diff options
Diffstat (limited to 'tools/testing')
104 files changed, 2767 insertions, 430 deletions
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c index 124bc883365e..cdd7a45c045d 100644 --- a/tools/testing/selftests/arm64/fp/fp-ptrace.c +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -1187,7 +1187,7 @@ static void sve_write_sve(pid_t child, struct test_config *config) if (!vl) return; - iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", @@ -1234,8 +1234,7 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config) if (!vl) return; - iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, - SVE_PT_REGS_FPSIMD); + iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", 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/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index d66687f1ee6a..56f660ca567b 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -86,6 +86,10 @@ 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; 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/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h index d67466c1ff77..f90531cf3ee5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h +++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h @@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val * barriers. */ if (val & _Q_LOCKED_MASK) - smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); + (void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); /* * take ownership and clear the pending bit. @@ -380,7 +380,7 @@ queue: /* Link @node into the waitqueue. */ WRITE_ONCE(prev->next, node); - arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); + (void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); /* * While waiting for the MCS lock, the next pointer may have diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c index 645be6cddf36..dfd8a258f14a 100644 --- a/tools/testing/selftests/bpf/progs/crypto_sanity.c +++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c @@ -14,7 +14,7 @@ unsigned char key[256] = {}; u16 udp_test_port = 7777; u32 authsize, key_len; char algo[128] = {}; -char dst[16] = {}; +char dst[16] = {}, dst_bad[8] = {}; int status; static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc) @@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx) .authsize = authsize, }; struct bpf_crypto_ctx *cctx; - int err = 0; + int err; status = 0; - if (key_len > 256) { status = -EINVAL; return 0; @@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx) __builtin_memcpy(¶ms.algo, algo, sizeof(algo)); __builtin_memcpy(¶ms.key, key, sizeof(key)); - cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); + cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); if (!cctx) { status = err; return 0; @@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx) err = crypto_ctx_insert(cctx); if (err && err != -EEXIST) status = err; - return 0; } @@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb) struct bpf_dynptr psrc, pdst; int err; + status = 0; err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } @@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb) int err; status = 0; - err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index 6438982b928b..ddd26d1a083f 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx) SEC("?tc") int obj_new_no_struct(void *ctx) { - - bpf_obj_new(union { int data; unsigned udata; }); + (void)bpf_obj_new(union { int data; unsigned udata; }); return 0; } @@ -252,7 +251,7 @@ int new_null_ret(void *ctx) SEC("?tc") int obj_new_acq(void *ctx) { - bpf_obj_new(struct foo); + (void)bpf_obj_new(struct foo); return 0; } diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..a47690174e0e 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } -__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); } -__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } +__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index 5a5a7a5f7e1d..a4ac80bb1003 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -446,9 +446,6 @@ TEST_F(coredump, socket_detect_userspace_client) if (info.coredump_mask & PIDFD_COREDUMPED) goto out; - if (read(fd_coredump, &c, 1) < 1) - goto out; - exit_code = EXIT_SUCCESS; out: if (fd_peer_pidfd >= 0) diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 5b230deb19e8..9a3499827d4b 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -4,6 +4,7 @@ TEST_GEN_FILES += access_memory access_memory_even TEST_FILES = _damon_sysfs.py +TEST_FILES += drgn_dump_damon_status.py # functionality tests TEST_PROGS += sysfs.sh diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 2b10854e4b1e..44b98f17f8ff 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -10,7 +10,8 @@ TEST_PROGS := \ mode-2-recovery-updelay.sh \ bond_options.sh \ bond-eth-type-change.sh \ - bond_macvlan_ipvlan.sh + bond_macvlan_ipvlan.sh \ + bond_passive_lacp.sh TEST_FILES := \ lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index 7bc148889ca7..187b478d0ddf 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -7,6 +7,8 @@ ALL_TESTS=" prio arp_validate num_grat_arp + fail_over_mac + vlan_over_bond " lib_dir=$(dirname "$0") @@ -352,8 +354,8 @@ garp_test() exp_num=$(echo "${param}" | cut -f6 -d ' ') active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") - slowwait_for_counter $((exp_num + 5)) $exp_num \ - tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" + slowwait_for_counter $((exp_num + 5)) $exp_num tc_rule_handle_stats_get \ + "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" &> /dev/null # check result real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}") @@ -376,6 +378,197 @@ num_grat_arp() done } +check_all_mac_same() +{ + RET=0 + # all slaves should have same mac address (with the first port's mac) + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + local eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + local eth1_mac=$(ip -n "$s_ns" -j link show eth1 | jq -r '.[]["address"]') + local eth2_mac=$(ip -n "$s_ns" -j link show eth2 | jq -r '.[]["address"]') + if [ "$bond_mac" != "${mac[0]}" ] || [ "$eth0_mac" != "$bond_mac" ] || \ + [ "$eth1_mac" != "$bond_mac" ] || [ "$eth2_mac" != "$bond_mac" ]; then + RET=1 + fi +} + +check_bond_mac_same_with_first() +{ + RET=0 + # bond mac address should be same with the first added slave + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + if [ "$bond_mac" != "${mac[0]}" ]; then + RET=1 + fi +} + +check_bond_mac_same_with_active() +{ + RET=0 + # bond mac address should be same with active slave + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + local active_slave_mac=$(ip -n "$s_ns" -j link show "$active_slave" | jq -r '.[]["address"]') + if [ "$bond_mac" != "$active_slave_mac" ]; then + RET=1 + fi +} + +check_backup_slave_mac_not_change() +{ + RET=0 + # backup slave's mac address is not changed + if ip -n "$s_ns" -d -j link show type bond_slave | jq -e '.[] + | select(.linkinfo.info_slave_data.state=="BACKUP") + | select(.address != .linkinfo.info_slave_data.perm_hwaddr)' &> /dev/null; then + RET=1 + fi +} + +check_backup_slave_mac_inherit() +{ + local backup_mac + RET=0 + + # backup slaves should use mac[1] or mac[2] + local backup_macs=$(ip -n "$s_ns" -d -j link show type bond_slave | \ + jq -r '.[] | select(.linkinfo.info_slave_data.state=="BACKUP") | .address') + for backup_mac in $backup_macs; do + if [ "$backup_mac" != "${mac[1]}" ] && [ "$backup_mac" != "${mac[2]}" ]; then + RET=1 + fi + done +} + +check_first_slave_random_mac() +{ + RET=0 + # remove the first added slave and added it back + ip -n "$s_ns" link set eth0 nomaster + ip -n "$s_ns" link set eth0 master bond0 + + # the first slave should use random mac address + eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + [ "$eth0_mac" = "${mac[0]}" ] && RET=1 + log_test "bond fail_over_mac follow" "random first slave mac" + + # remove the first slave, the permanent MAC address should be restored back + ip -n "$s_ns" link set eth0 nomaster + eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + [ "$eth0_mac" != "${mac[0]}" ] && RET=1 +} + +do_active_backup_failover() +{ + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + ip -n ${s_ns} link set ${active_slave} down + slowwait 2 active_slave_changed $active_slave + ip -n ${s_ns} link set ${active_slave} up +} + +fail_over_mac() +{ + # Bring down the first interface on the switch to force the bond to + # select another active interface instead of the first one that joined. + ip -n "$g_ns" link set s0 down + + # fail_over_mac none + bond_reset "mode active-backup miimon 100 fail_over_mac 0" + check_all_mac_same + log_test "fail_over_mac 0" "all slaves have same mac" + do_active_backup_failover + check_all_mac_same + log_test "fail_over_mac 0" "failover: all slaves have same mac" + + # fail_over_mac active + bond_reset "mode active-backup miimon 100 fail_over_mac 1" + check_bond_mac_same_with_active + log_test "fail_over_mac 1" "bond mac is same with active slave mac" + check_backup_slave_mac_not_change + log_test "fail_over_mac 1" "backup slave mac is not changed" + do_active_backup_failover + check_bond_mac_same_with_active + log_test "fail_over_mac 1" "failover: bond mac is same with active slave mac" + check_backup_slave_mac_not_change + log_test "fail_over_mac 1" "failover: backup slave mac is not changed" + + # fail_over_mac follow + bond_reset "mode active-backup miimon 100 fail_over_mac 2" + check_bond_mac_same_with_first + log_test "fail_over_mac 2" "bond mac is same with first slave mac" + check_bond_mac_same_with_active + log_test "fail_over_mac 2" "bond mac is same with active slave mac" + check_backup_slave_mac_inherit + log_test "fail_over_mac 2" "backup slave mac inherit" + do_active_backup_failover + check_bond_mac_same_with_first + log_test "fail_over_mac 2" "failover: bond mac is same with first slave mac" + check_bond_mac_same_with_active + log_test "fail_over_mac 2" "failover: bond mac is same with active slave mac" + check_backup_slave_mac_inherit + log_test "fail_over_mac 2" "failover: backup slave mac inherit" + check_first_slave_random_mac + log_test "fail_over_mac 2" "first slave mac random" +} + +vlan_over_bond_arp() +{ + local mode="$1" + RET=0 + + bond_reset "mode $mode arp_interval 100 arp_ip_target 192.0.3.10" + ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3 + ip -n "${s_ns}" link set bond0.3 up + ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3 + ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3 + + slowwait_for_counter 5 5 tc_rule_handle_stats_get \ + "dev eth0.3 ingress" 101 ".packets" "-n ${c_ns}" &> /dev/null || RET=1 + log_test "vlan over bond arp" "$mode" +} + +vlan_over_bond_ns() +{ + local mode="$1" + RET=0 + + if skip_ns; then + log_test_skip "vlan_over_bond ns" "$mode" + return 0 + fi + + bond_reset "mode $mode arp_interval 100 ns_ip6_target 2001:db8::3:10" + ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3 + ip -n "${s_ns}" link set bond0.3 up + ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3 + ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3 + + slowwait_for_counter 5 5 tc_rule_handle_stats_get \ + "dev eth0.3 ingress" 102 ".packets" "-n ${c_ns}" &> /dev/null || RET=1 + log_test "vlan over bond ns" "$mode" +} + +vlan_over_bond() +{ + # add vlan 3 for client + ip -n "${c_ns}" link add eth0.3 link eth0 type vlan id 3 + ip -n "${c_ns}" link set eth0.3 up + ip -n "${c_ns}" addr add 192.0.3.10/24 dev eth0.3 + ip -n "${c_ns}" addr add 2001:db8::3:10/64 dev eth0.3 + + # Add tc rule to check the vlan pkts + tc -n "${c_ns}" qdisc add dev eth0.3 clsact + tc -n "${c_ns}" filter add dev eth0.3 ingress protocol arp \ + handle 101 flower skip_hw arp_op request \ + arp_sip 192.0.3.1 arp_tip 192.0.3.10 action pass + tc -n "${c_ns}" filter add dev eth0.3 ingress protocol ipv6 \ + handle 102 flower skip_hw ip_proto icmpv6 \ + type 135 src_ip 2001:db8::3:1 action pass + + vlan_over_bond_arp "active-backup" + vlan_over_bond_ns "active-backup" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh new file mode 100755 index 000000000000..9c3b089813df --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh @@ -0,0 +1,105 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test if a bond interface works with lacp_active=off. + +# shellcheck disable=SC2034 +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +# shellcheck disable=SC1091 +source "$lib_dir"/../../../net/forwarding/lib.sh + +# shellcheck disable=SC2317 +check_port_state() +{ + local netns=$1 + local port=$2 + local state=$3 + + ip -n "${netns}" -d -j link show "$port" | \ + jq -e ".[].linkinfo.info_slave_data.ad_actor_oper_port_state_str | index(\"${state}\") != null" > /dev/null +} + +check_pkt_count() +{ + RET=0 + local ns="$1" + local iface="$2" + + # wait 65s, one per 30s + slowwait_for_counter 65 2 tc_rule_handle_stats_get \ + "dev ${iface} egress" 101 ".packets" "-n ${ns}" &> /dev/null +} + +setup() { + setup_ns c_ns s_ns + + # shellcheck disable=SC2154 + ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}" + ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}" + + # Add tc filter to count the pkts + tc -n "${c_ns}" qdisc add dev eth0 clsact + tc -n "${c_ns}" filter add dev eth0 egress handle 101 protocol 0x8809 matchall action pass + tc -n "${s_ns}" qdisc add dev eth1 clsact + tc -n "${s_ns}" filter add dev eth1 egress handle 101 protocol 0x8809 matchall action pass + + ip -n "${s_ns}" link add bond0 type bond mode 802.3ad lacp_active on lacp_rate fast + ip -n "${s_ns}" link set eth0 master bond0 + ip -n "${s_ns}" link set eth1 master bond0 + + ip -n "${c_ns}" link add bond0 type bond mode 802.3ad lacp_active off lacp_rate fast + ip -n "${c_ns}" link set eth0 master bond0 + ip -n "${c_ns}" link set eth1 master bond0 + +} + +trap cleanup_all_ns EXIT +setup + +# The bond will send 2 lacpdu pkts during init time, let's wait at least 2s +# after interface up +ip -n "${c_ns}" link set bond0 up +sleep 2 + +# 1. The passive side shouldn't send LACPDU. +check_pkt_count "${c_ns}" "eth0" && RET=1 +log_test "802.3ad lacp_active off" "init port" + +ip -n "${s_ns}" link set bond0 up +# 2. The passive side should not have the 'active' flag. +RET=0 +slowwait 2 check_port_state "${c_ns}" "eth0" "active" && RET=1 +log_test "802.3ad lacp_active off" "port state active" + +# 3. The active side should have the 'active' flag. +RET=0 +slowwait 2 check_port_state "${s_ns}" "eth0" "active" || RET=1 +log_test "802.3ad lacp_active on" "port state active" + +# 4. Make sure the connection is not expired. +RET=0 +slowwait 5 check_port_state "${s_ns}" "eth0" "distributing" +slowwait 10 check_port_state "${s_ns}" "eth0" "expired" && RET=1 +log_test "bond 802.3ad lacp_active off" "port connection" + +# After testing, disconnect one port on each side to check the state. +ip -n "${s_ns}" link set eth0 nomaster +ip -n "${s_ns}" link set eth0 up +ip -n "${c_ns}" link set eth1 nomaster +ip -n "${c_ns}" link set eth1 up +# Due to Periodic Machine and Rx Machine state change, the bond will still +# send lacpdu pkts in a few seconds. sleep at lease 5s to make sure +# negotiation finished +sleep 5 + +# 5. The active side should keep sending LACPDU. +check_pkt_count "${s_ns}" "eth1" || RET=1 +log_test "bond 802.3ad lacp_active on" "port pkt after disconnect" + +# 6. The passive side shouldn't send LACPDU anymore. +check_pkt_count "${c_ns}" "eth0" && RET=1 +log_test "bond 802.3ad lacp_active off" "port pkt after disconnect" + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh index 195ef83cfbf1..167aa4a4a12a 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh @@ -39,6 +39,8 @@ g_ip4="192.0.2.254" s_ip6="2001:db8::1" c_ip6="2001:db8::10" g_ip6="2001:db8::254" +mac[0]="00:0a:0b:0c:0d:01" +mac[1]="00:0a:0b:0c:0d:02" gateway_create() { @@ -62,6 +64,7 @@ server_create() for i in $(seq 0 1); do ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}" ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh index 3a1333d9a85b..23a2932301cc 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -26,6 +26,7 @@ # +-------------------------------------+ source bond_topo_2d1c.sh +mac[2]="00:0a:0b:0c:0d:03" setup_prepare() { @@ -36,6 +37,7 @@ setup_prepare() # Add the extra device as we use 3 down links for bond0 local i=2 ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}" ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 ip -n ${s_ns} link set eth${i} master bond0 diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index dad4e5fda4db..832fa1caeb66 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -6,6 +6,8 @@ CONFIG_MACVLAN=y CONFIG_IPVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y CONFIG_VETH=y +CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index cd23af875317..3e3a89a34afe 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -17,7 +17,7 @@ def test_receive(cfg, ipver="6", extra_args=None): ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}" rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}" - tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}" + tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}" with bkg(rx_cmd, exit_wait=True): wait_port_listen(34000, proto="udp") @@ -37,7 +37,7 @@ def test_transmit(cfg, ipver="6", extra_args=None): if extra_args != "-U -Z": extra_args += " -r 1" - rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}" + rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}" tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}" with bkg(rx_cmd, host=cfg.remote, exit_wait=True): diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c index 63ce708d93ed..e4b7c2b457ee 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c @@ -2,6 +2,13 @@ // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu> #define _GNU_SOURCE + +// Needed for linux/fanotify.h +typedef struct { + int val[2]; +} __kernel_fsid_t; +#define __kernel_fsid_t __kernel_fsid_t + #include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -10,20 +17,12 @@ #include <sys/mount.h> #include <unistd.h> #include <sys/syscall.h> +#include <sys/fanotify.h> #include "../../kselftest_harness.h" #include "../statmount/statmount.h" #include "../utils.h" -// Needed for linux/fanotify.h -#ifndef __kernel_fsid_t -typedef struct { - int val[2]; -} __kernel_fsid_t; -#endif - -#include <sys/fanotify.h> - static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX"; static const int mark_cmds[] = { diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c index 090a5ca65004..9f57ca46e3af 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c @@ -2,6 +2,13 @@ // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu> #define _GNU_SOURCE + +// Needed for linux/fanotify.h +typedef struct { + int val[2]; +} __kernel_fsid_t; +#define __kernel_fsid_t __kernel_fsid_t + #include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -10,21 +17,12 @@ #include <sys/mount.h> #include <unistd.h> #include <sys/syscall.h> +#include <sys/fanotify.h> #include "../../kselftest_harness.h" -#include "../../pidfd/pidfd.h" #include "../statmount/statmount.h" #include "../utils.h" -// Needed for linux/fanotify.h -#ifndef __kernel_fsid_t -typedef struct { - int val[2]; -} __kernel_fsid_t; -#endif - -#include <sys/fanotify.h> - static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX"; static const int mark_types[] = { diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 2925e47db995..8516e8434bc4 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -751,7 +751,7 @@ for (; _metadata->trigger; _metadata->trigger = \ __bail(_assert, _metadata)) -#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) +#define is_signed_var(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \ /* Avoid multiple evaluation of the cases */ \ @@ -759,7 +759,7 @@ __typeof__(_seen) __seen = (_seen); \ if (!