summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/cxl/test/mem.c2
-rw-r--r--tools/testing/kunit/configs/all_tests.config4
-rw-r--r--tools/testing/kunit/qemu_configs/sh.py4
-rw-r--r--tools/testing/memblock/tests/basic_api.c102
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/bpf/config.aarch641
-rw-r--r--tools/testing/selftests/bpf/config.s390x1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/for_each.c37
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c1
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_misc.h2
-rw-r--r--tools/testing/selftests/bpf/progs/for_each_hash_modify.c30
-rw-r--r--tools/testing/selftests/coredump/stackdump_test.c477
l---------tools/testing/selftests/drivers/net/dsa/tc_taprio.sh1
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/iou-zcrx.py4
-rw-r--r--tools/testing/selftests/drivers/net/hw/ncdevmem.c55
-rwxr-xr-xtools/testing/selftests/drivers/net/ocelot/psfp.sh8
-rwxr-xr-xtools/testing/selftests/drivers/net/ping.py45
-rw-r--r--tools/testing/selftests/filesystems/.gitignore1
-rw-r--r--tools/testing/selftests/filesystems/Makefile2
-rw-r--r--tools/testing/selftests/filesystems/anon_inode_test.c69
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/.gitignore1
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/Makefile9
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c93
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c557
-rw-r--r--tools/testing/selftests/filesystems/overlayfs/Makefile2
-rw-r--r--tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c2
-rw-r--r--tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c2
-rw-r--r--tools/testing/selftests/filesystems/statmount/Makefile6
-rw-r--r--tools/testing/selftests/filesystems/statmount/statmount.h36
-rw-r--r--tools/testing/selftests/filesystems/statmount/statmount_test_ns.c86
-rw-r--r--tools/testing/selftests/filesystems/utils.c88
-rw-r--r--tools/testing/selftests/filesystems/utils.h3
-rw-r--r--tools/testing/selftests/filesystems/wrappers.h (renamed from tools/testing/selftests/filesystems/overlayfs/wrappers.h)46
-rw-r--r--tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc23
-rw-r--r--tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc20
-rw-r--r--tools/testing/selftests/kvm/arm64/set_id_regs.c8
-rw-r--r--tools/testing/selftests/landlock/audit.h21
-rw-r--r--tools/testing/selftests/landlock/audit_test.c154
-rw-r--r--tools/testing/selftests/landlock/fs_test.c3
-rw-r--r--tools/testing/selftests/lib/config1
-rw-r--r--tools/testing/selftests/mincore/mincore_selftest.c16
-rwxr-xr-xtools/testing/selftests/mm/charge_reserved_hugetlb.sh4
-rw-r--r--tools/testing/selftests/mm/compaction_test.c19
-rw-r--r--tools/testing/selftests/mm/cow.c2
-rw-r--r--tools/testing/selftests/mm/guard-regions.c16
-rwxr-xr-xtools/testing/selftests/mm/hugetlb_reparenting_test.sh2
-rw-r--r--tools/testing/selftests/mm/pkey-powerpc.h14
-rw-r--r--tools/testing/selftests/mm/pkey_util.c1
-rw-r--r--tools/testing/selftests/mount_setattr/Makefile2
-rw-r--r--tools/testing/selftests/mount_setattr/mount_setattr_test.c61
-rw-r--r--tools/testing/selftests/net/Makefile1
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh34
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_vlan_aware.sh96
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_taprio.sh421
-rw-r--r--tools/testing/selftests/net/forwarding/tsn_lib.sh26
-rwxr-xr-xtools/testing/selftests/net/gre_ipv6_lladdr.sh177
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh5
-rw-r--r--tools/testing/selftests/pcie_bwctrl/Makefile3
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h22
-rw-r--r--tools/testing/selftests/pidfd/pidfd_bind_mount.c74
-rw-r--r--tools/testing/selftests/pidfd/pidfd_info_test.c13
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/infra/actions.json22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json287
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json24
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json24
-rw-r--r--tools/testing/selftests/ublk/Makefile21
-rw-r--r--tools/testing/selftests/ublk/fault_inject.c103
-rw-r--r--tools/testing/selftests/ublk/file_backed.c17
-rw-r--r--tools/testing/selftests/ublk/kublk.c505
-rw-r--r--tools/testing/selftests/ublk/kublk.h69
-rw-r--r--tools/testing/selftests/ublk/null.c55
-rw-r--r--tools/testing/selftests/ublk/stripe.c54
-rwxr-xr-xtools/testing/selftests/ublk/test_common.sh177
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_04.sh40
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_05.sh44
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_06.sh41
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_07.sh28
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_08.sh32
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_09.sh28
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_10.sh30
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_11.sh44
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_01.sh8
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_02.sh8
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_03.sh8
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_04.sh9
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_05.sh8
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_01.sh45
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_02.sh47
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_03.sh45
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_04.sh44
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_05.sh73
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_01.sh12
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_02.sh13
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_03.sh12
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_04.sh13
-rw-r--r--tools/testing/selftests/x86/bugs/Makefile3
-rwxr-xr-xtools/testing/selftests/x86/bugs/common.py164
-rwxr-xr-xtools/testing/selftests/x86/bugs/its_indirect_alignment.py150
-rwxr-xr-xtools/testing/selftests/x86/bugs/its_permutations.py109
-rwxr-xr-xtools/testing/selftests/x86/bugs/its_ret_alignment.py139
-rwxr-xr-xtools/testing/selftests/x86/bugs/its_sysfs.py65
-rw-r--r--tools/testing/shared/linux.c4
-rw-r--r--tools/testing/shared/linux/cleanup.h2
-rw-r--r--tools/testing/vsock/vsock_test.c28
108 files changed, 5135 insertions, 624 deletions
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index f2957a3e36fe7..bf9caa908f894 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1780,7 +1780,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
if (rc)
return rc;
- rc = devm_cxl_setup_fwctl(cxlmd);
+ rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
if (rc)
dev_dbg(dev, "No CXL FWCTL setup\n");
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index cdd9782f9646a..422e186cf3cf1 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -20,6 +20,7 @@ CONFIG_VFAT_FS=y
CONFIG_PCI=y
CONFIG_USB4=y
+CONFIG_I2C=y
CONFIG_NET=y
CONFIG_MCTP=y
@@ -43,6 +44,8 @@ CONFIG_REGMAP_BUILD=y
CONFIG_AUDIT=y
+CONFIG_PRIME_NUMBERS=y
+
CONFIG_SECURITY=y
CONFIG_SECURITY_APPARMOR=y
CONFIG_SECURITY_LANDLOCK=y
@@ -51,3 +54,4 @@ CONFIG_SOUND=y
CONFIG_SND=y
CONFIG_SND_SOC=y
CONFIG_SND_SOC_TOPOLOGY_BUILD=y
+CONFIG_SND_SOC_CS35L56_I2C=y
diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py
index 78a474a5b95f3..f00cb89fdef6a 100644
--- a/tools/testing/kunit/qemu_configs/sh.py
+++ b/tools/testing/kunit/qemu_configs/sh.py
@@ -7,7 +7,9 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
CONFIG_MEMORY_START=0x0c000000
CONFIG_SH_RTS7751R2D=y
CONFIG_RTS7751R2D_PLUS=y
-CONFIG_SERIAL_SH_SCI=y''',
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_CMDLINE_EXTEND=y
+''',
qemu_arch='sh4',
kernel_path='arch/sh/boot/zImage',
kernel_command_line='console=ttySC1',
diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c
index 67503089e6a0a..01e836fba4888 100644
--- a/tools/testing/memblock/tests/basic_api.c
+++ b/tools/testing/memblock/tests/basic_api.c
@@ -2434,6 +2434,107 @@ static int memblock_overlaps_region_checks(void)
return 0;
}
+#ifdef CONFIG_NUMA
+static int memblock_set_node_check(void)
+{
+ unsigned long i, max_reserved;
+ struct memblock_region *rgn;
+ void *orig_region;
+
+ PREFIX_PUSH();
+
+ reset_memblock_regions();
+ memblock_allow_resize();
+
+ dummy_physical_memory_init();
+ memblock_add(dummy_physical_memory_base(), MEM_SIZE);
+ orig_region = memblock.reserved.regions;
+
+ /* Equally Split range to node 0 and 1*/
+ memblock_set_node(memblock_start_of_DRAM(),
+ memblock_phys_mem_size() / 2, &memblock.memory, 0);
+ memblock_set_node(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2,
+ memblock_phys_mem_size() / 2, &memblock.memory, 1);
+
+ ASSERT_EQ(memblock.memory.cnt, 2);
+ rgn = &memblock.memory.regions[0];
+ ASSERT_EQ(rgn->base, memblock_start_of_DRAM());
+ ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+ ASSERT_EQ(memblock_get_region_node(rgn), 0);
+ rgn = &memblock.memory.regions[1];
+ ASSERT_EQ(rgn->base, memblock_start_of_DRAM() + memblock_phys_mem_size() / 2);
+ ASSERT_EQ(rgn->size, memblock_phys_mem_size() / 2);
+ ASSERT_EQ(memblock_get_region_node(rgn), 1);
+
+ /* Reserve 126 regions with the last one across node boundary */
+ for (i = 0; i < 125; i++)
+ memblock_reserve(memblock_start_of_DRAM() + SZ_16 * i, SZ_8);
+
+ memblock_reserve(memblock_start_of_DRAM() + memblock_phys_mem_size() / 2 - SZ_8,
+ SZ_16);
+
+ /*
+ * Commit 61167ad5fecd ("mm: pass nid to reserve_bootmem_region()")
+ * do following process to set nid to each memblock.reserved region.
+ * But it may miss some region if memblock_set_node() double the
+ * array.
+ *
+ * By checking 'max', we make sure all region nid is set properly.
+ */
+repeat:
+ max_reserved = memblock.reserved.max;
+ for_each_mem_region(rgn) {
+ int nid = memblock_get_region_node(rgn);
+
+ memblock_set_node(rgn->base, rgn->size, &memblock.reserved, nid);
+ }
+ if (max_reserved != memblock.reserved.max)
+ goto repeat;
+
+ /* Confirm each region has valid node set */
+ for_each_reserved_mem_region(rgn) {
+ ASSERT_TRUE(numa_valid_node(memblock_get_region_node(rgn)));
+ if (rgn == (memblock.reserved.regions + memblock.reserved.cnt - 1))
+ ASSERT_EQ(1, memblock_get_region_node(rgn));
+ else
+ ASSERT_EQ(0, memblock_get_region_node(rgn));
+ }
+
+ dummy_physical_memory_cleanup();
+
+ /*
+ * The current reserved.regions is occupying a range of memory that
+ * allocated from dummy_physical_memory_init(). After free the memory,
+ * we must not use it. So restore the origin memory region to make sure
+ * the tests can run as normal and not affected by the double array.
