * tld_create_key(). As the total size of TLDs created with tld_create_key() cannot be
+ * possibly known statically, a memory area of size TLD_DYN_DATA_SIZE will be allocated
+ * for these TLDs. This additional memory is allocated for every thread that calls
+ * tld_get_data() even if no tld_create_key are actually called, so be mindful of
+ * potential memory wastage. Use TLD_DEFINE_KEY() whenever possible as just enough memory
+ * will be allocated for TLDs created with it.
+ *
+ *
+ * TLD_NAME_LEN - The maximum length of the name of a TLD (default: 62)
+ *
+ * Setting TLD_NAME_LEN will affect the maximum number of TLDs a process can store,
+ * TLD_MAX_DATA_CNT.
+ *
+ *
+ * TLD_DATA_USE_ALIGNED_ALLOC - Always use aligned_alloc() instead of malloc()
+ *
+ * When allocating the memory for storing TLDs, we need to make sure there is a memory
+ * region of the X bytes within a page. This is due to the limit posed by UPTR: memory
+ * pinned to the kernel cannot exceed a page nor can it cross the page boundary. The
+ * library normally calls malloc(2*X) given X bytes of total TLDs, and only uses
+ * aligned_alloc(PAGE_SIZE, X) when X >= PAGE_SIZE / 2. This is to reduce memory wastage
+ * as not all memory allocator can use the exact amount of memory requested to fulfill
+ * aligned_alloc(). For example, some may round the size up to the alignment. Enable the
+ * option to always use aligned_alloc() if the implementation has low memory overhead.
+ */
+
+#define TLD_PAGE_SIZE getpagesize()
+#define TLD_PAGE_MASK (~(TLD_PAGE_SIZE - 1))
+
+#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1))
+#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1)
+
+#define TLD_READ_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+#ifndef TLD_DYN_DATA_SIZE
+#define TLD_DYN_DATA_SIZE 64
+#endif
+
+#define TLD_MAX_DATA_CNT (TLD_PAGE_SIZE / sizeof(struct tld_metadata) - 1)
+
+#ifndef TLD_NAME_LEN
+#define TLD_NAME_LEN 62
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ __s16 off;
+} tld_key_t;
+
+struct tld_metadata {
+ char name[TLD_NAME_LEN];
+ _Atomic __u16 size;
+};
+
+struct tld_meta_u {
+ _Atomic __u8 cnt;
+ __u16 size;
+ struct tld_metadata metadata[];
+};
+
+struct tld_data_u {
+ __u64 start; /* offset of tld_data_u->data in a page */
+ char data[];
+};
+
+struct tld_map_value {
+ void *data;
+ struct tld_meta_u *meta;
+};
+
+struct tld_meta_u * _Atomic tld_meta_p __attribute__((weak));
+__thread struct tld_data_u *tld_data_p __attribute__((weak));
+__thread void *tld_data_alloc_p __attribute__((weak));
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+pthread_key_t tld_pthread_key __attribute__((weak));
+
+static void tld_free(void);
+
+static void __tld_thread_exit_handler(void *unused)
+{
+ tld_free();
+}
+#endif
+
+static int __tld_init_meta_p(void)
+{
+ struct tld_meta_u *meta, *uninit = NULL;
+ int err = 0;
+
+ meta = (struct tld_meta_u *)aligned_alloc(TLD_PAGE_SIZE, TLD_PAGE_SIZE);
+ if (!meta) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ memset(meta, 0, TLD_PAGE_SIZE);
+ meta->size = TLD_DYN_DATA_SIZE;
+
+ if (!atomic_compare_exchange_strong(&tld_meta_p, &uninit, meta)) {
+ free(meta);
+ goto out;
+ }
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+ pthread_key_create(&tld_pthread_key, __tld_thread_exit_handler);
+#endif
+out:
+ return err;
+}
+
+static int __tld_init_data_p(int map_fd)
+{
+ bool use_aligned_alloc = false;
+ struct tld_map_value map_val;
+ struct tld_data_u *data;
+ void *data_alloc = NULL;
+ int err, tid_fd = -1;
+
+ tid_fd = syscall(SYS_pidfd_open, sys_gettid(), O_EXCL);
+ if (tid_fd < 0) {
+ err = -errno;
+ goto out;
+ }
+
+#ifdef TLD_DATA_USE_ALIGNED_ALLOC
+ use_aligned_alloc = true;
+#endif
+
+ /*
+ * tld_meta_p->size = TLD_DYN_DATA_SIZE +
+ * total size of TLDs defined via TLD_DEFINE_KEY()
+ */
+ data_alloc = (use_aligned_alloc || tld_meta_p->size * 2 >= TLD_PAGE_SIZE) ?
+ aligned_alloc(TLD_PAGE_SIZE, tld_meta_p->size) :
+ malloc(tld_meta_p->size * 2);
+ if (!data_alloc) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * Always pass a page-aligned address to UPTR since the size of tld_map_value::data
+ * is a page in BTF. If data_alloc spans across two pages, use the page that contains large
+ * enough memory.
+ */
+ if (TLD_PAGE_SIZE - (~TLD_PAGE_MASK & (intptr_t)data_alloc) >= tld_meta_p->size) {
+ map_val.data = (void *)(TLD_PAGE_MASK & (intptr_t)data_alloc);
+ data = data_alloc;
+ data->start = (~TLD_PAGE_MASK & (intptr_t)data_alloc) +
+ offsetof(struct tld_data_u, data);
+ } else {
+ map_val.data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE));
+ data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE));
+ data->start = offsetof(struct tld_data_u, data);
+ }
+ map_val.meta = TLD_READ_ONCE(tld_meta_p);
+
+ err = bpf_map_update_elem(map_fd, &tid_fd, &map_val, 0);
+ if (err) {
+ free(data_alloc);
+ goto out;
+ }
+
+ tld_data_p = data;
+ tld_data_alloc_p = data_alloc;
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+ pthread_setspecific(tld_pthread_key, (void *)1);
+#endif
+out:
+ if (tid_fd >= 0)
+ close(tid_fd);
+ return err;
+}
+
+static tld_key_t __tld_create_key(const char *name, size_t size, bool dyn_data)
+{
+ int err, i, sz, off = 0;
+ __u8 cnt;
+
+ if (!TLD_READ_ONCE(tld_meta_p)) {
+ err = __tld_init_meta_p();
+ if (err)
+ return (tld_key_t){err};
+ }
+
+ for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+retry:
+ cnt = atomic_load(&tld_meta_p->cnt);
+ if (i < cnt) {
+ /* A metadata is not ready until size is updated with a non-zero value */
+ while (!(sz = atomic_load(&tld_meta_p->metadata[i].size)))
+ sched_yield();
+
+ if (!strncmp(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN))
+ return (tld_key_t){-EEXIST};
+
+ off += TLD_ROUND_UP(sz, 8);
+ continue;
+ }
+
+ /*
+ * TLD_DEFINE_KEY() is given memory upto a page while at most
+ * TLD_DYN_DATA_SIZE is allocated for tld_create_key()
+ */
+ if (dyn_data) {
+ if (off + TLD_ROUND_UP(size, 8) > tld_meta_p->size)
+ return (tld_key_t){-E2BIG};
+ } else {
+ if (off + TLD_ROUND_UP(size, 8) > TLD_PAGE_SIZE - sizeof(struct tld_data_u))
+ return (tld_key_t){-E2BIG};
+ tld_meta_p->size += TLD_ROUND_UP(size, 8);
+ }
+
+ /*
+ * Only one tld_create_key() can increase the current cnt by one and
+ * takes the latest available slot. Other threads will check again if a new
+ * TLD can still be added, and then compete for the new slot after the
+ * succeeding thread update the size.
+ */
+ if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1))
+ goto retry;
+
+ strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN);
+ atomic_store(&tld_meta_p->metadata[i].size, size);
+ return (tld_key_t){(__s16)off};
+ }
+
+ return (tld_key_t){-ENOSPC};
+}
+
+/**
+ * TLD_DEFINE_KEY() - Define a TLD and a global variable key associated with the TLD.
+ *
+ * @name: The name of the TLD
+ * @size: The size of the TLD
+ * @key: The variable name of the key. Cannot exceed TLD_NAME_LEN
+ *
+ * The macro can only be used in file scope.
+ *
+ * A global variable key of opaque type, tld_key_t, will be declared and initialized before
+ * main() starts. Use tld_key_is_err() or tld_key_err_or_zero() later to check if the key
+ * creation succeeded. Pass the key to tld_get_data() to get a pointer to the TLD.
+ * bpf programs can also fetch the same key by name.
+ *
+ * The total size of TLDs created using TLD_DEFINE_KEY() cannot exceed a page. Just
+ * enough memory will be allocated for each thread on the first call to tld_get_data().
+ */
+#define TLD_DEFINE_KEY(key, name, size) \
+tld_key_t key; \
+ \
+__attribute__((constructor)) \
+void __tld_define_key_##key(void) \
+{ \
+ key = __tld_create_key(name, size, false); \
+}
+
+/**
+ * tld_create_key() - Create a TLD and return a key associated with the TLD.
+ *
+ * @name: The name the TLD
+ * @size: The size of the TLD
+ *
+ * Return an opaque object key. Use tld_key_is_err() or tld_key_err_or_zero() to check
+ * if the key creation succeeded. Pass the key to tld_get_data() to get a pointer to
+ * locate the TLD. bpf programs can also fetch the same key by name.
+ *
+ * Use tld_create_key() only when a TLD needs to be created dynamically (e.g., @name is
+ * not known statically or a TLD needs to be created conditionally)
+ *
+ * An additional TLD_DYN_DATA_SIZE bytes are allocated per-thread to accommodate TLDs
+ * created dynamically with tld_create_key(). Since only a user page is pinned to the
+ * kernel, when TLDs created with TLD_DEFINE_KEY() uses more than TLD_PAGE_SIZE -
+ * TLD_DYN_DATA_SIZE, the buffer size will be limited to the rest of the page.
+ */
+__attribute__((unused))
+static tld_key_t tld_create_key(const char *name, size_t size)
+{
+ return __tld_create_key(name, size, true);
+}
+
+__attribute__((unused))
+static inline bool tld_key_is_err(tld_key_t key)
+{
+ return key.off < 0;
+}
+
+__attribute__((unused))
+static inline int tld_key_err_or_zero(tld_key_t key)
+{
+ return tld_key_is_err(key) ? key.off : 0;
+}
+
+/**
+ * tld_get_data() - Get a pointer to the TLD associated with the given key of the
+ * calling thread.
+ *
+ * @map_fd: A file descriptor of tld_data_map, the underlying BPF task local storage map
+ * of task local data.
+ * @key: A key object created by TLD_DEFINE_KEY() or tld_create_key().
+ *
+ * Return a pointer to the TLD if the key is valid; NULL if not enough memory for TLD
+ * for this thread, or the key is invalid. The returned pointer is guaranteed to be 8-byte
+ * aligned.
+ *
+ * Threads that call tld_get_data() must call tld_free() on exit to prevent
+ * memory leak if TLD_FREE_DATA_ON_THREAD_EXIT is not defined.
+ */
+__attribute__((unused))
+static void *tld_get_data(int map_fd, tld_key_t key)
+{
+ if (!TLD_READ_ONCE(tld_meta_p))
+ return NULL;
+
+ /* tld_data_p is allocated on the first invocation of tld_get_data() */
+ if (!tld_data_p && __tld_init_data_p(map_fd))
+ return NULL;
+
+ return tld_data_p->data + key.off;
+}
+
+/**
+ * tld_free() - Free task local data memory of the calling thread
+ *
+ * For the calling thread, all pointers to TLDs acquired before will become invalid.
+ *
+ * Users must call tld_free() on thread exit to prevent memory leak. Alternatively,
+ * define TLD_FREE_DATA_ON_THREAD_EXIT and a thread exit handler will be registered
+ * to free the memory automatically.
+ */
+__attribute__((unused))
+static void tld_free(void)
+{
+ if (tld_data_alloc_p) {
+ free(tld_data_alloc_p);
+ tld_data_alloc_p = NULL;
+ tld_data_p = NULL;
+ }
+}
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __TASK_LOCAL_DATA_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/task_work_stress.c b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c
new file mode 100644
index 000000000000..450d17d91a56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+#include "task_work_stress.skel.h"
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
+#include <time.h>
+#include <stdlib.h>
+#include <stdatomic.h>
+
+struct test_data {
+ int prog_fd;
+ atomic_int exit;
+};
+
+void *runner(void *test_data)
+{
+ struct test_data *td = test_data;
+ int err = 0;
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+ while (!err && !atomic_load(&td->exit))
+ err = bpf_prog_test_run_opts(td->prog_fd, &opts);
+
+ return NULL;
+}
+
+static int get_env_int(const char *str, int def)
+{
+ const char *s = getenv(str);
+ char *end;
+ int retval;
+
+ if (!s || !*s)
+ return def;
+ errno = 0;
+ retval = strtol(s, &end, 10);
+ if (errno || *end || retval < 0)
+ return def;
+ return retval;
+}
+
+static void task_work_run(bool enable_delete)
+{
+ struct task_work_stress *skel;
+ struct bpf_program *scheduler, *deleter;
+ int nthreads = 16;
+ int test_time_s = get_env_int("BPF_TASK_WORK_TEST_TIME", 1);
+ pthread_t tid[nthreads], tid_del;
+ bool started[nthreads], started_del = false;
+ struct test_data td_sched = { .exit = 0 }, td_del = { .exit = 1 };
+ int i, err;
+
+ skel = task_work_stress__open();
+ if (!ASSERT_OK_PTR(skel, "task_work__open"))
+ return;
+
+ scheduler = bpf_object__find_program_by_name(skel->obj, "schedule_task_work");
+ bpf_program__set_autoload(scheduler, true);
+
+ deleter = bpf_object__find_program_by_name(skel->obj, "delete_task_work");
+ bpf_program__set_autoload(deleter, true);
+
+ err = task_work_stress__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ for (i = 0; i < nthreads; ++i)
+ started[i] = false;
+
+ td_sched.prog_fd = bpf_program__fd(scheduler);
+ for (i = 0; i < nthreads; ++i) {
+ if (pthread_create(&tid[i], NULL, runner, &td_sched) != 0) {
+ fprintf(stderr, "could not start thread");
+ goto cancel;
+ }
+ started[i] = true;
+ }
+
+ if (enable_delete)
+ atomic_store(&td_del.exit, 0);
+
+ td_del.prog_fd = bpf_program__fd(deleter);
+ if (pthread_create(&tid_del, NULL, runner, &td_del) != 0) {
+ fprintf(stderr, "could not start thread");
+ goto cancel;
+ }
+ started_del = true;
+
+ /* Run stress test for some time */
+ sleep(test_time_s);
+
+cancel:
+ atomic_store(&td_sched.exit, 1);
+ atomic_store(&td_del.exit, 1);
+ for (i = 0; i < nthreads; ++i) {
+ if (started[i])
+ pthread_join(tid[i], NULL);
+ }
+
+ if (started_del)
+ pthread_join(tid_del, NULL);
+
+ ASSERT_GT(skel->bss->callback_scheduled, 0, "work scheduled");
+ /* Some scheduling attempts should have failed due to contention */
+ ASSERT_GT(skel->bss->schedule_error, 0, "schedule error");
+
+ if (enable_delete) {
+ /* If delete thread is enabled, it has cancelled some callbacks */
+ ASSERT_GT(skel->bss->delete_success, 0, "delete success");
+ ASSERT_LT(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks");
+ } else {
+ /* Without delete thread number of scheduled callbacks is the same as fired */
+ ASSERT_EQ(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks");
+ }
+
+cleanup:
+ task_work_stress__destroy(skel);
+}
+
+void test_task_work_stress(void)
+{
+ if (test__start_subtest("no_delete"))
+ task_work_run(false);
+ if (test__start_subtest("with_delete"))
+ task_work_run(true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
index 924d0e25320c..d52a62af77bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
@@ -8,34 +8,6 @@
# define loopback 1
#endif
-static inline __u32 id_from_prog_fd(int fd)
-{
- struct bpf_prog_info prog_info = {};
- __u32 prog_info_len = sizeof(prog_info);
- int err;
-
- err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len);
- if (!ASSERT_OK(err, "id_from_prog_fd"))
- return 0;
-
- ASSERT_NEQ(prog_info.id, 0, "prog_info.id");
- return prog_info.id;
-}
-
-static inline __u32 id_from_link_fd(int fd)
-{
- struct bpf_link_info link_info = {};
- __u32 link_info_len = sizeof(link_info);
- int err;
-
- err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
- if (!ASSERT_OK(err, "id_from_link_fd"))
- return 0;
-
- ASSERT_NEQ(link_info.id, 0, "link_info.id");
- return link_info.id;
-}
-
static inline __u32 ifindex_from_link_fd(int fd)
{
struct bpf_link_info link_info = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index c85798966aec..76d72a59365e 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -56,6 +56,8 @@
#define MAC_DST_FWD "00:11:22:33:44:55"
#define MAC_DST "00:22:33:44:55:66"
+#define MAC_SRC_FWD "00:33:44:55:66:77"
+#define MAC_SRC "00:44:55:66:77:88"
#define IFADDR_STR_LEN 18
#define PING_ARGS "-i 0.2 -c 3 -w 10 -q"
@@ -207,11 +209,10 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
int err;
if (result->dev_mode == MODE_VETH) {
- SYS(fail, "ip link add src type veth peer name src_fwd");
- SYS(fail, "ip link add dst type veth peer name dst_fwd");
-
- SYS(fail, "ip link set dst_fwd address " MAC_DST_FWD);
- SYS(fail, "ip link set dst address " MAC_DST);
+ SYS(fail, "ip link add src address " MAC_SRC " type veth "
+ "peer name src_fwd address " MAC_SRC_FWD);
+ SYS(fail, "ip link add dst address " MAC_DST " type veth "
+ "peer name dst_fwd address " MAC_DST_FWD);
} else if (result->dev_mode == MODE_NETKIT) {
err = create_netkit(NETKIT_L3, "src", "src_fwd");
if (!ASSERT_OK(err, "create_ifindex_src"))
diff --git a/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c b/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c
new file mode 100644
index 000000000000..7d1b478c99a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms Inc. */
+#include <test_progs.h>
+#include "test_btf_ext.skel.h"
+#include "btf_helpers.h"
+
+static void subtest_line_func_info(void)
+{
+ struct test_btf_ext *skel;
+ struct bpf_prog_info info;
+ struct bpf_line_info line_info[128], *libbpf_line_info;
+ struct bpf_func_info func_info[128], *libbpf_func_info;
+ __u32 info_len = sizeof(info), libbbpf_line_info_cnt, libbbpf_func_info_cnt;
+ int err, fd;
+
+ skel = test_btf_ext__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+ return;
+
+ fd = bpf_program__fd(skel->progs.global_func);
+
+ memset(&info, 0, sizeof(info));
+ info.line_info = ptr_to_u64(&line_info);
+ info.nr_line_info = sizeof(line_info);
+ info.line_info_rec_size = sizeof(*line_info);
+ err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+ if (!ASSERT_OK(err, "prog_line_info"))
+ goto out;
+