(__exp _t __seen)) { \ /* Report with actual signedness to avoid weird output. */ \ - switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ + switch (is_signed_var(__exp) * 2 + is_signed_var(__seen)) { \ case 0: { \ uintmax_t __exp_print = (uintmax_t)__exp; \ uintmax_t __seen_print = (uintmax_t)__seen; \ diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index e6e410b938b9..148d427ff24b 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -157,6 +157,7 @@ TEST_GEN_PROGS_arm64 = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases TEST_GEN_PROGS_arm64 += arm64/debug-exceptions +TEST_GEN_PROGS_arm64 += arm64/hello_el2 TEST_GEN_PROGS_arm64 += arm64/host_sve TEST_GEN_PROGS_arm64 += arm64/hypercalls TEST_GEN_PROGS_arm64 += arm64/external_aborts @@ -170,11 +171,13 @@ TEST_GEN_PROGS_arm64 += arm64/vgic_irq TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3 +TEST_GEN_PROGS_arm64 += arm64/kvm-uuid TEST_GEN_PROGS_arm64 += access_tracking_perf_test TEST_GEN_PROGS_arm64 += arch_timer TEST_GEN_PROGS_arm64 += coalesced_io_test TEST_GEN_PROGS_arm64 += dirty_log_perf_test TEST_GEN_PROGS_arm64 += get-reg-list +TEST_GEN_PROGS_arm64 += guest_memfd_test TEST_GEN_PROGS_arm64 += memslot_modification_stress_test TEST_GEN_PROGS_arm64 += memslot_perf_test TEST_GEN_PROGS_arm64 += mmu_stress_test @@ -196,9 +199,15 @@ TEST_GEN_PROGS_s390 += rseq_test TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test TEST_GEN_PROGS_riscv += riscv/ebreak_test +TEST_GEN_PROGS_riscv += access_tracking_perf_test TEST_GEN_PROGS_riscv += arch_timer TEST_GEN_PROGS_riscv += coalesced_io_test +TEST_GEN_PROGS_riscv += dirty_log_perf_test TEST_GEN_PROGS_riscv += get-reg-list +TEST_GEN_PROGS_riscv += memslot_modification_stress_test +TEST_GEN_PROGS_riscv += memslot_perf_test +TEST_GEN_PROGS_riscv += mmu_stress_test +TEST_GEN_PROGS_riscv += rseq_test TEST_GEN_PROGS_riscv += steal_time TEST_GEN_PROGS_loongarch += coalesced_io_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index c9de66537ec3..b058f27b2141 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -50,6 +50,7 @@ #include "memstress.h" #include "guest_modes.h" #include "processor.h" +#include "ucall_common.h" #include "cgroup_util.h" #include "lru_gen_util.h" diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c index cef8f7323ceb..713005b6f508 100644 --- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c @@ -146,7 +146,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu) val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); + el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val); return el0 == ID_AA64PFR0_EL1_EL0_IMP; } diff --git a/tools/testing/selftests/kvm/arm64/arch_timer.c b/tools/testing/selftests/kvm/arm64/arch_timer.c index eeba1cc87ff8..d592a4515399 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer.c @@ -165,10 +165,8 @@ static void guest_code(void) static void test_init_timer_irq(struct kvm_vm *vm) { /* Timer initid should be same for all the vCPUs, so query only vCPU-0 */ - vcpu_device_attr_get(vcpus[0], KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq); - vcpu_device_attr_get(vcpus[0], KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq); + ptimer_irq = vcpu_get_ptimer_irq(vcpus[0]); + vtimer_irq = vcpu_get_vtimer_irq(vcpus[0]); sync_global_to_guest(vm, ptimer_irq); sync_global_to_guest(vm, vtimer_irq); @@ -176,14 +174,14 @@ static void test_init_timer_irq(struct kvm_vm *vm) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } -static int gic_fd; - struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; int nr_vcpus = test_args.nr_vcpus; + TEST_REQUIRE(kvm_supports_vgic_v3()); + vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); vm_init_descriptor_tables(vm); @@ -204,8 +202,6 @@ struct kvm_vm *test_vm_create(void) vcpu_init_descriptor_tables(vcpus[i]); test_init_timer_irq(vm); - gic_fd = vgic_v3_setup(vm, nr_vcpus, 64); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); @@ -215,6 +211,5 @@ struct kvm_vm *test_vm_create(void) void test_vm_cleanup(struct kvm_vm *vm) { - close(gic_fd); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index ce74d069cb7b..91906414a474 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c @@ -924,10 +924,8 @@ static void test_run(struct kvm_vm *vm, struct kvm_vcpu *vcpu) static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { - vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq); - vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, - KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq); + ptimer_irq = vcpu_get_ptimer_irq(vcpu); + vtimer_irq = vcpu_get_vtimer_irq(vcpu); sync_global_to_guest(vm, ptimer_irq); sync_global_to_guest(vm, vtimer_irq); @@ -935,8 +933,6 @@ static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } -static int gic_fd; - static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, enum arch_timer timer) { @@ -951,8 +947,6 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, vcpu_args_set(*vcpu, 1, timer); test_init_timer_irq(*vm, *vcpu); - gic_fd = vgic_v3_setup(*vm, 1, 64); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); sync_global_to_guest(*vm, test_args); sync_global_to_guest(*vm, CVAL_MAX); @@ -961,7 +955,6 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu, static void test_vm_cleanup(struct kvm_vm *vm) { - close(gic_fd); kvm_vm_free(vm); } @@ -1042,6 +1035,8 @@ int main(int argc, char *argv[]) /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); + TEST_REQUIRE(kvm_supports_vgic_v3()); + if (!parse_args(argc, argv)) exit(KSFT_SKIP); diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c index e34963956fbc..1d431de8729c 100644 --- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c @@ -116,12 +116,12 @@ static void reset_debug_state(void) /* Reset all bcr/bvr/wcr/wvr registers */ dfr0 = read_sysreg(id_aa64dfr0_el1); - brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), dfr0); + brps = FIELD_GET(ID_AA64DFR0_EL1_BRPs, dfr0); for (i = 0; i <= brps; i++) { write_dbgbcr(i, 0); write_dbgbvr(i, 0); } - wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), dfr0); + wrps = FIELD_GET(ID_AA64DFR0_EL1_WRPs, dfr0); for (i = 0; i <= wrps; i++) { write_dbgwcr(i, 0); write_dbgwvr(i, 0); @@ -418,7 +418,7 @@ static void guest_code_ss(int test_cnt) static int debug_version(uint64_t id_aa64dfr0) { - return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), id_aa64dfr0); + return FIELD_GET(ID_AA64DFR0_EL1_DebugVer, id_aa64dfr0); } static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn) @@ -539,14 +539,14 @@ void test_guest_debug_exceptions_all(uint64_t aa64dfr0) int b, w, c; /* Number of breakpoints */ - brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), aa64dfr0) + 1; + brp_num = FIELD_GET(ID_AA64DFR0_EL1_BRPs, aa64dfr0) + 1; __TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required"); /* Number of watchpoints */ - wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), aa64dfr0) + 1; + wrp_num = FIELD_GET(ID_AA64DFR0_EL1_WRPs, aa64dfr0) + 1; /* Number of context aware breakpoints */ - ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_CTX_CMPs), aa64dfr0) + 1; + ctx_brp_num = FIELD_GET(ID_AA64DFR0_EL1_CTX_CMPs, aa64dfr0) + 1; pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__, brp_num, wrp_num, ctx_brp_num); diff --git a/tools/testing/selftests/kvm/arm64/external_aborts.c b/tools/testing/selftests/kvm/arm64/external_aborts.c index 062bf84cced1..592b26ded779 100644 --- a/tools/testing/selftests/kvm/arm64/external_aborts.c +++ b/tools/testing/selftests/kvm/arm64/external_aborts.c @@ -250,6 +250,47 @@ static void test_serror(void) kvm_vm_free(vm); } +static void expect_sea_s1ptw_handler(struct ex_regs *regs) +{ + u64 esr = read_sysreg(esr_el1); + + GUEST_ASSERT_EQ(regs->pc, expected_abort_pc); + GUEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_DABT_CUR); + GUEST_ASSERT_EQ((esr & ESR_ELx_FSC), ESR_ELx_FSC_SEA_TTW(3)); + + GUEST_DONE(); +} + +static noinline void test_s1ptw_abort_guest(void) +{ + extern char test_s1ptw_abort_insn; + + WRITE_ONCE(expected_abort_pc, (u64)&test_s1ptw_abort_insn); + + asm volatile("test_s1ptw_abort_insn:\n\t" + "ldr x0, [%0]\n\t" + : : "r" (MMIO_ADDR) : "x0", "memory"); + + GUEST_FAIL("Load on S1PTW abort should not retire"); +} + +static void test_s1ptw_abort(void) +{ + struct kvm_vcpu *vcpu; + u64 *ptep, bad_pa; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_s1ptw_abort_guest, + expect_sea_s1ptw_handler); + + ptep = virt_get_pte_hva_at_level(vm, MMIO_ADDR, 2); + bad_pa = BIT(vm->pa_bits) - vm->page_size; + + *ptep &= ~GENMASK(47, 12); + *ptep |= bad_pa; + + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + static void test_serror_emulated_guest(void) { GUEST_ASSERT(!(read_sysreg(isr_el1) & ISR_EL1_A)); @@ -327,4 +368,5 @@ int main(void) test_serror_masked(); test_serror_emulated(); test_mmio_ease(); + test_s1ptw_abort(); } diff --git a/tools/testing/selftests/kvm/arm64/hello_el2.c b/tools/testing/selftests/kvm/arm64/hello_el2.c new file mode 100644 index 000000000000..bbe6862c6ab1 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/hello_el2.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * hello_el2 - Basic KVM selftest for VM running at EL2 with E2H=RES1 + * + * Copyright 2025 Google LLC + */ +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" +#include "ucall.h" + +#include <asm/sysreg.h> + +static void guest_code(void) +{ + u64 mmfr0 = read_sysreg_s(SYS_ID_AA64MMFR0_EL1); + u64 mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1); + u64 mmfr4 = read_sysreg_s(SYS_ID_AA64MMFR4_EL1); + u8 e2h0 = SYS_FIELD_GET(ID_AA64MMFR4_EL1, E2H0, mmfr4); + + GUEST_ASSERT_EQ(get_current_el(), 2); + GUEST_ASSERT(read_sysreg(hcr_el2) & HCR_EL2_E2H); + GUEST_ASSERT_EQ(SYS_FIELD_GET(ID_AA64MMFR1_EL1, VH, mmfr1), + ID_AA64MMFR1_EL1_VH_IMP); + + /* + * Traps of the complete ID register space are IMPDEF without FEAT_FGT, + * which is really annoying to deal with in KVM describing E2H as RES1. + * + * If the implementation doesn't honor the trap then expect the register + * to return all zeros. + */ + if (e2h0 == ID_AA64MMFR4_EL1_E2H0_IMP) + GUEST_ASSERT_EQ(SYS_FIELD_GET(ID_AA64MMFR0_EL1, FGT, mmfr0), + ID_AA64MMFR0_EL1_FGT_NI); + else + GUEST_ASSERT_EQ(e2h0, ID_AA64MMFR4_EL1_E2H0_NI_NV1); + + GUEST_DONE(); +} + +int main(void) +{ + struct kvm_vcpu_init init; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_ARM_EL2)); + + vm = vm_create(1); + + kvm_get_default_vcpu_target(vm, &init); + init.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2); + vcpu = aarch64_vcpu_add(vm, 0, &init, guest_code); + kvm_arch_vm_finalize_vcpus(vm); + + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + default: + TEST_FAIL("Unhandled ucall: %ld\n", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/arm64/hypercalls.c b/tools/testing/selftests/kvm/arm64/hypercalls.c index 44cfcf8a7f46..bf038a0371f4 100644 --- a/tools/testing/selftests/kvm/arm64/hypercalls.c +++ b/tools/testing/selftests/kvm/arm64/hypercalls.c @@ -108,7 +108,7 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info) for (i = 0; i < hvc_info_arr_sz; i++, hc_info++) { memset(&res, 0, sizeof(res)); - smccc_hvc(hc_info->func_id, hc_info->arg1, 0, 0, 0, 0, 0, 0, &res); + do_smccc(hc_info->func_id, hc_info->arg1, 0, 0, 0, 0, 0, 0, &res); switch (stage) { case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: diff --git a/tools/testing/selftests/kvm/arm64/kvm-uuid.c b/tools/testing/selftests/kvm/arm64/kvm-uuid.c new file mode 100644 index 000000000000..b5be9133535a --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/kvm-uuid.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Check that nobody has tampered with KVM's UID + +#include <errno.h> +#include <linux/arm-smccc.h> +#include <asm/kvm.h> +#include <kvm_util.h> + +#include "processor.h" + +/* + * Do NOT redefine these constants, or try to replace them with some + * "common" version. They are hardcoded here to detect any potential + * breakage happening in the rest of the kernel. + * + * KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 + */ +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU + +static void guest_code(void) +{ + struct arm_smccc_res res = {}; + + do_smccc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res); + + __GUEST_ASSERT(res.a0 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 && + res.a1 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 && + res.a2 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 && + res.a3 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3, + "Unexpected KVM-specific UID %lx %lx %lx %lx\n", res.a0, res.a1, res.a2, res.a3); + GUEST_DONE(); +} + +int main (int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + bool guest_done = false; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + while (!guest_done) { + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + break; + case UCALL_DONE: + guest_done = true; + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_PRINTF: + printf("%s", uc.buffer); + break; + default: + TEST_FAIL("Unexpected guest exit"); + } + } + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c index ebd70430c89d..152c34776981 100644 --- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c +++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c @@ -54,7 +54,7 @@ static void guest_code(void) * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having * hidden the feature at runtime without any other userspace action. */ - __GUEST_ASSERT(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), + __GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC, read_sysreg(id_aa64pfr0_el1)) == 0, "GICv3 wrongly advertised"); @@ -163,9 +163,11 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; uint64_t pfr0; + test_disable_default_vgic(); + vm = vm_create_with_one_vcpu(&vcpu, NULL); pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - __TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0), + __TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0), "GICv3 not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c index dc6559dad9d8..4ccbd389d133 100644 --- a/tools/testing/selftests/kvm/arm64/page_fault_test.c +++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c @@ -95,14 +95,14 @@ static bool guest_check_lse(void) uint64_t isar0 = read_sysreg(id_aa64isar0_el1); uint64_t atomic; - atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC), isar0); + atomic = FIELD_GET(ID_AA64ISAR0_EL1_ATOMIC, isar0); return atomic >= 2; } static bool guest_check_dc_zva(void) { uint64_t dczid = read_sysreg(dczid_el0); - uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_EL0_DZP), dczid); + uint64_t dzp = FIELD_GET(DCZID_EL0_DZP, dczid); return dzp == 0; } @@ -195,7 +195,7 @@ static bool guest_set_ha(void) uint64_t hadbs, tcr; /* Skip if HA is not supported. */ - hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS), mmfr1); + hadbs = FIELD_GET(ID_AA64MMFR1_EL1_HAFDBS, mmfr1); if (hadbs == 0) return false; diff --git a/tools/testing/selftests/kvm/arm64/psci_test.c b/tools/testing/selftests/kvm/arm64/psci_test.c index ab491ee9e5f7..98e49f710aef 100644 --- a/tools/testing/selftests/kvm/arm64/psci_test.c +++ b/tools/testing/selftests/kvm/arm64/psci_test.c @@ -27,7 +27,7 @@ static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, { struct arm_smccc_res res; - smccc_hvc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id, + do_smccc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id, 0, 0, 0, 0, &res); return res.a0; @@ -38,7 +38,7 @@ static uint64_t psci_affinity_info(uint64_t target_affinity, { struct arm_smccc_res res; - smccc_hvc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level, + do_smccc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level, 0, 0, 0, 0, 0, &res); return res.a0; @@ -48,7 +48,7 @@ static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id) { struct arm_smccc_res res; - smccc_hvc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id, + do_smccc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id, 0, 0, 0, 0, 0, &res); return res.a0; @@ -58,7 +58,7 @@ static uint64_t psci_system_off2(uint64_t type, uint64_t cookie) { struct arm_smccc_res res; - smccc_hvc(PSCI_1_3_FN64_SYSTEM_OFF2, type, cookie, 0, 0, 0, 0, 0, &res); + do_smccc(PSCI_1_3_FN64_SYSTEM_OFF2, type, cookie, 0, 0, 0, 0, 0, &res); return res.a0; } @@ -67,7 +67,7 @@ static uint64_t psci_features(uint32_t func_id) { struct arm_smccc_res res; - smccc_hvc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res); + do_smccc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res); return res.a0; } @@ -89,12 +89,13 @@ static struct kvm_vm *setup_vm(void *guest_code, struct kvm_vcpu **source, vm = vm_create(2); - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vm, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); *source = aarch64_vcpu_add(vm, 0, &init, guest_code); *target = aarch64_vcpu_add(vm, 1, &init, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index d3bf9204409c..8ff1e853f7f8 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -15,8 +15,6 @@ #include "test_util.h" #include <linux/bitfield.h> -bool have_cap_arm_mte; - enum ftr_type { FTR_EXACT, /* Use a predefined safe value */ FTR_LOWER_SAFE, /* Smaller value is safe */ @@ -125,6 +123,13 @@ static const struct reg_ftr_bits ftr_id_aa64isar2_el1[] = { REG_FTR_END, }; +static const struct reg_ftr_bits ftr_id_aa64isar3_el1[] = { + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR3_EL1, FPRCVT, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR3_EL1, LSFE, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ISAR3_EL1, FAMINMAX, 0), + REG_FTR_END, +}; + static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV3, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, CSV2, 0), @@ -165,7 +170,9 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { static const struct reg_ftr_bits ftr_id_aa64mmfr1_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, TIDCP1, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, AFP, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, HCX, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, ETS, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, TWED, 0), REG_FTR_BITS(FTR_HIGHER_SAFE, ID_AA64MMFR1_EL1, SpecSEI, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, PAN, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR1_EL1, LO, 0), @@ -221,6 +228,7 @@ static struct test_feature_reg