+ */
+ memblock.reserved.regions = orig_region;
+ memblock.reserved.cnt = INIT_MEMBLOCK_RESERVED_REGIONS;
+
+ test_pass_pop();
+
+ return 0;
+}
+
+static int memblock_set_node_checks(void)
+{
+ prefix_reset();
+ prefix_push("memblock_set_node");
+ test_print("Running memblock_set_node tests...\n");
+
+ memblock_set_node_check();
+
+ prefix_pop();
+
+ return 0;
+}
+#else
+static int memblock_set_node_checks(void)
+{
+ return 0;
+}
+#endif
+
int memblock_basic_checks(void)
{
memblock_initialization_check();
@@ -2444,6 +2545,7 @@ int memblock_basic_checks(void)
memblock_bottom_up_checks();
memblock_trim_memory_checks();
memblock_overlaps_region_checks();
+ memblock_set_node_checks();
return 0;
}
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c77c8c8e3d9bd..80fb84fa3cfcb 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -121,6 +121,7 @@ TARGETS += user_events
TARGETS += vDSO
TARGETS += mm
TARGETS += x86
+TARGETS += x86/bugs
TARGETS += zram
#Please keep the TARGETS list alphabetically sorted
# Run "make quicktest=1 run_tests" or
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index 3720b7611523b..e1495a4bbc99c 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -158,7 +158,6 @@ CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_TUN=y
CONFIG_UNIX=y
CONFIG_UPROBES=y
-CONFIG_USELIB=y
CONFIG_USER_NS=y
CONFIG_VETH=y
CONFIG_VLAN_8021Q=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index 706931a8c2c69..26c3bc2ce11d5 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -128,7 +128,6 @@ CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_TUN=y
CONFIG_UNIX=y
CONFIG_UPROBES=y
-CONFIG_USELIB=y
CONFIG_USER_NS=y
CONFIG_VETH=y
CONFIG_VLAN_8021Q=y
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 09f6487f58b9c..5fea3209566ed 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -6,6 +6,7 @@
#include "for_each_array_map_elem.skel.h"
#include "for_each_map_elem_write_key.skel.h"
#include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
static unsigned int duration;
@@ -203,6 +204,40 @@ out:
for_each_multi_maps__destroy(skel);
}
+static void test_hash_modify(void)
+{
+ struct for_each_hash_modify *skel;
+ int max_entries, i, err;
+ __u64 key, val;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1
+ );
+
+ skel = for_each_hash_modify__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+ return;
+
+ max_entries = bpf_map__max_entries(skel->maps.hashmap);
+ for (i = 0; i < max_entries; i++) {
+ key = i;
+ val = i;
+ err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+ &val, sizeof(val), BPF_ANY);
+ if (!ASSERT_OK(err, "map_update"))
+ goto out;
+ }
+
+ err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+ ASSERT_OK(err, "bpf_prog_test_run_opts");
+ ASSERT_OK(topts.retval, "retval");
+
+out:
+ for_each_hash_modify__destroy(skel);
+}
+
void test_for_each(void)
{
if (test__start_subtest("hash_map"))
@@ -213,4 +248,6 @@ void test_for_each(void)
test_write_map_key();
if (test__start_subtest("multi_maps"))
test_multi_maps();
+ if (test__start_subtest("hash_modify"))
+ test_hash_modify();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 2d0796314862a..0a99fd404f6dc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -68,7 +68,6 @@ static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
goto close_cli;
err = disconnect(cli);
- ASSERT_OK(err, "disconnect");
close_cli:
close(cli);
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 13a2e22f54658..863df7c0fdd02 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -221,7 +221,7 @@
#define CAN_USE_GOTOL
#endif
-#if _clang_major__ >= 18
+#if __clang_major__ >= 18
#define CAN_USE_BPF_ST
#endif
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_modify.c b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
new file mode 100644
index 0000000000000..82307166f7892
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Intel Corporation */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 128);
+ __type(key, __u64);
+ __type(value, __u64);
+} hashmap SEC(".maps");
+
+static int cb(struct bpf_map *map, __u64 *key, __u64 *val, void *arg)
+{
+ bpf_map_delete_elem(map, key);
+ bpf_map_update_elem(map, key, val, 0);
+ return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+ (void)skb;
+
+ bpf_for_each_map_elem(&hashmap, cb, NULL, 0);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
index 137b2364a0820..9984413be9f06 100644
--- a/tools/testing/selftests/coredump/stackdump_test.c
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -1,14 +1,20 @@
// SPDX-License-Identifier: GPL-2.0
#include <fcntl.h>
+#include <inttypes.h>
#include <libgen.h>
#include <linux/limits.h>
#include <pthread.h>
#include <string.h>
+#include <sys/mount.h>
#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/un.h>
#include <unistd.h>
#include "../kselftest_harness.h"
+#include "../pidfd/pidfd.h"
#define STACKDUMP_FILE "stack_values"
#define STACKDUMP_SCRIPT "stackdump"
@@ -35,6 +41,7 @@ static void crashing_child(void)
FIXTURE(coredump)
{
char original_core_pattern[256];
+ pid_t pid_coredump_server;
};
FIXTURE_SETUP(coredump)
@@ -44,6 +51,7 @@ FIXTURE_SETUP(coredump)
char *dir;
int ret;
+ self->pid_coredump_server = -ESRCH;
file = fopen("/proc/sys/kernel/core_pattern", "r");
ASSERT_NE(NULL, file);
@@ -61,10 +69,17 @@ FIXTURE_TEARDOWN(coredump)
{
const char *reason;
FILE *file;
- int ret;
+ int ret, status;
unlink(STACKDUMP_FILE);
+ if (self->pid_coredump_server > 0) {
+ kill(self->pid_coredump_server, SIGTERM);
+ waitpid(self->pid_coredump_server, &status, 0);
+ }
+ unlink("/tmp/coredump.file");
+ unlink("/tmp/coredump.socket");
+
file = fopen("/proc/sys/kernel/core_pattern", "w");
if (!file) {
reason = "Unable to open core_pattern";
@@ -89,14 +104,14 @@ fail:
fprintf(stderr, "Failed to cleanup stackdump test: %s\n", reason);
}
-TEST_F(coredump, stackdump)
+TEST_F_TIMEOUT(coredump, stackdump, 120)
{
struct sigaction action = {};
unsigned long long stack;
char *test_dir, *line;
size_t line_length;
char buf[PATH_MAX];
- int ret, i;
+ int ret, i, status;
FILE *file;
pid_t pid;
@@ -129,6 +144,10 @@ TEST_F(coredump, stackdump)
/*
* Step 3: Wait for the stackdump script to write the stack pointers to the stackdump file
*/
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_TRUE(WCOREDUMP(status));
+
for (i = 0; i < 10; ++i) {
file = fopen(STACKDUMP_FILE, "r");
if (file)
@@ -138,14 +157,466 @@ TEST_F(coredump, stackdump)
ASSERT_NE(file, NULL);
/* Step 4: Make sure all stack pointer values are non-zero */
+ line = NULL;
for (i = 0; -1 != getline(&line, &line_length, file); ++i) {
stack = strtoull(line, NULL, 10);
ASSERT_NE(stack, 0);
}
+ free(line);
ASSERT_EQ(i, 1 + NUM_THREAD_SPAWN);
fclose(file);
}
+TEST_F(coredump, socket)
+{
+ int fd, pidfd, ret, status;
+ FILE *file;
+ pid_t pid, pid_coredump_server;
+ struct stat st;
+ char core_file[PATH_MAX];
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+ const struct sockaddr_un coredump_sk = {
+ .sun_family = AF_UNIX,
+ .sun_path = "/tmp/coredump.socket",
+ };
+ size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
+ sizeof("/tmp/coredump.socket");
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ ASSERT_NE(file, NULL);
+
+ ret = fprintf(file, "@/tmp/coredump.socket");
+ ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
+ ASSERT_EQ(fclose(file), 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file;
+ socklen_t fd_peer_pidfd_len;
+
+ close(ipc_sockets[0]);
+
+ fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+ if (fd_server < 0)
+ _exit(EXIT_FAILURE);
+
+ ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to bind coredump socket\n");
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ ret = listen(fd_server, 1);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to listen on coredump socket\n");
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "Failed to accept coredump socket connection\n");
+ close(fd_server);
+ _exit(EXIT_FAILURE);
+ }
+
+ fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
+ ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD,
+ &fd_peer_pidfd, &fd_peer_pidfd_len);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n");
+ close(fd_coredump);
+ close(fd_server);
+ _exit(EXIT_FAILURE);
+ }
+
+ memset(&info, 0, sizeof(info));
+ info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+ ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "Missing coredump information from coredumping task\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "Received connection from non-coredumping task\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ fd_core_file = creat("/tmp/coredump.file", 0644);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "Failed to create coredump file\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read, bytes_write;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ close(fd_core_file);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (bytes_read == 0)
+ break;
+
+ bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_read != bytes_write) {
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ close(fd_core_file);
+ _exit(EXIT_FAILURE);
+ }
+ }
+
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ close(fd_core_file);
+ _exit(EXIT_SUCCESS);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_TRUE(WCOREDUMP(status));
+
+ info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+ ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0);
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ waitpid(pid_coredump_server, &status, 0);
+ self->pid_coredump_server = -ESRCH;
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
+ ASSERT_GT(st.st_size, 0);
+ /*
+ * We should somehow validate the produced core file.