+ libbpf_line_info = bpf_program__line_info(skel->progs.global_func);
+ libbbpf_line_info_cnt = bpf_program__line_info_cnt(skel->progs.global_func);
+
+ memset(&info, 0, sizeof(info));
+ info.func_info = ptr_to_u64(&func_info);
+ info.nr_func_info = sizeof(func_info);
+ info.func_info_rec_size = sizeof(*func_info);
+ err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+ if (!ASSERT_OK(err, "prog_func_info"))
+ goto out;
+
+ libbpf_func_info = bpf_program__func_info(skel->progs.global_func);
+ libbbpf_func_info_cnt = bpf_program__func_info_cnt(skel->progs.global_func);
+
+ if (!ASSERT_OK_PTR(libbpf_line_info, "bpf_program__line_info"))
+ goto out;
+ if (!ASSERT_EQ(libbbpf_line_info_cnt, info.nr_line_info, "line_info_cnt"))
+ goto out;
+ if (!ASSERT_OK_PTR(libbpf_func_info, "bpf_program__func_info"))
+ goto out;
+ if (!ASSERT_EQ(libbbpf_func_info_cnt, info.nr_func_info, "func_info_cnt"))
+ goto out;
+ ASSERT_MEMEQ(libbpf_line_info, line_info, libbbpf_line_info_cnt * sizeof(*line_info),
+ "line_info");
+ ASSERT_MEMEQ(libbpf_func_info, func_info, libbbpf_func_info_cnt * sizeof(*func_info),
+ "func_info");
+out:
+ test_btf_ext__destroy(skel);
+}
+
+void test_btf_ext(void)
+{
+ if (test__start_subtest("line_func_info"))
+ subtest_line_func_info();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c
new file mode 100644
index 000000000000..fd8762ba4b67
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_id_ops_mapping1.skel.h"
+#include "struct_ops_id_ops_mapping2.skel.h"
+
+static void test_st_ops_id_ops_mapping(void)
+{
+ struct struct_ops_id_ops_mapping1 *skel1 = NULL;
+ struct struct_ops_id_ops_mapping2 *skel2 = NULL;
+ struct bpf_map_info info = {};
+ __u32 len = sizeof(info);
+ int err, pid, prog1_fd, prog2_fd;
+
+ skel1 = struct_ops_id_ops_mapping1__open_and_load();
+ if (!ASSERT_OK_PTR(skel1, "struct_ops_id_ops_mapping1__open"))
+ goto out;
+
+ skel2 = struct_ops_id_ops_mapping2__open_and_load();
+ if (!ASSERT_OK_PTR(skel2, "struct_ops_id_ops_mapping2__open"))
+ goto out;
+
+ err = bpf_map_get_info_by_fd(bpf_map__fd(skel1->maps.st_ops_map),
+ &info, &len);
+ if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+ goto out;
+
+ skel1->bss->st_ops_id = info.id;
+
+ err = bpf_map_get_info_by_fd(bpf_map__fd(skel2->maps.st_ops_map),
+ &info, &len);
+ if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+ goto out;
+
+ skel2->bss->st_ops_id = info.id;
+
+ err = struct_ops_id_ops_mapping1__attach(skel1);
+ if (!ASSERT_OK(err, "struct_ops_id_ops_mapping1__attach"))
+ goto out;
+
+ err = struct_ops_id_ops_mapping2__attach(skel2);
+ if (!ASSERT_OK(err, "struct_ops_id_ops_mapping2__attach"))
+ goto out;
+
+ /* run tracing prog that calls .test_1 and checks return */
+ pid = getpid();
+ skel1->bss->test_pid = pid;
+ skel2->bss->test_pid = pid;
+ sys_gettid();
+ skel1->bss->test_pid = 0;
+ skel2->bss->test_pid = 0;
+
+ /* run syscall_prog that calls .test_1 and checks return */
+ prog1_fd = bpf_program__fd(skel1->progs.syscall_prog);
+ err = bpf_prog_test_run_opts(prog1_fd, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+ prog2_fd = bpf_program__fd(skel2->progs.syscall_prog);
+ err = bpf_prog_test_run_opts(prog2_fd, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+ ASSERT_EQ(skel1->bss->test_err, 0, "skel1->bss->test_err");
+ ASSERT_EQ(skel2->bss->test_err, 0, "skel2->bss->test_err");
+
+out:
+ struct_ops_id_ops_mapping1__destroy(skel1);
+ struct_ops_id_ops_mapping2__destroy(skel2);
+}
+
+void test_struct_ops_id_ops_mapping(void)
+{
+ if (test__start_subtest("st_ops_id_ops_mapping"))
+ test_st_ops_id_ops_mapping();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
new file mode 100644
index 000000000000..273dd41ca09e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
@@ -0,0 +1,1612 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+
+#define CG_PATH "/foo"
+#define MAX_INSNS 512
+#define FIXUP_SYSCTL_VALUE 0
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+struct sysctl_test {
+ const char *descr;
+ size_t fixup_value_insn;
+ struct bpf_insn insns[MAX_INSNS];
+ const char *prog_file;
+ enum bpf_attach_type attach_type;
+ const char *sysctl;
+ int open_flags;
+ int seek;
+ const char *newval;
+ const char *oldval;
+ enum {
+ LOAD_REJECT,
+ ATTACH_REJECT,
+ OP_EPERM,
+ SUCCESS,
+ } result;
+};
+
+static struct sysctl_test tests[] = {
+ {
+ .descr = "sysctl wrong attach_type",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = 0,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = ATTACH_REJECT,
+ },
+ {
+ .descr = "sysctl:read allow all",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl:read deny all",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "ctx:write sysctl:read read ok",
+ .insns = {
+ /* If (write) */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, write)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 1, 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "ctx:write sysctl:write read ok",
+ .insns = {
+ /* If (write) */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, write)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 1, 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/domainname",
+ .open_flags = O_WRONLY,
+ .newval = "(none)", /* same as default, should fail anyway */
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "ctx:write sysctl:write read ok narrow",
+ .insns = {
+ /* u64 w = (u16)write & 1; */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, write)),
+#else
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, write) + 2),
+#endif
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_7, 1),
+ /* return 1 - w; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/domainname",
+ .open_flags = O_WRONLY,
+ .newval = "(none)", /* same as default, should fail anyway */
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "ctx:write sysctl:read write reject",
+ .insns = {
+ /* write = X */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sysctl, write)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = LOAD_REJECT,
+ },
+ {
+ .descr = "ctx:file_pos sysctl:read read ok",
+ .insns = {
+ /* If (file_pos == X) */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, file_pos)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 3, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .seek = 3,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "ctx:file_pos sysctl:read read ok narrow",
+ .insns = {
+ /* If (file_pos == X) */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, file_pos)),
+#else
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
+ offsetof(struct bpf_sysctl, file_pos) + 3),
+#endif
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 4, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .seek = 4,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "ctx:file_pos sysctl:read write ok",
+ .insns = {
+ /* file_pos = X */
+ BPF_MOV64_IMM(BPF_REG_0, 2),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
+ offsetof(struct bpf_sysctl, file_pos)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .oldval = "nux\n",
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_name sysctl_value:base ok",
+ .insns = {
+ /* sysctl_get_name arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_name arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+
+ /* sysctl_get_name arg4 (flags) */
+ BPF_MOV64_IMM(BPF_REG_4, BPF_F_SYSCTL_BASE_NAME),
+
+ /* sysctl_get_name(ctx, buf, buf_len, flags) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, sizeof("tcp_mem") - 1, 6),
+ /* buf == "tcp_mem\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x7463705f6d656d00ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_name sysctl_value:base E2BIG truncated",
+ .insns = {
+ /* sysctl_get_name arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_name arg3 (buf_len) too small */
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+
+ /* sysctl_get_name arg4 (flags) */
+ BPF_MOV64_IMM(BPF_REG_4, BPF_F_SYSCTL_BASE_NAME),
+
+ /* sysctl_get_name(ctx, buf, buf_len, flags) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6),
+
+ /* buf[0:7] == "tcp_me\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x7463705f6d650000ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_name sysctl:full ok",
+ .insns = {
+ /* sysctl_get_name arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_name arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 17),
+
+ /* sysctl_get_name arg4 (flags) */
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+
+ /* sysctl_get_name(ctx, buf, buf_len, flags) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 16, 14),
+
+ /* buf[0:8] == "net/ipv4" && */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x6e65742f69707634ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10),
+
+ /* buf[8:16] == "/tcp_mem" && */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x2f7463705f6d656dULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6),
+
+ /* buf[16:24] == "\0") */
+ BPF_LD_IMM64(BPF_REG_8, 0x0ULL),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 16),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_name sysctl:full E2BIG truncated",
+ .insns = {
+ /* sysctl_get_name arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -16),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_name arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 16),
+
+ /* sysctl_get_name arg4 (flags) */
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+
+ /* sysctl_get_name(ctx, buf, buf_len, flags) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 10),
+
+ /* buf[0:8] == "net/ipv4" && */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x6e65742f69707634ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6),
+
+ /* buf[8:16] == "/tcp_me\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x2f7463705f6d6500ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_name sysctl:full E2BIG truncated small",
+ .insns = {
+ /* sysctl_get_name arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_name arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+
+ /* sysctl_get_name arg4 (flags) */
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+
+ /* sysctl_get_name(ctx, buf, buf_len, flags) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6),
+
+ /* buf[0:8] == "net/ip\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x6e65742f69700000ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_current_value sysctl:read ok, gt",
+ .insns = {
+ /* sysctl_get_current_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_current_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+
+ /* sysctl_get_current_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6),
+
+ /* buf[0:6] == "Linux\n\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x4c696e75780a0000ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_current_value sysctl:read ok, eq",
+ .insns = {
+ /* sysctl_get_current_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_B, BPF_REG_7, BPF_REG_0, 7),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_current_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+
+ /* sysctl_get_current_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6),
+
+ /* buf[0:6] == "Linux\n\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x4c696e75780a0000ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_current_value sysctl:read E2BIG truncated",
+ .insns = {
+ /* sysctl_get_current_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_H, BPF_REG_7, BPF_REG_0, 6),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_current_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 6),
+
+ /* sysctl_get_current_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6),
+
+ /* buf[0:6] == "Linux\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x4c696e7578000000ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "kernel/ostype",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_current_value sysctl:read EINVAL",
+ .insns = {
+ /* sysctl_get_current_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_current_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+
+ /* sysctl_get_current_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 4),
+
+ /* buf[0:8] is NUL-filled) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv6/conf/lo/stable_secret", /* -EIO */
+ .open_flags = O_RDONLY,
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "sysctl_get_current_value sysctl:write ok",
+ .fixup_value_insn = 6,
+ .insns = {
+ /* sysctl_get_current_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_current_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+
+ /* sysctl_get_current_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, 6),
+
+ /* buf[0:4] == expected) */
+ BPF_LD_IMM64(BPF_REG_8, FIXUP_SYSCTL_VALUE),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_WRONLY,
+ .newval = "600", /* same as default, should fail anyway */
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "sysctl_get_new_value sysctl:read EINVAL",
+ .insns = {
+ /* sysctl_get_new_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_new_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+
+ /* sysctl_get_new_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_get_new_value sysctl:write ok",
+ .insns = {
+ /* sysctl_get_new_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_new_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 4),
+
+ /* sysctl_get_new_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4),
+
+ /* buf[0:4] == "606\0") */
+ BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9,
+ bpf_ntohl(0x36303600), 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_WRONLY,
+ .newval = "606",
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "sysctl_get_new_value sysctl:write ok long",
+ .insns = {
+ /* sysctl_get_new_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_new_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 24),
+
+ /* sysctl_get_new_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 23, 14),
+
+ /* buf[0:8] == "3000000 " && */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x3330303030303020ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10),
+
+ /* buf[8:16] == "4000000 " && */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x3430303030303020ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6),
+
+ /* buf[16:24] == "6000000\0") */
+ BPF_LD_IMM64(BPF_REG_8,
+ bpf_be64_to_cpu(0x3630303030303000ULL)),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 16),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_WRONLY,
+ .newval = "3000000 4000000 6000000",
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "sysctl_get_new_value sysctl:write E2BIG",
+ .insns = {
+ /* sysctl_get_new_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_B, BPF_REG_7, BPF_REG_0, 3),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_get_new_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 3),
+
+ /* sysctl_get_new_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 4),
+
+ /* buf[0:3] == "60\0") */
+ BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9,
+ bpf_ntohl(0x36300000), 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_WRONLY,
+ .newval = "606",
+ .result = OP_EPERM,
+ },
+ {
+ .descr = "sysctl_set_new_value sysctl:read EINVAL",
+ .insns = {
+ /* sysctl_set_new_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x36303000)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_set_new_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 3),
+
+ /* sysctl_set_new_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_set_new_value),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ .descr = "sysctl_set_new_value sysctl:write ok",
+ .fixup_value_insn = 2,
+ .insns = {
+ /* sysctl_set_new_value arg2 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_LD_IMM64(BPF_REG_0, FIXUP_SYSCTL_VALUE),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+
+ /* sysctl_set_new_value arg3 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_3, 3),
+
+ /* sysctl_set_new_value(ctx, buf, buf_len) */
+ BPF_EMIT_CALL(BPF_FUNC_sysctl_set_new_value),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_WRONLY,
+ .newval = "606",
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtoul one number string",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x36303000)),
+ BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4),
+ /* res == expected) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 600, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtoul multi number string",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ /* "600 602\0" */
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3630302036303200ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 18),
+ /* res == expected) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 600, 16),
+
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_0),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -16),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, 4),