test_regs[] = { TEST_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0_el1), TEST_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1_el1), TEST_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2_el1), + TEST_REG(SYS_ID_AA64ISAR3_EL1, ftr_id_aa64isar3_el1), TEST_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0_el1), TEST_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1_el1), TEST_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0_el1), @@ -239,10 +247,12 @@ static void guest_code(void) GUEST_REG_SYNC(SYS_ID_AA64ISAR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64ISAR1_EL1); GUEST_REG_SYNC(SYS_ID_AA64ISAR2_EL1); + GUEST_REG_SYNC(SYS_ID_AA64ISAR3_EL1); GUEST_REG_SYNC(SYS_ID_AA64PFR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1); GUEST_REG_SYNC(SYS_ID_AA64MMFR2_EL1); + GUEST_REG_SYNC(SYS_ID_AA64MMFR3_EL1); GUEST_REG_SYNC(SYS_ID_AA64ZFR0_EL1); GUEST_REG_SYNC(SYS_CTR_EL0); GUEST_REG_SYNC(SYS_MIDR_EL1); @@ -567,7 +577,9 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) uint64_t mte_frac; int idx, err; - if (!have_cap_arm_mte) { + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); + mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val); + if (!mte) { ksft_test_result_skip("MTE capability not supported, nothing to test\n"); return; } @@ -592,10 +604,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) * from unsupported (0xF) to supported (0). * */ - val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); - - mte = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), val); - mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val); + mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val); if (mte != ID_AA64PFR1_EL1_MTE_MTE2 || mte_frac != ID_AA64PFR1_EL1_MTE_frac_NI) { ksft_test_result_skip("MTE_ASYNC or MTE_ASYMM are supported, nothing to test\n"); @@ -612,7 +621,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu) } val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); - mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val); + mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val); if (mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI) ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac=0 accepted and still 0xF\n"); else @@ -749,43 +758,35 @@ static void test_reset_preserves_id_regs(struct kvm_vcpu *vcpu) ksft_test_result_pass("%s\n", __func__); } -void kvm_arch_vm_post_create(struct kvm_vm *vm) -{ - if (vm_check_cap(vm, KVM_CAP_ARM_MTE)) { - vm_enable_cap(vm, KVM_CAP_ARM_MTE, 0); - have_cap_arm_mte = true; - } -} - int main(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm; bool aarch64_only; uint64_t val, el0; - int test_cnt; + int test_cnt, i, j; TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_WRITABLE_IMP_ID_REGS)); + test_wants_mte(); + vm = vm_create(1); vm_enable_cap(vm, KVM_CAP_ARM_WRITABLE_IMP_ID_REGS, 0); vcpu = vm_vcpu_add(vm, 0, guest_code); + kvm_arch_vm_finalize_vcpus(vm); /* Check for AARCH64 only system */ val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); - el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); + el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val); aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP); ksft_print_header(); - test_cnt = ARRAY_SIZE(ftr_id_aa64dfr0_el1) + ARRAY_SIZE(ftr_id_dfr0_el1) + - ARRAY_SIZE(ftr_id_aa64isar0_el1) + ARRAY_SIZE(ftr_id_aa64isar1_el1) + - ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) + - ARRAY_SIZE(ftr_id_aa64pfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + - ARRAY_SIZE(ftr_id_aa64mmfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + - ARRAY_SIZE(ftr_id_aa64mmfr3_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) - - ARRAY_SIZE(test_regs) + 3 + MPAM_IDREG_TEST + MTE_IDREG_TEST; + test_cnt = 3 + MPAM_IDREG_TEST + MTE_IDREG_TEST; + for (i = 0; i < ARRAY_SIZE(test_regs); i++) + for (j = 0; test_regs[i].ftr_bits[j].type != FTR_END; j++) + test_cnt++; ksft_set_plan(test_cnt); diff --git a/tools/testing/selftests/kvm/arm64/smccc_filter.c b/tools/testing/selftests/kvm/arm64/smccc_filter.c index 2d189f3da228..1763b9d45400 100644 --- a/tools/testing/selftests/kvm/arm64/smccc_filter.c +++ b/tools/testing/selftests/kvm/arm64/smccc_filter.c @@ -22,8 +22,20 @@ enum smccc_conduit { SMC_INSN, }; +static bool test_runs_at_el2(void) +{ + struct kvm_vm *vm = vm_create(1); + struct kvm_vcpu_init init; + + kvm_get_default_vcpu_target(vm, &init); + kvm_vm_free(vm); + + return init.features[0] & BIT(KVM_ARM_VCPU_HAS_EL2); +} + #define for_each_conduit(conduit) \ - for (conduit = HVC_INSN; conduit <= SMC_INSN; conduit++) + for (conduit = test_runs_at_el2() ? SMC_INSN : HVC_INSN; \ + conduit <= SMC_INSN; conduit++) static void guest_main(uint32_t func_id, enum smccc_conduit conduit) { @@ -64,7 +76,7 @@ static struct kvm_vm *setup_vm(struct kvm_vcpu **vcpu) struct kvm_vm *vm; vm = vm_create(1); - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vm, &init); /* * Enable in-kernel emulation of PSCI to ensure that calls are denied @@ -73,6 +85,7 @@ static struct kvm_vm *setup_vm(struct kvm_vcpu **vcpu) init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); *vcpu = aarch64_vcpu_add(vm, 0, &init, guest_main); + kvm_arch_vm_finalize_vcpus(vm); return vm; } diff --git a/tools/testing/selftests/kvm/arm64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c index a8e0f46bc0ab..8d6d3a4ae4db 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_init.c +++ b/tools/testing/selftests/kvm/arm64/vgic_init.c @@ -994,6 +994,8 @@ int main(int ac, char **av) int pa_bits; int cnt_impl = 0; + test_disable_default_vgic(); + pa_bits = vm_guest_mode_params[VM_MODE_DEFAULT].pa_bits; max_phys_size = 1ULL << pa_bits; diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index a09dd423c2d7..6338f5bbdb70 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c @@ -752,7 +752,6 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) vcpu_args_set(vcpu, 1, args_gva); gic_fd = vgic_v3_setup(vm, 1, nr_irqs); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3, skipping"); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handlers[args.eoi_split][args.level_sensitive]); @@ -802,6 +801,9 @@ int main(int argc, char **argv) int opt; bool eoi_split = false; + TEST_REQUIRE(kvm_supports_vgic_v3()); + test_disable_default_vgic(); + while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) { switch (opt) { case 'n': diff --git a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c index fc4fe52fb6f8..87922a89b134 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c +++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c @@ -27,7 +27,7 @@ static vm_paddr_t gpa_base; static struct kvm_vm *vm; static struct kvm_vcpu **vcpus; -static int gic_fd, its_fd; +static int its_fd; static struct test_data { bool request_vcpus_stop; @@ -214,9 +214,6 @@ static void setup_test_data(void) static void setup_gic(void) { - gic_fd = vgic_v3_setup(vm, test_data.nr_cpus, 64); - __TEST_REQUIRE(gic_fd >= 0, "Failed to create GICv3"); - its_fd = vgic_its_setup(vm); } @@ -355,7 +352,6 @@ static void setup_vm(void) static void destroy_vm(void) { close(its_fd); - close(gic_fd); kvm_vm_free(vm); free(vcpus); } @@ -374,6 +370,8 @@ int main(int argc, char **argv) u32 nr_threads; int c; + TEST_REQUIRE(kvm_supports_vgic_v3()); + while ((c = getopt(argc, argv, "hv:d:e:i:")) != -1) { switch (c) { case 'v': diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c index f16b3b27e32e..ae36325c022f 100644 --- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c @@ -28,7 +28,6 @@ struct vpmu_vm { struct kvm_vm *vm; struct kvm_vcpu *vcpu; - int gic_fd; }; static struct vpmu_vm vpmu_vm; @@ -45,11 +44,6 @@ static uint64_t get_pmcr_n(uint64_t pmcr) return FIELD_GET(ARMV8_PMU_PMCR_N, pmcr); } -static void set_pmcr_n(uint64_t *pmcr, uint64_t pmcr_n) -{ - u64p_replace_bits((__u64 *) pmcr, pmcr_n, ARMV8_PMU_PMCR_N); -} - static uint64_t get_counters_mask(uint64_t n) { uint64_t mask = BIT(ARMV8_PMU_CYCLE_IDX); @@ -415,10 +409,6 @@ static void create_vpmu_vm(void *guest_code) .attr = KVM_ARM_VCPU_PMU_V3_IRQ, .addr = (uint64_t)&irq, }; - struct kvm_device_attr init_attr = { - .group = KVM_ARM_VCPU_PMU_V3_CTRL, - .attr = KVM_ARM_VCPU_PMU_V3_INIT, - }; /* The test creates the vpmu_vm multiple times. Ensure a clean state */ memset(&vpmu_vm, 0, sizeof(vpmu_vm)); @@ -431,29 +421,25 @@ static void create_vpmu_vm(void *guest_code) } /* Create vCPU with PMUv3 */ - vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vpmu_vm.vm, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3); vpmu_vm.vcpu = aarch64_vcpu_add(vpmu_vm.vm, 0, &init, guest_code); vcpu_init_descriptor_tables(vpmu_vm.vcpu); - vpmu_vm.gic_fd = vgic_v3_setup(vpmu_vm.vm, 1, 64); - __TEST_REQUIRE(vpmu_vm.gic_fd >= 0, - "Failed to create vgic-v3, skipping"); + + kvm_arch_vm_finalize_vcpus(vpmu_vm.vm); /* Make sure that PMUv3 support is indicated in the ID register */ dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); - pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0); + pmuver = FIELD_GET(ID_AA64DFR0_EL1_PMUVer, dfr0); TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP, "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver); - /* Initialize vPMU */ vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &irq_attr); - vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &init_attr); } static void destroy_vpmu_vm(void) { - close(vpmu_vm.gic_fd); kvm_vm_free(vpmu_vm.vm); } @@ -475,33 +461,28 @@ static void run_vcpu(struct kvm_vcpu *vcpu, uint64_t pmcr_n) } } -static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) +static void test_create_vpmu_vm_with_nr_counters(unsigned int nr_counters, bool expect_fail) { struct kvm_vcpu *vcpu; - uint64_t pmcr, pmcr_orig; + unsigned int prev; + int ret; create_vpmu_vm(guest_code); vcpu = vpmu_vm.vcpu; - pmcr_orig = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); - pmcr = pmcr_orig; + prev = get_pmcr_n(vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0))); - /* - * Setting a larger value of PMCR.N should not modify the field, and - * return a success. - */ - set_pmcr_n(&pmcr, pmcr_n); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr); - pmcr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); + ret = __vcpu_device_attr_set(vcpu, KVM_ARM_VCPU_PMU_V3_CTRL, + KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS, &nr_counters); if (expect_fail) - TEST_ASSERT(pmcr_orig == pmcr, - "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx", - pmcr, pmcr_n); + TEST_ASSERT(ret && errno == EINVAL, + "Setting more PMU counters (%u) than available (%u) unexpectedly succeeded", + nr_counters, prev); else - TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr), - "Failed to update PMCR.N to %lu (received: %lu)", - pmcr_n, get_pmcr_n(pmcr)); + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); + + vcpu_device_attr_set(vcpu, KVM_ARM_VCPU_PMU_V3_CTRL, KVM_ARM_VCPU_PMU_V3_INIT, NULL); } /* @@ -516,11 +497,11 @@ static void run_access_test(uint64_t pmcr_n) pr_debug("Test with pmcr_n %lu\n", pmcr_n); - test_create_vpmu_vm_with_pmcr_n(pmcr_n, false); + test_create_vpmu_vm_with_nr_counters(pmcr_n, false); vcpu = vpmu_vm.vcpu; /* Save the initial sp to restore them later to run the guest again */ - sp = vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1)); + sp = vcpu_get_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1)); run_vcpu(vcpu, pmcr_n); @@ -528,11 +509,11 @@ static void run_access_test(uint64_t pmcr_n) * Reset and re-initialize the vCPU, and run the guest code again to * check if PMCR_EL0.N is preserved. */ - vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init); + kvm_get_default_vcpu_target(vpmu_vm.vm, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3); aarch64_vcpu_setup(vcpu, &init); vcpu_init_descriptor_tables(vcpu); - vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), sp); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), sp); vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); run_vcpu(vcpu, pmcr_n); @@ -557,7 +538,7 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) uint64_t set_reg_id, clr_reg_id, reg_val; uint64_t valid_counters_mask, max_counters_mask; - test_create_vpmu_vm_with_pmcr_n(pmcr_n, false); + test_create_vpmu_vm_with_nr_counters(pmcr_n, false); vcpu = vpmu_vm.vcpu; valid_counters_mask = get_counters_mask(pmcr_n); @@ -611,7 +592,7 @@ static void run_error_test(uint64_t pmcr_n) { pr_debug("Error test with pmcr_n %lu (larger than the host)\n", pmcr_n); - test_create_vpmu_vm_with_pmcr_n(pmcr_n, true); + test_create_vpmu_vm_with_nr_counters(pmcr_n, true); destroy_vpmu_vm(); } @@ -629,11 +610,25 @@ static uint64_t get_pmcr_n_limit(void) return get_pmcr_n(pmcr); } +static bool kvm_supports_nr_counters_attr(void) +{ + bool supported; + + create_vpmu_vm(NULL); + supported = !__vcpu_has_device_attr(vpmu_vm.vcpu, KVM_ARM_VCPU_PMU_V3_CTRL, + KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS); + destroy_vpmu_vm(); + + return supported; +} + int main(void) { uint64_t i, pmcr_n; TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_PMU_V3)); + TEST_REQUIRE(kvm_supports_vgic_v3()); + TEST_REQUIRE(kvm_supports_nr_counters_attr()); pmcr_n = get_pmcr_n_limit(); for (i = 0; i <= pmcr_n; i++) { diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index e79817bd0e29..0a1ea1d1e2d8 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -20,38 +20,6 @@ #include "guest_modes.h" #include "ucall_common.h" -#ifdef __aarch64__ -#include "arm64/vgic.h" - -static int gic_fd; - -static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) -{ - /* - * The test can still run even if hardware does not support GICv3, as it - * is only an optimization to reduce guest exits. - */ - gic_fd = vgic_v3_setup(vm, nr_vcpus, 64); -} - -static void arch_cleanup_vm(struct kvm_vm *vm) -{ - if (gic_fd > 0) - close(gic_fd); -} - -#else /* __aarch64__ */ - -static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) -{ -} - -static void arch_cleanup_vm(struct kvm_vm *vm) -{ -} - -#endif - /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ #define TEST_HOST_LOOP_N 2UL @@ -166,8 +134,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, dirty_log_manual_caps); - arch_setup_vm(vm, nr_vcpus); - /* Start the iterations */ iteration = 0; host_quit = false; @@ -285,7 +251,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) } memstress_free_bitmaps(bitmaps, p->slots); - arch_cleanup_vm(vm); memstress_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 23593d9eeba9..d58a641b0e6a 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -585,6 +585,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, log_mode_create_vm_done(vm); *vcpu = vm_vcpu_add(vm, 0, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c index 91f05f78e824..f4644c9d2d3b 100644 --- a/tools/testing/selftests/kvm/get-reg-list.c +++ b/tools/testing/selftests/kvm/get-reg-list.c @@ -116,10 +116,13 @@ void __weak finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) } #ifdef __aarch64__ -static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *init) +static void prepare_vcpu_init(struct kvm_vm *vm, struct vcpu_reg_list *c, + struct kvm_vcpu_init *init) { struct vcpu_reg_sublist *s; + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, init); + for_each_sublist(c, s) if (s->capability) init->features[s->feature / 32] |= 1 << (s->feature % 32); @@ -127,10 +130,10 @@ static void prepare_vcpu_init(struct vcpu_reg_list *c, struct kvm_vcpu_init *ini static struct kvm_vcpu *vcpu_config_get_vcpu(struct vcpu_reg_list *c, struct kvm_vm *vm) { - struct kvm_vcpu_init init = { .target = -1, }; + struct kvm_vcpu_init init; struct kvm_vcpu *vcpu; - prepare_vcpu_init(c, &init); + prepare_vcpu_init(vm, c, &init); vcpu = __vm_vcpu_add(vm, 0); aarch64_vcpu_setup(vcpu, &init); diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index ce687f8d248f..b3ca6737f304 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -13,12 +13,16 @@ #include <linux/bitmap.h> #include <linux/falloc.h> +#include <linux/sizes.h> +#include <setjmp.h> +#include <signal.h> #include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> #include "kvm_util.h" #include "test_util.h" +#include "ucall_common.h" static void test_file_read_write(int fd) { @@ -34,12 +38,83 @@ static void test_file_read_write(int fd) "pwrite on a guest_mem fd should fail"); } -static void test_mmap(int fd, size_t page_size) +static void test_mmap_supported(int fd, size_t page_size, size_t total_size) +{ + const char val = 0xaa; + char *mem; + size_t i; + int ret; + + mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + TEST_ASSERT(mem == MAP_FAILED, "Copy-on-write not allowed by guest_memfd."); + + mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed."); + + memset(mem, val, total_size); + for (i = 0; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, + page_size); + TEST_ASSERT(!ret, "fallocate the first page should succeed."); + + for (i = 0; i < page_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), 0x00); + for (; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + memset(mem, val, page_size); + for (i = 0; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + ret = munmap(mem, total_size); + TEST_ASSERT(!ret, "munmap() should succeed."); +} + +static sigjmp_buf jmpbuf; +void fault_sigbus_handler(int signum) +{ + siglongjmp(jmpbuf, 1); +} + +static void test_fault_overflow(int fd, size_t page_size, size_t total_size) +{ + struct sigaction sa_old, sa_new = { + .sa_handler = fault_sigbus_handler, + }; + size_t map_size = total_size * 4; + const char val = 0xaa; + char *mem; + size_t i; + int ret; + + mem = mmap(NULL, map_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() for guest_memfd should succeed."); + + sigaction(SIGBUS, &sa_new, &sa_old); + if (sigsetjmp(jmpbuf, 1) == 0) { + memset(mem, 0xaa, map_size); + TEST_ASSERT(false, "memset() should have triggered SIGBUS."); + } + sigaction(SIGBUS, &sa_old, NULL); + + for (i = 0; i < total_size; i++) + TEST_ASSERT_EQ(READ_ONCE(mem[i]), val); + + ret = munmap(mem, map_size); + TEST_ASSERT(!ret, "munmap() should succeed."); +} + +static void test_mmap_not_supported(int fd, size_t page_size, size_t total_size) { char *mem; mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); TEST_ASSERT_EQ(mem, MAP_FAILED); + + mem = mmap(NULL, total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT_EQ(mem, MAP_FAILED); } static void test_file_size(int fd, size_t page_size, size_t total_size) @@ -120,80 +195,187 @@ static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size) } } -static void test_create_guest_memfd_invalid(struct kvm_vm *vm) +static void test_create_guest_memfd_invalid_sizes(struct kvm_vm *vm, + uint64_t guest_memfd_flags, + size_t page_size) { - size_t page_size = getpagesize(); - uint64_t flag; size_t size; int fd; for (size = 1; size < page_size; size++) { - fd = __vm_create_guest_memfd(vm, size, 0); - TEST_ASSERT(fd == -1 && errno == EINVAL, + fd = __vm_create_guest_memfd(vm, size, guest_memfd_flags); + TEST_ASSERT(fd < 0 && errno == EINVAL, "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL", size); } - - for (flag = BIT(0); flag; flag <<= 1) { - fd = __vm_create_guest_memfd(vm, page_size, flag); - TEST_ASSERT(fd == -1 && errno == EINVAL, - "guest_memfd() with flag '0x%lx' should fail with EINVAL", - flag); - } } static void test_create_guest_memfd_multiple(struct kvm_vm *vm) { int fd1, fd2, ret; struct stat st1, st2; + size_t page_size = getpagesize(); - fd1 = __vm_create_guest_memfd(vm, 4096, 0); + fd1 = __vm_create_guest_memfd(vm, page_size, 0); TEST_ASSERT(fd1 != -1, "memfd creation should succeed"); ret = fstat(fd1, &st1); TEST_ASSERT(ret != -1, "memfd fstat should succeed"); - TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size"); + TEST_ASSERT(st1.st_size == page_size, "memfd st_size should match requested size"); - fd2 = __vm_create_guest_memfd(vm, 8192, 0); + fd2 = __vm_create_guest_memfd(vm, page_size * 2, 0); TEST_ASSERT(fd2 != -1, "memfd creation should succeed"); ret = fstat(fd2, &st2); TEST_ASSERT(ret != -1, "memfd fstat should succeed"); - TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size"); + TEST_ASSERT(st2.st_size == page_size * 2, "second memfd st_size should match requested size"); ret = fstat(fd1, &st1); TEST_ASSERT(ret != -1, "memfd fstat should succeed"); - TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size"); + TEST_ASSERT(st1.st_size == page_size, "first memfd st_size should still match requested size"); TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers"); close(fd2); close(fd1); } -int main(int argc, char *argv[]) +static void test_guest_memfd_flags(struct kvm_vm *vm, uint64_t valid_flags) { - size_t page_size; - size_t total_size; + size_t page_size = getpagesize(); + uint64_t flag; int fd; - struct kvm_vm *vm; - TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + for (flag = BIT(0); flag; flag <<= 1) { + fd = __vm_create_guest_memfd(vm, page_size, flag); + if (flag & valid_flags) { + TEST_ASSERT(fd >= 0, + "guest_memfd() with flag '0x%lx' should succeed", + flag); + close(fd); + } else { + TEST_ASSERT(fd < 0 && errno == EINVAL, + "guest_memfd() with flag '0x%lx' should fail with EINVAL", + flag); + } + } +} + +static void test_guest_memfd(unsigned long vm_type) +{ + uint64_t flags = 0; + struct kvm_vm *vm; + size_t total_size; + size_t page_size; + int fd; page_size = getpagesize(); total_size = page_size * 4; - vm = vm_create_barebones(); + vm = vm_create_barebones_type(vm_type); + + if (vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP)) + flags |= GUEST_MEMFD_FLAG_MMAP; - test_create_guest_memfd_invalid(vm); test_create_guest_memfd_multiple(vm); + test_create_guest_memfd_invalid_sizes(vm, flags, page_size); - fd = vm_create_guest_memfd(vm, total_size, 0); + fd = vm_create_guest_memfd(vm, total_size, flags); test_file_read_write(fd); - test_mmap(fd, page_size); + + if (flags & GUEST_MEMFD_FLAG_MMAP) { + test_mmap_supported(fd, page_size, total_size); + test_fault_overflow(fd, page_size, total_size); + } else { + test_mmap_not_supported(fd, page_size, total_size); + } + test_file_size(fd, page_size, total_size); test_fallocate(fd, page_size, total_size); test_invalid_punch_hole(fd, page_size, total_size); + test_guest_memfd_flags(vm, flags); + close(fd); + kvm_vm_free(vm); +} + +static void guest_code(uint8_t *mem, uint64_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + __GUEST_ASSERT(mem[i] == 0xaa, + "Guest expected 0xaa at offset %lu, got 0x%x", i, mem[i]); + + memset(mem, 0xff, size); + GUEST_DONE(); +} + +static void test_guest_memfd_guest(void) +{ + /* + * Skip the first 4gb and slot0. slot0 maps <1gb and is used to back + * the guest's code, stack, and page tables, and low memory contains + * the PCI hole and other MMIO regions that need to be avoided. + */ + const uint64_t gpa = SZ_4G; + const int slot = 1; + + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + uint8_t *mem; + size_t size; + int fd, i; + + if (!kvm_has_cap(KVM_CAP_GUEST_MEMFD_MMAP)) + return; + + vm = __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, &vcpu, 1, guest_code); + + TEST_ASSERT(vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_MMAP), + "Default VM type should always support guest_memfd mmap()"); + + size = vm->page_size; + fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP); + vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed"); + memset(mem, 0xaa, size); + munmap(mem, size); + + virt_pg_map(vm, gpa, gpa); + vcpu_args_set(vcpu, 2, gpa, size); + vcpu_run(vcpu); + + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT(mem != MAP_FAILED, "mmap() on guest_memfd failed"); + for (i = 0; i < size; i++) + TEST_ASSERT_EQ(mem[i], 0xff); + + close(fd); + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + unsigned long vm_types, vm_type; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + + /* + * Not all architectures support KVM_CAP_VM_TYPES. However, those that + * support guest_memfd have that support for the default VM type. + */ + vm_types = kvm_check_cap(KVM_CAP_VM_TYPES); + if (!vm_types) + vm_types = BIT(VM_TYPE_DEFAULT); + + for_each_set_bit(vm_type, &vm_types, BITS_PER_TYPE(vm_types)) + test_guest_memfd(vm_type); + + test_guest_memfd_guest(); } diff --git a/tools/testing/selftests/kvm/include/arm64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h index bf461de34785..e2c4e9f0010f 100644 --- a/tools/testing/selftests/kvm/include/arm64/arch_timer.h +++ b/tools/testing/selftests/kvm/include/arm64/arch_timer.h @@ -155,4 +155,28 @@ static inline void timer_set_next_tval_ms(enum arch_timer timer, uint32_t msec) timer_set_tval(timer, msec_to_cycles(msec)); } +static inline u32 vcpu_get_vtimer_irq(struct kvm_vcpu *vcpu) +{ + u32 intid; + u64 attr; + + attr = vcpu_has_el2(vcpu) ? KVM_ARM_VCPU_TIMER_IRQ_HVTIMER : + KVM_ARM_VCPU_TIMER_IRQ_VTIMER; + vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, attr, &intid); + + return intid; +} + +static inline u32 vcpu_get_ptimer_irq(struct kvm_vcpu *vcpu) +{ + u32 intid; + u64 attr; + + attr = vcpu_has_el2(vcpu) ? KVM_ARM_VCPU_TIMER_IRQ_HPTIMER : + KVM_ARM_VCPU_TIMER_IRQ_PTIMER; + vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, attr, &intid); + + return intid; +} + #endif /* SELFTEST_KVM_ARCH_TIMER_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h index e43a57d99b56..b973bb2c64a6 100644 --- a/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h @@ -2,6 +2,9 @@ #ifndef SELFTEST_KVM_UTIL_ARCH_H #define SELFTEST_KVM_UTIL_ARCH_H -struct kvm_vm_arch {}; +struct kvm_vm_arch { + bool has_gic; + int gic_fd; +}; #endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h index 255fed769a8a..6f481475c135 100644 --- a/tools/testing/selftests/kvm/include/arm64/processor.h +++ b/tools/testing/selftests/kvm/include/arm64/processor.h @@ -175,6 +175,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec, handler_fn handler); +uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level); uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva); static inline void cpu_relax(void) @@ -300,4 +301,77 @@ void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, /* Execute a Wait For Interrupt instruction. */ void wfi(void); +void test_wants_mte(void); +void test_disable_default_vgic(void); + +bool vm_supports_el2(struct kvm_vm *vm); +static bool vcpu_has_el2(struct kvm_vcpu *vcpu) +{ + return vcpu->init.features[0] & BIT(KVM_ARM_VCPU_HAS_EL2); +} + +#define MAPPED_EL2_SYSREG(el2, el1) \ + case SYS_##el1: \ + if (vcpu_has_el2(vcpu)) \ + alias = SYS_##el2; \ + break + + +static __always_inline u64 ctxt_reg_alias(struct kvm_vcpu *vcpu, u32 encoding) +{ + u32 alias = encoding; + + BUILD_BUG_ON(!__builtin_constant_p(encoding)); + + switch (encoding) { + MAPPED_EL2_SYSREG(SCTLR_EL2, SCTLR_EL1); + MAPPED_EL2_SYSREG(CPTR_EL2, CPACR_EL1); + MAPPED_EL2_SYSREG(TTBR0_EL2, TTBR0_EL1); + MAPPED_EL2_SYSREG(TTBR1_EL2, TTBR1_EL1); + MAPPED_EL2_SYSREG(TCR_EL2, TCR_EL1); + MAPPED_EL2_SYSREG(VBAR_EL2, VBAR_EL1); + MAPPED_EL2_SYSREG(AFSR0_EL2, AFSR0_EL1); + MAPPED_EL2_SYSREG(AFSR1_EL2, AFSR1_EL1); + MAPPED_EL2_SYSREG(ESR_EL2, ESR_EL1); + MAPPED_EL2_SYSREG(FAR_EL2, FAR_EL1); + MAPPED_EL2_SYSREG(MAIR_EL2, MAIR_EL1); + MAPPED_EL2_SYSREG(TCR2_EL2, TCR2_EL1); + MAPPED_EL2_SYSREG(PIR_EL2, PIR_EL1); + MAPPED_EL2_SYSREG(PIRE0_EL2, PIRE0_EL1); + MAPPED_EL2_SYSREG(POR_EL2, POR_EL1); + MAPPED_EL2_SYSREG(AMAIR_EL2, AMAIR_EL1); + MAPPED_EL2_SYSREG(ELR_EL2, ELR_EL1); + MAPPED_EL2_SYSREG(SPSR_EL2, SPSR_EL1); + MAPPED_EL2_SYSREG(ZCR_EL2, ZCR_EL1); + MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1); + MAPPED_EL2_SYSREG(SCTLR2_EL2, SCTLR2_EL1); + MAPPED_EL2_SYSREG(CNTHCTL_EL2, CNTKCTL_EL1); + case SYS_SP_EL1: + if (!vcpu_has_el2(vcpu)) + return ARM64_CORE_REG(sp_el1); + + alias = SYS_SP_EL2; + break; + default: + BUILD_BUG(); + } + + return KVM_ARM64_SYS_REG(alias); +} + +void kvm_get_default_vcpu_target(struct kvm_vm *vm, struct kvm_vcpu_init *init); + +static inline unsigned int get_current_el(void) +{ + return (read_sysreg(CurrentEL) >> 2) & 0x3; +} + +#define do_smccc(...) \ +do { \ + if (get_current_el() == 2) \ + smccc_smc(__VA_ARGS__); \ + else \ + smccc_hvc(__VA_ARGS__); \ +} while (0) + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h index c481d0c00a5d..688beccc9436 100644 --- a/tools/testing/selftests/kvm/include/arm64/vgic.h +++ b/tools/testing/selftests/kvm/include/arm64/vgic.h @@ -16,6 +16,9 @@ ((uint64_t)(flags) << 12) | \ index) +bool kvm_supports_vgic_v3(void); +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); +void __vgic_v3_init(int fd); int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); #define VGIC_MAX_RESERVED 1023 diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 652ac01e1adc..26cc30290e76 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -64,6 +64,9 @@ struct kvm_vcpu { #ifdef __x86_64__ struct kvm_cpuid2 *cpuid; #endif +#ifdef __aarch64__ + struct kvm_vcpu_init init; +#endif struct kvm_binary_stats stats; struct kvm_dirty_gfn *dirty_gfns; uint32_t fetch_index; @@ -1262,7 +1265,9 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) */ void kvm_selftest_arch_init(void); -void kvm_arch_vm_post_create(struct kvm_vm *vm); +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus); +void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm); +void kvm_arch_vm_release(struct kvm_vm *vm); bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index 162f303d9daa..e58282488beb 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -9,6 +9,7 @@ #include <linux/stringify.h> #include <asm/csr.h> +#include <asm/vdso/processor.h> #include "kvm_util.h" #define INSN_OPCODE_MASK 0x007c diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c index 9d69904cb608..369a4c87dd8f 100644 --- a/tools/testing/selftests/kvm/lib/arm64/processor.c +++ b/tools/testing/selftests/kvm/lib/arm64/processor.c @@ -12,6 +12,7 @@ #include "kvm_util.h" #include "processor.h" #include "ucall_common.h" +#include "vgic.h" #include <linux/bitfield.h> #include <linux/sizes.h> @@ -185,7 +186,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) _virt_pg_map(vm, vaddr, paddr, attr_idx); } -uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) +uint64_t *virt_get_pte_hva_at_level(struct kvm_vm *vm, vm_vaddr_t gva, int level) { uint64_t *ptep; @@ -195,17 +196,23 @@ uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8; if (!ptep) goto unmapped_gva; + if (level == 0) + return ptep; switch (vm->pgtable_levels) { case 4: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8; if (!ptep) goto unmapped_gva; + if (level == 1) + break; /* fall through */ case 3: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8; if (!ptep) goto unmapped_gva; + if (level == 2) + break; /* fall through */ case 2: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8; @@ -223,6 +230,11 @@ unmapped_gva: exit(EXIT_FAILURE); } +uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva) +{ + return virt_get_pte_hva_at_level(vm, gva, 3); +} + vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint64_t *ptep = virt_get_pte_hva(vm, gva); @@ -266,31 +278,49 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } +bool vm_supports_el2(struct kvm_vm *vm) +{ + const char *value = getenv("NV"); + + if (value && *value == '0') + return false; + + return vm_check_cap(vm, KVM_CAP_ARM_EL2) && vm->arch.has_gic; +} + +void kvm_get_default_vcpu_target(struct kvm_vm *vm, struct kvm_vcpu_init *init) +{ + struct kvm_vcpu_init preferred = {}; + + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &preferred); + if (vm_supports_el2(vm)) + preferred.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2); + + *init = preferred; +} + void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; struct kvm_vm *vm = vcpu->vm; uint64_t sctlr_el1, tcr_el1, ttbr0_el1; - if (!init) + if (!init) { + kvm_get_default_vcpu_target(vm, &default_init); init = &default_init; - - if (init->target == -1) { - struct kvm_vcpu_init preferred; - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &preferred); - init->target = preferred.target; } vcpu_ioctl(vcpu, KVM_ARM_VCPU_INIT, init); + vcpu->init = *init; /* * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15 * registers, which the variable argument list macros do. */ - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_CPACR_EL1), 3 << 20); - sctlr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1)); - tcr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1)); + sctlr_el1 = vcpu_get_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SCTLR_EL1)); + tcr_el1 = vcpu_get_reg(vcpu, ctxt_reg_alias(vcpu, SYS_TCR_EL1)); /* Configure base granule size */ switch (vm->mode) { @@ -357,11 +387,17 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) if (use_lpa2_pte_format(vm)) tcr_el1 |= TCR_DS; - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), ttbr0_el1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SCTLR_EL1), sctlr_el1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_TCR_EL1), tcr_el1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_MAIR_EL1), DEFAULT_MAIR_EL1); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_TTBR0_EL1), ttbr0_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpu->id); + + if (!vcpu_has_el2(vcpu)) + return; + + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_HCR_EL2), + HCR_EL2_RW | HCR_EL2_TGE | HCR_EL2_E2H); } void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) @@ -395,7 +431,7 @@ static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, aarch64_vcpu_setup(vcpu, init); - vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_SP_EL1), stack_vaddr + stack_size); return vcpu; } @@ -465,7 +501,7 @@ void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) { extern char vectors; - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors); + vcpu_set_reg(vcpu, ctxt_reg_alias(vcpu, SYS_VBAR_EL1), (uint64_t)&vectors); } void route_exception(struct ex_regs *regs, int vector) @@ -573,15 +609,15 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd)); - gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val); + gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN4, val); *ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI, ID_AA64MMFR0_EL1_TGRAN4_52_BIT); - gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val); + gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN64, val); *ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI, ID_AA64MMFR0_EL1_TGRAN64_IMP); - gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val); + gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN16, val); *ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI, ID_AA64MMFR0_EL1_TGRAN16_52_BIT); @@ -653,3 +689,39 @@ void wfi(void) { asm volatile("wfi"); } + +static bool request_mte; +static bool request_vgic = true; + +void test_wants_mte(void) +{ + request_mte = true; +} + +void test_disable_default_vgic(void) +{ + request_vgic = false; +} + +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) +{ + if (request_mte && vm_check_cap(vm, KVM_CAP_ARM_MTE)) + vm_enable_cap(vm, KVM_CAP_ARM_MTE, 0); + + if (request_vgic && kvm_supports_vgic_v3()) { + vm->arch.gic_fd = __vgic_v3_setup(vm, nr_vcpus, 64); + vm->arch.has_gic = true; + } +} + +void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm) +{ + if (vm->arch.has_gic) + __vgic_v3_init(vm->arch.gic_fd); +} + +void kvm_arch_vm_release(struct kvm_vm *vm) +{ + if (vm->arch.has_gic) + close(vm->arch.gic_fd); +} diff --git a/tools/testing/selftests/kvm/lib/arm64/vgic.c b/tools/testing/selftests/kvm/lib/arm64/vgic.c index 4427f43f73ea..d0f7bd0984b8 100644 --- a/tools/testing/selftests/kvm/lib/arm64/vgic.c +++ b/tools/testing/selftests/kvm/lib/arm64/vgic.c @@ -15,6 +15,17 @@ #include "gic.h" #include "gic_v3.h" +bool kvm_supports_vgic_v3(void) +{ + struct kvm_vm *vm = vm_create_barebones(); + int r; + + r = __kvm_test_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); + kvm_vm_free(vm); + + return !r; +} + /* * vGIC-v3 default host setup * @@ -30,24 +41,11 @@ * redistributor regions of the guest. Since it depends on the number of * vCPUs for the VM, it must be called after all the vCPUs have been created. */ -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) { int gic_fd; uint64_t attr; - struct list_head *iter; - unsigned int nr_gic_pages, nr_vcpus_created = 0; - - TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty"); - - /* - * Make sure that the caller is infact calling this - * function after all the vCPUs are added. - */ - list_for_each(iter, &vm->vcpus) - nr_vcpus_created++; - TEST_ASSERT(nr_vcpus == nr_vcpus_created, - "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)", - nr_vcpus, nr_vcpus_created); + unsigned int nr_gic_pages; /* Distributor setup */ gic_fd = __kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); @@ -56,9 +54,6 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, 0, &nr_irqs); - kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, - KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); - attr = GICD_BASE_GPA; kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST, &attr); @@ -73,10 +68,39 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) KVM_VGIC_V3_REDIST_SIZE * nr_vcpus); virt_map(vm, GICR_BASE_GPA, GICR_BASE_GPA, nr_gic_pages); - kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + return gic_fd; +} + +void __vgic_v3_init(int fd) +{ + kvm_device_attr_set(fd, KVM_DEV_ARM_VGIC_GRP_CTRL, KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); +} - return gic_fd; +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs) +{ + unsigned int nr_vcpus_created = 0; + struct list_head *iter; + int fd; + + TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty"); + + /* + * Make sure that the caller is infact calling this + * function after all the vCPUs are added. + */ + list_for_each(iter, &vm->vcpus) + nr_vcpus_created++; + TEST_ASSERT(nr_vcpus == nr_vcpus_created, + "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)", + nr_vcpus, nr_vcpus_created); + + fd = __vgic_v3_setup(vm, nr_vcpus, nr_irqs); + if (fd < 0) + return fd; + + __vgic_v3_init(fd); + return fd; } /* should only work for level sensitive interrupts */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 