+ * For now just allow for visual inspection
+ */
+ system("file /tmp/coredump.file");
+}
+
+TEST_F(coredump, socket_detect_userspace_client)
+{
+ int fd, pidfd, ret, status;
+ FILE *file;
+ pid_t pid, pid_coredump_server;
+ struct stat st;
+ char core_file[PATH_MAX];
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+ const struct sockaddr_un coredump_sk = {
+ .sun_family = AF_UNIX,
+ .sun_path = "/tmp/coredump.socket",
+ };
+ size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
+ sizeof("/tmp/coredump.socket");
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ ASSERT_NE(file, NULL);
+
+ ret = fprintf(file, "@/tmp/coredump.socket");
+ ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
+ ASSERT_EQ(fclose(file), 0);
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file;
+ socklen_t fd_peer_pidfd_len;
+
+ close(ipc_sockets[0]);
+
+ fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+ if (fd_server < 0)
+ _exit(EXIT_FAILURE);
+
+ ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to bind coredump socket\n");
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ ret = listen(fd_server, 1);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to listen on coredump socket\n");
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "Failed to accept coredump socket connection\n");
+ close(fd_server);
+ _exit(EXIT_FAILURE);
+ }
+
+ fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
+ ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD,
+ &fd_peer_pidfd, &fd_peer_pidfd_len);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n");
+ close(fd_coredump);
+ close(fd_server);
+ _exit(EXIT_FAILURE);
+ }
+
+ memset(&info, 0, sizeof(info));
+ info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+ ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "Missing coredump information from coredumping task\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (info.coredump_mask & PIDFD_COREDUMPED) {
+ fprintf(stderr, "Received unexpected connection from coredumping task\n");
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ _exit(EXIT_FAILURE);
+ }
+
+ close(fd_coredump);
+ close(fd_server);
+ close(fd_peer_pidfd);
+ close(fd_core_file);
+ _exit(EXIT_SUCCESS);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0) {
+ int fd_socket;
+ ssize_t ret;
+
+ fd_socket = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (fd_socket < 0)
+ _exit(EXIT_FAILURE);
+
+
+ ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+ if (ret < 0)
+ _exit(EXIT_FAILURE);
+
+ (void *)write(fd_socket, &(char){ 0 }, 1);
+ close(fd_socket);
+ _exit(EXIT_SUCCESS);
+ }
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+ ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0);
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ waitpid(pid_coredump_server, &status, 0);
+ self->pid_coredump_server = -ESRCH;
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_NE(stat("/tmp/coredump.file", &st), 0);
+ ASSERT_EQ(errno, ENOENT);
+}
+
+TEST_F(coredump, socket_enoent)
+{
+ int pidfd, ret, status;
+ FILE *file;
+ pid_t pid;
+ char core_file[PATH_MAX];
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ ASSERT_NE(file, NULL);
+
+ ret = fprintf(file, "@/tmp/coredump.socket");
+ ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
+ ASSERT_EQ(fclose(file), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+}
+
+TEST_F(coredump, socket_no_listener)
+{
+ int pidfd, ret, status;
+ FILE *file;
+ pid_t pid, pid_coredump_server;
+ int ipc_sockets[2];
+ char c;
+ const struct sockaddr_un coredump_sk = {
+ .sun_family = AF_UNIX,
+ .sun_path = "/tmp/coredump.socket",
+ };
+ size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
+ sizeof("/tmp/coredump.socket");
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ ASSERT_NE(file, NULL);
+
+ ret = fprintf(file, "@/tmp/coredump.socket");
+ ASSERT_EQ(ret, strlen("@/tmp/coredump.socket"));
+ ASSERT_EQ(fclose(file), 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server;
+ socklen_t fd_peer_pidfd_len;
+
+ close(ipc_sockets[0]);
+
+ fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+ if (fd_server < 0)
+ _exit(EXIT_FAILURE);
+
+ ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to bind coredump socket\n");
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_FAILURE);
+ }
+
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(EXIT_SUCCESS);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ waitpid(pid_coredump_server, &status, 0);
+ self->pid_coredump_server = -ESRCH;
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
new file mode 120000
index 0000000000000..d16a65e7595d9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
@@ -0,0 +1 @@
+run_net_forwarding_test.sh \ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
index 9f271ab6ec04e..6a0378e06cabd 100755
--- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -35,6 +35,7 @@ def test_zcrx(cfg) -> None:
rx_ring = _get_rx_ring_entries(cfg)
try:
+ ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
@@ -48,6 +49,7 @@ def test_zcrx(cfg) -> None:
ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
def test_zcrx_oneshot(cfg) -> None:
@@ -59,6 +61,7 @@ def test_zcrx_oneshot(cfg) -> None:
rx_ring = _get_rx_ring_entries(cfg)
try:
+ ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
@@ -72,6 +75,7 @@ def test_zcrx_oneshot(cfg) -> None:
ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
def main() -> None:
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 2bf14ac2b8c62..9d48004ff1a17 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -431,6 +431,22 @@ static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
return 0;
}
+static struct netdev_queue_id *create_queues(void)
+{
+ struct netdev_queue_id *queues;
+ size_t i = 0;
+
+ queues = calloc(num_queues, sizeof(*queues));
+ for (i = 0; i < num_queues; i++) {
+ queues[i]._present.type = 1;
+ queues[i]._present.id = 1;
+ queues[i].type = NETDEV_QUEUE_TYPE_RX;
+ queues[i].id = start_queue + i;
+ }
+
+ return queues;
+}
+
int do_server(struct memory_buffer *mem)
{
char ctrl_data[sizeof(int) * 20000];
@@ -448,7 +464,6 @@ int do_server(struct memory_buffer *mem)
char buffer[256];
int socket_fd;
int client_fd;
- size_t i = 0;
int ret;
ret = parse_address(server_ip, atoi(port), &server_sin);
@@ -471,16 +486,7 @@ int do_server(struct memory_buffer *mem)
sleep(1);
- queues = malloc(sizeof(*queues) * num_queues);
-
- for (i = 0; i < num_queues; i++) {
- queues[i]._present.type = 1;
- queues[i]._present.id = 1;
- queues[i].type = NETDEV_QUEUE_TYPE_RX;
- queues[i].id = start_queue + i;
- }
-
- if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
error(1, 0, "Failed to bind\n");
tmp_mem = malloc(mem->size);
@@ -545,7 +551,6 @@ int do_server(struct memory_buffer *mem)
goto cleanup;
}
- i++;
for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
if (cm->cmsg_level != SOL_SOCKET ||
(cm->cmsg_type != SCM_DEVMEM_DMABUF &&
@@ -630,10 +635,8 @@ cleanup:
void run_devmem_tests(void)
{
- struct netdev_queue_id *queues;
struct memory_buffer *mem;
struct ynl_sock *ys;
- size_t i = 0;
mem = provider->alloc(getpagesize() * NUM_PAGES);
@@ -641,38 +644,24 @@ void run_devmem_tests(void)
if (configure_rss())
error(1, 0, "rss error\n");
- queues = calloc(num_queues, sizeof(*queues));
-
if (configure_headersplit(1))
error(1, 0, "Failed to configure header split\n");
- if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (!bind_rx_queue(ifindex, mem->fd,
+ calloc(num_queues, sizeof(struct netdev_queue_id)),
+ num_queues, &ys))
error(1, 0, "Binding empty queues array should have failed\n");
- for (i = 0; i < num_queues; i++) {
- queues[i]._present.type = 1;
- queues[i]._present.id = 1;
- queues[i].type = NETDEV_QUEUE_TYPE_RX;
- queues[i].id = start_queue + i;
- }
-
if (configure_headersplit(0))
error(1, 0, "Failed to configure header split\n");
- if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (!bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
error(1, 0, "Configure dmabuf with header split off should have failed\n");
if (configure_headersplit(1))
error(1, 0, "Failed to configure header split\n");
- for (i = 0; i < num_queues; i++) {
- queues[i]._present.type = 1;
- queues[i]._present.id = 1;
- queues[i].type = NETDEV_QUEUE_TYPE_RX;
- queues[i].id = start_queue + i;
- }
-
- if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys))
+ if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys))
error(1, 0, "Failed to bind\n");
/* Deactivating a bound queue should not be legal */
diff --git a/tools/testing/selftests/drivers/net/ocelot/psfp.sh b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
index bed748dde4b06..8972f42dfe03e 100755
--- a/tools/testing/selftests/drivers/net/ocelot/psfp.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
@@ -266,18 +266,14 @@ run_test()
"${base_time}" \
"${CYCLE_TIME_NS}" \
"${SHIFT_TIME_NS}" \
+ "${GATE_DURATION_NS}" \
"${NUM_PKTS}" \
"${STREAM_VID}" \
"${STREAM_PRIO}" \
"" \
"${isochron_dat}"
- # Count all received packets by looking at the non-zero RX timestamps
- received=$(isochron report \
- --input-file "${isochron_dat}" \
- --printf-format "%u\n" --printf-args "R" | \
- grep -w -v '0' | wc -l)
-
+ received=$(isochron_report_num_received "${isochron_dat}")
if [ "${received}" = "${expected}" ]; then
RET=0
else
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 4b68228660661..af8df2313a3b4 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -9,11 +9,11 @@ from lib.py import EthtoolFamily, NetDrvEpEnv
from lib.py import bkg, cmd, wait_port_listen, rand_port
from lib.py import defer, ethtool, ip
-remote_ifname=""
no_sleep=False
def _test_v4(cfg) -> None:
- cfg.require_ipver("4")
+ if not cfg.addr_v["4"]:
+ return
cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
@@ -21,7 +21,8 @@ def _test_v4(cfg) -> None:
cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
def _test_v6(cfg) -> None:
- cfg.require_ipver("6")
+ if not cfg.addr_v["6"]:
+ return
cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"])
cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote)
@@ -57,7 +58,7 @@ def _set_offload_checksum(cfg, netnl, on) -> None:
def _set_xdp_generic_sb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
@@ -66,8 +67,8 @@ def _set_xdp_generic_sb_on(cfg) -> None:
def _set_xdp_generic_mb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
- defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+ defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off")
@@ -76,7 +77,7 @@ def _set_xdp_generic_mb_on(cfg) -> None:
def _set_xdp_native_sb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
@@ -93,8 +94,8 @@ def _set_xdp_native_sb_on(cfg) -> None:
def _set_xdp_native_mb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
- defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+ defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
try:
cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
@@ -112,18 +113,15 @@ def _set_xdp_offload_on(cfg) -> None:
except Exception as e:
raise KsftSkipEx('device does not support offloaded XDP')
defer(ip, f"link set dev {cfg.ifname} xdpoffload off")
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
if no_sleep != True:
time.sleep(10)
def get_interface_info(cfg) -> None:
- global remote_ifname
global no_sleep
- remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
- remote_ifname = remote_info.rstrip('\n')
- if remote_ifname == "":
+ if cfg.remote_ifname == "":
raise KsftFailEx('Can not get remote interface')
local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim":
@@ -136,15 +134,25 @@ def set_interface_init(cfg) -> None:
cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True)
cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True)
cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True)
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+def test_default_v4(cfg, netnl) -> None:
+ cfg.require_ipver("4")
-def test_default(cfg, netnl) -> None:
_set_offload_checksum(cfg, netnl, "off")
_test_v4(cfg)
- _test_v6(cfg)
_test_tcp(cfg)
_set_offload_checksum(cfg, netnl, "on")
_test_v4(cfg)
+ _test_tcp(cfg)
+
+def test_default_v6(cfg, netnl) -> None:
+ cfg.require_ipver("6")
+
+ _set_offload_checksum(cfg, netnl, "off")
+ _test_v6(cfg)
+ _test_tcp(cfg)
+ _set_offload_checksum(cfg, netnl, "on")
_test_v6(cfg)
_test_tcp(cfg)
@@ -202,7 +210,8 @@ def main() -> None:
with NetDrvEpEnv(__file__) as cfg:
get_interface_info(cfg)
set_interface_init(cfg)
- ksft_run([test_default,
+ ksft_run([test_default_v4,
+ test_default_v6,
test_xdp_generic_sb,
test_xdp_generic_mb,
test_xdp_native_sb,
diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
index 828b66a10c63f..7afa58e2bb200 100644
--- a/tools/testing/selftests/filesystems/.gitignore
+++ b/tools/testing/selftests/filesystems/.gitignore
@@ -2,3 +2,4 @@
dnotify_test
devpts_pts
file_stressor
+anon_inode_test
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 66305fc34c60d..b02326193fee5 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := devpts_pts file_stressor
+TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test
TEST_GEN_PROGS_EXTENDED := dnotify_test
include ../lib.mk
diff --git a/tools/testing/selftests/filesystems/anon_inode_test.c b/tools/testing/selftests/filesystems/anon_inode_test.c
new file mode 100644
index 0000000000000..e8e0ef1460d27
--- /dev/null
+++ b/tools/testing/selftests/filesystems/anon_inode_test.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <sys/stat.h>
+
+#include "../kselftest_harness.h"
+#include "overlayfs/wrappers.h"
+
+TEST(anon_inode_no_chown)
+{
+ int fd_context;
+
+ fd_context = sys_fsopen("tmpfs", 0);
+ ASSERT_GE(fd_context, 0);
+
+ ASSERT_LT(fchown(fd_context, 1234, 5678), 0);
+ ASSERT_EQ(errno, EOPNOTSUPP);
+
+ EXPECT_EQ(close(fd_context), 0);
+}
+
+TEST(anon_inode_no_chmod)
+{
+ int fd_context;
+
+ fd_context = sys_fsopen("tmpfs", 0);
+ ASSERT_GE(fd_context, 0);
+
+ ASSERT_LT(fchmod(fd_context, 0777), 0);
+ ASSERT_EQ(errno, EOPNOTSUPP);
+
+ EXPECT_EQ(close(fd_context), 0);
+}
+
+TEST(anon_inode_no_exec)
+{
+ int fd_context;
+
+ fd_context = sys_fsopen("tmpfs", 0);
+ ASSERT_GE(fd_context, 0);
+
+ ASSERT_LT(execveat(fd_context, "", NULL, NULL, AT_EMPTY_PATH), 0);
+ ASSERT_EQ(errno, EACCES);
+
+ EXPECT_EQ(close(fd_context), 0);
+}
+
+TEST(anon_inode_no_open)
+{
+ int fd_context;
+
+ fd_context = sys_fsopen("tmpfs", 0);
+ ASSERT_GE(fd_context, 0);
+
+ ASSERT_GE(dup2(fd_context, 500), 0);
+ ASSERT_EQ(close(fd_context), 0);
+ fd_context = 500;
+
+ ASSERT_LT(open("/proc/self/fd/500", 0), 0);
+ ASSERT_EQ(errno, ENXIO);
+
+ EXPECT_EQ(close(fd_context), 0);
+}
+
+TEST_HARNESS_MAIN
+
diff --git a/tools/testing/selftests/filesystems/mount-notify/.gitignore b/tools/testing/selftests/filesystems/mount-notify/.gitignore
index 82a4846cbc4b2..124339ea78451 100644
--- a/tools/testing/selftests/filesystems/mount-notify/.gitignore
+++ b/tools/testing/selftests/filesystems/mount-notify/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
/*_test
+/*_test_ns
diff --git a/tools/testing/selftests/filesystems/mount-notify/Makefile b/tools/testing/selftests/filesystems/mount-notify/Makefile
index 10be0227b5aea..836a4eb7be062 100644
--- a/tools/testing/selftests/filesystems/mount-notify/Makefile
+++ b/tools/testing/selftests/filesystems/mount-notify/Makefile
@@ -1,6 +1,11 @@
# SPDX-License-Identifier: GPL-2.0-or-later
-CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
-TEST_GEN_PROGS := mount-notify_test
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+LDLIBS += -lcap
+
+TEST_GEN_PROGS := mount-notify_test mount-notify_test_ns
include ../../lib.mk
+
+$(OUTPUT)/mount-notify_test: ../utils.c
+$(OUTPUT)/mount-notify_test_ns: ../utils.c
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 4a2d5c454fd15..63ce708d93ed0 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -8,48 +8,34 @@
#include <string.h>
#include <sys/stat.h>
#include <sys/mount.h>
-#include <linux/fanotify.h>
#include <unistd.h>
-#include <sys/fanotify.h>
#include <sys/syscall.h>
#include "../../kselftest_harness.h"
#include "../statmount/statmount.h"
+#include "../utils.h"
-#ifndef FAN_MNT_ATTACH
-struct fanotify_event_info_mnt {
- struct fanotify_event_info_header hdr;
- __u64 mnt_id;
-};
-#define FAN_MNT_ATTACH 0x01000000 /* Mount was attached */
-#endif
-
-#ifndef FAN_MNT_DETACH
-#define FAN_MNT_DETACH 0x02000000 /* Mount was detached */
-#endif
-
-#ifndef FAN_REPORT_MNT
-#define FAN_REPORT_MNT 0x00004000 /* Report mount events */
+// Needed for linux/fanotify.h
+#ifndef __kernel_fsid_t
+typedef struct {
+ int val[2];
+} __kernel_fsid_t;
#endif
-#ifndef FAN_MARK_MNTNS
-#define FAN_MARK_MNTNS 0x00000110
-#endif
+#include <sys/fanotify.h>
-static uint64_t get_mnt_id(struct __test_metadata *const _metadata,
- const char *path)
-{
- struct statx sx;
+static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
- ASSERT_EQ(statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx), 0);
- ASSERT_TRUE(!!(sx.stx_mask & STATX_MNT_ID_UNIQUE));
- return sx.stx_mnt_id;
-}
+static const int mark_cmds[] = {
+ FAN_MARK_ADD,
+ FAN_MARK_REMOVE,
+ FAN_MARK_FLUSH
+};
-static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
+#define NUM_FAN_FDS ARRAY_SIZE(mark_cmds)
FIXTURE(fanotify) {
- int fan_fd;
+ int fan_fd[NUM_FAN_FDS];
char buf[256];
unsigned int rem;
void *next;
@@ -61,7 +47,7 @@ FIXTURE(fanotify) {
FIXTURE_SETUP(fanotify)
{
- int ret;
+ int i, ret;
ASSERT_EQ(unshare(CLONE_NEWNS), 0);
@@ -86,23 +72,37 @@ FIXTURE_SETUP(fanotify)
ASSERT_EQ(mkdir("b", 0700), 0);
- self->root_id = get_mnt_id(_metadata, "/");
+ self->root_id = get_unique_mnt_id("/");
ASSERT_NE(self->root_id, 0);
- self->fan_fd = fanotify_init(FAN_REPORT_MNT, 0);
- ASSERT_GE(self->fan_fd, 0);
-
- ret = fanotify_mark(self->fan_fd, FAN_MARK_ADD | FAN_MARK_MNTNS,
- FAN_MNT_ATTACH | FAN_MNT_DETACH, self->ns_fd, NULL);
- ASSERT_EQ(ret, 0);
+ for (i = 0; i < NUM_FAN_FDS; i++) {
+ self->fan_fd[i] = fanotify_init(FAN_REPORT_MNT | FAN_NONBLOCK,
+ 0);
+ ASSERT_GE(self->fan_fd[i], 0);
+ ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ // On fd[0] we do an extra ADD that changes nothing.
+ // On fd[1]/fd[2] we REMOVE/FLUSH which removes the mark.
+ ret = fanotify_mark(self->fan_fd[i], mark_cmds[i] |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ }
self->rem = 0;
}
FIXTURE_TEARDOWN(fanotify)
{
+ int i;
+
ASSERT_EQ(self->rem, 0);
- close(self->fan_fd);
+ for (i = 0; i < NUM_FAN_FDS; i++)
+ close(self->fan_fd[i]);
ASSERT_EQ(fchdir(self->orig_root), 0);
@@ -123,8 +123,21 @@ static uint64_t expect_notify(struct __test_metadata *const _metadata,
unsigned int thislen;
if (!self->rem) {
- ssize_t len = read(self->fan_fd, self->buf, sizeof(self->buf));
- ASSERT_GT(len, 0);
+ ssize_t len;
+ int i;
+
+ for (i = NUM_FAN_FDS - 1; i >= 0; i--) {
+ len = read(self->fan_fd[i], self->buf,
+ sizeof(self->buf));
+ if (i > 0) {
+ // Groups 1,2 should get EAGAIN
+ ASSERT_EQ(len, -1);
+ ASSERT_EQ(errno, EAGAIN);
+ } else {
+ // Group 0 should get events
+ ASSERT_GT(len, 0);
+ }
+ }
self->rem = len;
self->next = (void *) self->buf;
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
new file mode 100644
index 0000000000000..090a5ca65004a
--- /dev/null
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
@@ -0,0 +1,557 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <unistd.h>
+#include <sys/syscall.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[] = {
+ FAN_MARK_FILESYSTEM,
+ FAN_MARK_MOUNT,
+ FAN_MARK_INODE
+};
+
+static const int mark_cmds[] = {
+ FAN_MARK_ADD,
+ FAN_MARK_REMOVE,
+ FAN_MARK_FLUSH
+};
+
+#define NUM_FAN_FDS ARRAY_SIZE(mark_cmds)
+
+FIXTURE(fanotify) {
+ int fan_fd[NUM_FAN_FDS];
+ char buf[256];
+ unsigned int rem;
+ void *next;
+ char root_mntpoint[sizeof(root_mntpoint_templ)];
+ int orig_root;
+ int orig_ns_fd;
+ int ns_fd;
+ uint64_t root_id;
+};
+
+FIXTURE_SETUP(fanotify)
+{
+ int i, ret;
+
+ self->orig_ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+ ASSERT_GE(self->orig_ns_fd, 0);
+
+ ret = setup_userns();
+ ASSERT_EQ(ret, 0);
+
+ self->ns_fd = open("/proc/self/ns/mnt", O_RDONLY);
+ ASSERT_GE(self->ns_fd, 0);
+
+ strcpy(self->root_mntpoint, root_mntpoint_templ);
+ ASSERT_NE(mkdtemp(self->root_mntpoint), NULL);
+
+ self->orig_root = open("/", O_PATH | O_CLOEXEC);
+ ASSERT_GE(self->orig_root, 0);
+
+ ASSERT_EQ(mount("tmpfs", self->root_mntpoint, "tmpfs", 0, NULL), 0);
+
+ ASSERT_EQ(chroot(self->root_mntpoint), 0);
+
+ ASSERT_EQ(chdir("/"), 0);
+
+ ASSERT_EQ(mkdir("a", 0700), 0);
+
+ ASSERT_EQ(mkdir("b", 0700), 0);
+
+ self->root_id = get_unique_mnt_id("/");
+ ASSERT_NE(self->root_id, 0);
+
+ for (i = 0; i < NUM_FAN_FDS; i++) {
+ int fan_fd = fanotify_init(FAN_REPORT_FID, 0);
+ // Verify that watching tmpfs mounted inside userns is allowed
+ ret = fanotify_mark(fan_fd, FAN_MARK_ADD | mark_types[i],
+ FAN_OPEN, AT_FDCWD, "/");
+ ASSERT_EQ(ret, 0);
+ // ...but watching entire orig root filesystem is not allowed
+ ret = fanotify_mark(fan_fd, FAN_MARK_ADD | FAN_MARK_FILESYSTEM,
+ FAN_OPEN, self->orig_root, ".");
+ ASSERT_NE(ret, 0);
+ close(fan_fd);
+
+ self->fan_fd[i] = fanotify_init(FAN_REPORT_MNT | FAN_NONBLOCK,
+ 0);
+ ASSERT_GE(self->fan_fd[i], 0);
+ // Verify that watching mntns where group was created is allowed
+ ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ // ...but watching orig mntns is not allowed
+ ret = fanotify_mark(self->fan_fd[i], FAN_MARK_ADD |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->orig_ns_fd, NULL);
+ ASSERT_NE(ret, 0);
+ // On fd[0] we do an extra ADD that changes nothing.