+ /* res == expected) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 602, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtoul buf_len = 0, reject",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x36303000)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = LOAD_REJECT,
+ },
+ {
+ "bpf_strtoul supported base, ok",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x30373700)),
+ BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4),
+ /* res == expected) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 63, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtoul unsupported base, EINVAL",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x36303000)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 3),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtoul buf with spaces only, EINVAL",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x0d0c0a09)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtoul negative number, EINVAL",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ /* " -6\0" */
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x0a2d3600)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtoul),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtol negative number, ok",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ /* " -6\0" */
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x0a2d3600)),
+ BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 10),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtol),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4),
+ /* res == expected) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, -6, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtol hex number, ok",
+ .insns = {
+ /* arg1 (buf) */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ /* "0xfe" */
+ BPF_MOV64_IMM(BPF_REG_0,
+ bpf_ntohl(0x30786665)),
+ BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtol),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, 4),
+ /* res == expected) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 254, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtol max long",
+ .insns = {
+ /* arg1 (buf) 9223372036854775807 */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24),
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3932323333373230ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3336383534373735ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8),
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3830370000000000ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 19),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtol),
+
+ /* if (ret == expected && */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 19, 6),
+ /* res == expected) */
+ BPF_LD_IMM64(BPF_REG_8, 0x7fffffffffffffffULL),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0),
+ BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "bpf_strtol overflow, ERANGE",
+ .insns = {
+ /* arg1 (buf) 9223372036854775808 */
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24),
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3932323333373230ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3336383534373735ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8),
+ BPF_LD_IMM64(BPF_REG_0,
+ bpf_be64_to_cpu(0x3830380000000000ULL)),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16),
+
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+
+ /* arg2 (buf_len) */
+ BPF_MOV64_IMM(BPF_REG_2, 19),
+
+ /* arg3 (flags) */
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+
+ /* arg4 (res) */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
+
+ BPF_EMIT_CALL(BPF_FUNC_strtol),
+
+ /* if (ret == expected) */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -ERANGE, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+ {
+ "C prog: deny all writes",
+ .prog_file = "./test_sysctl_prog.bpf.o",
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_WRONLY,
+ .newval = "123 456 789",
+ .result = OP_EPERM,
+ },
+ {
+ "C prog: deny access by name",
+ .prog_file = "./test_sysctl_prog.bpf.o",
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/route/mtu_expires",
+ .open_flags = O_RDONLY,
+ .result = OP_EPERM,
+ },
+ {
+ "C prog: read tcp_mem",
+ .prog_file = "./test_sysctl_prog.bpf.o",
+ .attach_type = BPF_CGROUP_SYSCTL,
+ .sysctl = "net/ipv4/tcp_mem",
+ .open_flags = O_RDONLY,
+ .result = SUCCESS,
+ },
+};
+
+static size_t probe_prog_length(const struct bpf_insn *fp)
+{
+ size_t len;
+
+ for (len = MAX_INSNS - 1; len > 0; --len)
+ if (fp[len].code != 0 || fp[len].imm != 0)
+ break;
+ return len + 1;
+}
+
+static int fixup_sysctl_value(const char *buf, size_t buf_len,
+ struct bpf_insn *prog, size_t insn_num)
+{
+ union {
+ uint8_t raw[sizeof(uint64_t)];
+ uint64_t num;
+ } value = {};
+
+ if (buf_len > sizeof(value)) {
+ log_err("Value is too big (%zd) to use in fixup", buf_len);
+ return -1;
+ }
+ if (prog[insn_num].code != (BPF_LD | BPF_DW | BPF_IMM)) {
+ log_err("Can fixup only BPF_LD_IMM64 insns");
+ return -1;
+ }
+
+ memcpy(value.raw, buf, buf_len);
+ prog[insn_num].imm = (uint32_t)value.num;
+ prog[insn_num + 1].imm = (uint32_t)(value.num >> 32);
+
+ return 0;
+}
+
+static int load_sysctl_prog_insns(struct sysctl_test *test,
+ const char *sysctl_path)
+{
+ struct bpf_insn *prog = test->insns;
+ LIBBPF_OPTS(bpf_prog_load_opts, opts);
+ int ret, insn_cnt;
+
+ insn_cnt = probe_prog_length(prog);
+
+ if (test->fixup_value_insn) {
+ char buf[128];
+ ssize_t len;
+ int fd;
+
+ fd = open(sysctl_path, O_RDONLY | O_CLOEXEC);
+ if (fd < 0) {
+ log_err("open(%s) failed", sysctl_path);
+ return -1;
+ }
+ len = read(fd, buf, sizeof(buf));
+ if (len == -1) {
+ log_err("read(%s) failed", sysctl_path);
+ close(fd);
+ return -1;
+ }
+ close(fd);
+ if (fixup_sysctl_value(buf, len, prog, test->fixup_value_insn))
+ return -1;
+ }
+
+ opts.log_buf = bpf_log_buf;
+ opts.log_size = BPF_LOG_BUF_SIZE;
+
+ ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SYSCTL, NULL, "GPL", prog, insn_cnt, &opts);
+ if (ret < 0 && test->result != LOAD_REJECT) {
+ log_err(">>> Loading program error.\n"
+ ">>> Verifier output:\n%s\n-------\n", bpf_log_buf);
+ }
+
+ return ret;
+}
+
+static int load_sysctl_prog_file(struct sysctl_test *test)
+{
+ struct bpf_object *obj;
+ int prog_fd;
+
+ if (bpf_prog_test_load(test->prog_file, BPF_PROG_TYPE_CGROUP_SYSCTL, &obj, &prog_fd)) {
+ if (test->result != LOAD_REJECT)
+ log_err(">>> Loading program (%s) error.\n",
+ test->prog_file);
+ return -1;
+ }
+
+ return prog_fd;
+}
+
+static int load_sysctl_prog(struct sysctl_test *test, const char *sysctl_path)
+{
+ return test->prog_file
+ ? load_sysctl_prog_file(test)
+ : load_sysctl_prog_insns(test, sysctl_path);
+}
+
+static int access_sysctl(const char *sysctl_path,
+ const struct sysctl_test *test)
+{
+ int err = 0;
+ int fd;
+
+ fd = open(sysctl_path, test->open_flags | O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ if (test->seek && lseek(fd, test->seek, SEEK_SET) == -1) {
+ log_err("lseek(%d) failed", test->seek);
+ goto err;
+ }
+
+ if (test->open_flags == O_RDONLY) {
+ char buf[128];
+
+ if (read(fd, buf, sizeof(buf)) == -1)
+ goto err;
+ if (test->oldval &&
+ strncmp(buf, test->oldval, strlen(test->oldval))) {
+ log_err("Read value %s != %s", buf, test->oldval);
+ goto err;
+ }
+ } else if (test->open_flags == O_WRONLY) {
+ if (!test->newval) {
+ log_err("New value for sysctl is not set");
+ goto err;
+ }
+ if (write(fd, test->newval, strlen(test->newval)) == -1)
+ goto err;
+ } else {
+ log_err("Unexpected sysctl access: neither read nor write");
+ goto err;
+ }
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(fd);
+ return err;
+}
+
+static int run_test_case(int cgfd, struct sysctl_test *test)
+{
+ enum bpf_attach_type atype = test->attach_type;
+ char sysctl_path[128];
+ int progfd = -1;
+ int err = 0;
+
+ printf("Test case: %s .. ", test->descr);
+
+ snprintf(sysctl_path, sizeof(sysctl_path), "/proc/sys/%s",
+ test->sysctl);
+
+ progfd = load_sysctl_prog(test, sysctl_path);
+ if (progfd < 0) {
+ if (test->result == LOAD_REJECT)
+ goto out;
+ else
+ goto err;
+ }
+
+ if (bpf_prog_attach(progfd, cgfd, atype, BPF_F_ALLOW_OVERRIDE) < 0) {
+ if (test->result == ATTACH_REJECT)
+ goto out;
+ else
+ goto err;
+ }
+
+ errno = 0;
+ if (access_sysctl(sysctl_path, test) == -1) {
+ if (test->result == OP_EPERM && errno == EPERM)
+ goto out;
+ else
+ goto err;
+ }
+
+ if (test->result != SUCCESS) {
+ log_err("Unexpected success");
+ goto err;
+ }
+
+ goto out;
+err:
+ err = -1;
+out:
+ /* Detaching w/o checking return code: best effort attempt. */
+ if (progfd != -1)
+ bpf_prog_detach(cgfd, atype);
+ close(progfd);
+ printf("[%s]\n", err ? "FAIL" : "PASS");
+ return err;
+}
+
+static int run_tests(int cgfd)
+{
+ int passes = 0;
+ int fails = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+ if (run_test_case(cgfd, &tests[i]))
+ ++fails;
+ else
+ ++passes;
+ }
+ printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
+ return fails ? -1 : 0;
+}
+
+void test_sysctl(void)
+{
+ int cgfd;
+
+ cgfd = cgroup_setup_and_join(CG_PATH);
+ if (!ASSERT_OK_FD(cgfd < 0, "create_cgroup"))
+ goto out;
+
+ if (!ASSERT_OK(run_tests(cgfd), "run_tests"))
+ goto out;
+
+out:
+ close(cgfd);
+ cleanup_cgroup_environment();
+ return;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
new file mode 100644
index 000000000000..9fd6306b455c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <bpf/btf.h>
+#include <test_progs.h>
+
+#define TLD_FREE_DATA_ON_THREAD_EXIT
+#define TLD_DYN_DATA_SIZE 4096
+#include "task_local_data.h"
+
+struct test_tld_struct {
+ __u64 a;
+ __u64 b;
+ __u64 c;
+ __u64 d;
+};
+
+#include "test_task_local_data.skel.h"
+
+TLD_DEFINE_KEY(value0_key, "value0", sizeof(int));
+
+/*
+ * Reset task local data between subtests by clearing metadata other
+ * than the statically defined value0. This is safe as subtests run
+ * sequentially. Users of task local data library should not touch
+ * library internal.
+ */
+static void reset_tld(void)
+{
+ if (TLD_READ_ONCE(tld_meta_p)) {
+ /* Remove TLDs created by tld_create_key() */
+ tld_meta_p->cnt = 1;
+ tld_meta_p->size = TLD_DYN_DATA_SIZE;
+ memset(&tld_meta_p->metadata[1], 0,
+ (TLD_MAX_DATA_CNT - 1) * sizeof(struct tld_metadata));
+ }
+}
+
+/* Serialize access to bpf program's global variables */
+static pthread_mutex_t global_mutex;
+
+static tld_key_t *tld_keys;
+
+#define TEST_BASIC_THREAD_NUM 32
+
+void *test_task_local_data_basic_thread(void *arg)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ struct test_task_local_data *skel = (struct test_task_local_data *)arg;
+ int fd, err, tid, *value0, *value1;
+ struct test_tld_struct *value2;
+
+ fd = bpf_map__fd(skel->maps.tld_data_map);
+
+ value0 = tld_get_data(fd, value0_key);
+ if (!ASSERT_OK_PTR(value0, "tld_get_data"))
+ goto out;
+
+ value1 = tld_get_data(fd, tld_keys[1]);
+ if (!ASSERT_OK_PTR(value1, "tld_get_data"))
+ goto out;
+
+ value2 = tld_get_data(fd, tld_keys[2]);
+ if (!ASSERT_OK_PTR(value2, "tld_get_data"))
+ goto out;
+
+ tid = sys_gettid();
+
+ *value0 = tid + 0;
+ *value1 = tid + 1;
+ value2->a = tid + 2;
+ value2->b = tid + 3;
+ value2->c = tid + 4;
+ value2->d = tid + 5;
+
+ pthread_mutex_lock(&global_mutex);
+ /* Run task_main that read task local data and save to global variables */
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+ ASSERT_OK(err, "run task_main");
+ ASSERT_OK(opts.retval, "task_main retval");
+
+ ASSERT_EQ(skel->bss->test_value0, tid + 0, "tld_get_data value0");
+ ASSERT_EQ(skel->bss->test_value1, tid + 1, "tld_get_data value1");
+ ASSERT_EQ(skel->bss->test_value2.a, tid + 2, "tld_get_data value2.a");
+ ASSERT_EQ(skel->bss->test_value2.b, tid + 3, "tld_get_data value2.b");
+ ASSERT_EQ(skel->bss->test_value2.c, tid + 4, "tld_get_data value2.c");
+ ASSERT_EQ(skel->bss->test_value2.d, tid + 5, "tld_get_data value2.d");
+ pthread_mutex_unlock(&global_mutex);
+
+ /* Make sure valueX are indeed local to threads */
+ ASSERT_EQ(*value0, tid + 0, "value0");
+ ASSERT_EQ(*value1, tid + 1, "value1");
+ ASSERT_EQ(value2->a, tid + 2, "value2.a");
+ ASSERT_EQ(value2->b, tid + 3, "value2.b");
+ ASSERT_EQ(value2->c, tid + 4, "value2.c");
+ ASSERT_EQ(value2->d, tid + 5, "value2.d");
+
+ *value0 = tid + 5;
+ *value1 = tid + 4;
+ value2->a = tid + 3;
+ value2->b = tid + 2;
+ value2->c = tid + 1;
+ value2->d = tid + 0;
+
+ /* Run task_main again */
+ pthread_mutex_lock(&global_mutex);
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+ ASSERT_OK(err, "run task_main");
+ ASSERT_OK(opts.retval, "task_main retval");
+
+ ASSERT_EQ(skel->bss->test_value0, tid + 5, "tld_get_data value0");
+ ASSERT_EQ(skel->bss->test_value1, tid + 4, "tld_get_data value1");
+ ASSERT_EQ(skel->bss->test_value2.a, tid + 3, "tld_get_data value2.a");
+ ASSERT_EQ(skel->bss->test_value2.b, tid + 2, "tld_get_data value2.b");
+ ASSERT_EQ(skel->bss->test_value2.c, tid + 1, "tld_get_data value2.c");
+ ASSERT_EQ(skel->bss->test_value2.d, tid + 0, "tld_get_data value2.d");
+ pthread_mutex_unlock(&global_mutex);
+
+out:
+ pthread_exit(NULL);
+}
+
+static void test_task_local_data_basic(void)
+{
+ struct test_task_local_data *skel;
+ pthread_t thread[TEST_BASIC_THREAD_NUM];
+ char dummy_key_name[TLD_NAME_LEN];
+ tld_key_t key;
+ int i, err;
+
+ reset_tld();
+
+ ASSERT_OK(pthread_mutex_init(&global_mutex, NULL), "pthread_mutex_init");
+
+ skel = test_task_local_data__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+ return;
+
+ tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t));
+ if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys"))
+ goto out;
+
+ ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY");
+ tld_keys[1] = tld_create_key("value1", sizeof(int));
+ ASSERT_FALSE(tld_key_is_err(tld_keys[1]), "tld_create_key");
+ tld_keys[2] = tld_create_key("value2", sizeof(struct test_tld_struct));
+ ASSERT_FALSE(tld_key_is_err(tld_keys[2]), "tld_create_key");
+
+ /*
+ * Shouldn't be able to store data exceed a page. Create a TLD just big
+ * enough to exceed a page. TLDs already created are int value0, int
+ * value1, and struct test_tld_struct value2.
+ */
+ key = tld_create_key("value_not_exist",
+ TLD_PAGE_SIZE - 2 * sizeof(int) - sizeof(struct test_tld_struct) + 1);
+ ASSERT_EQ(tld_key_err_or_zero(key), -E2BIG, "tld_create_key");
+
+ key = tld_create_key("value2", sizeof(struct test_tld_struct));
+ ASSERT_EQ(tld_key_err_or_zero(key), -EEXIST, "tld_create_key");
+
+ /* Shouldn't be able to create the (TLD_MAX_DATA_CNT+1)-th TLD */
+ for (i = 3; i < TLD_MAX_DATA_CNT; i++) {
+ snprintf(dummy_key_name, TLD_NAME_LEN, "dummy_value%d", i);
+ tld_keys[i] = tld_create_key(dummy_key_name, sizeof(int));
+ ASSERT_FALSE(tld_key_is_err(tld_keys[i]), "tld_create_key");
+ }
+ key = tld_create_key("value_not_exist", sizeof(struct test_tld_struct));
+ ASSERT_EQ(tld_key_err_or_zero(key), -ENOSPC, "tld_create_key");
+
+ /* Access TLDs from multiple threads and check if they are thread-specific */
+ for (i = 0; i < TEST_BASIC_THREAD_NUM; i++) {
+ err = pthread_create(&thread[i], NULL, test_task_local_data_basic_thread, skel);
+ if (!ASSERT_OK(err, "pthread_create"))
+ goto out;
+ }
+
+out:
+ for (i = 0; i < TEST_BASIC_THREAD_NUM; i++)
+ pthread_join(thread[i], NULL);
+
+ if (tld_keys) {
+ free(tld_keys);
+ tld_keys = NULL;
+ }
+ tld_free();
+ test_task_local_data__destroy(skel);
+}
+
+#define TEST_RACE_THREAD_NUM (TLD_MAX_DATA_CNT - 3)
+
+void *test_task_local_data_race_thread(void *arg)
+{
+ int err = 0, id = (intptr_t)arg;
+ char key_name[32];
+ tld_key_t key;
+
+ key = tld_create_key("value_not_exist", TLD_PAGE_SIZE + 1);
+ if (tld_key_err_or_zero(key) != -E2BIG) {
+ err = 1;
+ goto out;
+ }
+
+ /* Only one thread will succeed in creating value1 */
+ key = tld_create_key("value1", sizeof(int));
+ if (!tld_key_is_err(key))
+ tld_keys[1] = key;
+
+ /* Only one thread will succeed in creating value2 */
+ key = tld_create_key("value2", sizeof(struct test_tld_struct));
+ if (!tld_key_is_err(key))
+ tld_keys[2] = key;
+
+ snprintf(key_name, 32, "thread_%d", id);
+ tld_keys[id] = tld_create_key(key_name, sizeof(int));
+ if (tld_key_is_err(tld_keys[id]))
+ err = 2;
+out:
+ return (void *)(intptr_t)err;
+}
+
+static void test_task_local_data_race(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+ pthread_t thread[TEST_RACE_THREAD_NUM];
+ struct test_task_local_data *skel;
+ int fd, i, j, err, *data;
+ void *ret = NULL;
+
+ skel = test_task_local_data__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+ return;
+
+ tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t));
+ if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys"))
+ goto out;
+
+ fd = bpf_map__fd(skel->maps.tld_data_map);
+
+ ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY");
+ tld_keys[0] = value0_key;
+
+ for (j = 0; j < 100; j++) {
+ reset_tld();
+
+ for (i = 0; i < TEST_RACE_THREAD_NUM; i++) {
+ /*
+ * Try to make tld_create_key() race with each other. Call
+ * tld_create_key(), both valid and invalid, from different threads.