98cb8073c82b..6743fbd9bd67 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -487,7 +487,7 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, guest_rng = new_guest_random_state(guest_random_seed); sync_global_to_guest(vm, guest_rng); - kvm_arch_vm_post_create(vm); + kvm_arch_vm_post_create(vm, nr_runnable_vcpus); return vm; } @@ -525,6 +525,7 @@ struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, for (i = 0; i < nr_vcpus; ++i) vcpus[i] = vm_vcpu_add(vm, i, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } @@ -775,6 +776,8 @@ void kvm_vm_release(struct kvm_vm *vmp) /* Free cached stats metadata and close FD */ kvm_stats_release(&vmp->stats); + + kvm_arch_vm_release(vmp); } static void __vm_mem_region_delete(struct kvm_vm *vm, @@ -2300,7 +2303,15 @@ void kvm_get_stat(struct kvm_binary_stats *stats, const char *name, TEST_FAIL("Unable to find stat '%s'", name); } -__weak void kvm_arch_vm_post_create(struct kvm_vm *vm) +__weak void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) +{ +} + +__weak void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm) +{ +} + +__weak void kvm_arch_vm_release(struct kvm_vm *vm) { } diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index 33b0c436b006..c748cd9b2eef 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -659,7 +659,7 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) REPORT_GUEST_ASSERT(uc); } -void kvm_arch_vm_post_create(struct kvm_vm *vm) +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) { int r; diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index c81a84990eab..3cdfa3b19b85 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -22,6 +22,7 @@ #include "processor.h" #include "test_util.h" #include "guest_modes.h" +#include "ucall_common.h" #define DUMMY_MEMSLOT_INDEX 7 diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e3711beff7f3..5087d082c4b0 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -25,6 +25,7 @@ #include <test_util.h> #include <kvm_util.h> #include <processor.h> +#include <ucall_common.h> #define MEM_EXTRA_SIZE SZ_64K diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index a0b7dabb5040..705ab3d7778b 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -80,9 +80,11 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZCF: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZCMOP: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFBFMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOP: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICCRSE: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR: @@ -103,6 +105,8 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZTSO: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFBFMIN: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFBFWMA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB: @@ -128,6 +132,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SUSP: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR: return true; @@ -255,6 +260,8 @@ static const char *config_id_to_str(const char *prefix, __u64 id) return "KVM_REG_RISCV_CONFIG_REG(zicbom_block_size)"; case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): return "KVM_REG_RISCV_CONFIG_REG(zicboz_block_size)"; + case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size): + return "KVM_REG_RISCV_CONFIG_REG(zicbop_block_size)"; case KVM_REG_RISCV_CONFIG_REG(mvendorid): return "KVM_REG_RISCV_CONFIG_REG(mvendorid)"; case KVM_REG_RISCV_CONFIG_REG(marchid): @@ -532,9 +539,11 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZCF), KVM_ISA_EXT_ARR(ZCMOP), KVM_ISA_EXT_ARR(ZFA), + KVM_ISA_EXT_ARR(ZFBFMIN), KVM_ISA_EXT_ARR(ZFH), KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), + KVM_ISA_EXT_ARR(ZICBOP), KVM_ISA_EXT_ARR(ZICBOZ), KVM_ISA_EXT_ARR(ZICCRSE), KVM_ISA_EXT_ARR(ZICNTR), @@ -555,6 +564,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZTSO), KVM_ISA_EXT_ARR(ZVBB), KVM_ISA_EXT_ARR(ZVBC), + KVM_ISA_EXT_ARR(ZVFBFMIN), + KVM_ISA_EXT_ARR(ZVFBFWMA), KVM_ISA_EXT_ARR(ZVFH), KVM_ISA_EXT_ARR(ZVFHMIN), KVM_ISA_EXT_ARR(ZVKB), @@ -627,6 +638,7 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off) KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SUSP), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_FWFT), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR), }; @@ -683,6 +695,19 @@ static const char *sbi_sta_id_to_str(__u64 reg_off) return strdup_printf("KVM_REG_RISCV_SBI_STA | %lld /* UNKNOWN */", reg_off); } +static const char *sbi_fwft_id_to_str(__u64 reg_off) +{ + switch (reg_off) { + case 0: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.enable)"; + case 1: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.flags)"; + case 2: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.value)"; + case 3: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.enable)"; + case 4: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.flags)"; + case 5: return "KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.value)"; + } + return strdup_printf("KVM_REG_RISCV_SBI_FWFT | %lld /* UNKNOWN */", reg_off); +} + static const char *sbi_id_to_str(const char *prefix, __u64 id) { __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_STATE); @@ -695,6 +720,8 @@ static const char *sbi_id_to_str(const char *prefix, __u64 id) switch (reg_subtype) { case KVM_REG_RISCV_SBI_STA: return sbi_sta_id_to_str(reg_off); + case KVM_REG_RISCV_SBI_FWFT: + return sbi_fwft_id_to_str(reg_off); } return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off); @@ -780,10 +807,13 @@ void print_reg(const char *prefix, __u64 id) */ static __u64 base_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(isa), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mvendorid), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(marchid), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(mimpid), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(satp_mode), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbop_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.pc), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.ra), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CORE | KVM_REG_RISCV_CORE_REG(regs.sp), @@ -859,11 +889,26 @@ static __u64 sbi_sta_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi), }; +static __u64 sbi_fwft_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.enable), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.flags), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(misaligned_deleg.value), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.enable), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.flags), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_FWFT | KVM_REG_RISCV_SBI_FWFT_REG(pointer_masking.value), +}; + static __u64 zicbom_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM, }; +static __u64 zicbop_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbop_block_size), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOP, +}; + static __u64 zicboz_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ, @@ -1010,8 +1055,13 @@ static __u64 vector_regs[] = { #define SUBLIST_SBI_STA \ {"sbi-sta", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_STA, \ .regs = sbi_sta_regs, .regs_n = ARRAY_SIZE(sbi_sta_regs),} +#define SUBLIST_SBI_FWFT \ + {"sbi-fwft", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_FWFT, \ + .regs = sbi_fwft_regs, .regs_n = ARRAY_SIZE(sbi_fwft_regs),} #define SUBLIST_ZICBOM \ {"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),} +#define SUBLIST_ZICBOP \ + {"zicbop", .feature = KVM_RISCV_ISA_EXT_ZICBOP, .regs = zicbop_regs, .regs_n = ARRAY_SIZE(zicbop_regs),} #define SUBLIST_ZICBOZ \ {"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),} #define SUBLIST_AIA \ @@ -1092,6 +1142,7 @@ KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA); KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU); KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN); KVM_SBI_EXT_SIMPLE_CONFIG(susp, SUSP); +KVM_SBI_EXT_SUBLIST_CONFIG(fwft, FWFT); KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA); KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); @@ -1127,9 +1178,11 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zcd, ZCD); KVM_ISA_EXT_SIMPLE_CONFIG(zcf, ZCF); KVM_ISA_EXT_SIMPLE_CONFIG(zcmop, ZCMOP); KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA); +KVM_ISA_EXT_SIMPLE_CONFIG(zfbfmin, ZFBFMIN); KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH); KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN); KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM); +KVM_ISA_EXT_SUBLIST_CONFIG(zicbop, ZICBOP); KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ); KVM_ISA_EXT_SIMPLE_CONFIG(ziccrse, ZICCRSE); KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR); @@ -1150,6 +1203,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT); KVM_ISA_EXT_SIMPLE_CONFIG(ztso, ZTSO); KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB); KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC); +KVM_ISA_EXT_SIMPLE_CONFIG(zvfbfmin, ZVFBFMIN); +KVM_ISA_EXT_SIMPLE_CONFIG(zvfbfwma, ZVFBFWMA); KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH); KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN); KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB); @@ -1167,6 +1222,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_sbi_pmu, &config_sbi_dbcn, &config_sbi_susp, + &config_sbi_fwft, &config_aia, &config_fp_f, &config_fp_d, @@ -1201,9 +1257,11 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_zcf, &config_zcmop, &config_zfa, + &config_zfbfmin, &config_zfh, &config_zfhmin, &config_zicbom, + &config_zicbop, &config_zicboz, &config_ziccrse, &config_zicntr, @@ -1224,6 +1282,8 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_ztso, &config_zvbb, &config_zvbc, + &config_zvfbfmin, + &config_zvfbfwma, &config_zvfh, &config_zvfhmin, &config_zvkb, diff --git a/tools/testing/selftests/kvm/s390/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c index 85cc8c18d6e7..e39a724fe860 100644 --- a/tools/testing/selftests/kvm/s390/cmma_test.c +++ b/tools/testing/selftests/kvm/s390/cmma_test.c @@ -145,7 +145,7 @@ static void finish_vm_setup(struct kvm_vm *vm) slot0 = memslot2region(vm, 0); ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size); - kvm_arch_vm_post_create(vm); + kvm_arch_vm_post_create(vm, 0); } static struct kvm_vm *create_vm_two_memslots(void) diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index cce2520af720..8edc1fca345b 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -118,7 +118,7 @@ static int64_t smccc(uint32_t func, uint64_t arg) { struct arm_smccc_res res; - smccc_hvc(func, arg, 0, 0, 0, 0, 0, 0, &res); + do_smccc(func, arg, 0, 0, 0, 0, 0, 0, &res); return res.a0; } diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index d30625c18259..c744c603d688 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1554,8 +1554,8 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc) } /* Read from the page to populate the shared zeropage. */ - FORCE_READ(mem); - FORCE_READ(smem); + FORCE_READ(*mem); + FORCE_READ(*smem); fn(mem, smem, pagesize); munmap: diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index b0d42eb04e3a..8dd81c0a4a5a 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -145,7 +145,7 @@ static bool try_access_buf(char *ptr, bool write) if (write) *ptr = 'x'; else - FORCE_READ(ptr); + FORCE_READ(*ptr); } signal_jump_set = false; diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 1afe14b9dc0c..c5940c0595be 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -50,8 +50,10 @@ void read_fault_pages(void *addr, unsigned long nr_pages) unsigned long i; for (i = 0; i < nr_pages; i++) { + unsigned long *addr2 = + ((unsigned long *)(addr + (i * huge_page_size))); /* Prevent the compiler from optimizing out the entire loop: */ - FORCE_READ(((unsigned long *)(addr + (i * huge_page_size)))); + FORCE_READ(*addr2); } } diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index c5a73617796a..ea945eebec2f 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -110,7 +110,7 @@ void *access_mem(void *ptr) * the memory access actually happens and prevents the compiler * from optimizing away this entire loop. */ - FORCE_READ((uint64_t *)ptr); + FORCE_READ(*(uint64_t *)ptr); } return NULL; diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index fccf9e797a0c..5bd52a951cbd 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -5,10 +5,14 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> +#include <linux/userfaultfd.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <sys/ioctl.h> #include <sys/mman.h> +#include <syscall.h> #include <time.h> #include <stdbool.h> @@ -168,6 +172,7 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start, if (first_val <= start && second_val >= end) { success = true; + fflush(maps_fp); break; } } @@ -175,6 +180,15 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start, return success; } +/* Check if [ptr, ptr + size) mapped in /proc/self/maps. */ +static bool is_ptr_mapped(FILE *maps_fp, void *ptr, unsigned long size) +{ + unsigned long start = (unsigned long)ptr; + unsigned long end = start + size; + + return is_range_mapped(maps_fp, start, end); +} + /* * Returns the start address of the mapping on success, else returns * NULL on failure. @@ -733,6 +747,249 @@ out: dont_unmap ? " [dontunnmap]" : ""); } +#ifdef __NR_userfaultfd +static void mremap_move_multi_invalid_vmas(FILE *maps_fp, + unsigned long page_size) +{ + char *test_name = "mremap move multiple invalid vmas"; + const size_t size = 10 * page_size; + bool success = true; + char *ptr, *tgt_ptr; + int uffd, err, i; + void *res; + struct uffdio_api api = { + .api = UFFD_API, + .features = UFFD_EVENT_PAGEFAULT, + }; + + uffd = syscall(__NR_userfaultfd, O_NONBLOCK); + if (uffd == -1) { + err = errno; + perror("userfaultfd"); + if (err == EPERM) { + ksft_test_result_skip("%s - missing uffd", test_name); + return; + } + success = false; + goto out; + } + if (ioctl(uffd, UFFDIO_API, &api)) { + perror("ioctl UFFDIO_API"); + success = false; + goto out_close_uffd; + } + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_close_uffd; + } + + tgt_ptr = mmap(NULL, size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0); + if (tgt_ptr == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_close_uffd; + } + if (munmap(tgt_ptr, size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + + /* + * Unmap so we end up with: + * + * 0 2 4 6 8 10 offset in buffer + * |*| |*| |*| |*| |*| + * |*| |*| |*| |*| |*| + * + * Additionally, register each with UFFD. + */ + for (i = 0; i < 10; i += 2) { + void *unmap_ptr = &ptr[(i + 1) * page_size]; + unsigned long start = (unsigned long)&ptr[i * page_size]; + struct uffdio_register reg = { + .range = { + .start = start, + .len = page_size, + }, + .mode = UFFDIO_REGISTER_MODE_MISSING, + }; + + if (ioctl(uffd, UFFDIO_REGISTER, ®) == -1) { + perror("ioctl UFFDIO_REGISTER"); + success = false; + goto out_unmap; + } + if (munmap(unmap_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + } + + /* + * Now try to move the entire range which is invalid for multi VMA move. + * + * This will fail, and no VMA should be moved, as we check this ahead of + * time. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mrmeap() unexpected error"); + success = false; + goto out_unmap; + } + if (is_ptr_mapped(maps_fp, tgt_ptr, page_size)) { + fprintf(stderr, + "Invalid uffd-armed VMA at start of multi range moved\n"); + success = false; + goto out_unmap; + } + + /* + * Now try to move a single VMA, this should succeed as not multi VMA + * move. + */ + res = mremap(ptr, page_size, page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + if (res == MAP_FAILED) { + perror("mremap single invalid-multi VMA"); + success = false; + goto out_unmap; + } + + /* + * Unmap the VMA, and remap a non-uffd registered (therefore, multi VMA + * move valid) VMA at the start of ptr range. + */ + if (munmap(tgt_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + res = mmap(ptr, page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + if (res == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_unmap; + } + + /* + * Now try to move the entire range, we should succeed in moving the + * first VMA, but no others, and report a failure. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mrmeap() unexpected error"); + success = false; + goto out_unmap; + } + if (!is_ptr_mapped(maps_fp, tgt_ptr, page_size)) { + fprintf(stderr, "Valid VMA not moved\n"); + success = false; + goto out_unmap; + } + + /* + * Unmap the VMA, and map valid VMA at start of ptr range, and replace + * all existing multi-move invalid VMAs, except the last, with valid + * multi-move VMAs. + */ + if (munmap(tgt_ptr, page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + if (munmap(ptr, size - 2 * page_size)) { + perror("munmap"); + success = false; + goto out_unmap; + } + for (i = 0; i < 8; i += 2) { + res = mmap(&ptr[i * page_size], page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + if (res == MAP_FAILED) { + perror("mmap"); + success = false; + goto out_unmap; + } + } + + /* + * Now try to move the entire range, we should succeed in moving all but + * the last VMA, and report a failure. + */ + res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr); + err = errno; + if (res != MAP_FAILED) { + fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n"); + success = false; + goto out_unmap; + } + if (err != EFAULT) { + errno = err; + perror("mrmeap() unexpected error"); + success = false; + goto out_unmap; + } + + for (i = 0; i < 10; i += 2) { + bool is_mapped = is_ptr_mapped(maps_fp, + &tgt_ptr[i * page_size], page_size); + + if (i < 8 && !is_mapped) { + fprintf(stderr, "Valid VMA not moved at %d\n", i); + success = false; + goto out_unmap; + } else if (i == 8 && is_mapped) { + fprintf(stderr, "Invalid VMA moved at %d\n", i); + success = false; + goto out_unmap; + } + } + +out_unmap: + if (munmap(tgt_ptr, size)) + perror("munmap tgt"); + if (munmap(ptr, size)) + perror("munmap src"); +out_close_uffd: + close(uffd); +out: + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} +#else +static void mremap_move_multi_invalid_vmas(FILE *maps_fp, unsigned long page_size) +{ + char *test_name = "mremap move multiple invalid vmas"; + + ksft_test_result_skip("%s - missing uffd", test_name); +} +#endif /* __NR_userfaultfd */ + /* Returns the time taken for the remap on success else returns -1. */ static long long remap_region(struct config c, unsigned int threshold_mb, char *rand_addr) @@ -1074,7 +1331,7 @@ int main(int argc, char **argv) char *rand_addr; size_t rand_size; int num_expand_tests = 2; - int num_misc_tests = 8; + int num_misc_tests = 9; struct test test_cases[MAX_TEST] = {}; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; @@ -1197,8 +1454,6 @@ int main(int argc, char **argv) mremap_expand_merge(maps_fp, page_size); mremap_expand_merge_offset(maps_fp, page_size); - fclose(maps_fp); - mremap_move_within_range(pattern_seed, rand_addr); mremap_move_1mb_from_start(pattern_seed, rand_addr); mremap_shrink_multiple_vmas(page_size, /* inplace= */true); @@ -1207,6 +1462,9 @@ int main(int argc, char **argv) mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ true); mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ false); mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ true); + mremap_move_multi_invalid_vmas(maps_fp, page_size); + + fclose(maps_fp); if (run_perf_tests) { ksft_print_msg("\n%s\n", diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 0d4209eef0c3..e6face7c0166 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1525,7 +1525,7 @@ void zeropfn_tests(void) ret = madvise(mem, hpage_size, MADV_HUGEPAGE); if (!ret) { - FORCE_READ(mem); + FORCE_READ(*mem); ret = pagemap_ioctl(mem, hpage_size, &vec, 1, 0, 0, PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO); diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 05de1fc0005b..44a3f8a58806 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -439,8 +439,11 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, } madvise(*addr, fd_size, MADV_HUGEPAGE); - for (size_t i = 0; i < fd_size; i++) - FORCE_READ((*addr + i)); + for (size_t i = 0; i < fd_size; i++) { + char *addr2 = *addr + i; + + FORCE_READ(*addr2); + } if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) { ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n"); diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index c20298ae98ea..b55d1809debc 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -23,7 +23,7 @@ * anything with it in order to trigger a read page fault. We therefore must use * volatile to stop the compiler from optimising this away. */ -#define FORCE_READ(x) (*(volatile typeof(x) *)x) +#define FORCE_READ(x) (*(const volatile typeof(x) *)&(x)) extern unsigned int __page_size; extern unsigned int __page_shift; diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index b1e4618399be..a688871a98eb 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -107,6 +107,26 @@ #endif #endif +#ifndef __NR_open_tree_attr + #if defined __alpha__ + #define __NR_open_tree_attr 577 + #elif defined _MIPS_SIM + #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ + #define __NR_open_tree_attr (467 + 4000) + #endif + #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ + #define __NR_open_tree_attr (467 + 6000) + #endif + #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ + #define __NR_open_tree_attr (467 + 5000) + #endif + #elif defined __ia64__ + #define __NR_open_tree_attr (467 + 1024) + #else + #define __NR_open_tree_attr 467 + #endif +#endif + #ifndef MOUNT_ATTR_IDMAP #define MOUNT_ATTR_IDMAP 0x00100000 #endif @@ -121,6 +141,12 @@ static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flag return syscall(__NR_mount_setattr, dfd, path, flags, attr, size); } +static inline int sys_open_tree_attr(int dfd, const char *path, unsigned int flags, + struct mount_attr *attr, size_t size) +{ + return syscall(__NR_open_tree_attr, dfd, path, flags, attr, size); +} + static ssize_t write_nointr(int fd, const void *buf, size_t count) { ssize_t ret; @@ -1222,6 +1248,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace) attr.userns_fd = get_userns_fd(0, 10000, 10000); ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } @@ -1255,6 +1287,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace) ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } @@ -1321,6 +1359,19 @@ TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace) ASSERT_EQ(close(open_tree_fd), 0); } +static bool expected_uid_gid(int dfd, const char *path, int flags, + uid_t expected_uid, gid_t expected_gid) +{ + int ret; + struct stat st; + + ret = fstatat(dfd, path, &st, flags); + if (ret < 0) + return false; + + return st.st_uid == expected_uid && st.st_gid == expected_gid; +} + /** * Validate that currently changing the idmapping of an idmapped mount fails. */ @@ -1331,6 +1382,8 @@ TEST_F(mount_setattr_idmapped, change_idmapping) .attr_set = MOUNT_ATTR_IDMAP, }; + ASSERT_TRUE(expected_uid_gid(-EBADF, "/mnt/D", 0, 0, 0)); + if (!mount_setattr_supported()) SKIP(return, "mount_setattr syscall not supported"); @@ -1348,27 +1401,25 @@ TEST_F(mount_setattr_idmapped, change_idmapping) AT_EMPTY_PATH, &attr, sizeof(attr)), 0); ASSERT_EQ(close(attr.userns_fd), 0); + EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 0, 0)); + EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000)); + /* Change idmapping on a detached mount that is already idmapped. */ attr.userns_fd = get_userns_fd(0, 20000, 10000); ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + EXPECT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 20000, 20000)); + EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000)); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } -static bool expected_uid_gid(int dfd, const char *path, int flags, - uid_t expected_uid, gid_t expected_gid) -{ - int ret; - struct stat st; - - ret = fstatat(dfd, path, &st, flags); - if (ret < 0) - return false; - - return st.st_uid == expected_uid && st.st_gid == expected_gid; -} - TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) { int open_tree_fd = -EBADF; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b31a71f2b372..2b31d4a93ad7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -99,6 +99,7 @@ TEST_GEN_PROGS += bind_wildcard TEST_GEN_PROGS += bind_timewait TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh +TEST_PROGS += test_vxlan_nh.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += test_neigh.sh @@ -115,6 +116,7 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += broadcast_ether_dst.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c index 57ff67a3751e..da04b0b19b73 100644 --- a/tools/testing/selftests/net/bind_bhash.c +++ b/tools/testing/selftests/net/bind_bhash.c @@ -75,7 +75,7 @@ static void *setup(void *arg) int *array = (int *)arg; for (i = 0; i < MAX_CONNECTIONS; i++) { - sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr); + sock_fd = bind_socket(SO_REUSEPORT, setup_addr); if (sock_fd < 0) { ret = sock_fd; pthread_exit(&ret); @@ -103,7 +103,7 @@ int main(int argc, const char *argv[]) setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4; - listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr); + listener_fd = bind_socket(SO_REUSEPORT, setup_addr); if (listen(listener_fd, 100) < 0) { perror("listen failed"); return -1; diff --git a/tools/testing/selftests/net/broadcast_ether_dst.sh b/tools/testing/selftests/net/broadcast_ether_dst.sh new file mode 100755 index 000000000000..334a7eca8a80 --- /dev/null +++ b/tools/testing/selftests/net/broadcast_ether_dst.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Author: Brett A C Sheffield <bacs@librecast.net> +# Author: Oscar Maes <oscmaes92@gmail.com> +# +# Ensure destination ethernet field is correctly set for +# broadcast packets + +source lib.sh + +CLIENT_IP4="192.168.0.1" +GW_IP4="192.168.0.2" + +setup() { + setup_ns CLIENT_NS SERVER_NS + + ip -net "${SERVER_NS}" link add link1 type veth \ + peer name link0 netns "${CLIENT_NS}" + + ip -net "${CLIENT_NS}" link set link0 up + ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}"/24 dev link0 + + ip -net "${SERVER_NS}" link set link1 up + + ip -net "${CLIENT_NS}" route add default via "${GW_IP4}" + ip netns exec "${CLIENT_NS}" arp -s "${GW_IP4}" 00:11:22:33:44:55 +} + +cleanup() { + rm -f "${CAPFILE}" "${OUTPUT}" + ip -net "${SERVER_NS}" link del link1 + cleanup_ns "${CLIENT_NS}" "${SERVER_NS}" +} + +test_broadcast_ether_dst() { + local rc=0 + CAPFILE=$(mktemp -u cap.XXXXXXXXXX) + OUTPUT=$(mktemp -u out.XXXXXXXXXX) + + echo "Testing ethernet broadcast destination" + + # start tcpdump listening for icmp + # tcpdump will exit after receiving a single packet + # timeout will kill tcpdump if it is still running after 2s + timeout 2s ip netns exec "${CLIENT_NS}" \ + tcpdump -i link0 -c 1 -w "${CAPFILE}" icmp &> "${OUTPUT}" & + pid=$! + slowwait 1 grep -qs "listening" "${OUTPUT}" + + # send broadcast ping + ip netns exec "${CLIENT_NS}" \ + ping -W0.01 -c1 -b 255.255.255.255 &> /dev/null + + # wait for tcpdump for exit after receiving packet + wait "${pid}" + + # compare ethernet destination field to ff:ff:ff:ff:ff:ff + ether_dst=$(tcpdump -r "${CAPFILE}" -tnne 2>/dev/null | \ + awk '{sub(/,/,"",$3); print $3}') + if [[ "${ether_dst}" == "ff:ff:ff:ff:ff:ff" ]]; then + echo "[ OK ]" + rc="${ksft_pass}" + else + echo "[FAIL] expected dst ether addr to be ff:ff:ff:ff:ff:ff," \ + "got ${ether_dst}" + rc="${ksft_fail}" + fi + + return "${rc}" +} + +if [ ! -x "$(command -v tcpdump)" ]; then + echo "SKIP: Could not run test without tcpdump tool" + exit "${ksft_skip}" +fi + +trap cleanup EXIT + +setup +test_broadcast_ether_dst + +exit $? diff --git a/tools/testing/selftests/net/can/config b/tools/testing/selftests/net/can/config new file mode 100644 index 000000000000..188f79796670 --- /dev/null +++ b/tools/testing/selftests/net/can/config @@ -0,0 +1,3 @@ +CONFIG_CAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_VCAN=m diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index b98ea9449b8b..dfb6646cb97b 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -18,6 +18,8 @@ # | 2001:db8:1::1/64 2001:db8:2::1/64 | # | | # +-----------------------------------------------------------------+ +# +#shellcheck disable=SC2034 # SC doesn't see our uses of global variables ALL_TESTS=" ping_ipv4 @@ -27,6 +29,7 @@ ALL_TESTS=" ipv4_sip_equal_dip ipv6_sip_equal_dip ipv4_dip_link_local + ipv4_sip_link_local " NUM_NETIFS=4 @@ -330,6 +333,32 @@ ipv4_dip_link_local() tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower } +ipv4_sip_link_local() +{ + local sip=169.254.1.1 + + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf."$rp1".rp_filter 0 + + tc filter add dev "$rp2" egress protocol ip pref 1 handle 101 \ + flower src_ip "$sip" action pass + + $MZ "$h1" -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b "$rp1mac" \ + -A "$sip" -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "IPv4 source IP is link-local" + + tc filter del dev "$rp2" egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf."$rp1".rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 7a3cb4c09e45..d847ff1737c3 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -28,7 +28,7 @@ flush_pids() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index ac1349c4b9e5..b148cadb96d0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; @@ -1092,6 +1093,7 @@ int main_loop_s(int listensock) struct pollfd polls; socklen_t salen; int remotesock; + int err = 0; int fd = 0; again: @@ -1124,7 +1126,7 @@ again: SOCK_TEST_TCPULP(remotesock, 0); memset(&winfo, 0, sizeof(winfo)); - copyfd_io(fd, remotesock, 1, true, &winfo); + err = copyfd_io(fd, remotesock, 1, true, &winfo); } else { perror("accept"); return 1; @@ -1133,10 +1135,10 @@ again: if (cfg_input) close(fd); - if (--cfg_repeat > 0) + if (!err && --cfg_repeat > 0) goto again; - return 0; + return err; } static void init_rng(void) @@ -1246,7 +1248,7 @@ void xdisconnect(int fd) else xerror("bad family"); - strcpy(cmd, "ss -M | grep -q "); + strcpy(cmd, "ss -Mnt | grep -q "); cmdlen = strlen(cmd); if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], sizeof(cmd) - cmdlen)) @@ -1256,7 +1258,7 @@ void xdisconnect(int fd) /* * wait until the pending data is completely flushed and all - * the MPTCP sockets reached the closed status. + * the sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 5e3c56253274..47ecb5b3836e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -134,7 +134,7 @@ ns4="" TEST_GROUP="" # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "$cin_disconnect" @@ -211,6 +211,11 @@ if $checksum; then done fi +if $capture; then + rndh="${ns1:4}" + mptcp_lib_pr_info "Packet capture files will have this prefix: ${rndh}-" +fi + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -361,7 +366,6 @@ do_transfer() if $capture; then local capuser - local rndh="${connector_ns:4}" if [ -z $SUDO_USER ] ; then capuser="" else diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 3cf1e2a612ce..f3bcaa48df8f 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index b8af65373b3a..7fd555b123b9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -8,7 +8,7 @@ # ShellCheck incorrectly believes that most of the code here is unreachable # because it's invoked by variable name, see how the "tests" array is used -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 . "$(dirname "${0}")/mptcp_lib.sh" @@ -3842,6 +3842,7 @@ endpoint_tests() # remove and re-add if reset_with_events "delete re-add signal" && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0 pm_nl_set_limits $ns1 0 3 pm_nl_set_limits $ns2 3 3 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 09cd24b2ae46..d62e653d48b0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -384,7 +384,7 @@ mptcp_lib_make_file() { mptcp_lib_print_file_err() { ls -l "${1}" 1>&2 echo "Trailing bytes are: " - tail -c 27 "${1}" + tail -c 32 "${1}" | od -x | head -n2 } # $1: input file ; $2: output file ; $3: what kind of file diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index 9934a68df237..112c07c4c37a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -162,9 +162,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; @@ -666,22 +667,26 @@ static void process_one_client(int fd, int pipefd) do_getsockopts(&s, fd, ret, ret2); if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) - xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64, + s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - (ret + 1)); /* be nice when running on top of older kernel */ if (s.pkt_stats_avail) { if (s.last_sample.mptcpi_bytes_sent != ret2) - xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_sent, ret2, s.last_sample.mptcpi_bytes_sent - ret2); if (s.last_sample.mptcpi_bytes_received != ret) - xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_received, ret, s.last_sample.mptcpi_bytes_received - ret); if (s.last_sample.mptcpi_bytes_acked != ret) - xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64, - s.last_sample.mptcpi_bytes_acked, ret2, - s.last_sample.mptcpi_bytes_acked - ret2); + xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, + s.last_sample.mptcpi_bytes_acked, ret, + s.last_sample.mptcpi_bytes_acked - ret); } close(fd); diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 418a903c3a4d..f01989be6e9b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -95,7 +95,7 @@ init() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}" diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 2e6648a2b2c0..ec6a87588191 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -32,7 +32,7 @@ ns1="" err=$(mktemp) # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "${err}" @@ -70,8 +70,9 @@ format_endpoints() { mptcp_lib_pm_nl_format_endpoints "${@}" } +# This function is invoked indirectly +#shellcheck disable=SC2317,SC2329 get_endpoint() { - # shellcheck disable=SC2317 # invoked indirectly mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}" } @@ -198,6 +199,7 @@ set_limits 1 9 2>/dev/null check "get_limits" "${default_limits}" "subflows above hard limit" set_limits 8 8 +flush_endpoint ## to make sure it doesn't affect the limits check "get_limits" "$(format_limits 8 8)" "set limits" flush_endpoint diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 994a556f46c1..93fea3442216 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -188,6 +188,13 @@ static int capture_events(int fd, int event_group) fprintf(stderr, ",error:%u", *(__u8 *)RTA_DATA(attrs)); else if (attrs->rta_type == MPTCP_ATTR_SERVER_SIDE) fprintf(stderr, ",server_side:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_FLAGS) { + __u16 flags = *(__u16 *)RTA_DATA(attrs); + + /* only print when present, easier */ + if (flags & MPTCP_PM_EV_FLAG_DENY_JOIN_ID0) + fprintf(stderr, ",deny_join_id0:1"); + } attrs = RTA_NEXT(attrs, msg_len); } diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 2329c2f8519b..1903e8e84a31 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -35,7 +35,7 @@ usage() { } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "$cout" "$sout" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 333064b0b5ac..3d45991f24ed 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -94,7 +94,7 @@ test_fail() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { print_title "Cleanup" @@ -201,6 +201,9 @@ make_connection() is_v6="v4" fi + # set this on the client side only: will not affect the rest + ip netns exec "$ns2" sysctl -q net.mptcp.allow_join_initial_addr_port=0 + :>"$client_evts" :>"$server_evts" @@ -223,23 +226,28 @@ make_connection() local client_token local client_port local client_serverside + local client_nojoin local server_token local server_serverside + local server_nojoin client_token=$(mptcp_lib_evts_get_info token "$client_evts") client_port=$(mptcp_lib_evts_get_info sport "$client_evts") client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts") + client_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$client_evts") server_token=$(mptcp_lib_evts_get_info token "$server_evts") server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts") + server_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$server_evts") print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1" - if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && - [ "$server_serverside" = 1 ] + if [ "${client_token}" != "" ] && [ "${server_token}" != "" ] && + [ "${client_serverside}" = 0 ] && [ "${server_serverside}" = 1 ] && + [ "${client_nojoin:-0}" = 0 ] && [ "${server_nojoin:-0}" = 1 ] then test_pass print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else - test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" + test_fail "Expected tokens (c:${client_token} - s:${server_token}), server (c:${client_serverside} - s:${server_serverside}), nojoin (c:${client_nojoin} - s:${server_nojoin})" mptcp_lib_result_print_all_tap exit ${KSFT_FAIL} fi diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 606a43a60f73..7fc6c5dbd551 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -99,7 +99,7 @@ run_one_clash_test() local entries local cre - if ! ip netns exec "$ns" ./udpclash $daddr $dport;then + if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then echo "INFO: did not receive expected number of replies for $daddr:$dport" ip netns exec "$ctns" conntrack -S # don't fail: check if clash resolution triggered after all. diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh index 788cd56ea4a0..615fe3c6f405 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh @@ -187,7 +187,7 @@ ct_udpclash() [ -x udpclash ] || return while [ $now -lt $end ]; do - ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 + ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 now=$(date +%s) done @@ -277,6 +277,7 @@ check_taint() insert_flood() { local n="$1" + local timeout="$2" local r=0 r=$((RANDOM%$insert_count)) @@ -302,7 +303,7 @@ test_floodresize_all() read tainted_then < /proc/sys/kernel/tainted for n in "$nsclient1" "$nsclient2";do - insert_flood "$n" & + insert_flood "$n" "$timeout" & done # resize table constantly while flood/insert/dump/flushs diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index a4ee5496f2a1..45832df98295 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -20,6 +20,7 @@ ret=0 SOCAT_TIMEOUT=60 nsin="" +nsin_small="" ns1out="" ns2out="" @@ -36,7 +37,7 @@ cleanup() { cleanup_all_ns - rm -f "$nsin" "$ns1out" "$ns2out" + rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out" [ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns" } @@ -72,6 +73,7 @@ lmtu=1500 rmtu=2000 filesize=$((2 * 1024 * 1024)) +filesize_small=$((filesize / 16)) usage(){ echo "nft_flowtable.sh [OPTIONS]" @@ -89,7 +91,10 @@ do o) omtu=$OPTARG;; l) lmtu=$OPTARG;; r) rmtu=$OPTARG;; - s) filesize=$OPTARG;; + s) + filesize=$OPTARG + filesize_small=$((OPTARG / 16)) + ;; *) usage;; esac done @@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then fi nsin=$(mktemp) +nsin_small=$(mktemp) ns1out=$(mktemp) ns2out=$(mktemp) @@ -265,6 +271,7 @@ check_counters() check_dscp() { local what=$1 + local pmtud="$2" local ok=1 local counter @@ -277,37 +284,39 @@ check_dscp() local pc4z=${counter%*bytes*} local pc4z=${pc4z#*packets} + local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected" + case "$what" in "dscp_none") if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_fwd") if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_ingress") if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_egress") if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; *) - echo "FAIL: Unknown DSCP check" 1>&2 + echo "$failmsg: Unknown DSCP check" 1>&2 ret=1 ok=0 esac @@ -319,9 +328,9 @@ check_dscp() check_transfer() { - in=$1 - out=$2 - what=$3 + local in=$1 + local out=$2 + local what=$3 if ! cmp "$in" "$out" > /dev/null 2>&1; then echo "FAIL: file mismatch for $what" 1>&2 @@ -342,25 +351,39 @@ test_tcp_forwarding_ip() { local nsa=$1 local nsb=$2 - local dstip=$3 - local dstport=$4 + local pmtu=$3 + local dstip=$4 + local dstport=$5 local lret=0 + local socatc + local socatl + local infile="$nsin" + + if [ $pmtu -eq 0 ]; then + infile="$nsin_small" + fi - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" & + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & lpid=$! busywait 1000 listener_ready - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out" + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" + socatc=$? wait $lpid + socatl=$? - if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then + if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then + rc=1 + fi + + if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then lret=1 ret=1 fi - if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then + if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then lret=1 ret=1 fi @@ -370,14 +393,16 @@ test_tcp_forwarding_ip() test_tcp_forwarding() { - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + local pmtu="$3" + + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 return $? } test_tcp_forwarding_set_dscp() { - check_dscp "dscp_none" + local pmtu="$3" ip netns exec "$nsr1" nft -f - <<EOF table netdev dscpmangle { @@ -388,8 +413,8 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_ingress" + test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345 + check_dscp "dscp_ingress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle else @@ -405,10 +430,10 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_egress" + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + check_dscp "dscp_egress" "$pmtu" - ip netns exec "$nsr1" nft flush table netdev dscpmangle + ip netns exec "$nsr1" nft delete table netdev dscpmangle else echo "SKIP: Could not load netdev:egress for veth1" fi @@ -416,48 +441,53 @@ fi # partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3 # counters should have seen packets (before and after ft offload kicks in). ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3 - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_fwd" + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + check_dscp "dscp_fwd" "$pmtu" } test_tcp_forwarding_nat() { + local nsa="$1" + local nsb="$2" + local pmtu="$3" + local what="$4" local lret - local pmtu - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - lret=$? + [ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)" - pmtu=$3 - what=$4 + test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345 + lret=$? if [ "$lret" -eq 0 ] ; then if [ "$pmtu" -eq 1 ] ;then - check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what" + check_counters "flow offload for ns1/ns2 with masquerade $what" else echo "PASS: flow offload for ns1/ns2 with masquerade $what" fi - test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666 lret=$? if [ "$pmtu" -eq 1 ] ;then - check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what" + check_counters "flow offload for ns1/ns2 with dnat $what" elif [ "$lret" -eq 0 ] ; then echo "PASS: flow offload for ns1/ns2 with dnat $what" fi + else + echo "FAIL: flow offload for ns1/ns2 with dnat $what" fi return $lret } make_file "$nsin" "$filesize" +make_file "$nsin_small" "$filesize_small" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. # Due to MTU mismatch in both directions, all packets (except small packets like pure # acks) have to be handled by normal forwarding path. Therefore, packet counters # are not checked. -if test_tcp_forwarding "$ns1" "$ns2"; then +if test_tcp_forwarding "$ns1" "$ns2" 0; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -489,8 +519,9 @@ table ip nat { } EOF +check_dscp "dscp_none" "0" if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then - echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2 + echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2 exit 0 fi @@ -513,6 +544,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null # For earlier tests (large mtus), packets cannot be handled via flowtable # (except pure acks and other small packets). ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null +ip netns exec "$ns2" nft reset counters table inet filter >/dev/null + +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then + echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2 + exit 0 +fi + +ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2 @@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1 ip -net "$ns2" route add default via 10.0.2.1 ip -net "$ns2" route add default via dead:2::1 -if test_tcp_forwarding "$ns1" "$ns2"; then +if test_tcp_forwarding "$ns1" "$ns2" 1; then check_counters "ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" @@ -668,7 +707,7 @@ if [ "$1" = "" ]; then fi echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize" - $0 -o "$o" -l "$l" -r "$r" -s "$filesize" + $0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1 fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c index 85c7b906ad08..79de163d61ab 100644 --- a/tools/testing/selftests/net/netfilter/udpclash.c +++ b/tools/testing/selftests/net/netfilter/udpclash.c @@ -29,7 +29,7 @@ struct thread_args { int sockfd; }; -static int wait = 1; +static volatile int wait = 1; static void *thread_main(void *varg) { diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 3c8d3455d8e7..b327d3061ed5 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -25,6 +25,7 @@ tests=" nat_related_v4 ip4-nat-related: ICMP related matches work with SNAT netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces + tunnel_metadata ovs: test extraction of tunnel metadata drop_reason drop: test drop reasons are emitted psample psample: Sampling packets with psample" @@ -113,13 +114,13 @@ ovs_add_dp () { } ovs_add_if () { - info "Adding IF to DP: br:$2 if:$3" - if [ "$4" != "-u" ]; then - ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if "$2" "$3" \ - || return 1 + info "Adding IF to DP: br:$3 if:$4 ($2)" + if [ "$5" != "-u" ]; then + ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if \ + -t "$2" "$3" "$4" || return 1 else python3 $ovs_base/ovs-dpctl.py add-if \ - -u "$2" "$3" >$ovs_dir/$3.out 2>$ovs_dir/$3.err & + -u -t "$2" "$3" "$4" >$ovs_dir/$4.out 2>$ovs_dir/$4.err & pid=$! on_exit "ovs_sbx $1 kill -TERM $pid 2>/dev/null" fi @@ -166,9 +167,9 @@ ovs_add_netns_and_veths () { fi if [ "$7" != "-u" ]; then - ovs_add_if "$1" "$2" "$4" || return 1 + ovs_add_if "$1" "netdev" "$2" "$4" || return 1 else - ovs_add_if "$1" "$2" "$4" -u || return 1 + ovs_add_if "$1" "netdev" "$2" "$4" -u || return 1 fi if [ $TRACING -eq 1 ]; then @@ -756,6 +757,79 @@ test_upcall_interfaces() { return 0 } +ovs_add_kernel_tunnel() { + local sbxname=$1; shift + local ns=$1; shift + local tnl_type=$1; shift + local name=$1; shift + local addr=$1; shift + + info "setting up kernel ${tnl_type} tunnel ${name}" + ovs_sbx "${sbxname}" ip -netns ${ns} link add dev ${name} type ${tnl_type} $* || return 1 + on_exit "ovs_sbx ${sbxname} ip -netns ${ns} link del ${name} >/dev/null 2>&1" + ovs_sbx "${sbxname}" ip -netns ${ns} addr add dev ${name} ${addr} || return 1 + ovs_sbx "${sbxname}" ip -netns ${ns} link set dev ${name} mtu 1450 up || return 1 +} + +test_tunnel_metadata() { + which arping >/dev/null 2>&1 || return $ksft_skip + + sbxname="test_tunnel_metadata" + sbx_add "${sbxname}" || return 1 + + info "setting up new DP" + ovs_add_dp "${sbxname}" tdp0 -V 2:1 || return 1 + + ovs_add_netns_and_veths "${sbxname}" tdp0 tns left0 l0 \ + 172.31.110.1/24 || return 1 + + info "removing veth interface from openvswitch and setting IP" + ovs_del_if "${sbxname}" tdp0 left0 || return 1 + ovs_sbx "${sbxname}" ip addr add 172.31.110.2/24 dev left0 || return 1 + ovs_sbx "${sbxname}" ip link set left0 up || return 1 + + info "setting up tunnel port in openvswitch" + ovs_add_if "${sbxname}" "vxlan" tdp0 ovs-vxlan0 -u || return 1 + on_exit "ovs_sbx ${sbxname} ip link del ovs-vxlan0" + ovs_wait ip link show ovs-vxlan0 &>/dev/null || return 1 + ovs_sbx "${sbxname}" ip link set ovs-vxlan0 up || return 1 + + configs=$(echo ' + 1 172.31.221.1/24 1155332 32 set udpcsum flags\(df\|csum\) + 2 172.31.222.1/24 1234567 45 set noudpcsum flags\(df\) + 3 172.31.223.1/24 1020304 23 unset udpcsum flags\(csum\) + 4 172.31.224.1/24 1357986 15 unset noudpcsum' | sed '/^$/d') + + while read -r i addr id ttl df csum flags; do + ovs_add_kernel_tunnel "${sbxname}" tns vxlan vxlan${i} ${addr} \ + remote 172.31.110.2 id ${id} dstport 4789 \ + ttl ${ttl} df ${df} ${csum} || return 1 + done <<< "${configs}" + + ovs_wait grep -q 'listening on upcall packet handler' \ + ${ovs_dir}/ovs-vxlan0.out || return 1 + + info "sending arping" + for i in 1 2 3 4; do + ovs_sbx "${sbxname}" ip netns exec tns \ + arping -I vxlan${i} 172.31.22${i}.2 -c 1 \ + >${ovs_dir}/arping.stdout 2>${ovs_dir}/arping.stderr + done + + info "checking that received decapsulated packets carry correct metadata" + while read -r i addr id ttl df csum flags; do + arp_hdr="arp\\(sip=172.31.22${i}.1,tip=172.31.22${i}.2,op=1,sha=" + addrs="src=172.31.110.1,dst=172.31.110.2" + ports="tp_src=[0-9]*,tp_dst=4789" + tnl_md="tunnel\\(tun_id=${id},${addrs},ttl=${ttl},${ports},${flags}\\)" + + ovs_sbx "${sbxname}" grep -qE "MISS upcall.*${tnl_md}.*${arp_hdr}" \ + ${ovs_dir}/ovs-vxlan0.out || return 1 + done <<< "${configs}" + + return 0 +} + run_test() { ( tname="$1" diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt new file mode 100644 index 000000000000..26794e7ddfd5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh + ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x602 /proc/sys/net/ipv4/tcp_timestamps=0` + + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:10(10) win 32792 <mss 1460,nop,nop,sackOK> + +0 > S. 0:0(0) ack 11 win 65535 <mss 1460,nop,nop,sackOK> + +// sk->sk_state is TCP_SYN_RECV + +.1 accept(3, ..., ...) = 4 + +// tcp_disconnect() sets sk->sk_state to TCP_CLOSE + +0 connect(4, AF_UNSPEC, ...) = 0 + +0 > R. 1:1(0) ack 11 win 65535 + +// connect() sets sk->sk_state to TCP_SYN_SENT + +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation is now in progress) + +0 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +// tp->fastopen_rsk must be NULL + +1 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8> diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh new file mode 100755 index 000000000000..20f3369f776b --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_nh.sh @@ -0,0 +1,223 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + basic_tx_ipv4 + basic_tx_ipv6 + learning + proxy_ipv4 + proxy_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Cleanup + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +nh_stats_get() +{ + ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]" +} + +tc_stats_get() +{ + tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1" +} + +basic_tx_common() +{ + local af_str=$1; shift + local proto=$1; shift + local local_addr=$1; shift + local plen=$1; shift + local remote_addr=$1; shift + + RET=0 + + # Test basic Tx functionality. Check that stats are incremented on + # both the FDB nexthop group and the egress device. + + run_cmd "ip -n $ns1 link add name dummy1 up type dummy" + run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1" + run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact" + run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass" + + run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789" + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10" + + run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q" + + busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null + check_err $? "FDB nexthop group stats did not increase" + + busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null + check_err $? "tc filter stats did not increase" + + log_test "VXLAN FDB nexthop: $af_str basic Tx" +} + +basic_tx_ipv4() +{ + basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2 +} + +basic_tx_ipv6() +{ + basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2 +} + +learning() +{ + RET=0 + + # When learning is enabled on the VXLAN device, an incoming packet + # might try to refresh an FDB entry that points to an FDB nexthop group + # instead of an ordinary remote destination. Check that the kernel does + # not crash in this situation. + + run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo" + run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass" + run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning" + + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020" + run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10" + + run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q" + + log_test "VXLAN FDB nexthop: learning" +} + +proxy_common() +{ + local af_str=$1; shift + local local_addr=$1; shift + local plen=$1; shift + local remote_addr=$1; shift + local neigh_addr=$1; shift + local ping_cmd=$1; shift + + RET=0 + + # When the "proxy" option is enabled on the VXLAN device, the device + # will suppress ARP requests and IPv6 Neighbor Solicitation messages if + # it is able to reply on behalf of the remote host. That is, if a + # matching and valid neighbor entry is configured on the VXLAN device + # whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The + # FDB entry for the neighbor's MAC address might point to an FDB + # nexthop group instead of an ordinary remote destination. Check that + # the kernel does not crash in this situation. + + run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy" + + run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0" + + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10" + + run_cmd "ip netns exec $ns1 $ping_cmd" + + log_test "VXLAN FDB nexthop: $af_str proxy" +} + +proxy_ipv4() +{ + proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \ + "arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3" +} + +proxy_ipv6() +{ + proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \ + "ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command mausezahn +require_command arping +require_command ndisc6 +require_command jq + +if ! ip nexthop help 2>&1 | grep -q "stats"; then + echo "SKIP: iproute2 ip too old, missing nexthop stats support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup_ns ns1; $t; cleanup_all_ns; +done diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index d8cfcf9bb825..dd093f9df6f1 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -181,13 +181,12 @@ static int tls_send_cmsg(int fd, unsigned char record_type, return sendmsg(fd, &msg, flags); } -static int tls_recv_cmsg(struct __test_metadata *_metadata, - int fd, unsigned char record_type, - void *data, size_t len, int flags) +static int __tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char *ctype, + void *data, size_t len, int flags) { char cbuf[CMSG_SPACE(sizeof(char))]; struct cmsghdr *cmsg; - unsigned char ctype; struct msghdr msg; struct iovec vec; int n; @@ -206,7 +205,20 @@ static int tls_recv_cmsg(struct __test_metadata *_metadata, EXPECT_NE(cmsg, NULL); EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - ctype = *((unsigned char *)CMSG_DATA(cmsg)); + if (ctype) + *ctype = *((unsigned char *)CMSG_DATA(cmsg)); + + return n; +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + unsigned char ctype; + int n; + + n = __tls_recv_cmsg(_metadata, fd, &ctype, data, len, flags); EXPECT_EQ(ctype, record_type); return n; @@ -2164,6 +2176,284 @@ TEST_F(tls, rekey_poll_delay) } } +struct raw_rec { + unsigned int plain_len; + unsigned char plain_data[100]; + unsigned int cipher_len; + unsigned char cipher_data[128]; +}; + +/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: 'Hello world' */ +static const struct raw_rec id0_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x26, 0xa2, 0x33, + 0xde, 0x8d, 0x94, 0xf0, 0x29, 0x6c, 0xb1, 0xaf, + 0x6a, 0x75, 0xb2, 0x93, 0xad, 0x45, 0xd5, 0xfd, + 0x03, 0x51, 0x57, 0x8f, 0xf9, 0xcc, 0x3b, 0x42, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:0, plaintext: '' */ +static const struct raw_rec id0_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x38, 0x7b, + 0xa6, 0x1c, 0xdd, 0xa7, 0x19, 0x33, 0xab, 0xae, + 0x88, 0xe1, 0xd2, 0x08, 0x4f, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: '' */ +static const struct raw_rec id0_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, 0x37, 0x90, + 0x70, 0x45, 0x89, 0xfb, 0x5c, 0xc7, 0x89, 0x03, + 0x68, 0x80, 0xd3, 0xd8, 0xcc, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: 'Hello world' */ +static const struct raw_rec id1_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x3a, 0x1a, 0x9c, + 0xd0, 0xa8, 0x9a, 0xd6, 0x69, 0xd6, 0x1a, 0xe3, + 0xb5, 0x1f, 0x0d, 0x2c, 0xe2, 0x97, 0x46, 0xff, + 0x2b, 0xcc, 0x5a, 0xc4, 0xa3, 0xb9, 0xef, 0xba, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:1, plaintext: '' */ +static const struct raw_rec id1_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x3e, 0xf0, 0xfe, + 0xee, 0xd9, 0xe2, 0x5d, 0xc7, 0x11, 0x4c, 0xe6, + 0xb4, 0x7e, 0xef, 0x40, 0x2b, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: '' */ +static const struct raw_rec id1_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0xce, 0xfc, 0x86, + 0xc8, 0xf0, 