+ // On fd[1]/fd[2] we REMOVE/FLUSH which removes the mark.
+ ret = fanotify_mark(self->fan_fd[i], mark_cmds[i] |
+ FAN_MARK_MNTNS,
+ FAN_MNT_ATTACH | FAN_MNT_DETACH,
+ self->ns_fd, NULL);
+ ASSERT_EQ(ret, 0);
+ }
+
+ self->rem = 0;
+}
+
+FIXTURE_TEARDOWN(fanotify)
+{
+ int i;
+
+ ASSERT_EQ(self->rem, 0);
+ for (i = 0; i < NUM_FAN_FDS; i++)
+ close(self->fan_fd[i]);
+
+ ASSERT_EQ(fchdir(self->orig_root), 0);
+
+ ASSERT_EQ(chroot("."), 0);
+
+ EXPECT_EQ(umount2(self->root_mntpoint, MNT_DETACH), 0);
+ EXPECT_EQ(chdir(self->root_mntpoint), 0);
+ EXPECT_EQ(chdir("/"), 0);
+ EXPECT_EQ(rmdir(self->root_mntpoint), 0);
+}
+
+static uint64_t expect_notify(struct __test_metadata *const _metadata,
+ FIXTURE_DATA(fanotify) *self,
+ uint64_t *mask)
+{
+ struct fanotify_event_metadata *meta;
+ struct fanotify_event_info_mnt *mnt;
+ unsigned int thislen;
+
+ if (!self->rem) {
+ ssize_t len;
+ int i;
+
+ for (i = NUM_FAN_FDS - 1; i >= 0; i--) {
+ len = read(self->fan_fd[i], self->buf,
+ sizeof(self->buf));
+ if (i > 0) {
+ // Groups 1,2 should get EAGAIN
+ ASSERT_EQ(len, -1);
+ ASSERT_EQ(errno, EAGAIN);
+ } else {
+ // Group 0 should get events
+ ASSERT_GT(len, 0);
+ }
+ }
+
+ self->rem = len;
+ self->next = (void *) self->buf;
+ }
+
+ meta = self->next;
+ ASSERT_TRUE(FAN_EVENT_OK(meta, self->rem));
+
+ thislen = meta->event_len;
+ self->rem -= thislen;
+ self->next += thislen;
+
+ *mask = meta->mask;
+ thislen -= sizeof(*meta);
+
+ mnt = ((void *) meta) + meta->event_len - thislen;
+
+ ASSERT_EQ(thislen, sizeof(*mnt));
+
+ return mnt->mnt_id;
+}
+
+static void expect_notify_n(struct __test_metadata *const _metadata,
+ FIXTURE_DATA(fanotify) *self,
+ unsigned int n, uint64_t mask[], uint64_t mnts[])
+{
+ unsigned int i;
+
+ for (i = 0; i < n; i++)
+ mnts[i] = expect_notify(_metadata, self, &mask[i]);
+}
+
+static uint64_t expect_notify_mask(struct __test_metadata *const _metadata,
+ FIXTURE_DATA(fanotify) *self,
+ uint64_t expect_mask)
+{
+ uint64_t mntid, mask;
+
+ mntid = expect_notify(_metadata, self, &mask);
+ ASSERT_EQ(expect_mask, mask);
+
+ return mntid;
+}
+
+
+static void expect_notify_mask_n(struct __test_metadata *const _metadata,
+ FIXTURE_DATA(fanotify) *self,
+ uint64_t mask, unsigned int n, uint64_t mnts[])
+{
+ unsigned int i;
+
+ for (i = 0; i < n; i++)
+ mnts[i] = expect_notify_mask(_metadata, self, mask);
+}
+
+static void verify_mount_ids(struct __test_metadata *const _metadata,
+ const uint64_t list1[], const uint64_t list2[],
+ size_t num)
+{
+ unsigned int i, j;
+
+ // Check that neither list has any duplicates
+ for (i = 0; i < num; i++) {
+ for (j = 0; j < num; j++) {
+ if (i != j) {
+ ASSERT_NE(list1[i], list1[j]);
+ ASSERT_NE(list2[i], list2[j]);
+ }
+ }
+ }
+ // Check that all list1 memebers can be found in list2. Together with
+ // the above it means that the list1 and list2 represent the same sets.
+ for (i = 0; i < num; i++) {
+ for (j = 0; j < num; j++) {
+ if (list1[i] == list2[j])
+ break;
+ }
+ ASSERT_NE(j, num);
+ }
+}
+
+static void check_mounted(struct __test_metadata *const _metadata,
+ const uint64_t mnts[], size_t num)
+{
+ ssize_t ret;
+ uint64_t *list;
+
+ list = malloc((num + 1) * sizeof(list[0]));
+ ASSERT_NE(list, NULL);
+
+ ret = listmount(LSMT_ROOT, 0, 0, list, num + 1, 0);
+ ASSERT_EQ(ret, num);
+
+ verify_mount_ids(_metadata, mnts, list, num);
+
+ free(list);
+}
+
+static void setup_mount_tree(struct __test_metadata *const _metadata,
+ int log2_num)
+{
+ int ret, i;
+
+ ret = mount("", "/", NULL, MS_SHARED, NULL);
+ ASSERT_EQ(ret, 0);
+
+ for (i = 0; i < log2_num; i++) {
+ ret = mount("/", "/", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+ }
+}
+
+TEST_F(fanotify, bind)
+{
+ int ret;
+ uint64_t mnts[2] = { self->root_id };
+
+ ret = mount("/", "/", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+ ASSERT_NE(mnts[0], mnts[1]);
+
+ check_mounted(_metadata, mnts, 2);
+
+ // Cleanup
+ uint64_t detach_id;
+ ret = umount("/");
+ ASSERT_EQ(ret, 0);
+
+ detach_id = expect_notify_mask(_metadata, self, FAN_MNT_DETACH);
+ ASSERT_EQ(detach_id, mnts[1]);
+
+ check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, move)
+{
+ int ret;
+ uint64_t mnts[2] = { self->root_id };
+ uint64_t move_id;
+
+ ret = mount("/", "/a", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+ ASSERT_NE(mnts[0], mnts[1]);
+
+ check_mounted(_metadata, mnts, 2);
+
+ ret = move_mount(AT_FDCWD, "/a", AT_FDCWD, "/b", 0);
+ ASSERT_EQ(ret, 0);
+
+ move_id = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH | FAN_MNT_DETACH);
+ ASSERT_EQ(move_id, mnts[1]);
+
+ // Cleanup
+ ret = umount("/b");
+ ASSERT_EQ(ret, 0);
+
+ check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, propagate)
+{
+ const unsigned int log2_num = 4;
+ const unsigned int num = (1 << log2_num);
+ uint64_t mnts[num];
+
+ setup_mount_tree(_metadata, log2_num);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, num - 1, mnts + 1);
+
+ mnts[0] = self->root_id;
+ check_mounted(_metadata, mnts, num);
+
+ // Cleanup
+ int ret;
+ uint64_t mnts2[num];
+ ret = umount2("/", MNT_DETACH);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount("", "/", NULL, MS_PRIVATE, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mnts2[0] = self->root_id;
+ expect_notify_mask_n(_metadata, self, FAN_MNT_DETACH, num - 1, mnts2 + 1);
+ verify_mount_ids(_metadata, mnts, mnts2, num);
+
+ check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, fsmount)
+{
+ int ret, fs, mnt;
+ uint64_t mnts[2] = { self->root_id };
+
+ fs = fsopen("tmpfs", 0);
+ ASSERT_GE(fs, 0);
+
+ ret = fsconfig(fs, FSCONFIG_CMD_CREATE, 0, 0, 0);
+ ASSERT_EQ(ret, 0);
+
+ mnt = fsmount(fs, 0, 0);
+ ASSERT_GE(mnt, 0);
+
+ close(fs);
+
+ ret = move_mount(mnt, "", AT_FDCWD, "/a", MOVE_MOUNT_F_EMPTY_PATH);
+ ASSERT_EQ(ret, 0);
+
+ close(mnt);
+
+ mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+ ASSERT_NE(mnts[0], mnts[1]);
+
+ check_mounted(_metadata, mnts, 2);
+
+ // Cleanup
+ uint64_t detach_id;
+ ret = umount("/a");
+ ASSERT_EQ(ret, 0);
+
+ detach_id = expect_notify_mask(_metadata, self, FAN_MNT_DETACH);
+ ASSERT_EQ(detach_id, mnts[1]);
+
+ check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, reparent)
+{
+ uint64_t mnts[6] = { self->root_id };
+ uint64_t dmnts[3];
+ uint64_t masks[3];
+ unsigned int i;
+ int ret;
+
+ // Create setup with a[1] -> b[2] propagation
+ ret = mount("/", "/a", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount("", "/a", NULL, MS_SHARED, NULL);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount("/a", "/b", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount("", "/b", NULL, MS_SLAVE, NULL);
+ ASSERT_EQ(ret, 0);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, 2, mnts + 1);
+
+ check_mounted(_metadata, mnts, 3);
+
+ // Mount on a[3], which is propagated to b[4]
+ ret = mount("/", "/a", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, 2, mnts + 3);
+
+ check_mounted(_metadata, mnts, 5);
+
+ // Mount on b[5], not propagated
+ ret = mount("/", "/b", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mnts[5] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+
+ check_mounted(_metadata, mnts, 6);
+
+ // Umount a[3], which is propagated to b[4], but not b[5]
+ // This will result in b[5] "falling" on b[2]
+ ret = umount("/a");
+ ASSERT_EQ(ret, 0);
+
+ expect_notify_n(_metadata, self, 3, masks, dmnts);
+ verify_mount_ids(_metadata, mnts + 3, dmnts, 3);
+
+ for (i = 0; i < 3; i++) {
+ if (dmnts[i] == mnts[5]) {
+ ASSERT_EQ(masks[i], FAN_MNT_ATTACH | FAN_MNT_DETACH);
+ } else {
+ ASSERT_EQ(masks[i], FAN_MNT_DETACH);
+ }
+ }
+
+ mnts[3] = mnts[5];
+ check_mounted(_metadata, mnts, 4);
+
+ // Cleanup
+ ret = umount("/b");
+ ASSERT_EQ(ret, 0);
+
+ ret = umount("/a");
+ ASSERT_EQ(ret, 0);
+
+ ret = umount("/b");
+ ASSERT_EQ(ret, 0);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_DETACH, 3, dmnts);
+ verify_mount_ids(_metadata, mnts + 1, dmnts, 3);
+
+ check_mounted(_metadata, mnts, 1);
+}
+
+TEST_F(fanotify, rmdir)
+{
+ uint64_t mnts[3] = { self->root_id };
+ int ret;
+
+ ret = mount("/", "/a", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount("/", "/a/b", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH, 2, mnts + 1);
+
+ check_mounted(_metadata, mnts, 3);
+
+ ret = chdir("/a");
+ ASSERT_EQ(ret, 0);
+
+ ret = fork();
+ ASSERT_GE(ret, 0);
+
+ if (ret == 0) {
+ chdir("/");
+ unshare(CLONE_NEWNS);
+ mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
+ umount2("/a", MNT_DETACH);
+ // This triggers a detach in the other namespace
+ rmdir("/a");
+ exit(0);
+ }
+ wait(NULL);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_DETACH, 2, mnts + 1);
+ check_mounted(_metadata, mnts, 1);
+
+ // Cleanup
+ ret = chdir("/");
+ ASSERT_EQ(ret, 0);
+}
+
+TEST_F(fanotify, pivot_root)
+{
+ uint64_t mnts[3] = { self->root_id };
+ uint64_t mnts2[3];
+ int ret;
+
+ ret = mount("tmpfs", "/a", "tmpfs", 0, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mnts[2] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+
+ ret = mkdir("/a/new", 0700);
+ ASSERT_EQ(ret, 0);
+
+ ret = mkdir("/a/old", 0700);
+ ASSERT_EQ(ret, 0);
+