+ */
+ err = pthread_create(&thread[i], NULL, test_task_local_data_race_thread,
+ (void *)(intptr_t)(i + 3));
+ if (CHECK_FAIL(err))
+ break;
+ }
+
+ /* Wait for all tld_create_key() to return */
+ for (i = 0; i < TEST_RACE_THREAD_NUM; i++) {
+ pthread_join(thread[i], &ret);
+ if (CHECK_FAIL(ret))
+ break;
+ }
+
+ /* Write a unique number to each TLD */
+ for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+ data = tld_get_data(fd, tld_keys[i]);
+ if (CHECK_FAIL(!data))
+ break;
+ *data = i;
+ }
+
+ /* Read TLDs and check the value to see if any address collides with another */
+ for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+ data = tld_get_data(fd, tld_keys[i]);
+ if (CHECK_FAIL(*data != i))
+ break;
+ }
+
+ /* Run task_main to make sure no invalid TLDs are added */
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+ ASSERT_OK(err, "run task_main");
+ ASSERT_OK(opts.retval, "task_main retval");
+ }
+out:
+ if (tld_keys) {
+ free(tld_keys);
+ tld_keys = NULL;
+ }
+ tld_free();
+ test_task_local_data__destroy(skel);
+}
+
+void test_task_local_data(void)
+{
+ if (test__start_subtest("task_local_data_basic"))
+ test_task_local_data_basic();
+ if (test__start_subtest("task_local_data_race"))
+ test_task_local_data_race();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_work.c b/tools/testing/selftests/bpf/prog_tests/test_task_work.c
new file mode 100644
index 000000000000..774b31a5f6ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_work.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+#include "task_work.skel.h"
+#include "task_work_fail.skel.h"
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
+#include <time.h>
+
+static int perf_event_open(__u32 type, __u64 config, int pid)
+{
+ struct perf_event_attr attr = {
+ .type = type,
+ .config = config,
+ .size = sizeof(struct perf_event_attr),
+ .sample_period = 100000,
+ };
+
+ return syscall(__NR_perf_event_open, &attr, pid, -1, -1, 0);
+}
+
+struct elem {
+ char data[128];
+ struct bpf_task_work tw;
+};
+
+static int verify_map(struct bpf_map *map, const char *expected_data)
+{
+ int err;
+ struct elem value;
+ int processed_values = 0;
+ int k, sz;
+
+ sz = bpf_map__max_entries(map);
+ for (k = 0; k < sz; ++k) {
+ err = bpf_map__lookup_elem(map, &k, sizeof(int), &value, sizeof(struct elem), 0);
+ if (err)
+ continue;
+ if (!ASSERT_EQ(strcmp(expected_data, value.data), 0, "map data")) {
+ fprintf(stderr, "expected '%s', found '%s' in %s map", expected_data,
+ value.data, bpf_map__name(map));
+ return 2;
+ }
+ processed_values++;
+ }
+
+ return processed_values == 0;
+}
+
+static void task_work_run(const char *prog_name, const char *map_name)
+{
+ struct task_work *skel;
+ struct bpf_program *prog;
+ struct bpf_map *map;
+ struct bpf_link *link = NULL;
+ int err, pe_fd = -1, pid, status, pipefd[2];
+ char user_string[] = "hello world";
+
+ if (!ASSERT_NEQ(pipe(pipefd), -1, "pipe"))
+ return;
+
+ pid = fork();
+ if (pid == 0) {
+ __u64 num = 1;
+ int i;
+ char buf;
+
+ close(pipefd[1]);
+ read(pipefd[0], &buf, sizeof(buf));
+ close(pipefd[0]);
+
+ for (i = 0; i < 10000; ++i)
+ num *= time(0) % 7;
+ (void)num;
+ exit(0);
+ }
+ if (!ASSERT_GT(pid, 0, "fork() failed")) {
+ close(pipefd[0]);
+ close(pipefd[1]);
+ return;
+ }
+
+ skel = task_work__open();
+ if (!ASSERT_OK_PTR(skel, "task_work__open"))
+ return;
+
+ bpf_object__for_each_program(prog, skel->obj) {
+ bpf_program__set_autoload(prog, false);
+ }
+
+ prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+ if (!ASSERT_OK_PTR(prog, "prog_name"))
+ goto cleanup;
+ bpf_program__set_autoload(prog, true);
+ skel->bss->user_ptr = (char *)user_string;
+
+ err = task_work__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ pe_fd = perf_event_open(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, pid);
+ if (pe_fd == -1 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+ printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+ test__skip();
+ goto cleanup;
+ }
+ if (!ASSERT_NEQ(pe_fd, -1, "pe_fd")) {
+ fprintf(stderr, "perf_event_open errno: %d, pid: %d\n", errno, pid);
+ goto cleanup;
+ }
+
+ link = bpf_program__attach_perf_event(prog, pe_fd);
+ if (!ASSERT_OK_PTR(link, "attach_perf_event"))
+ goto cleanup;
+
+ /* perf event fd ownership is passed to bpf_link */
+ pe_fd = -1;
+ close(pipefd[0]);
+ write(pipefd[1], user_string, 1);
+ close(pipefd[1]);
+ /* Wait to collect some samples */
+ waitpid(pid, &status, 0);
+ pid = 0;
+ map = bpf_object__find_map_by_name(skel->obj, map_name);
+ if (!ASSERT_OK_PTR(map, "find map_name"))
+ goto cleanup;
+ if (!ASSERT_OK(verify_map(map, user_string), "verify map"))
+ goto cleanup;
+cleanup:
+ if (pe_fd >= 0)
+ close(pe_fd);
+ bpf_link__destroy(link);
+ task_work__destroy(skel);
+ if (pid > 0) {
+ close(pipefd[0]);
+ write(pipefd[1], user_string, 1);
+ close(pipefd[1]);
+ waitpid(pid, &status, 0);
+ }
+}
+
+void test_task_work(void)
+{
+ if (test__start_subtest("test_task_work_hash_map"))
+ task_work_run("oncpu_hash_map", "hmap");
+
+ if (test__start_subtest("test_task_work_array_map"))
+ task_work_run("oncpu_array_map", "arrmap");
+
+ if (test__start_subtest("test_task_work_lru_map"))
+ task_work_run("oncpu_lru_map", "lrumap");
+
+ RUN_TESTS(task_work_fail);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
index a95b42bf744a..b38c16b4247f 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -60,24 +60,41 @@ static void test_set_global_vars_succeeds(void)
" -G \"var_s8 = -128\" "\
" -G \"var_u8 = 255\" "\
" -G \"var_ea = EA2\" "\
- " -G \"var_eb = EB2\" "\
- " -G \"var_ec = EC2\" "\
+ " -G \"var_eb = EB2\" "\
+ " -G \"var_ec=EC2\" "\
" -G \"var_b = 1\" "\
- "-vl2 > %s", fix->veristat, fix->tmpfile);
+ " -G \"struct1[2].struct2[1][2].u.var_u8[2]=170\" "\
+ " -G \"union1.struct3.var_u8_l = 0xaa\" "\
+ " -G \"union1.struct3.var_u8_h = 0xaa\" "\
+ " -G \"arr[3]= 171\" " \
+ " -G \"arr[EA2] =172\" " \
+ " -G \"enum_arr[EC2]=EA3\" " \
+ " -G \"three_d[31][7][EA2]=173\"" \
+ " -G \"struct1[2].struct2[1][2].u.mat[5][3]=174\" " \
+ " -G \"struct11 [ 7 ] [ 5 ] .struct2[0][1].u.mat[3][0] = 175\" " \
+ " -vl2 > %s", fix->veristat, fix->tmpfile);
read(fix->fd, fix->output, fix->sz);
- __CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
- __CHECK_STR("_w=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
- __CHECK_STR("_w=0x80000000 ", "var_s32 = -0x80000000");
- __CHECK_STR("_w=0x76543210 ", "var_u32 = 0x76543210");
- __CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
- __CHECK_STR("_w=0xecec ", "var_u16 = 60652");
- __CHECK_STR("_w=128 ", "var_s8 = -128");
- __CHECK_STR("_w=255 ", "var_u8 = 255");
- __CHECK_STR("_w=11 ", "var_ea = EA2");
- __CHECK_STR("_w=12 ", "var_eb = EB2");
- __CHECK_STR("_w=13 ", "var_ec = EC2");
- __CHECK_STR("_w=1 ", "var_b = 1");
+ __CHECK_STR("=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
+ __CHECK_STR("=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
+ __CHECK_STR("=0x80000000 ", "var_s32 = -0x80000000");
+ __CHECK_STR("=0x76543210 ", "var_u32 = 0x76543210");
+ __CHECK_STR("=0x8000 ", "var_s16 = -32768");
+ __CHECK_STR("=0xecec ", "var_u16 = 60652");
+ __CHECK_STR("=128 ", "var_s8 = -128");
+ __CHECK_STR("=255 ", "var_u8 = 255");
+ __CHECK_STR("=11 ", "var_ea = EA2");
+ __CHECK_STR("=12 ", "var_eb = EB2");
+ __CHECK_STR("=13 ", "var_ec = EC2");
+ __CHECK_STR("=1 ", "var_b = 1");
+ __CHECK_STR("=170 ", "struct1[2].struct2[1][2].u.var_u8[2]=170");
+ __CHECK_STR("=0xaaaa ", "union1.var_u16 = 0xaaaa");
+ __CHECK_STR("=171 ", "arr[3]= 171");
+ __CHECK_STR("=172 ", "arr[EA2] =172");
+ __CHECK_STR("=10 ", "enum_arr[EC2]=EA3");
+ __CHECK_STR("=173 ", "matrix[31][7][11]=173");
+ __CHECK_STR("=174 ", "struct1[2].struct2[1][2].u.mat[5][3]=174");
+ __CHECK_STR("=175 ", "struct11[7][5].struct2[0][1].u.mat[3][0]=175");
out:
teardown_fixture(fix);
@@ -100,8 +117,8 @@ static void test_set_global_vars_from_file_succeeds(void)
SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s",
fix->veristat, input_file, fix->tmpfile);
read(fix->fd, fix->output, fix->sz);
- __CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
- __CHECK_STR("_w=0xecec ", "var_u16 = 60652");
+ __CHECK_STR("=0x8000 ", "var_s16 = -32768");
+ __CHECK_STR("=0xecec ", "var_u16 = 60652");
out:
close(fd);
@@ -124,6 +141,95 @@ out:
teardown_fixture(fix);
}
+static void test_unsupported_ptr_array_type(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"ptr_arr[0] = 0\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("Can't set ptr_arr[0]. Only ints and enums are supported", "ptr_arr");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_array_out_of_bounds(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"arr[99] = 0\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("Array index 99 is out of bounds", "arr[99]");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_array_index_not_found(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"arr[EG2] = 0\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("Can't resolve enum value EG2", "arr[EG2]");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_array_index_for_non_array(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"var_b[0] = 1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Array index is not expected for var_b", "var_b[0] = 1");
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"union1.struct3[0].var_u8_l=1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Array index is not expected for struct3", "union1.struct3[0].var_u8_l=1");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_no_array_index_for_array(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"arr = 1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Can't set arr. Only ints and enums are supported", "arr = 1");
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"struct1[0].struct2.u.var_u8[2]=1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Can't resolve field u for non-composite type", "struct1[0].struct2.u.var_u8[2]=1");
+
+out:
+ teardown_fixture(fix);
+}
+
void test_veristat(void)
{
if (test__start_subtest("set_global_vars_succeeds"))
@@ -134,6 +240,22 @@ void test_veristat(void)
if (test__start_subtest("set_global_vars_from_file_succeeds"))
test_set_global_vars_from_file_succeeds();
+
+ if (test__start_subtest("test_unsupported_ptr_array_type"))
+ test_unsupported_ptr_array_type();
+
+ if (test__start_subtest("test_array_out_of_bounds"))
+ test_array_out_of_bounds();
+
+ if (test__start_subtest("test_array_index_not_found"))
+ test_array_index_not_found();
+
+ if (test__start_subtest("test_array_index_for_non_array"))
+ test_array_index_for_non_array();
+
+ if (test__start_subtest("test_no_array_index_for_array"))
+ test_no_array_index_for_array();
+
}
#undef __CHECK_STR
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index d66687f1ee6a..34f9ccce2602 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -3,6 +3,7 @@
#include <test_progs.h>
#include "timer.skel.h"
#include "timer_failure.skel.h"
+#include "timer_interrupt.skel.h"
#define NUM_THR 8
@@ -86,6 +87,10 @@ void serial_test_timer(void)
int err;
timer_skel = timer__open_and_load();
+ if (!timer_skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
return;
@@ -95,3 +100,36 @@ void serial_test_timer(void)
RUN_TESTS(timer_failure);
}
+
+void test_timer_interrupt(void)
+{
+ struct timer_interrupt *skel = NULL;
+ int err, prog_fd;
+ LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+ skel = timer_interrupt__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
+ if (!ASSERT_OK_PTR(skel, "timer_interrupt__open_and_load"))
+ return;
+
+ err = timer_interrupt__attach(skel);
+ if (!ASSERT_OK(err, "timer_interrupt__attach"))
+ goto out;
+
+ prog_fd = bpf_program__fd(skel->progs.test_timer_interrupt);
+ err = bpf_prog_test_run_opts(prog_fd, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+ goto out;
+
+ usleep(50);
+
+ ASSERT_EQ(skel->bss->in_interrupt, 0, "in_interrupt");
+ if (skel->bss->preempt_count)
+ ASSERT_NEQ(skel->bss->in_interrupt_cb, 0, "in_interrupt_cb");
+
+out:
+ timer_interrupt__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
index f74b82305da8..b841597c8a3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode)
struct timer_crash *skel;
skel = timer_crash__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
return;
skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
index 1a2f99596916..eb303fa1e09a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
@@ -59,6 +59,10 @@ void test_timer_lockup(void)
}
skel = timer_lockup__open_and_load();
+ if (!skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index 9ff7843909e7..c930c7d7105b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -65,6 +65,10 @@ void serial_test_timer_mim(void)
goto cleanup;
timer_skel = timer_mim__open_and_load();
+ if (!timer_skel && errno == EOPNOTSUPP) {
+ test__skip();
+ return;
+ }
if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
index f9392df23f8a..b81dde283052 100644
--- a/tools/testing/selftests/bpf/prog_tests/token.c
+++ b/tools/testing/selftests/bpf/prog_tests/token.c
@@ -115,7 +115,7 @@ static int create_bpffs_fd(void)
static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts)
{
- int mnt_fd, err;
+ int err;
/* set up token delegation mount options */
err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str);
@@ -136,12 +136,7 @@ static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts)
if (err < 0)
return -errno;
- /* create O_PATH fd for detached mount */
- mnt_fd = sys_fsmount(fs_fd, 0, 0);
- if (err < 0)
- return -errno;
-
- return mnt_fd;
+ return 0;
}
/* send FD over Unix domain (AF_UNIX) socket */
@@ -287,6 +282,7 @@ static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callba
{
int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1, token_fd = -1;
struct token_lsm *lsm_skel = NULL;
+ char one;