0x55, 0xf9, 0x47, 0x3f, 0x74, 0xdc, + 0xc9, 0xbf, 0xfe, 0x5b, 0xb1, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: 'Hello world' */ +static const struct raw_rec id2_ctrl_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19, + 0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87, + 0x2a, 0x04, 0x11, 0x3d, 0xf8, 0x64, 0x5f, 0x36, + 0x8b, 0xa8, 0xee, 0x4c, 0x6d, 0x62, 0xa5, 0x00, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: 'Hello world' */ +static const struct raw_rec id2_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19, + 0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87, + 0x8e, 0xa1, 0xd0, 0xcd, 0x33, 0xb5, 0x86, 0x2b, + 0x17, 0xf1, 0x52, 0x2a, 0x55, 0x62, 0x65, 0x11, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: '' */ +static const struct raw_rec id2_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xdc, 0x5c, 0x0e, + 0x41, 0xdd, 0xba, 0xd3, 0xcc, 0xcf, 0x6d, 0xd9, + 0x06, 0xdb, 0x79, 0xe5, 0x5d, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: '' */ +static const struct raw_rec id2_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xc3, 0xca, 0x26, + 0x22, 0xe4, 0x25, 0xfb, 0x5f, 0x6d, 0xbf, 0x83, + 0x30, 0x48, 0x69, 0x1a, 0x47, + }, +}; + +FIXTURE(zero_len) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_VARIANT(zero_len) +{ + const struct raw_rec *recs[4]; + ssize_t recv_ret[4]; +}; + +FIXTURE_VARIANT_ADD(zero_len, data_data_data) +{ + .recs = { &id0_data_l11, &id1_data_l11, &id2_data_l11, }, + .recv_ret = { 33, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, data_0ctrl_data) +{ + .recs = { &id0_data_l11, &id1_ctrl_l0, &id2_data_l11, }, + .recv_ret = { 11, 0, 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0data) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_data_l0, }, + .recv_ret = { -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_ctrl) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l11, }, + .recv_ret = { 0, 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0ctrl) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l0, }, + .recv_ret = { 0, 0, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0ctrl_0ctrl_0ctrl) +{ + .recs = { &id0_ctrl_l0, &id1_ctrl_l0, &id2_ctrl_l0, }, + .recv_ret = { 0, 0, 0, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_data) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_data_l11, }, + .recv_ret = { 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, data_0data_0data) +{ + .recs = { &id0_data_l11, &id1_data_l0, &id2_data_l0, }, + .recv_ret = { 11, -EAGAIN, }, +}; + +FIXTURE_SETUP(zero_len) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + if (self->notls) + return; + + /* Don't install keys on fd, we'll send raw records */ + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(zero_len) +{ + close(self->fd); + close(self->cfd); +} + +TEST_F(zero_len, test) +{ + const struct raw_rec *const *rec; + unsigned char buf[128]; + int rec_off; + int i; + + for (i = 0; i < 4 && variant->recs[i]; i++) + EXPECT_EQ(send(self->fd, variant->recs[i]->cipher_data, + variant->recs[i]->cipher_len, 0), + variant->recs[i]->cipher_len); + + rec = &variant->recs[0]; + rec_off = 0; + for (i = 0; i < 4; i++) { + int j, ret; + + ret = variant->recv_ret[i] >= 0 ? variant->recv_ret[i] : -1; + EXPECT_EQ(__tls_recv_cmsg(_metadata, self->cfd, NULL, + buf, sizeof(buf), MSG_DONTWAIT), ret); + if (ret == -1) + EXPECT_EQ(errno, -variant->recv_ret[i]); + if (variant->recv_ret[i] == -EAGAIN) + break; + + for (j = 0; j < ret; j++) { + while (rec_off == (*rec)->plain_len) { + rec++; + rec_off = 0; + } + EXPECT_EQ(buf[j], (*rec)->plain_data[rec_off]); + rec_off++; + } + } +}; + FIXTURE(tls_err) { int fd, cfd; @@ -2480,6 +2770,22 @@ TEST_F(tls_err, poll_partial_rec_async) } } +/* Use OOB+large send to trigger copy mode due to memory pressure. + * OOB causes a short read. + */ +TEST_F(tls_err, oob_pressure) +{ + char buf[1<<16]; + int i; + + memrnd(buf, sizeof(buf)); + + EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + for (i = 0; i < 64; i++) + EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; @@ -2748,17 +3054,18 @@ TEST(data_steal) { pid = fork(); ASSERT_GE(pid, 0); if (!pid) { - EXPECT_EQ(recv(cfd, buf, sizeof(buf), MSG_WAITALL), - sizeof(buf)); + EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL), + sizeof(buf) / 2); exit(!__test_passed(_metadata)); } - usleep(2000); + usleep(10000); ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0); ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0); EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf)); - usleep(2000); + EXPECT_EQ(wait(&status), pid); + EXPECT_EQ(status, 0); EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1); /* Don't check errno, the error will be different depending * on what random bytes TLS interpreted as the record length. @@ -2766,9 +3073,6 @@ TEST(data_steal) { close(fd); close(cfd); - - EXPECT_EQ(wait(&status), pid); - EXPECT_EQ(status, 0); } static void __attribute__((constructor)) fips_check(void) { diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h index 67d544aaa9a3..06c840e81c8b 100644 --- a/tools/testing/selftests/rseq/rseq-riscv.h +++ b/tools/testing/selftests/rseq/rseq-riscv.h @@ -8,6 +8,7 @@ * exception when executed in all modes. */ #include <endian.h> +#include <asm/fence.h> #if defined(__BYTE_ORDER) ? (__BYTE_ORDER == __LITTLE_ENDIAN) : defined(__LITTLE_ENDIAN) #define RSEQ_SIG 0xf1401073 /* csrr mhartid, x0 */ @@ -24,8 +25,6 @@ #define REG_L __REG_SEL("ld ", "lw ") #define REG_S __REG_SEL("sd ", "sw ") -#define RISCV_FENCE(p, s) \ - __asm__ __volatile__ ("fence " #p "," #s : : : "memory") #define rseq_smp_mb() RISCV_FENCE(rw, rw) #define rseq_smp_rmb() RISCV_FENCE(r, r) #define rseq_smp_wmb() RISCV_FENCE(w, w) diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 1c9ceb661c43..0cfbb111a2d0 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -6,7 +6,6 @@ #include <bpf/bpf.h> #include <sched.h> #include <scx/common.h> -#include <sched.h> #include <sys/wait.h> #include <unistd.h> diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 23a61e5b99d0..998e5a2f4579 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -186,6 +186,204 @@ ] }, { + "id": "34c0", + "name": "Test TBF with HHF Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "hhf" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 hhf limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 hhf limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "fd68", + "name": "Test TBF with CODEL Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "codel" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 codel limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 codel limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "514e", + "name": "Test TBF with PIE Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "pie" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 pie limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 pie limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "6c97", + "name": "Test TBF with FQ Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "5d0b", + "name": "Test TBF with FQ_CODEL Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq_codel" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_codel limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_codel limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "21c3", + "name": "Test TBF with FQ_PIE Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq_pie" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_pie limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_pie limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { "id": "a4bb", "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue", "category": [ diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c index 2d93ac860bd5..cd9fe69ecce2 100644 --- a/tools/testing/selftests/ublk/file_backed.c +++ b/tools/testing/selftests/ublk/file_backed.c @@ -20,7 +20,7 @@ static int loop_queue_flush_io(struct ublk_thread *t, struct ublk_queue *q, struct io_uring_sqe *sqe[1]; ublk_io_alloc_sqes(t, sqe, 1); - io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC); + io_uring_prep_fsync(sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, IORING_FSYNC_DATASYNC); io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE); /* bit63 marks us as tgt io */ sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1); @@ -42,7 +42,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, if (!sqe[0]) return -ENOMEM; - io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/, + io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, addr, iod->nr_sectors << 9, iod->start_sector << 9); @@ -56,19 +56,19 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, 3); - io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); - io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0, + io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0, iod->nr_sectors << 9, iod->start_sector << 9); sqe[1]->buf_index = tag; sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK; sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1); - io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1); return 2; diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 95188065b2e9..b71faba86c3b 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -432,7 +432,7 @@ static void ublk_thread_deinit(struct ublk_thread *t) } } -static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) +static int ublk_queue_init(struct ublk_queue *q, unsigned long long extra_flags) { struct ublk_dev *dev = q->dev; int depth = dev->dev_info.queue_depth; @@ -446,6 +446,9 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) q->flags = dev->dev_info.flags; q->flags |= extra_flags; + /* Cache fd in queue for fast path access */ + q->ublk_fd = dev->fds[0]; + cmd_buf_size = ublk_queue_cmd_buf_sz(q); off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz(); q->io_cmd_buf = mmap(0, cmd_buf_size, PROT_READ, @@ -481,9 +484,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags) return -ENOMEM; } -static int ublk_thread_init(struct ublk_thread *t) +static int ublk_thread_init(struct ublk_thread *t, unsigned long long extra_flags) { struct ublk_dev *dev = t->dev; + unsigned long long flags = dev->dev_info.flags | extra_flags; int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth; int ret; @@ -512,7 +516,17 @@ static int ublk_thread_init(struct ublk_thread *t) io_uring_register_ring_fd(&t->ring); - ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds); + if (flags & UBLKS_Q_NO_UBLK_FIXED_FD) { + /* Register only backing files starting from index 1, exclude ublk control device */ + if (dev->nr_fds > 1) { + ret = io_uring_register_files(&t->ring, &dev->fds[1], dev->nr_fds - 1); + } else { + /* No backing files to register, skip file registration */ + ret = 0; + } + } else { + ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds); + } if (ret) { ublk_err("ublk dev %d thread %d register files failed %d\n", t->dev->dev_info.dev_id, t->idx, ret); @@ -626,9 +640,12 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io) /* These fields should be written once, never change */ ublk_set_sqe_cmd_op(sqe[0], cmd_op); - sqe[0]->fd = 0; /* dev->fds[0] */ + sqe[0]->fd = ublk_get_registered_fd(q, 0); /* dev->fds[0] */ sqe[0]->opcode = IORING_OP_URING_CMD; - sqe[0]->flags = IOSQE_FIXED_FILE; + if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) + sqe[0]->flags = 0; /* Use raw FD, not fixed file */ + else + sqe[0]->flags = IOSQE_FIXED_FILE; sqe[0]->rw_flags = 0; cmd->tag = io->tag; cmd->q_id = q->q_id; @@ -832,6 +849,7 @@ struct ublk_thread_info { unsigned idx; sem_t *ready; cpu_set_t *affinity; + unsigned long long extra_flags; }; static void *ublk_io_handler_fn(void *data) @@ -844,7 +862,7 @@ static void *ublk_io_handler_fn(void *data) t->dev = info->dev; t->idx = info->idx; - ret = ublk_thread_init(t); + ret = ublk_thread_init(t, info->extra_flags); if (ret) { ublk_err("ublk dev %d thread %u init failed\n", dev_id, t->idx); @@ -934,6 +952,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) if (ctx->auto_zc_fallback) extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK; + if (ctx->no_ublk_fixed_fd) + extra_flags |= UBLKS_Q_NO_UBLK_FIXED_FD; for (i = 0; i < dinfo->nr_hw_queues; i++) { dev->q[i].dev = dev; @@ -951,6 +971,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) tinfo[i].dev = dev; tinfo[i].idx = i; tinfo[i].ready = &ready; + tinfo[i].extra_flags = extra_flags; /* * If threads are not tied 1:1 to queues, setting thread @@ -1400,7 +1421,7 @@ static int cmd_dev_get_features(void) if (!((1ULL << i) & features)) continue; - if (i < sizeof(feat_map) / sizeof(feat_map[0])) + if (i < ARRAY_SIZE(feat_map)) feat = feat_map[i]; else feat = "unknown"; @@ -1471,13 +1492,13 @@ static void __cmd_create_help(char *exe, bool recovery) printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n", exe, recovery ? "recover" : "add"); printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n"); - printf("\t[-e 0|1 ] [-i 0|1]\n"); + printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n"); printf("\t[--nthreads threads] [--per_io_tasks]\n"); printf("\t[target options] [backfile1] [backfile2] ...\n"); printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n"); printf("\tdefault: nthreads=nr_queues"); - for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++) { const struct ublk_tgt_ops *ops = tgt_ops_list[i]; if (ops->usage) @@ -1534,6 +1555,7 @@ int main(int argc, char *argv[]) { "size", 1, NULL, 's'}, { "nthreads", 1, NULL, 0 }, { "per_io_tasks", 0, NULL, 0 }, + { "no_ublk_fixed_fd", 0, NULL, 0 }, { 0, 0, 0, 0 } }; const struct ublk_tgt_ops *ops = NULL; @@ -1613,6 +1635,8 @@ int main(int argc, char *argv[]) ctx.nthreads = strtol(optarg, NULL, 10); if (!strcmp(longopts[option_idx].name, "per_io_tasks")) ctx.per_io_tasks = 1; + if (!strcmp(longopts[option_idx].name, "no_ublk_fixed_fd")) + ctx.no_ublk_fixed_fd = 1; break; case '?': /* diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index 219233f8a053..5e55484fb0aa 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -77,6 +77,7 @@ struct dev_ctx { unsigned int recovery:1; unsigned int auto_zc_fallback:1; unsigned int per_io_tasks:1; + unsigned int no_ublk_fixed_fd:1; int _evtfd; int _shmid; @@ -166,7 +167,9 @@ struct ublk_queue { /* borrow one bit of ublk uapi flags, which may never be used */ #define UBLKS_Q_AUTO_BUF_REG_FALLBACK (1ULL << 63) +#define UBLKS_Q_NO_UBLK_FIXED_FD (1ULL << 62) __u64 flags; + int ublk_fd; /* cached ublk char device fd */ struct ublk_io ios[UBLK_QUEUE_DEPTH]; }; @@ -273,34 +276,48 @@ static inline int ublk_io_alloc_sqes(struct ublk_thread *t, return nr_sqes; } -static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe, - int dev_fd, int tag, int q_id, __u64 index) +static inline int ublk_get_registered_fd(struct ublk_queue *q, int fd_index) +{ + if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) { + if (fd_index == 0) + /* Return the raw ublk FD for index 0 */ + return q->ublk_fd; + /* Adjust index for backing files (index 1 becomes 0, etc.) */ + return fd_index - 1; + } + return fd_index; +} + +static inline void __io_uring_prep_buf_reg_unreg(struct io_uring_sqe *sqe, + struct ublk_queue *q, int tag, int q_id, __u64 index) { struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd; + int dev_fd = ublk_get_registered_fd(q, 0); io_uring_prep_read(sqe, dev_fd, 0, 0, 0); sqe->opcode = IORING_OP_URING_CMD; - sqe->flags |= IOSQE_FIXED_FILE; - sqe->cmd_op = UBLK_U_IO_REGISTER_IO_BUF; + if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) + sqe->flags &= ~IOSQE_FIXED_FILE; + else + sqe->flags |= IOSQE_FIXED_FILE; cmd->tag = tag; cmd->addr = index; cmd->q_id = q_id; } -static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe, - int dev_fd, int tag, int q_id, __u64 index) +static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe, + struct ublk_queue *q, int tag, int q_id, __u64 index) { - struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd; + __io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index); + sqe->cmd_op = UBLK_U_IO_REGISTER_IO_BUF; +} - io_uring_prep_read(sqe, dev_fd, 0, 0, 0); - sqe->opcode = IORING_OP_URING_CMD; - sqe->flags |= IOSQE_FIXED_FILE; +static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe, + struct ublk_queue *q, int tag, int q_id, __u64 index) +{ + __io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index); sqe->cmd_op = UBLK_U_IO_UNREGISTER_IO_BUF; - - cmd->tag = tag; - cmd->addr = index; - cmd->q_id = q_id; } static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe) diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c index f0e0003a4860..280043f6b689 100644 --- a/tools/testing/selftests/ublk/null.c +++ b/tools/testing/selftests/ublk/null.c @@ -63,7 +63,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, 3); - io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; @@ -71,7 +71,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q, __setup_nop_io(tag, iod, sqe[1], q->q_id); sqe[1]->flags |= IOSQE_IO_HARDLINK; - io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1); // buf register is marked as IOSQE_CQE_SKIP_SUCCESS diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c index 1fb9b7cc281b..791fa8dc1651 100644 --- a/tools/testing/selftests/ublk/stripe.c +++ b/tools/testing/selftests/ublk/stripe.c @@ -142,7 +142,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, s->nr + extra); if (zc) { - io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); @@ -168,7 +168,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, if (zc) { struct io_uring_sqe *unreg = sqe[s->nr + 1]; - io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, io->buf_index); + io_uring_prep_buf_unregister(unreg, q, tag, q->q_id, io->buf_index); unreg->user_data = build_user_data( tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1); } diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh index 40d1437ca298..3f901db4d09d 100755 --- a/tools/testing/selftests/ublk/test_stress_04.sh +++ b/tools/testing/selftests/ublk/test_stress_04.sh @@ -28,14 +28,14 @@ _create_backfile 0 256M _create_backfile 1 128M _create_backfile 2 128M -ublk_io_and_kill_daemon 8G -t null -q 4 -z & -ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" & +ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd & +ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" & ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & if _have_feature "AUTO_BUF_REG"; then ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc & ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" & - ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & + ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback & fi diff --git a/tools/testing/shared/linux/idr.h b/tools/testing/shared/linux/idr.h index 4e342f2e37cf..676c5564e33f 100644 --- a/tools/testing/shared/linux/idr.h +++ b/tools/testing/shared/linux/idr.h @@ -1 +1,5 @@ +/* Avoid duplicate definitions due to system headers. */ +#ifdef __CONCAT +#undef __CONCAT +#endif #include "../../../../include/linux/idr.h" |