+ ret = mount("/a", "/a/new", NULL, MS_BIND, NULL);
+ ASSERT_EQ(ret, 0);
+
+ mnts[1] = expect_notify_mask(_metadata, self, FAN_MNT_ATTACH);
+ check_mounted(_metadata, mnts, 3);
+
+ ret = syscall(SYS_pivot_root, "/a/new", "/a/new/old");
+ ASSERT_EQ(ret, 0);
+
+ expect_notify_mask_n(_metadata, self, FAN_MNT_ATTACH | FAN_MNT_DETACH, 2, mnts2);
+ verify_mount_ids(_metadata, mnts, mnts2, 2);
+ check_mounted(_metadata, mnts, 3);
+
+ // Cleanup
+ ret = syscall(SYS_pivot_root, "/old", "/old/a/new");
+ ASSERT_EQ(ret, 0);
+
+ ret = umount("/a/new");
+ ASSERT_EQ(ret, 0);
+
+ ret = umount("/a");
+ ASSERT_EQ(ret, 0);
+
+ check_mounted(_metadata, mnts, 1);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/overlayfs/Makefile b/tools/testing/selftests/filesystems/overlayfs/Makefile
index 6c661232b3b56..d3ad4a77db9ba 100644
--- a/tools/testing/selftests/filesystems/overlayfs/Makefile
+++ b/tools/testing/selftests/filesystems/overlayfs/Makefile
@@ -4,7 +4,7 @@ CFLAGS += -Wall
CFLAGS += $(KHDR_INCLUDES)
LDLIBS += -lcap
-LOCAL_HDRS += wrappers.h log.h
+LOCAL_HDRS += ../wrappers.h log.h
TEST_GEN_PROGS := dev_in_maps
TEST_GEN_PROGS += set_layers_via_fds
diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
index 3b796264223f8..31db54b00e64e 100644
--- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
+++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
@@ -17,7 +17,7 @@
#include "../../kselftest.h"
#include "log.h"
-#include "wrappers.h"
+#include "../wrappers.h"
static long get_file_dev_and_inode(void *addr, struct statx *stx)
{
diff --git a/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c b/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c
index 5074e64e74a8a..dc0449fa628f8 100644
--- a/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c
+++ b/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c
@@ -16,7 +16,7 @@
#include "../../pidfd/pidfd.h"
#include "log.h"
#include "../utils.h"
-#include "wrappers.h"
+#include "../wrappers.h"
FIXTURE(set_layers_via_fds) {
int pidfd;
diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile
index 14ee91a416509..8e354fe99b447 100644
--- a/tools/testing/selftests/filesystems/statmount/Makefile
+++ b/tools/testing/selftests/filesystems/statmount/Makefile
@@ -1,6 +1,10 @@
# SPDX-License-Identifier: GPL-2.0-or-later
-CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+LDLIBS += -lcap
+
TEST_GEN_PROGS := statmount_test statmount_test_ns listmount_test
include ../../lib.mk
+
+$(OUTPUT)/statmount_test_ns: ../utils.c
diff --git a/tools/testing/selftests/filesystems/statmount/statmount.h b/tools/testing/selftests/filesystems/statmount/statmount.h
index a7a5289ddae97..99e5ad082fb1e 100644
--- a/tools/testing/selftests/filesystems/statmount/statmount.h
+++ b/tools/testing/selftests/filesystems/statmount/statmount.h
@@ -7,6 +7,42 @@
#include <linux/mount.h>
#include <asm/unistd.h>
+#ifndef __NR_statmount
+ #if defined __alpha__
+ #define __NR_statmount 567
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_statmount 4457
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_statmount 6457
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_statmount 5457
+ #endif
+ #else
+ #define __NR_statmount 457
+ #endif
+#endif
+
+#ifndef __NR_listmount
+ #if defined __alpha__
+ #define __NR_listmount 568
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_listmount 4458
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_listmount 6458
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_listmount 5458
+ #endif
+ #else
+ #define __NR_listmount 458
+ #endif
+#endif
+
static inline int statmount(uint64_t mnt_id, uint64_t mnt_ns_id, uint64_t mask,
struct statmount *buf, size_t bufsize,
unsigned int flags)
diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c
index 70cb0c8b21cf0..605a3fa16bf77 100644
--- a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c
+++ b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c
@@ -14,6 +14,7 @@
#include <linux/stat.h>
#include "statmount.h"
+#include "../utils.h"
#include "../../kselftest.h"
#define NSID_PASS 0
@@ -78,87 +79,10 @@ static int get_mnt_ns_id(const char *mnt_ns, uint64_t *mnt_ns_id)
return NSID_PASS;
}
-static int get_mnt_id(const char *path, uint64_t *mnt_id)
-{
- struct statx sx;
- int ret;
-
- ret = statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx);
- if (ret == -1) {
- ksft_print_msg("retrieving unique mount ID for %s: %s\n", path,
- strerror(errno));
- return NSID_ERROR;
- }
-
- if (!(sx.stx_mask & STATX_MNT_ID_UNIQUE)) {
- ksft_print_msg("no unique mount ID available for %s\n", path);
- return NSID_ERROR;
- }
-
- *mnt_id = sx.stx_mnt_id;
- return NSID_PASS;
-}
-
-static int write_file(const char *path, const char *val)
-{
- int fd = open(path, O_WRONLY);
- size_t len = strlen(val);
- int ret;
-
- if (fd == -1) {
- ksft_print_msg("opening %s for write: %s\n", path, strerror(errno));
- return NSID_ERROR;
- }
-
- ret = write(fd, val, len);
- if (ret == -1) {
- ksft_print_msg("writing to %s: %s\n", path, strerror(errno));
- return NSID_ERROR;
- }
- if (ret != len) {
- ksft_print_msg("short write to %s\n", path);
- return NSID_ERROR;
- }
-
- ret = close(fd);
- if (ret == -1) {
- ksft_print_msg("closing %s\n", path);
- return NSID_ERROR;
- }
-
- return NSID_PASS;
-}
-
static int setup_namespace(void)
{
- int ret;
- char buf[32];
- uid_t uid = getuid();
- gid_t gid = getgid();
-
- ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID);
- if (ret == -1)
- ksft_exit_fail_msg("unsharing mountns and userns: %s\n",
- strerror(errno));
-
- sprintf(buf, "0 %d 1", uid);
- ret = write_file("/proc/self/uid_map", buf);
- if (ret != NSID_PASS)
- return ret;
- ret = write_file("/proc/self/setgroups", "deny");
- if (ret != NSID_PASS)
- return ret;
- sprintf(buf, "0 %d 1", gid);
- ret = write_file("/proc/self/gid_map", buf);
- if (ret != NSID_PASS)
- return ret;
-
- ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
- if (ret == -1) {
- ksft_print_msg("making mount tree private: %s\n",
- strerror(errno));
+ if (setup_userns() != 0)
return NSID_ERROR;
- }
return NSID_PASS;
}
@@ -174,9 +98,9 @@ static int _test_statmount_mnt_ns_id(void)
if (ret != NSID_PASS)
return ret;
- ret = get_mnt_id("/", &root_id);
- if (ret != NSID_PASS)
- return ret;
+ root_id = get_unique_mnt_id("/");
+ if (!root_id)
+ return NSID_ERROR;
ret = statmount(root_id, 0, STATMOUNT_MNT_NS_ID, &sm, sizeof(sm), 0);
if (ret == -1) {
diff --git a/tools/testing/selftests/filesystems/utils.c b/tools/testing/selftests/filesystems/utils.c
index e553c89c5b19a..c43a69dffd83f 100644
--- a/tools/testing/selftests/filesystems/utils.c
+++ b/tools/testing/selftests/filesystems/utils.c
@@ -18,7 +18,10 @@
#include <sys/types.h>
#include <sys/wait.h>
#include <sys/xattr.h>
+#include <sys/mount.h>
+#include "../kselftest.h"
+#include "wrappers.h"
#include "utils.h"
#define MAX_USERNS_LEVEL 32
@@ -447,6 +450,71 @@ out_close:
return fret;
}
+static int write_file(const char *path, const char *val)
+{
+ int fd = open(path, O_WRONLY);
+ size_t len = strlen(val);
+ int ret;
+
+ if (fd == -1) {
+ ksft_print_msg("opening %s for write: %s\n", path, strerror(errno));
+ return -1;
+ }
+
+ ret = write(fd, val, len);
+ if (ret == -1) {
+ ksft_print_msg("writing to %s: %s\n", path, strerror(errno));
+ return -1;
+ }
+ if (ret != len) {
+ ksft_print_msg("short write to %s\n", path);
+ return -1;
+ }
+
+ ret = close(fd);
+ if (ret == -1) {
+ ksft_print_msg("closing %s\n", path);
+ return -1;
+ }
+
+ return 0;
+}
+
+int setup_userns(void)
+{
+ int ret;
+ char buf[32];
+ uid_t uid = getuid();
+ gid_t gid = getgid();
+
+ ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID);
+ if (ret) {
+ ksft_exit_fail_msg("unsharing mountns and userns: %s\n",
+ strerror(errno));
+ return ret;
+ }
+
+ sprintf(buf, "0 %d 1", uid);
+ ret = write_file("/proc/self/uid_map", buf);
+ if (ret)
+ return ret;
+ ret = write_file("/proc/self/setgroups", "deny");
+ if (ret)
+ return ret;
+ sprintf(buf, "0 %d 1", gid);
+ ret = write_file("/proc/self/gid_map", buf);
+ if (ret)
+ return ret;
+
+ ret = mount("", "/", NULL, MS_REC|MS_PRIVATE, NULL);
+ if (ret) {
+ ksft_print_msg("making mount tree private: %s\n", strerror(errno));
+ return ret;
+ }
+
+ return 0;
+}
+
/* caps_down - lower all effective caps */
int caps_down(void)
{
@@ -499,3 +567,23 @@ out:
cap_free(caps);
return fret;
}
+
+uint64_t get_unique_mnt_id(const char *path)
+{
+ struct statx sx;
+ int ret;
+
+ ret = statx(AT_FDCWD, path, 0, STATX_MNT_ID_UNIQUE, &sx);
+ if (ret == -1) {
+ ksft_print_msg("retrieving unique mount ID for %s: %s\n", path,
+ strerror(errno));
+ return 0;
+ }
+
+ if (!(sx.stx_mask & STATX_MNT_ID_UNIQUE)) {
+ ksft_print_msg("no unique mount ID available for %s\n", path);
+ return 0;
+ }
+
+ return sx.stx_mnt_id;
+}
diff --git a/tools/testing/selftests/filesystems/utils.h b/tools/testing/selftests/filesystems/utils.h
index 7f1df2a3e94cf..70f7ccc607f49 100644
--- a/tools/testing/selftests/filesystems/utils.h
+++ b/tools/testing/selftests/filesystems/utils.h
@@ -27,6 +27,7 @@ extern int caps_down(void);
extern int cap_down(cap_value_t down);
extern bool switch_ids(uid_t uid, gid_t gid);