/* load and attach LSM "policy" before we go into unpriv userns */
lsm_skel = token_lsm__open_and_load();
@@ -333,13 +329,19 @@ static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callba
err = sendfd(sock_fd, fs_fd);
if (!ASSERT_OK(err, "send_fs_fd"))
goto cleanup;
- zclose(fs_fd);
+
+ /* wait that the parent reads the fd, does the fsconfig() calls
+ * and send us a signal that it is done
+ */
+ err = read(sock_fd, &one, sizeof(one));
+ if (!ASSERT_GE(err, 0, "read_one"))
+ goto cleanup;
/* avoid mucking around with mount namespaces and mounting at
- * well-known path, just get detach-mounted BPF FS fd back from parent
+ * well-known path, just create O_PATH fd for detached mount
*/
- err = recvfd(sock_fd, &mnt_fd);
- if (!ASSERT_OK(err, "recv_mnt_fd"))
+ mnt_fd = sys_fsmount(fs_fd, 0, 0);
+ if (!ASSERT_OK_FD(mnt_fd, "mnt_fd"))
goto cleanup;
/* try to fspick() BPF FS and try to add some delegation options */
@@ -429,24 +431,24 @@ again:
static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd)
{
- int fs_fd = -1, mnt_fd = -1, token_fd = -1, err;
+ int fs_fd = -1, token_fd = -1, err;
+ char one = 1;
err = recvfd(sock_fd, &fs_fd);
if (!ASSERT_OK(err, "recv_bpffs_fd"))
goto cleanup;
- mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts);
- if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) {
+ err = materialize_bpffs_fd(fs_fd, bpffs_opts);
+ if (!ASSERT_GE(err, 0, "materialize_bpffs_fd")) {
err = -EINVAL;
goto cleanup;
}
- zclose(fs_fd);
- /* pass BPF FS context object to parent */
- err = sendfd(sock_fd, mnt_fd);
- if (!ASSERT_OK(err, "send_mnt_fd"))
+ /* notify the child that we did the fsconfig() calls and it can proceed. */
+ err = write(sock_fd, &one, sizeof(one));
+ if (!ASSERT_EQ(err, sizeof(one), "send_one"))
goto cleanup;
- zclose(mnt_fd);
+ zclose(fs_fd);
/* receive BPF token FD back from child for some extra tests */
err = recvfd(sock_fd, &token_fd);
@@ -459,7 +461,6 @@ static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd)
cleanup:
zclose(sock_fd);
zclose(fs_fd);
- zclose(mnt_fd);
zclose(token_fd);
if (child_pid > 0)
@@ -1046,6 +1047,41 @@ err_out:
#define bit(n) (1ULL << (n))
+static int userns_bpf_token_info(int mnt_fd, struct token_lsm *lsm_skel)
+{
+ int err, token_fd = -1;
+ struct bpf_token_info info;
+ u32 len = sizeof(struct bpf_token_info);
+
+ /* create BPF token from BPF FS mount */
+ token_fd = bpf_token_create(mnt_fd, NULL);
+ if (!ASSERT_GT(token_fd, 0, "token_create")) {
+ err = -EINVAL;
+ goto cleanup;
+ }
+
+ memset(&info, 0, len);
+ err = bpf_obj_get_info_by_fd(token_fd, &info, &len);
+ if (!ASSERT_ERR(err, "bpf_obj_get_token_info"))
+ goto cleanup;
+ if (!ASSERT_EQ(info.allowed_cmds, bit(BPF_MAP_CREATE), "token_info_cmds_map_create")) {
+ err = -EINVAL;
+ goto cleanup;
+ }
+ if (!ASSERT_EQ(info.allowed_progs, bit(BPF_PROG_TYPE_XDP), "token_info_progs_xdp")) {
+ err = -EINVAL;
+ goto cleanup;
+ }
+
+ /* The BPF_PROG_TYPE_EXT is not set in token */
+ if (ASSERT_EQ(info.allowed_progs, bit(BPF_PROG_TYPE_EXT), "token_info_progs_ext"))
+ err = -EINVAL;
+
+cleanup:
+ zclose(token_fd);
+ return err;
+}
+
void test_token(void)
{
if (test__start_subtest("map_token")) {
@@ -1149,4 +1185,13 @@ void test_token(void)
subtest_userns(&opts, userns_obj_priv_implicit_token_envvar);
}
+ if (test__start_subtest("bpf_token_info")) {
+ struct bpffs_opts opts = {
+ .cmds = bit(BPF_MAP_CREATE),
+ .progs = bit(BPF_PROG_TYPE_XDP),
+ .attachs = ~0ULL,
+ };
+
+ subtest_userns(&opts, userns_bpf_token_info);
+ }
}
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
index a222df765bc3..10e231965589 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
@@ -28,10 +28,62 @@ out:
tracing_failure__destroy(skel);
}
+static void test_tracing_fail_prog(const char *prog_name, const char *exp_msg)
+{
+ struct tracing_failure *skel;
+ struct bpf_program *prog;
+ char log_buf[256];
+ int err;
+
+ skel = tracing_failure__open();
+ if (!ASSERT_OK_PTR(skel, "tracing_failure__open"))
+ return;
+
+ prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+ if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+ goto out;
+
+ bpf_program__set_autoload(prog, true);
+ bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf));
+
+ err = tracing_failure__load(skel);
+ if (!ASSERT_ERR(err, "tracing_failure__load"))
+ goto out;
+
+ ASSERT_HAS_SUBSTR(log_buf, exp_msg, "log_buf");
+out:
+ tracing_failure__destroy(skel);
+}
+
+static void test_tracing_deny(void)
+{
+ int btf_id;
+
+ /* __rcu_read_lock depends on CONFIG_PREEMPT_RCU */
+ btf_id = libbpf_find_vmlinux_btf_id("__rcu_read_lock", BPF_TRACE_FENTRY);
+ if (btf_id <= 0) {
+ test__skip();
+ return;
+ }
+
+ test_tracing_fail_prog("tracing_deny",
+ "Attaching tracing programs to function '__rcu_read_lock' is rejected.");
+}
+
+static void test_fexit_noreturns(void)
+{
+ test_tracing_fail_prog("fexit_noreturns",
+ "Attaching fexit/fmod_ret to __noreturn function 'do_exit' is rejected.");
+}
+
void test_tracing_failure(void)
{
if (test__start_subtest("bpf_spin_lock"))
test_bpf_spin_lock(true);
if (test__start_subtest("bpf_spin_unlock"))
test_bpf_spin_lock(false);
+ if (test__start_subtest("tracing_deny"))
+ test_tracing_deny();
+ if (test__start_subtest("fexit_noreturns"))
+ test_fexit_noreturns();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
index 19e68d4b3532..6f8c0bfb0415 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
@@ -112,10 +112,39 @@ destroy_skel:
tracing_struct_many_args__destroy(skel);
}
+static void test_union_args(void)
+{
+ struct tracing_struct *skel;
+ int err;
+
+ skel = tracing_struct__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "tracing_struct__open_and_load"))
+ return;
+
+ err = tracing_struct__attach(skel);
+ if (!ASSERT_OK(err, "tracing_struct__attach"))
+ goto out;
+
+ ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+ ASSERT_EQ(skel->bss->ut1_a_a, 1, "ut1:a.arg.a");
+ ASSERT_EQ(skel->bss->ut1_b, 4, "ut1:b");
+ ASSERT_EQ(skel->bss->ut1_c, 5, "ut1:c");
+
+ ASSERT_EQ(skel->bss->ut2_a, 6, "ut2:a");
+ ASSERT_EQ(skel->bss->ut2_b_a, 2, "ut2:b.arg.a");
+ ASSERT_EQ(skel->bss->ut2_b_b, 3, "ut2:b.arg.b");
+
+out:
+ tracing_struct__destroy(skel);
+}
+
void test_tracing_struct(void)
{
if (test__start_subtest("struct_args"))
test_struct_args();
if (test__start_subtest("struct_many_args"))
test_struct_many_args();
+ if (test__start_subtest("union_args"))
+ test_union_args();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe.c b/tools/testing/selftests/bpf/prog_tests/uprobe.c
index cf3e0e7a64fa..86404476c1da 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2023 Hengqi Chen */
#include <test_progs.h>
+#include <asm/ptrace.h>
#include "test_uprobe.skel.h"
static FILE *urand_spawn(int *pid)
@@ -33,7 +34,7 @@ static int urand_trigger(FILE **urand_pipe)
return exit_code;
}
-void test_uprobe(void)
+static void test_uprobe_attach(void)
{
LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
struct test_uprobe *skel;
@@ -93,3 +94,156 @@ cleanup:
pclose(urand_pipe);
test_uprobe__destroy(skel);
}
+
+#ifdef __x86_64__
+__naked __maybe_unused unsigned long uprobe_regs_change_trigger(void)
+{
+ asm volatile (
+ "ret\n"
+ );
+}
+
+static __naked void uprobe_regs_change(struct pt_regs *before, struct pt_regs *after)
+{
+ asm volatile (
+ "movq %r11, 48(%rdi)\n"
+ "movq %r10, 56(%rdi)\n"
+ "movq %r9, 64(%rdi)\n"
+ "movq %r8, 72(%rdi)\n"
+ "movq %rax, 80(%rdi)\n"
+ "movq %rcx, 88(%rdi)\n"
+ "movq %rdx, 96(%rdi)\n"
+ "movq %rsi, 104(%rdi)\n"
+ "movq %rdi, 112(%rdi)\n"
+
+ /* save 2nd argument */
+ "pushq %rsi\n"
+ "call uprobe_regs_change_trigger\n"
+
+ /* save return value and load 2nd argument pointer to rax */
+ "pushq %rax\n"
+ "movq 8(%rsp), %rax\n"
+
+ "movq %r11, 48(%rax)\n"
+ "movq %r10, 56(%rax)\n"
+ "movq %r9, 64(%rax)\n"
+ "movq %r8, 72(%rax)\n"
+ "movq %rcx, 88(%rax)\n"
+ "movq %rdx, 96(%rax)\n"
+ "movq %rsi, 104(%rax)\n"
+ "movq %rdi, 112(%rax)\n"
+
+ /* restore return value and 2nd argument */
+ "pop %rax\n"
+ "pop %rsi\n"
+
+ "movq %rax, 80(%rsi)\n"
+ "ret\n"
+ );
+}
+
+static void regs_common(void)
+{
+ struct pt_regs before = {}, after = {}, expected = {
+ .rax = 0xc0ffe,
+ .rcx = 0xbad,
+ .rdx = 0xdead,
+ .r8 = 0x8,
+ .r9 = 0x9,
+ .r10 = 0x10,
+ .r11 = 0x11,
+ .rdi = 0x12,
+ .rsi = 0x13,
+ };
+ LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+ struct test_uprobe *skel;
+
+ skel = test_uprobe__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->bss->my_pid = getpid();
+ skel->bss->regs = expected;
+
+ uprobe_opts.func_name = "uprobe_regs_change_trigger";
+ skel->links.test_regs_change = bpf_program__attach_uprobe_opts(skel->progs.test_regs_change,
+ -1,
+ "/proc/self/exe",
+ 0 /* offset */,
+ &uprobe_opts);
+ if (!ASSERT_OK_PTR(skel->links.test_regs_change, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ uprobe_regs_change(&before, &after);
+
+ ASSERT_EQ(after.rax, expected.rax, "ax");
+ ASSERT_EQ(after.rcx, expected.rcx, "cx");
+ ASSERT_EQ(after.rdx, expected.rdx, "dx");
+ ASSERT_EQ(after.r8, expected.r8, "r8");
+ ASSERT_EQ(after.r9, expected.r9, "r9");
+ ASSERT_EQ(after.r10, expected.r10, "r10");
+ ASSERT_EQ(after.r11, expected.r11, "r11");
+ ASSERT_EQ(after.rdi, expected.rdi, "rdi");
+ ASSERT_EQ(after.rsi, expected.rsi, "rsi");
+
+cleanup:
+ test_uprobe__destroy(skel);
+}
+
+static noinline unsigned long uprobe_regs_change_ip_1(void)
+{
+ return 0xc0ffee;
+}
+
+static noinline unsigned long uprobe_regs_change_ip_2(void)
+{
+ return 0xdeadbeef;
+}
+
+static void regs_ip(void)
+{
+ LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+ struct test_uprobe *skel;
+ unsigned long ret;
+
+ skel = test_uprobe__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->bss->my_pid = getpid();
+ skel->bss->ip = (unsigned long) uprobe_regs_change_ip_2;
+
+ uprobe_opts.func_name = "uprobe_regs_change_ip_1";
+ skel->links.test_regs_change_ip = bpf_program__attach_uprobe_opts(
+ skel->progs.test_regs_change_ip,
+ -1,
+ "/proc/self/exe",
+ 0 /* offset */,
+ &uprobe_opts);
+ if (!ASSERT_OK_PTR(skel->links.test_regs_change_ip, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ ret = uprobe_regs_change_ip_1();
+ ASSERT_EQ(ret, 0xdeadbeef, "ret");
+
+cleanup:
+ test_uprobe__destroy(skel);
+}
+
+static void test_uprobe_regs_change(void)
+{
+ if (test__start_subtest("regs_change_common"))
+ regs_common();
+ if (test__start_subtest("regs_change_ip"))
+ regs_ip();
+}
+#else
+static void test_uprobe_regs_change(void) { }
+#endif
+
+void test_uprobe(void)
+{
+ if (test__start_subtest("attach"))
+ test_uprobe_attach();
+ test_uprobe_regs_change();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index c397336fe1ed..955a37751b52 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -8,22 +8,31 @@
#include <asm/ptrace.h>
#include <linux/compiler.h>
#include <linux/stringify.h>
+#include <linux/kernel.h>
#include <sys/wait.h>
#include <sys/syscall.h>
#include <sys/prctl.h>
#include <asm/prctl.h>
#include "uprobe_syscall.skel.h"
#include "uprobe_syscall_executed.skel.h"
+#include "bpf/libbpf_internal.h"
-__naked unsigned long uretprobe_regs_trigger(void)
+#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00
+#include "usdt.h"
+
+#pragma GCC diagnostic ignored "-Wattributes"
+
+__attribute__((aligned(16)))
+__nocf_check __weak __naked unsigned long uprobe_regs_trigger(void)
{
asm volatile (
+ ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */
"movq $0xdeadbeef, %rax\n"
"ret\n"
);
}
-__naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
+__naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after)
{
asm volatile (
"movq %r15, 0(%rdi)\n"
@@ -44,15 +53,17 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
"movq $0, 120(%rdi)\n" /* orig_rax */
"movq $0, 128(%rdi)\n" /* rip */
"movq $0, 136(%rdi)\n" /* cs */
+ "pushq %rax\n"
"pushf\n"
"pop %rax\n"
"movq %rax, 144(%rdi)\n" /* eflags */
+ "pop %rax\n"
"movq %rsp, 152(%rdi)\n" /* rsp */
"movq $0, 160(%rdi)\n" /* ss */
/* save 2nd argument */
"pushq %rsi\n"
- "call uretprobe_regs_trigger\n"
+ "call uprobe_regs_trigger\n"
/* save return value and load 2nd argument pointer to rax */
"pushq %rax\n"
@@ -92,25 +103,37 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
);
}
-static void test_uretprobe_regs_equal(void)
+static void test_uprobe_regs_equal(bool retprobe)
{
+ LIBBPF_OPTS(bpf_uprobe_opts, opts,
+ .retprobe = retprobe,
+ );
struct uprobe_syscall *skel = NULL;
struct pt_regs before = {}, after = {};
unsigned long *pb = (unsigned long *) &before;
unsigned long *pa = (unsigned long *) &after;
unsigned long *pp;
+ unsigned long offset;
unsigned int i, cnt;
- int err;
+
+ offset = get_uprobe_offset(&uprobe_regs_trigger);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ return;
skel = uprobe_syscall__open_and_load();
if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load"))
goto cleanup;
- err = uprobe_syscall__attach(skel);
- if (!ASSERT_OK(err, "uprobe_syscall__attach"))
+ skel->links.probe = bpf_program__attach_uprobe_opts(skel->progs.probe,
+ 0, "/proc/self/exe", offset, &opts);
+ if (!ASSERT_OK_PTR(skel->links.probe, "bpf_program__attach_uprobe_opts"))
goto cleanup;
- uretprobe_regs(&before, &after);
+ /* make sure uprobe gets optimized */
+ if (!retprobe)
+ uprobe_regs_trigger();
+
+ uprobe_regs(&before, &after);
pp = (unsigned long *) &skel->bss->regs;
cnt = sizeof(before)/sizeof(*pb);
@@ -119,7 +142,7 @@ static void test_uretprobe_regs_equal(void)
unsigned int offset = i * sizeof(unsigned long);
/*
- * Check register before and after uretprobe_regs_trigger call
+ * Check register before and after uprobe_regs_trigger call
* that triggers the uretprobe.
*/
switch (offset) {
@@ -133,7 +156,7 @@ static void test_uretprobe_regs_equal(void)
/*
* Check register seen from bpf program and register after
- * uretprobe_regs_trigger call
+ * uprobe_regs_trigger call (with rax exception, check below).
*/
switch (offset) {
/*
@@ -146,6 +169,15 @@ static void test_uretprobe_regs_equal(void)
case offsetof(struct pt_regs, rsp):
case offsetof(struct pt_regs, ss):
break;
+ /*
+ * uprobe does not see return value in rax, it needs to see the
+ * original (before) rax value
+ */
+ case offsetof(struct pt_regs, rax):
+ if (!retprobe) {
+ ASSERT_EQ(pp[i], pb[i], "uprobe rax prog-before value check");
+ break;
+ }
default:
if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check"))
fprintf(stdout, "failed register offset %u\n", offset);
@@ -175,7 +207,7 @@ static int write_bpf_testmod_uprobe(unsigned long offset)
return ret != n ? (int) ret : 0;
}
-static void test_uretprobe_regs_change(void)
+static void test_regs_change(void)
{
struct pt_regs before = {}, after = {};
unsigned long *pb = (unsigned long *) &before;
@@ -183,13 +215,16 @@ static void test_uretprobe_regs_change(void)
unsigned long cnt = sizeof(before)/sizeof(*pb);
unsigned int i, err, offset;
- offset = get_uprobe_offset(uretprobe_regs_trigger);
+ offset = get_uprobe_offset(uprobe_regs_trigger);
err = write_bpf_testmod_uprobe(offset);
if (!ASSERT_OK(err, "register_uprobe"))
return;
- uretprobe_regs(&before, &after);
+ /* make sure uprobe gets optimized */
+ uprobe_regs_trigger();
+
+ uprobe_regs(&before, &after);
err = write_bpf_testmod_uprobe(0);
if (!ASSERT_OK(err, "unregister_uprobe"))
@@ -251,7 +286,8 @@ static void test_uretprobe_syscall_call(void)
.retprobe = true,
);
struct uprobe_syscall_executed *skel;
- int pid, status, err, go[2], c;
+ int pid, status, err, go[2], c = 0;
+ struct bpf_link *link;
if (!ASSERT_OK(pipe(go), "pipe"))
return;
@@ -277,11 +313,14 @@ static void test_uretprobe_syscall_call(void)
_exit(0);
}
- skel->links.test = bpf_program__attach_uprobe_multi(skel->progs.test, pid,
- "/proc/self/exe",
- "uretprobe_syscall_call", &opts);
- if (!ASSERT_OK_PTR(skel->links.test, "bpf_program__attach_uprobe_multi"))
+ skel->bss->pid = pid;
+
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+ pid, "/proc/self/exe",
+ "uretprobe_syscall_call", &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
goto cleanup;
+ skel->links.test_uretprobe_multi = link;
/* kick the child */
write(go[1], &c, 1);
@@ -301,6 +340,256 @@ cleanup:
close(go[0]);
}
+#define TRAMP "[uprobes-trampoline]"
+
+__attribute__((aligned(16)))
+__nocf_check __weak __naked void uprobe_test(void)
+{
+ asm volatile (" \n"
+ ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00 \n"
+ "ret \n"
+ );
+}
+
+__attribute__((aligned(16)))
+__nocf_check __weak void usdt_test(void)
+{
+ USDT(optimized_uprobe, usdt);
+}
+
+static int find_uprobes_trampoline(void *tramp_addr)
+{
+ void *start, *end;
+ char line[128];
+ int ret = -1;
+ FILE *maps;
+
+ maps = fopen("/proc/self/maps", "r");
+ if (!maps) {
+ fprintf(stderr, "cannot open maps\n");
+ return -1;
+ }
+
+ while (fgets(line, sizeof(line), maps)) {
+ int m = -1;
+
+ /* We care only about private r-x mappings. */
+ if (sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", &start, &end, &m) != 2)
+ continue;
+ if (m < 0)
+ continue;
+ if (!strncmp(&line[m], TRAMP, sizeof(TRAMP)-1) && (start == tramp_addr)) {
+ ret = 0;
+ break;
+ }
+ }
+
+ fclose(maps);
+ return ret;
+}
+
+static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+
+static void *find_nop5(void *fn)
+{
+ int i;
+
+ for (i = 0; i < 10; i++) {
+ if (!memcmp(nop5, fn + i, 5))
+ return fn + i;
+ }
+ return NULL;
+}
+
+typedef void (__attribute__((nocf_check)) *trigger_t)(void);
+
+static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger,
+ void *addr, int executed)
+{
+ struct __arch_relative_insn {
+ __u8 op;
+ __s32 raddr;
+ } __packed *call;
+ void *tramp = NULL;
+
+ /* Uprobe gets optimized after first trigger, so let's press twice. */
+ trigger();
+ trigger();
+
+ /* Make sure bpf program got executed.. */
+ ASSERT_EQ(skel->bss->executed, executed, "executed");
+
+ /* .. and check the trampoline is as expected. */
+ call = (struct __arch_relative_insn *) addr;
+ tramp = (void *) (call + 1) + call->raddr;
+ ASSERT_EQ(call->op, 0xe8, "call");
+ ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+
+ return tramp;
+}
+
+static void check_detach(void *addr, void *tramp)
+{
+ /* [uprobes_trampoline] stays after detach */
+ ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+ ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+}
+
+static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+ trigger_t trigger, void *addr, int executed)
+{
+ void *tramp;
+
+ tramp = check_attach(skel, trigger, addr, executed);
+ bpf_link__destroy(link);
+ check_detach(addr, tramp);
+}
+
+static void test_uprobe_legacy(void)
+{
+ struct uprobe_syscall_executed *skel = NULL;
+ LIBBPF_OPTS(bpf_uprobe_opts, opts,
+ .retprobe = true,
+ );
+ struct bpf_link *link;
+ unsigned long offset;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ goto cleanup;
+
+ /* uprobe */
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+ 0, "/proc/self/exe", offset, NULL);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+ /* uretprobe */
+ skel->bss->executed = 0;
+
+ link = bpf_program__attach_uprobe_opts(skel->progs.test_uretprobe,
+ 0, "/proc/self/exe", offset, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_multi(void)
+{
+ struct uprobe_syscall_executed *skel = NULL;
+ LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+ struct bpf_link *link;
+ unsigned long offset;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ goto cleanup;
+
+ opts.offsets = &offset;
+ opts.cnt = 1;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ /* uprobe.multi */
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+ 0, "/proc/self/exe", NULL, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+ /* uretprobe.multi */
+ skel->bss->executed = 0;
+ opts.retprobe = true;
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+ 0, "/proc/self/exe", NULL, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 2);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_session(void)
+{
+ struct uprobe_syscall_executed *skel = NULL;
+ LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+ .session = true,
+ );
+ struct bpf_link *link;
+ unsigned long offset;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ goto cleanup;
+
+ opts.offsets = &offset;
+ opts.cnt = 1;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+ 0, "/proc/self/exe", NULL, &opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+ goto cleanup;
+
+ check(skel, link, uprobe_test, uprobe_test, 4);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_usdt(void)
+{
+ struct uprobe_syscall_executed *skel;
+ struct bpf_link *link;
+ void *addr;
+
+ errno = 0;
+ addr = find_nop5(usdt_test);
+ if (!ASSERT_OK_PTR(addr, "find_nop5"))
+ return;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ link = bpf_program__attach_usdt(skel->progs.test_usdt,
+ -1 /* all PIDs */, "/proc/self/exe",
+ "optimized_uprobe", "usdt", NULL);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+ goto cleanup;
+
+ check(skel, link, usdt_test, addr, 2);
+
+cleanup:
+ uprobe_syscall_executed__destroy(skel);
+}
+
/*
* Borrowed from tools/testing/selftests/x86/test_shadow_stack.c.
*
@@ -343,43 +632,172 @@ static void test_uretprobe_shadow_stack(void)
return;
}
- /* Run all of the uretprobe tests. */
- test_uretprobe_regs_equal();
- test_uretprobe_regs_change();
+ /* Run all the tests with shadow stack in place. */
+
+ test_uprobe_regs_equal(false);
+ test_uprobe_regs_equal(true);
test_uretprobe_syscall_call();
+ test_uprobe_legacy();
+ test_uprobe_multi();
+ test_uprobe_session();
+ test_uprobe_usdt();
+
+ test_regs_change();
+
ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
}
-#else
-static void test_uretprobe_regs_equal(void)
+
+static volatile bool race_stop;
+
+static USDT_DEFINE_SEMA(race);
+
+static void *worker_trigger(void *arg)
{
- test__skip();
+ unsigned long rounds = 0;
+
+ while (!race_stop) {
+ uprobe_test();
+ rounds++;
+ }
+
+ printf("tid %ld trigger rounds: %lu\n", sys_gettid(), rounds);
+ return NULL;
}
-static void test_uretprobe_regs_change(void)
+static void *worker_attach(void *arg)
{
- test__skip();
+ LIBBPF_OPTS(bpf_uprobe_opts, opts);
+ struct uprobe_syscall_executed *skel;
+ unsigned long rounds = 0, offset;
+ const char *sema[2] = {
+ __stringify(USDT_SEMA(race)),
+ NULL,
+ };
+ unsigned long *ref;
+ int err;
+
+ offset = get_uprobe_offset(&uprobe_test);
+ if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+ return NULL;
+
+ err = elf_resolve_syms_offsets("/proc/self/exe", 1, (const char **) &sema, &ref, STT_OBJECT);
+ if (!ASSERT_OK(err, "elf_resolve_syms_offsets_sema"))
+ return NULL;
+
+ opts.ref_ctr_offset = *ref;
+
+ skel = uprobe_syscall_executed__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+ return NULL;
+
+ skel->bss->pid = getpid();
+
+ while (!race_stop) {
+ skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+ 0, "/proc/self/exe", offset, &opts);
+ if (!ASSERT_OK_PTR(skel->links.test_uprobe, "bpf_program__attach_uprobe_opts"))
+ break;
+
+ bpf_link__destroy(skel->links.test_uprobe);
+ skel->links.test_uprobe = NULL;
+ rounds++;
+ }
+
+ printf("tid %ld attach rounds: %lu hits: %d\n", sys_gettid(), rounds, skel->bss->executed);
+ uprobe_syscall_executed__destroy(skel);
+ free(ref);
+ return NULL;
}
-static void test_uretprobe_syscall_call(void)
+static useconds_t race_msec(void)
{
- test__skip();
+ char *env;
+
+ env = getenv("BPF_SELFTESTS_UPROBE_SYSCALL_RACE_MSEC");
+ if (env)
+ return atoi(env);
+
+ /* default duration is 500ms */
+ return 500;
}
-static void test_uretprobe_shadow_stack(void)
+static void test_uprobe_race(void)
{
- test__skip();
+ int err, i, nr_threads;
+ pthread_t *threads;
+
+ nr_threads = libbpf_num_possible_cpus();
+ if (!ASSERT_GT(nr_threads, 0, "libbpf_num_possible_cpus"))
+ return;
+ nr_threads = max(2, nr_threads);
+
+ threads = alloca(sizeof(*threads) * nr_threads);
+ if (!ASSERT_OK_PTR(threads, "malloc"))
+ return;
+
+ for (i = 0; i < nr_threads; i++) {
+ err = pthread_create(&threads[i], NULL, i % 2 ? worker_trigger : worker_attach,
+ NULL);
+ if (!ASSERT_OK(err, "pthread_create"))
+ goto cleanup;
+ }
+
+ usleep(race_msec() * 1000);
+
+cleanup:
+ race_stop = true;
+ for (nr_threads = i, i = 0; i < nr_threads; i++)
+ pthread_join(threads[i], NULL);
+
+ ASSERT_FALSE(USDT_SEMA_IS_ACTIVE(race), "race_semaphore");
}
+
+#ifndef __NR_uprobe
+#define __NR_uprobe 336
#endif
-void test_uprobe_syscall(void)
+static void test_uprobe_error(void)
+{
+ long err = syscall(__NR_uprobe);
+
+ ASSERT_EQ(err, -1, "error");
+ ASSERT_EQ(errno, ENXIO, "errno");
+}
+
+static void __test_uprobe_syscall(void)
{
if (test__start_subtest("uretprobe_regs_equal"))
- test_uretprobe_regs_equal();
- if (test__start_subtest("uretprobe_regs_change"))
- test_uretprobe_regs_change();
+ test_uprobe_regs_equal(true);
if (test__start_subtest("uretprobe_syscall_call"))
test_uretprobe_syscall_call();
if (test__start_subtest("uretprobe_shadow_stack"))
test_uretprobe_shadow_stack();
+ if (test__start_subtest("uprobe_legacy"))
+ test_uprobe_legacy();
+ if (test__start_subtest("uprobe_multi"))
+ test_uprobe_multi();
+ if (test__start_subtest("uprobe_session"))
+ test_uprobe_session();
+ if (test__start_subtest("uprobe_usdt"))
+ test_uprobe_usdt();
+ if (test__start_subtest("uprobe_race"))
+ test_uprobe_race();
+ if (test__start_subtest("uprobe_error"))
+ test_uprobe_error();
+ if (test__start_subtest("uprobe_regs_equal"))
+ test_uprobe_regs_equal(false);
+ if (test__start_subtest("regs_change"))
+ test_regs_change();
+}
+#else
+static void __test_uprobe_syscall(void)
+{
+ test__skip();
+}
+#endif
+
+void test_uprobe_syscall(void)
+{
+ __test_uprobe_syscall();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 495d66414b57..f4be5269fa90 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -40,12 +40,79 @@ static void __always_inline trigger_func(int x) {
}
}
-static void subtest_basic_usdt(void)
+#if defined(__x86_64__) || defined(__i386__)
+/*
+ * SIB (Scale-Index-Base) addressing format: "size@(base_reg, index_reg, scale)"
+ * - 'size' is the size in bytes of the array element, and its sign indicates
+ * whether the type is signed (negative) or unsigned (positive).
+ * - 'base_reg' is the register holding the base address, normally rdx or edx
+ * - 'index_reg' is the register holding the index, normally rax or eax
+ * - 'scale' is the scaling factor (typically 1, 2, 4, or 8), which matches the
+ * size of the element type.
+ *
+ * For example, for an array of 'short' (signed 2-byte elements), the SIB spec would be:
+ * - size: -2 (negative because 'short' is signed)
+ * - scale: 2 (since sizeof(short) == 2)
+ *
+ * The resulting SIB format: "-2@(%%rdx,%%rax,2)" for x86_64, "-2@(%%edx,%%eax,2)" for i386
+ */
+static volatile short array[] = {-1, -2, -3, -4};
+
+#if defined(__x86_64__)
+#define USDT_SIB_ARG_SPEC -2@(%%rdx,%%rax,2)
+#else
+#define USDT_SIB_ARG_SPEC -2@(%%edx,%%eax,2)
+#endif
+
+unsigned short test_usdt_sib_semaphore SEC(".probes");
+
+static void trigger_sib_spec(void)
+{
+ /*
+ * Force SIB addressing with inline assembly.
+ *
+ * You must compile with -std=gnu99 or -std=c99 to use the
+ * STAP_PROBE_ASM macro.
+ *
+ * The STAP_PROBE_ASM macro generates a quoted string that gets
+ * inserted between the surrounding assembly instructions. In this
+ * case, USDT_SIB_ARG_SPEC is embedded directly into the instruction
+ * stream, creating a probe point between the asm statement boundaries.
+ * It works fine with gcc/clang.
+ *
+ * Register constraints:
+ * - "d"(array): Binds the 'array' variable to %rdx or %edx register
+ * - "a"(0): Binds the constant 0 to %rax or %eax register
+ * These ensure that when USDT_SIB_ARG_SPEC references %%rdx(%edx) and
+ * %%rax(%eax), they contain the expected values for SIB addressing.
+ *
+ * The "memory" clobber prevents the compiler from reordering memory
+ * accesses around the probe point, ensuring that the probe behavior
+ * is predictable and consistent.
+ */
+ asm volatile(
+ STAP_PROBE_ASM(test, usdt_sib, USDT_SIB_ARG_SPEC)
+ :
+ : "d"(array), "a"(0)
+ : "memory"
+ );
+}
+#endif
+
+static void subtest_basic_usdt(bool optimized)
{
LIBBPF_OPTS(bpf_usdt_opts, opts);
struct test_usdt *skel;
struct test_usdt__bss *bss;
- int err, i;
+ int err, i, called;
+ const __u64 expected_cookie = 0xcafedeadbeeffeed;
+
+#define TRIGGER(x) ({ \
+ trigger_func(x); \
+ if (optimized) \
+ trigger_func(x); \
+ optimized ? 2 : 1; \
+ })
skel = test_usdt__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -59,20 +126,29 @@ static void subtest_basic_usdt(void)
goto cleanup;
/* usdt0 won't be auto-attached */
- opts.usdt_cookie = 0xcafedeadbeeffeed;
+ opts.usdt_cookie = expected_cookie;
skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0,
0 /*self*/, "/proc/self/exe",
"test", "usdt0", &opts);
if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link"))
goto cleanup;
- trigger_func(1);
+#if defined(__x86_64__) || defined(__i386__)
+ opts.usdt_cookie = expected_cookie;
+ skel->links.usdt_sib = bpf_program__attach_usdt(skel->progs.usdt_sib,
+ 0 /*self*/, "/proc/self/exe",
+ "test", "usdt_sib", &opts);
+ if (!ASSERT_OK_PTR(skel->links.usdt_sib, "usdt_sib_link"))
+ goto cleanup;
+#endif
+
+ called = TRIGGER(1);
- ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called");
- ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called");
- ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called");
+ ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+ ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+ ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
- ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
+ ASSERT_EQ(bss->usdt0_cookie, expected_cookie, "usdt0_cookie");
ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size");
@@ -119,11 +195,11 @@ static void subtest_basic_usdt(void)
* bpf_program__attach_usdt() handles this properly and attaches to
* all possible places of USDT invocation.