+extern int setup_userns(void);
static inline bool switch_userns(int fd, uid_t uid, gid_t gid, bool drop_caps)
{
@@ -42,4 +43,6 @@ static inline bool switch_userns(int fd, uid_t uid, gid_t gid, bool drop_caps)
return true;
}
+extern uint64_t get_unique_mnt_id(const char *path);
+
#endif /* __IDMAP_UTILS_H */
diff --git a/tools/testing/selftests/filesystems/overlayfs/wrappers.h b/tools/testing/selftests/filesystems/wrappers.h
index c38bc48e0cfaf..420ae4f908cf2 100644
--- a/tools/testing/selftests/filesystems/overlayfs/wrappers.h
+++ b/tools/testing/selftests/filesystems/wrappers.h
@@ -9,6 +9,10 @@
#include <linux/mount.h>
#include <sys/syscall.h>
+#ifndef STATX_MNT_ID_UNIQUE
+#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
+#endif
+
static inline int sys_fsopen(const char *fsname, unsigned int flags)
{
return syscall(__NR_fsopen, fsname, flags);
@@ -36,6 +40,28 @@ static inline int sys_mount(const char *src, const char *tgt, const char *fst,
#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
#endif
+#ifndef MOVE_MOUNT_T_EMPTY_PATH
+#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
+#endif
+
+#ifndef __NR_move_mount
+ #if defined __alpha__
+ #define __NR_move_mount 539
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_move_mount 4429
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_move_mount 6429
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_move_mount 5429
+ #endif
+ #else
+ #define __NR_move_mount 429
+ #endif
+#endif
+
static inline int sys_move_mount(int from_dfd, const char *from_pathname,
int to_dfd, const char *to_pathname,
unsigned int flags)
@@ -53,7 +79,25 @@ static inline int sys_move_mount(int from_dfd, const char *from_pathname,
#endif
#ifndef AT_RECURSIVE
-#define AT_RECURSIVE 0x8000
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+#endif
+
+#ifndef __NR_open_tree
+ #if defined __alpha__
+ #define __NR_open_tree 538
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_open_tree 4428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_open_tree 6428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_open_tree 5428
+ #endif
+ #else
+ #define __NR_open_tree 428
+ #endif
#endif
static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
index 6b94b678741a4..f656bccb1a149 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
@@ -7,11 +7,32 @@
MAX_ARGS=128
EXCEED_ARGS=$((MAX_ARGS + 1))
+# bash and dash evaluate variables differently.
+# dash will evaluate '\\' every time it is read whereas bash does not.
+#
+# TEST_STRING="$TEST_STRING \\$i"
+# echo $TEST_STRING
+#
+# With i=123
+# On bash, that will print "\123"
+# but on dash, that will print the escape sequence of \123 as the \ will
+# be interpreted again in the echo.
+#
+# Set a variable "bs" to save a double backslash, then echo that
+# to "ts" to see if $ts changed or not. If it changed, it's dash,
+# if not, it's bash, and then bs can equal a single backslash.
+bs='\\'
+ts=`echo $bs`
+if [ "$ts" = '\\' ]; then
+ # this is bash
+ bs='\'
+fi
+
check_max_args() { # event_header
TEST_STRING=$1
# Acceptable
for i in `seq 1 $MAX_ARGS`; do
- TEST_STRING="$TEST_STRING \\$i"
+ TEST_STRING="$TEST_STRING $bs$i"
done
echo "$TEST_STRING" >> dynamic_events
echo > dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
index 118247b8dd84d..c62165fabd0ce 100644
--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
+++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
@@ -80,6 +80,26 @@ if [ $misscnt -gt 0 ]; then
exit_fail
fi
+# Check strings too
+if [ -f events/syscalls/sys_enter_openat/filter ]; then
+ DIRNAME=`basename $TMPDIR`
+ echo "filename.ustring ~ \"*$DIRNAME*\"" > events/syscalls/sys_enter_openat/filter
+ echo 1 > events/syscalls/sys_enter_openat/enable
+ echo 1 > tracing_on
+ ls /bin/sh
+ nocnt=`grep openat trace | wc -l`
+ ls $TMPDIR
+ echo 0 > tracing_on
+ hitcnt=`grep openat trace | wc -l`;
+ echo 0 > events/syscalls/sys_enter_openat/enable
+ if [ $nocnt -gt 0 ]; then
+ exit_fail
+ fi
+ if [ $hitcnt -eq 0 ]; then
+ exit_fail
+ fi
+fi
+
reset_events_filter
exit 0
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 322b9d3b01255..57708de2075df 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -129,10 +129,10 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = {
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0),
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0),
REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1),
+ REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 1),
REG_FTR_END,
};
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
index b9054086a0c92..18a6014920b5f 100644
--- a/tools/testing/selftests/landlock/audit.h
+++ b/tools/testing/selftests/landlock/audit.h
@@ -300,15 +300,22 @@ out:
return err;
}
-static int __maybe_unused matches_log_domain_allocated(int audit_fd,
+static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid,
__u64 *domain_id)
{
- return audit_match_record(
- audit_fd, AUDIT_LANDLOCK_DOMAIN,
- REGEX_LANDLOCK_PREFIX
- " status=allocated mode=enforcing pid=[0-9]\\+ uid=[0-9]\\+"
- " exe=\"[^\"]\\+\" comm=\".*_test\"$",
- domain_id);
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " status=allocated mode=enforcing pid=%d uid=[0-9]\\+"
+ " exe=\"[^\"]\\+\" comm=\".*_test\"$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len =
+ snprintf(log_match, sizeof(log_match), log_template, pid);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+ domain_id);
}
static int __maybe_unused matches_log_domain_deallocated(
diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c
index a0643070c403d..cfc571afd0eb8 100644
--- a/tools/testing/selftests/landlock/audit_test.c
+++ b/tools/testing/selftests/landlock/audit_test.c
@@ -9,6 +9,7 @@
#include <errno.h>
#include <limits.h>
#include <linux/landlock.h>
+#include <pthread.h>
#include <stdlib.h>
#include <sys/mount.h>
#include <sys/prctl.h>
@@ -40,7 +41,6 @@ FIXTURE(audit)
{
struct audit_filter audit_filter;
int audit_fd;
- __u64(*domain_stack)[16];
};
FIXTURE_SETUP(audit)
@@ -60,18 +60,10 @@ FIXTURE_SETUP(audit)
TH_LOG("Failed to initialize audit: %s", error_msg);
}
clear_cap(_metadata, CAP_AUDIT_CONTROL);
-
- self->domain_stack = mmap(NULL, sizeof(*self->domain_stack),
- PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_ANONYMOUS, -1, 0);
- ASSERT_NE(MAP_FAILED, self->domain_stack);
- memset(self->domain_stack, 0, sizeof(*self->domain_stack));
}
FIXTURE_TEARDOWN(audit)
{
- EXPECT_EQ(0, munmap(self->domain_stack, sizeof(*self->domain_stack)));
-
set_cap(_metadata, CAP_AUDIT_CONTROL);
EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
clear_cap(_metadata, CAP_AUDIT_CONTROL);
@@ -83,9 +75,15 @@ TEST_F(audit, layers)
.scoped = LANDLOCK_SCOPE_SIGNAL,
};
int status, ruleset_fd, i;
+ __u64(*domain_stack)[16];
__u64 prev_dom = 3;
pid_t child;
+ domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(MAP_FAILED, domain_stack);
+ memset(domain_stack, 0, sizeof(*domain_stack));
+
ruleset_fd =
landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
@@ -94,7 +92,7 @@ TEST_F(audit, layers)
child = fork();
ASSERT_LE(0, child);
if (child == 0) {
- for (i = 0; i < ARRAY_SIZE(*self->domain_stack); i++) {
+ for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) {
__u64 denial_dom = 1;
__u64 allocated_dom = 2;
@@ -107,7 +105,8 @@ TEST_F(audit, layers)
matches_log_signal(_metadata, self->audit_fd,
getppid(), &denial_dom));
EXPECT_EQ(0, matches_log_domain_allocated(
- self->audit_fd, &allocated_dom));
+ self->audit_fd, getpid(),
+ &allocated_dom));
EXPECT_NE(denial_dom, 1);
EXPECT_NE(denial_dom, 0);
EXPECT_EQ(denial_dom, allocated_dom);
@@ -115,7 +114,7 @@ TEST_F(audit, layers)
/* Checks that the new domain is younger than the previous one. */
EXPECT_GT(allocated_dom, prev_dom);
prev_dom = allocated_dom;
- (*self->domain_stack)[i] = allocated_dom;
+ (*domain_stack)[i] = allocated_dom;
}
/* Checks that we reached the maximum number of layers. */
@@ -142,23 +141,143 @@ TEST_F(audit, layers)
/* Purges log from deallocated domains. */
EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
- for (i = ARRAY_SIZE(*self->domain_stack) - 1; i >= 0; i--) {
+ for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) {
__u64 deallocated_dom = 2;
EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
&deallocated_dom));
- EXPECT_EQ((*self->domain_stack)[i], deallocated_dom)
+ EXPECT_EQ((*domain_stack)[i], deallocated_dom)
{
TH_LOG("Failed to match domain %llx (#%d)",
- (*self->domain_stack)[i], i);
+ (*domain_stack)[i], i);
}
}
+ EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack)));
EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
&audit_tv_default, sizeof(audit_tv_default)));
-
EXPECT_EQ(0, close(ruleset_fd));
}
+struct thread_data {
+ pid_t parent_pid;
+ int ruleset_fd, pipe_child, pipe_parent;
+};
+
+static void *thread_audit_test(void *arg)
+{
+ const struct thread_data *data = (struct thread_data *)arg;
+ uintptr_t err = 0;
+ char buffer;
+
+ /* TGID and TID are different for a second thread. */
+ if (getpid() == gettid()) {
+ err = 1;
+ goto out;
+ }
+
+ if (landlock_restrict_self(data->ruleset_fd, 0)) {