*/
- trigger_func(2);
+ called += TRIGGER(2);
- ASSERT_EQ(bss->usdt0_called, 2, "usdt0_called");
- ASSERT_EQ(bss->usdt3_called, 2, "usdt3_called");
- ASSERT_EQ(bss->usdt12_called, 2, "usdt12_called");
+ ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+ ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+ ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
/* only check values that depend on trigger_func()'s input value */
ASSERT_EQ(bss->usdt3_args[0], 2, "usdt3_arg1");
@@ -142,9 +218,9 @@ static void subtest_basic_usdt(void)
if (!ASSERT_OK_PTR(skel->links.usdt3, "usdt3_reattach"))
goto cleanup;
- trigger_func(3);
+ called += TRIGGER(3);
- ASSERT_EQ(bss->usdt3_called, 3, "usdt3_called");
+ ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
/* this time usdt3 has custom cookie */
ASSERT_EQ(bss->usdt3_cookie, 0xBADC00C51E, "usdt3_cookie");
ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt");
@@ -156,8 +232,19 @@ static void subtest_basic_usdt(void)
ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+#if defined(__x86_64__) || defined(__i386__)
+ trigger_sib_spec();
+ ASSERT_EQ(bss->usdt_sib_called, 1, "usdt_sib_called");
+ ASSERT_EQ(bss->usdt_sib_cookie, expected_cookie, "usdt_sib_cookie");
+ ASSERT_EQ(bss->usdt_sib_arg_cnt, 1, "usdt_sib_arg_cnt");
+ ASSERT_EQ(bss->usdt_sib_arg, nums[0], "usdt_sib_arg");
+ ASSERT_EQ(bss->usdt_sib_arg_ret, 0, "usdt_sib_arg_ret");
+ ASSERT_EQ(bss->usdt_sib_arg_size, sizeof(nums[0]), "usdt_sib_arg_size");
+#endif
+
cleanup:
test_usdt__destroy(skel);
+#undef TRIGGER
}
unsigned short test_usdt_100_semaphore SEC(".probes");
@@ -270,8 +357,16 @@ static void subtest_multispec_usdt(void)
*/
trigger_300_usdts();
- /* we'll reuse usdt_100 BPF program for usdt_300 test */
bpf_link__destroy(skel->links.usdt_100);
+
+ bss->usdt_100_called = 0;
+ bss->usdt_100_sum = 0;
+
+ /* If built with arm64/clang, there will be much less number of specs
+ * for usdt_300 call sites.
+ */
+#if !defined(__aarch64__) || !defined(__clang__)
+ /* we'll reuse usdt_100 BPF program for usdt_300 test */
skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1, "/proc/self/exe",
"test", "usdt_300", NULL);
err = -errno;
@@ -282,13 +377,11 @@ static void subtest_multispec_usdt(void)
/* let's check that there are no "dangling" BPF programs attached due
* to partial success of the above test:usdt_300 attachment
*/
- bss->usdt_100_called = 0;
- bss->usdt_100_sum = 0;
-
f300(777); /* this is 301st instance of usdt_300 */
ASSERT_EQ(bss->usdt_100_called, 0, "usdt_301_called");
ASSERT_EQ(bss->usdt_100_sum, 0, "usdt_301_sum");
+#endif
/* This time we have USDT with 400 inlined invocations, but arg specs
* should be the same across all sites, so libbpf will only need to
@@ -419,7 +512,11 @@ cleanup:
void test_usdt(void)
{
if (test__start_subtest("basic"))
- subtest_basic_usdt();
+ subtest_basic_usdt(false);
+#ifdef __x86_64__
+ if (test__start_subtest("basic_optimized"))
+ subtest_basic_usdt(true);
+#endif
if (test__start_subtest("multispec"))
subtest_multispec_usdt();
if (test__start_subtest("urand_auto_attach"))
diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
index d424e7ecbd12..9fd3ae987321 100644
--- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
@@ -21,8 +21,7 @@
#include "../progs/test_user_ringbuf.h"
static const long c_sample_size = sizeof(struct sample) + BPF_RINGBUF_HDR_SZ;
-static const long c_ringbuf_size = 1 << 12; /* 1 small page */
-static const long c_max_entries = c_ringbuf_size / c_sample_size;
+static long c_ringbuf_size, c_max_entries;
static void drain_current_samples(void)
{
@@ -424,7 +423,9 @@ static void test_user_ringbuf_loop(void)
uint32_t remaining_samples = total_samples;
int err;
- BUILD_BUG_ON(total_samples <= c_max_entries);
+ if (!ASSERT_LT(c_max_entries, total_samples, "compare_c_max_entries"))
+ return;
+
err = load_skel_create_user_ringbuf(&skel, &ringbuf);
if (err)
return;
@@ -686,6 +687,9 @@ void test_user_ringbuf(void)
{
int i;
+ c_ringbuf_size = getpagesize(); /* 1 page */
+ c_max_entries = c_ringbuf_size / c_sample_size;
+
for (i = 0; i < ARRAY_SIZE(success_tests); i++) {
if (!test__start_subtest(success_tests[i].test_name))
continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index e66a57970d28..28e81161e6fc 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -14,6 +14,7 @@
#include "verifier_bounds_deduction_non_const.skel.h"
#include "verifier_bounds_mix_sign_unsign.skel.h"
#include "verifier_bpf_get_stack.skel.h"
+#include "verifier_bpf_trap.skel.h"
#include "verifier_bswap.skel.h"
#include "verifier_btf_ctx_access.skel.h"
#include "verifier_btf_unreliable_prog.skel.h"
@@ -45,6 +46,7 @@
#include "verifier_ldsx.skel.h"
#include "verifier_leak_ptr.skel.h"
#include "verifier_linked_scalars.skel.h"
+#include "verifier_live_stack.skel.h"
#include "verifier_load_acquire.skel.h"
#include "verifier_loops1.skel.h"
#include "verifier_lwt.skel.h"
@@ -58,6 +60,7 @@
#include "verifier_meta_access.skel.h"
#include "verifier_movsx.skel.h"
#include "verifier_mtu.skel.h"
+#include "verifier_mul.skel.h"
#include "verifier_netfilter_ctx.skel.h"
#include "verifier_netfilter_retcode.skel.h"
#include "verifier_bpf_fastcall.skel.h"
@@ -84,6 +87,7 @@
#include "verifier_store_release.skel.h"
#include "verifier_subprog_precision.skel.h"
#include "verifier_subreg.skel.h"
+#include "verifier_tailcall.skel.h"
#include "verifier_tailcall_jit.skel.h"
#include "verifier_typedef.skel.h"
#include "verifier_uninit.skel.h"
@@ -148,6 +152,7 @@ void test_verifier_bounds_deduction(void) { RUN(verifier_bounds_deduction);
void test_verifier_bounds_deduction_non_const(void) { RUN(verifier_bounds_deduction_non_const); }
void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_unsign); }
void test_verifier_bpf_get_stack(void) { RUN(verifier_bpf_get_stack); }
+void test_verifier_bpf_trap(void) { RUN(verifier_bpf_trap); }
void test_verifier_bswap(void) { RUN(verifier_bswap); }
void test_verifier_btf_ctx_access(void) { RUN(verifier_btf_ctx_access); }
void test_verifier_btf_unreliable_prog(void) { RUN(verifier_btf_unreliable_prog); }
@@ -180,6 +185,7 @@ void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); }
void test_verifier_ldsx(void) { RUN(verifier_ldsx); }
void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); }
void test_verifier_linked_scalars(void) { RUN(verifier_linked_scalars); }
+void test_verifier_live_stack(void) { RUN(verifier_live_stack); }
void test_verifier_loops1(void) { RUN(verifier_loops1); }
void test_verifier_lwt(void) { RUN(verifier_lwt); }
void test_verifier_map_in_map(void) { RUN(verifier_map_in_map); }
@@ -191,6 +197,7 @@ void test_verifier_may_goto_1(void) { RUN(verifier_may_goto_1); }
void test_verifier_may_goto_2(void) { RUN(verifier_may_goto_2); }
void test_verifier_meta_access(void) { RUN(verifier_meta_access); }
void test_verifier_movsx(void) { RUN(verifier_movsx); }
+void test_verifier_mul(void) { RUN(verifier_mul); }
void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); }
void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); }
void test_verifier_bpf_fastcall(void) { RUN(verifier_bpf_fastcall); }
@@ -217,6 +224,7 @@ void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); }
void test_verifier_store_release(void) { RUN(verifier_store_release); }
void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); }
void test_verifier_subreg(void) { RUN(verifier_subreg); }
+void test_verifier_tailcall(void) { RUN(verifier_tailcall); }
void test_verifier_tailcall_jit(void) { RUN(verifier_tailcall_jit); }
void test_verifier_typedef(void) { RUN(verifier_typedef); }
void test_verifier_uninit(void) { RUN(verifier_uninit); }
diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
index ab0f02faa80c..4d69d9d55e17 100644
--- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
@@ -268,7 +268,7 @@ static void test_verify_pkcs7_sig_from_map(void)
char *tmp_dir;
struct test_verify_pkcs7_sig *skel = NULL;
struct bpf_map *map;
- struct data data;
+ struct data data = {};
int ret, zero = 0;
/* Trigger creation of session keyring. */
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index b2b2d85dbb1b..43264347e7d7 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -37,21 +37,26 @@ static void test_xdp_adjust_tail_shrink(void)
bpf_object__close(obj);
}
-static void test_xdp_adjust_tail_grow(void)
+static void test_xdp_adjust_tail_grow(bool is_64k_pagesize)
{
const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
struct bpf_object *obj;
- char buf[4096]; /* avoid segfault: large buf to hold grow results */
+ char buf[8192]; /* avoid segfault: large buf to hold grow results */
__u32 expect_sz;
int err, prog_fd;
LIBBPF_OPTS(bpf_test_run_opts, topts,
.data_in = &pkt_v4,
- .data_size_in = sizeof(pkt_v4),
.data_out = buf,
.data_size_out = sizeof(buf),
.repeat = 1,
);
+ /* topts.data_size_in as a special signal to bpf prog */
+ if (is_64k_pagesize)
+ topts.data_size_in = sizeof(pkt_v4) - 1;
+ else
+ topts.data_size_in = sizeof(pkt_v4);
+
err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
if (!ASSERT_OK(err, "test_xdp_adjust_tail_grow"))
return;
@@ -208,7 +213,7 @@ out:
bpf_object__close(obj);
}
-static void test_xdp_adjust_frags_tail_grow(void)
+static void test_xdp_adjust_frags_tail_grow_4k(void)
{
const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
__u32 exp_size;
@@ -246,14 +251,20 @@ static void test_xdp_adjust_frags_tail_grow(void)
ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval");
ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size");
- for (i = 0; i < 9000; i++)
- ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+ for (i = 0; i < 9000; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+ }
- for (i = 9000; i < 9010; i++)
- ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+ for (i = 9000; i < 9010; i++) {
+ if (buf[i] != 0)
+ ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+ }
- for (i = 9010; i < 16384; i++)
- ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+ for (i = 9010; i < 16384; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+ }
/* Test a too large grow */
memset(buf, 1, 16384);
@@ -273,16 +284,93 @@ out:
bpf_object__close(obj);
}
+static void test_xdp_adjust_frags_tail_grow_64k(void)
+{
+ const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
+ __u32 exp_size;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int err, i, prog_fd;
+ __u8 *buf;
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+ obj = bpf_object__open(file);
+ if (libbpf_get_error(obj))
+ return;
+
+ prog = bpf_object__next_program(obj, NULL);
+ if (bpf_object__load(obj))
+ goto out;
+
+ prog_fd = bpf_program__fd(prog);
+
+ buf = malloc(262144);
+ if (!ASSERT_OK_PTR(buf, "alloc buf 256Kb"))
+ goto out;
+
+ /* Test case add 10 bytes to last frag */
+ memset(buf, 1, 262144);
+ exp_size = 90000 + 10;
+
+ topts.data_in = buf;
+ topts.data_out = buf;
+ topts.data_size_in = 90000;
+ topts.data_size_out = 262144;
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+ ASSERT_OK(err, "90Kb+10b");
+ ASSERT_EQ(topts.retval, XDP_TX, "90Kb+10b retval");
+ ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size");
+
+ for (i = 0; i < 90000; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "90Kb+10b-old");
+ }
+
+ for (i = 90000; i < 90010; i++) {
+ if (buf[i] != 0)
+ ASSERT_EQ(buf[i], 0, "90Kb+10b-new");
+ }
+
+ for (i = 90010; i < 262144; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "90Kb+10b-untouched");
+ }
+
+ /* Test a too large grow */
+ memset(buf, 1, 262144);
+ exp_size = 90001;
+
+ topts.data_in = topts.data_out = buf;
+ topts.data_size_in = 90001;
+ topts.data_size_out = 262144;
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+ ASSERT_OK(err, "90Kb+10b");
+ ASSERT_EQ(topts.retval, XDP_DROP, "90Kb+10b retval");
+ ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size");
+
+ free(buf);
+out:
+ bpf_object__close(obj);
+}
+
void test_xdp_adjust_tail(void)
{
+ int page_size = getpagesize();
+
if (test__start_subtest("xdp_adjust_tail_shrink"))
test_xdp_adjust_tail_shrink();
if (test__start_subtest("xdp_adjust_tail_grow"))
- test_xdp_adjust_tail_grow();
+ test_xdp_adjust_tail_grow(page_size == 65536);
if (test__start_subtest("xdp_adjust_tail_grow2"))
test_xdp_adjust_tail_grow2();
if (test__start_subtest("xdp_adjust_frags_tail_shrink"))
test_xdp_adjust_frags_tail_shrink();
- if (test__start_subtest("xdp_adjust_frags_tail_grow"))
- test_xdp_adjust_frags_tail_grow();
+ if (test__start_subtest("xdp_adjust_frags_tail_grow")) {
+ if (page_size == 65536)
+ test_xdp_adjust_frags_tail_grow_64k();
+ else
+ test_xdp_adjust_frags_tail_grow_4k();
+ }
}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index b9d9f0a502ce..178292d1251a 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -9,6 +9,7 @@
#define TX_NETNS "xdp_context_tx"
#define RX_NETNS "xdp_context_rx"
#define TAP_NAME "tap0"
+#define DUMMY_NAME "dum0"
#define TAP_NETNS "xdp_context_tuntap"
#define TEST_PAYLOAD_LEN 32
@@ -96,9 +97,7 @@ void test_xdp_context_test_run(void)
/* Meta data must be 255 bytes or smaller */
test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0);
- /* Total size of data must match data_end - data_meta */
- test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
- sizeof(data) - 1, 0, 0, 0);
+ /* Total size of data must be data_end - data_meta or larger */
test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
sizeof(data) + 1, 0, 0, 0);
@@ -156,15 +155,30 @@ err:
return -1;
}
-static void assert_test_result(struct test_xdp_meta *skel)
+static int write_test_packet(int tap_fd)
+{
+ __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
+ int n;
+
+ /* The ethernet header doesn't need to be valid for this test */
+ memset(packet, 0, sizeof(struct ethhdr));
+ memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN);
+
+ n = write(tap_fd, packet, sizeof(packet));
+ if (!ASSERT_EQ(n, sizeof(packet), "write packet"))
+ return -1;
+
+ return 0;
+}
+
+static void assert_test_result(const struct bpf_map *result_map)
{
int err;
__u32 map_key = 0;
__u8 map_value[TEST_PAYLOAD_LEN];
- err = bpf_map__lookup_elem(skel->maps.test_result, &map_key,
- sizeof(map_key), &map_value,
- TEST_PAYLOAD_LEN, BPF_ANY);
+ err = bpf_map__lookup_elem(result_map, &map_key, sizeof(map_key),
+ &map_value, TEST_PAYLOAD_LEN, BPF_ANY);
if (!ASSERT_OK(err, "lookup test_result"))
return;
@@ -172,6 +186,18 @@ static void assert_test_result(struct test_xdp_meta *skel)
"test_result map contains test payload");
}
+static bool clear_test_result(struct bpf_map *result_map)
+{
+ const __u8 v[sizeof(test_payload)] = {};
+ const __u32 k = 0;
+ int err;
+
+ err = bpf_map__update_elem(result_map, &k, sizeof(k), v, sizeof(v), BPF_ANY);
+ ASSERT_OK(err, "update test_result");
+
+ return err == 0;
+}
+
void test_xdp_context_veth(void)
{
LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
@@ -248,7 +274,7 @@ void test_xdp_context_veth(void)
if (!ASSERT_OK(ret, "send_test_packet"))
goto close;
- assert_test_result(skel);
+ assert_test_result(skel->maps.test_result);
close:
close_netns(nstoken);
@@ -257,17 +283,21 @@ close:
netns_free(tx_ns);
}
-void test_xdp_context_tuntap(void)
+static void test_tuntap(struct bpf_program *xdp_prog,
+ struct bpf_program *tc_prio_1_prog,
+ struct bpf_program *tc_prio_2_prog,
+ struct bpf_map *result_map)
{
LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
struct netns_obj *ns = NULL;
- struct test_xdp_meta *skel = NULL;
- __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
int tap_fd = -1;
int tap_ifindex;
int ret;
+ if (!clear_test_result(result_map))
+ return;
+
ns = netns_new(TAP_NETNS, true);
if (!ASSERT_OK_PTR(ns, "create and open ns"))
return;
@@ -278,10 +308,6 @@ void test_xdp_context_tuntap(void)
SYS(close, "ip link set dev " TAP_NAME " up");
- skel = test_xdp_meta__open_and_load();
- if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
- goto close;
-
tap_ifindex = if_nametoindex(TAP_NAME);
if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
goto close;
@@ -291,33 +317,175 @@ void test_xdp_context_tuntap(void)
if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
goto close;
- tc_opts.prog_fd = bpf_program__fd(skel->progs.ing_cls);
+ tc_opts.prog_fd = bpf_program__fd(tc_prio_1_prog);
ret = bpf_tc_attach(&tc_hook, &tc_opts);
if (!ASSERT_OK(ret, "bpf_tc_attach"))
goto close;
- ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp),
+ if (tc_prio_2_prog) {
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 2,
+ .prog_fd = bpf_program__fd(tc_prio_2_prog));
+
+ ret = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(ret, "bpf_tc_attach"))
+ goto close;
+ }
+
+ ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog),
0, NULL);
if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
goto close;
- /* The ethernet header is not relevant for this test and doesn't need to
- * be meaningful.
- */
- struct ethhdr eth = { 0 };
+ ret = write_test_packet(tap_fd);
+ if (!ASSERT_OK(ret, "write_test_packet"))
+ goto close;
- memcpy(packet, &eth, sizeof(eth));
- memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN);
+ assert_test_result(result_map);
+
+close:
+ if (tap_fd >= 0)
+ close(tap_fd);
+ netns_free(ns);
+}
+
+/* Write a packet to a tap dev and copy it to ingress of a dummy dev */
+static void test_tuntap_mirred(struct bpf_program *xdp_prog,
+ struct bpf_program *tc_prog,
+ bool *test_pass)
+{
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+ struct netns_obj *ns = NULL;
+ int dummy_ifindex;
+ int tap_fd = -1;
+ int tap_ifindex;
+ int ret;
+
+ *test_pass = false;
+
+ ns = netns_new(TAP_NETNS, true);
+ if (!ASSERT_OK_PTR(ns, "netns_new"))
+ return;
- ret = write(tap_fd, packet, sizeof(packet));
- if (!ASSERT_EQ(ret, sizeof(packet), "write packet"))
+ /* Setup dummy interface */
+ SYS(close, "ip link add name " DUMMY_NAME " type dummy");
+ SYS(close, "ip link set dev " DUMMY_NAME " up");
+
+ dummy_ifindex = if_nametoindex(DUMMY_NAME);
+ if (!ASSERT_GE(dummy_ifindex, 0, "if_nametoindex"))
goto close;
- assert_test_result(skel);
+ tc_hook.ifindex = dummy_ifindex;
+ ret = bpf_tc_hook_create(&tc_hook);
+ if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+ goto close;
+
+ tc_opts.prog_fd = bpf_program__fd(tc_prog);
+ ret = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(ret, "bpf_tc_attach"))
+ goto close;
+
+ /* Setup TAP interface */
+ tap_fd = open_tuntap(TAP_NAME, true);
+ if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+ goto close;
+
+ SYS(close, "ip link set dev " TAP_NAME " up");
+
+ tap_ifindex = if_nametoindex(TAP_NAME);
+ if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
+ goto close;
+
+ ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL);
+ if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+ goto close;
+
+ /* Copy all packets received from TAP to dummy ingress */
+ SYS(close, "tc qdisc add dev " TAP_NAME " clsact");
+ SYS(close, "tc filter add dev " TAP_NAME " ingress "
+ "protocol all matchall "
+ "action mirred ingress mirror dev " DUMMY_NAME);
+
+ /* Receive a packet on TAP */
+ ret = write_test_packet(tap_fd);
+ if (!ASSERT_OK(ret, "write_test_packet"))
+ goto close;
+
+ ASSERT_TRUE(*test_pass, "test_pass");
close:
if (tap_fd >= 0)
close(tap_fd);
- test_xdp_meta__destroy(skel);
netns_free(ns);
}
+
+void test_xdp_context_tuntap(void)
+{
+ struct test_xdp_meta *skel = NULL;
+
+ skel = test_xdp_meta__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+ return;
+
+ if (test__start_subtest("data_meta"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls,
+ NULL, /* tc prio 2 */
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_read"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls_dynptr_read,
+ NULL, /* tc prio 2 */
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_slice"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls_dynptr_slice,
+ NULL, /* tc prio 2 */
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_write"))
+ test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+ skel->progs.ing_cls_dynptr_write,
+ skel->progs.ing_cls_dynptr_read,
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_slice_rdwr"))
+ test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+ skel->progs.ing_cls_dynptr_slice_rdwr,
+ skel->progs.ing_cls_dynptr_slice,
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_offset"))
+ test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+ skel->progs.ing_cls_dynptr_offset_wr,
+ skel->progs.ing_cls_dynptr_offset_rd,
+ skel->maps.test_result);
+ if (test__start_subtest("dynptr_offset_oob"))
+ test_tuntap(skel->progs.ing_xdp,
+ skel->progs.ing_cls_dynptr_offset_oob,
+ skel->progs.ing_cls,
+ skel->maps.test_result);
+ if (test__start_subtest("clone_data_meta_empty_on_data_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_data_meta_empty_on_data_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_data_meta_empty_on_meta_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_data_meta_empty_on_meta_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_empty_on_data_slice_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_empty_on_data_slice_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_empty_on_meta_slice_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_empty_on_meta_slice_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_rdonly_before_data_dynptr_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_rdonly_before_data_dynptr_write,
+ &skel->bss->test_pass);
+ if (test__start_subtest("clone_dynptr_rdonly_before_meta_dynptr_write"))
+ test_tuntap_mirred(skel->progs.ing_xdp,
+ skel->progs.clone_dynptr_rdonly_before_meta_dynptr_write,
+ &skel->bss->test_pass);
+
+ test_xdp_meta__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index 461ab18705d5..a8ab05216c38 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -7,6 +7,7 @@
#include <test_progs.h>
#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_devmap_tailcall.skel.h"
#include "test_xdp_with_devmap_frags_helpers.skel.h"
#include "test_xdp_with_devmap_helpers.skel.h"
@@ -107,6 +108,29 @@ static void test_neg_xdp_devmap_helpers(void)
}
}
+static void test_xdp_devmap_tailcall(enum bpf_attach_type prog_dev,
+ enum bpf_attach_type prog_tail,
+ bool expect_reject)
+{
+ struct test_xdp_devmap_tailcall *skel;
+ int err;
+
+ skel = test_xdp_devmap_tailcall__open();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_devmap_tailcall__open"))
+ return;
+
+ bpf_program__set_expected_attach_type(skel->progs.xdp_devmap, prog_dev);
+ bpf_program__set_expected_attach_type(skel->progs.xdp_entry, prog_tail);
+
+ err = test_xdp_devmap_tailcall__load(skel);
+ if (expect_reject)
+ ASSERT_ERR(err, "test_xdp_devmap_tailcall__load");
+ else
+ ASSERT_OK(err, "test_xdp_devmap_tailcall__load");
+
+ test_xdp_devmap_tailcall__destroy(skel);
+}
+
static void test_xdp_with_devmap_frags_helpers(void)
{
struct test_xdp_with_devmap_frags_helpers *skel;
@@ -238,8 +262,13 @@ void serial_test_xdp_devmap_attach(void)
if (test__start_subtest("DEVMAP with frags programs in entries"))
test_xdp_with_devmap_frags_helpers();
- if (test__start_subtest("Verifier check of DEVMAP programs"))
+ if (test__start_subtest("Verifier check of DEVMAP programs")) {
test_neg_xdp_devmap_helpers();
+ test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, BPF_XDP_DEVMAP, false);
+ test_xdp_devmap_tailcall(0, 0, true);
+ test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, 0, true);
+ test_xdp_devmap_tailcall(0, BPF_XDP_DEVMAP, true);
+ }
if (test__start_subtest("DEVMAP with programs in entries on veth"))
test_xdp_with_devmap_helpers_veth();
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index 7dac044664ac..dd34b0cc4b4e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -66,16 +66,25 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd)
#else
#define MAX_PKT_SIZE 3408
#endif
+
+#define PAGE_SIZE_4K 4096
+#define PAGE_SIZE_64K 65536
+
static void test_max_pkt_size(int fd)
{
- char data[MAX_PKT_SIZE + 1] = {};
+ char data[PAGE_SIZE_64K + 1] = {};
int err;
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
.data_in = &data,
- .data_size_in = MAX_PKT_SIZE,
.flags = BPF_F_TEST_XDP_LIVE_FRAMES,
.repeat = 1,
);
+
+ if (getpagesize() == PAGE_SIZE_64K)
+ opts.data_size_in = MAX_PKT_SIZE + PAGE_SIZE_64K - PAGE_SIZE_4K;
+ else
+ opts.data_size_in = MAX_PKT_SIZE;
+
err = bpf_prog_test_run_opts(fd, &opts);
ASSERT_OK(err, "prog_run_max_size");
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 3d47878ef6bf..19f92affc2da 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -351,9 +351,10 @@ void test_xdp_metadata(void)
struct xdp_metadata2 *bpf_obj2 = NULL;
struct xdp_metadata *bpf_obj = NULL;
struct bpf_program *new_prog, *prog;
+ struct bpf_devmap_val devmap_e = {};
+ struct bpf_map *prog_arr, *devmap;
struct nstoken *tok = NULL;
__u32 queue_id = QUEUE_ID;
- struct bpf_map *prog_arr;
struct xsk tx_xsk = {};
struct xsk rx_xsk = {};
__u32 val, key = 0;
@@ -409,6 +410,13 @@ void test_xdp_metadata(void)
bpf_program__set_ifindex(prog, rx_ifindex);
bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY);
+ /* Make sure we can load a dev-bound program that performs
+ * XDP_REDIRECT into a devmap.
+ */
+ new_prog = bpf_object__find_program_by_name(bpf_obj->obj, "redirect");
+ bpf_program__set_ifindex(new_prog, rx_ifindex);
+ bpf_program__set_flags(new_prog, BPF_F_XDP_DEV_BOUND_ONLY);
+
if (!ASSERT_OK(xdp_metadata__load(bpf_obj), "load skeleton"))
goto out;
@@ -423,6 +431,18 @@ void test_xdp_metadata(void)
"update prog_arr"))
goto out;
+ /* Make sure we can't add dev-bound programs to devmaps. */
+ devmap = bpf_object__find_map_by_name(bpf_obj->obj, "dev_map");
+ if (!ASSERT_OK_PTR(devmap, "no dev_map found"))
+ goto out;
+
+ devmap_e.bpf_prog.fd = val;
+ if (!ASSERT_ERR(bpf_map__update_elem(devmap, &key, sizeof(key),
+ &devmap_e, sizeof(devmap_e),
+ BPF_ANY),
+ "update dev_map"))
+ goto out;
+
/* Attach BPF program to RX interface. */
ret = bpf_xdp_attach(rx_ifindex,
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
new file mode 100644
index 000000000000..efa350d04ec5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_xdp_pull_data.skel.h"
+
+#define PULL_MAX (1 << 31)
+#define PULL_PLUS_ONE (1 << 30)
+
+#define XDP_PACKET_HEADROOM 256
+
+/* Find headroom and tailroom occupied by struct xdp_frame and struct
+ * skb_shared_info so that we can calculate the maximum pull lengths for
+ * test cases. They might not be the real size of the structures due to
+ * cache alignment.
+ */
+static int find_xdp_sizes(struct test_xdp_pull_data *skel, int frame_sz)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ struct xdp_md ctx = {};
+ int prog_fd, err;
+ __u8 *buf;
+
+ buf = calloc(frame_sz, sizeof(__u8));
+ if (!ASSERT_OK_PTR(buf, "calloc buf"))
+ return -ENOMEM;
+
+ topts.data_in = buf;
+ topts.data_out = buf;
+ topts.data_size_in = frame_sz;
+ topts.data_size_out = frame_sz;
+ /* Pass a data_end larger than the linear space available to make sure
+ * bpf_prog_test_run_xdp() will fill the linear data area so that
+ * xdp_find_sizes can infer the size of struct skb_shared_info
+ */
+ ctx.data_end = frame_sz;
+ topts.ctx_in = &ctx;
+ topts.ctx_out = &ctx;
+ topts.ctx_size_in = sizeof(ctx);
+ topts.ctx_size_out = sizeof(ctx);
+
+ prog_fd = bpf_program__fd(skel->progs.xdp_find_sizes);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+ free(buf);
+
+ return err;
+}
+
+/* xdp_pull_data_prog will directly read a marker 0xbb stored at buf[1024]
+ * so caller expecting XDP_PASS should always pass pull_len no less than 1024
+ */
+static void run_test(struct test_xdp_pull_data *skel, int retval,
+ int frame_sz, int buff_len, int meta_len, int data_len,
+ int pull_len)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ struct xdp_md ctx = {};
+ int prog_fd, err;
+ __u8 *buf;
+
+ buf = calloc(buff_len, sizeof(__u8));
+ if (!ASSERT_OK_PTR(buf, "calloc buf"))
+ return;
+
+ buf[meta_len + 1023] = 0xaa;
+ buf[meta_len + 1024] = 0xbb;
+ buf[meta_len + 1025] = 0xcc;
+
+ topts.data_in = buf;
+ topts.data_out = buf;
+ topts.data_size_in = buff_len;
+ topts.data_size_out = buff_len;
+ ctx.data = meta_len;
+ ctx.data_end = meta_len + data_len;
+ topts.ctx_in = &ctx;
+ topts.ctx_out = &ctx;
+ topts.ctx_size_in = sizeof(ctx);
+ topts.ctx_size_out = sizeof(ctx);
+
+ skel->bss->data_len = data_len;
+ if (pull_len & PULL_MAX) {
+ int headroom = XDP_PACKET_HEADROOM - meta_len - skel->bss->xdpf_sz;
+ int tailroom = frame_sz - XDP_PACKET_HEADROOM -
+ data_len - skel->bss->sinfo_sz;
+
+ pull_len = pull_len & PULL_PLUS_ONE ? 1 : 0;
+ pull_len += headroom + tailroom + data_len;
+ }
+ skel->bss->pull_len = pull_len;
+
+ prog_fd = bpf_program__fd(skel->progs.xdp_pull_data_prog);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+ ASSERT_EQ(topts.retval, retval, "xdp_pull_data_prog retval");
+
+ if (retval == XDP_DROP)
+ goto out;
+
+ ASSERT_EQ(ctx.data_end, meta_len + pull_len, "linear data size");
+ ASSERT_EQ(topts.data_size_out, buff_len, "linear + non-linear data size");
+ /* Make sure data around xdp->data_end was not messed up by
+ * bpf_xdp_pull_data()
+ */
+ ASSERT_EQ(buf[meta_len + 1023], 0xaa, "data[1023]");
+ ASSERT_EQ(buf[meta_len + 1024], 0xbb, "data[1024]");
+ ASSERT_EQ(buf[meta_len + 1025], 0xcc, "data[1025]");
+out:
+ free(buf);
+}
+
+static void test_xdp_pull_data_basic(void)
+{
+ u32 pg_sz, max_meta_len, max_data_len;
+ struct test_xdp_pull_data *skel;
+
+ skel = test_xdp_pull_data__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_pull_data__open_and_load"))
+ return;
+
+ pg_sz = sysconf(_SC_PAGE_SIZE);
+
+ if (find_xdp_sizes(skel, pg_sz))
+ goto out;
+
+ max_meta_len = XDP_PACKET_HEADROOM - skel->bss->xdpf_sz;
+ max_data_len = pg_sz - XDP_PACKET_HEADROOM - skel->bss->sinfo_sz;
+
+ /* linear xdp pkt, pull 0 byte */
+ run_test(skel, XDP_PASS, pg_sz, 2048, 0, 2048, 2048);
+
+ /* multi-buf pkt, pull results in linear xdp pkt */
+ run_test(skel, XDP_PASS, pg_sz, 2048, 0, 1024, 2048);
+
+ /* multi-buf pkt, pull 1 byte to linear data area */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1024, 1025);
+
+ /* multi-buf pkt, pull 0 byte to linear data area */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1025, 1025);
+
+ /* multi-buf pkt, empty linear data area, pull requires memmove */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, 0, PULL_MAX);
+
+ /* multi-buf pkt, no headroom */
+ run_test(skel, XDP_PASS, pg_sz, 9000, max_meta_len, 1024, PULL_MAX);
+
+ /* multi-buf pkt, no tailroom, pull requires memmove */
+ run_test(skel, XDP_PASS, pg_sz, 9000, 0, max_data_len, PULL_MAX);
+
+ /* Test cases with invalid pull length */
+
+ /* linear xdp pkt, pull more than total data len */
+ run_test(skel, XDP_DROP, pg_sz, 2048, 0, 2048, 2049);
+
+ /* multi-buf pkt with no space left in linear data area */
+ run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, max_data_len,
+ PULL_MAX | PULL_PLUS_ONE);
+
+ /* multi-buf pkt, empty linear data area */
+ run_test(skel, XDP_DROP, pg_sz, 9000, 0, 0, PULL_MAX | PULL_PLUS_ONE);
+
+ /* multi-buf pkt, no headroom */
+ run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, 1024,
+ PULL_MAX | PULL_PLUS_ONE);
+
+ /* multi-buf pkt, no tailroom */
+ run_test(skel, XDP_DROP, pg_sz, 9000, 0, max_data_len,
+ PULL_MAX | PULL_PLUS_ONE);
+
+out:
+ test_xdp_pull_data__destroy(skel);
+}
+
+void test_xdp_pull_data(void)
+{
+ if (test__start_subtest("xdp_pull_data"))
+ test_xdp_pull_data_basic();
+}