+ err = 2;
+ goto out;
+ }
+
+ if (close(data->ruleset_fd)) {
+ err = 3;
+ goto out;
+ }
+
+ /* Creates a denial to get the domain ID. */
+ if (kill(data->parent_pid, 0) != -1) {
+ err = 4;
+ goto out;
+ }
+
+ if (EPERM != errno) {
+ err = 5;
+ goto out;
+ }
+
+ /* Signals the parent to read denial logs. */
+ if (write(data->pipe_child, ".", 1) != 1) {
+ err = 6;
+ goto out;
+ }
+
+ /* Waits for the parent to update audit filters. */
+ if (read(data->pipe_parent, &buffer, 1) != 1) {
+ err = 7;
+ goto out;
+ }
+
+out:
+ close(data->pipe_child);
+ close(data->pipe_parent);
+ return (void *)err;
+}
+
+/* Checks that the PID tied to a domain is not a TID but the TGID. */
+TEST_F(audit, thread)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ __u64 denial_dom = 1;
+ __u64 allocated_dom = 2;
+ __u64 deallocated_dom = 3;
+ pthread_t thread;
+ int pipe_child[2], pipe_parent[2];
+ char buffer;
+ struct thread_data child_data;
+
+ child_data.parent_pid = getppid();
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ child_data.pipe_child = pipe_child[1];
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+ child_data.pipe_parent = pipe_parent[0];
+ child_data.ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, child_data.ruleset_fd);
+
+ /* TGID and TID are the same for the initial thread . */
+ EXPECT_EQ(getpid(), gettid());
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test,
+ &child_data));
+
+ /* Waits for the child to generate a denial. */
+ ASSERT_EQ(1, read(pipe_child[0], &buffer, 1));
+ EXPECT_EQ(0, close(pipe_child[0]));
+
+ /* Matches the signal log to get the domain ID. */
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ child_data.parent_pid, &denial_dom));
+ EXPECT_NE(denial_dom, 1);
+ EXPECT_NE(denial_dom, 0);
+
+ EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(),
+ &allocated_dom));
+ EXPECT_EQ(denial_dom, allocated_dom);
+
+ /* Updates filter rules to match the drop record. */
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+ EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ /* Signals the thread to exit, which will generate a domain deallocation. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(0, close(pipe_parent[1]));
+ ASSERT_EQ(0, pthread_join(thread, NULL));
+
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+ EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+ &deallocated_dom));
+ EXPECT_EQ(denial_dom, deallocated_dom);
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_default, sizeof(audit_tv_default)));
+}
+
FIXTURE(audit_flags)
{
struct audit_filter audit_filter;
@@ -273,7 +392,8 @@ TEST_F(audit_flags, signal)
/* Checks domain information records. */
EXPECT_EQ(0, matches_log_domain_allocated(
- self->audit_fd, &allocated_dom));
+ self->audit_fd, getpid(),
+ &allocated_dom));
EXPECT_NE(*self->domain_id, 1);
EXPECT_NE(*self->domain_id, 0);
EXPECT_EQ(*self->domain_id, allocated_dom);
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index f819011a87986..73729382d40f8 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -5964,7 +5964,8 @@ TEST_F(audit_layout1, refer_handled)
EXPECT_EQ(EXDEV, errno);
EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
dir_s1d1));
- EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, NULL));
+ EXPECT_EQ(0,
+ matches_log_domain_allocated(self->audit_fd, getpid(), NULL));
EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
dir_s1d3));
diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config
index 81a1f64a22e86..377b3699ff312 100644
--- a/tools/testing/selftests/lib/config
+++ b/tools/testing/selftests/lib/config
@@ -1,2 +1,3 @@
CONFIG_TEST_BITMAP=m
+CONFIG_PRIME_NUMBERS=m
CONFIG_TEST_BITOPS=m
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index efabfcbe0b498..17ed3e9917ca1 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -283,8 +283,7 @@ out_free:
/*
* Test mincore() behavior on a page backed by a tmpfs file. This test
- * performs the same steps as the previous one. However, we don't expect
- * any readahead in this case.
+ * performs the same steps as the previous one.
*/
TEST(check_tmpfs_mmap)
{
@@ -295,7 +294,6 @@ TEST(check_tmpfs_mmap)
int page_size;
int fd;
int i;
- int ra_pages = 0;
page_size = sysconf(_SC_PAGESIZE);
vec_size = FILE_SIZE / page_size;
@@ -338,8 +336,7 @@ TEST(check_tmpfs_mmap)
}
/*
- * Touch a page in the middle of the mapping. We expect only
- * that page to be fetched into memory.
+ * Touch a page in the middle of the mapping.
*/
addr[FILE_SIZE / 2] = 1;
retval = mincore(addr, FILE_SIZE, vec);
@@ -348,15 +345,6 @@ TEST(check_tmpfs_mmap)
TH_LOG("Page not found in memory after use");
}
- i = FILE_SIZE / 2 / page_size + 1;
- while (i < vec_size && vec[i]) {
- ra_pages++;
- i++;
- }
- ASSERT_EQ(ra_pages, 0) {
- TH_LOG("Read-ahead pages found in memory");
- }
-
munmap(addr, FILE_SIZE);
close(fd);
free(vec);
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 67df7b47087f0..e1fe16bcbbe88 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -29,7 +29,7 @@ fi
if [[ $cgroup2 ]]; then
cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
- cgroup_path=/dev/cgroup/memory
+ cgroup_path=$(mktemp -d)
mount -t cgroup2 none $cgroup_path
do_umount=1
fi
@@ -37,7 +37,7 @@ if [[ $cgroup2 ]]; then
else
cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
- cgroup_path=/dev/cgroup/memory
+ cgroup_path=$(mktemp -d)
mount -t cgroup memory,hugetlb $cgroup_path
do_umount=1
fi
diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c
index 2c3a0eb6b22d3..9bc4591c7b169 100644
--- a/tools/testing/selftests/mm/compaction_test.c
+++ b/tools/testing/selftests/mm/compaction_test.c
@@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
int compaction_index = 0;
char nr_hugepages[20] = {0};
char init_nr_hugepages[24] = {0};
+ char target_nr_hugepages[24] = {0};
+ int slen;
snprintf(init_nr_hugepages, sizeof(init_nr_hugepages),
"%lu", initial_nr_hugepages);
@@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size,
goto out;
}
- /* Request a large number of huge pages. The Kernel will allocate
- as much as it can */
- if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
- ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n",
- strerror(errno));
+ /*
+ * Request huge pages for about half of the free memory. The Kernel
+ * will allocate as much as it can, and we expect it will get at least 1/3
+ */
+ nr_hugepages_ul = mem_free / hugepage_size / 2;
+ snprintf(target_nr_hugepages, sizeof(target_nr_hugepages),
+ "%lu", nr_hugepages_ul);
+
+ slen = strlen(target_nr_hugepages);
+ if (write(fd, target_nr_hugepages, slen) != slen) {
+ ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n",
+ nr_hugepages_ul, strerror(errno));
goto close_fd;
}
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index f0cb14ea86084..b6cfe0a4b7dfd 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -293,7 +293,7 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
.iov_base = mem,
.iov_len = size,
};
- ssize_t cur, total, transferred;
+ ssize_t cur, total, transferred = 0;
struct comm_pipes comm_pipes;
char *old, *new;
int ret, fds[2];
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b3d0e27710961..eba43ead13ae8 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions)
self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
setup_sighandler();
- if (variant->backing == ANON_BACKED)
+ switch (variant->backing) {
+ case ANON_BACKED:
return;
-
- self->fd = open_file(
- variant->backing == SHMEM_BACKED ? "/tmp/" : "",
- self->path);
+ case LOCAL_FILE_BACKED:
+ self->fd = open_file("", self->path);
+ break;
+ case SHMEM_BACKED:
+ self->fd = memfd_create(self->path, 0);
+ break;
+ }
/* We truncate file to at least 100 pages, tests can modify as needed. */
ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
@@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file)
char *ptr;
int i;
- if (variant->backing == ANON_BACKED)
+ if (variant->backing != LOCAL_FILE_BACKED)
SKIP(return, "Read-only test specific to file-backed");
/* Map shared so we can populate with pattern, populate it, unmap. */
diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
index 11f9bbe7dc222..0b0d4ba1af277 100755
--- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
@@ -23,7 +23,7 @@ fi
if [[ $cgroup2 ]]; then
CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$CGROUP_ROOT" ]]; then
- CGROUP_ROOT=/dev/cgroup/memory
+ CGROUP_ROOT=$(mktemp -d)
mount -t cgroup2 none $CGROUP_ROOT
do_umount=1
fi
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 1bad310d282ad..17bf2d1b0192e 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -3,6 +3,8 @@
#ifndef _PKEYS_POWERPC_H
#define _PKEYS_POWERPC_H
+#include <sys/stat.h>
+
#ifndef SYS_pkey_alloc
# define SYS_pkey_alloc 384
# define SYS_pkey_free 385
@@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
return;
}
+#define REPEAT_8(s) s s s s s s s s
+#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \
+ REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s)
+#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \
+ REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s)
+#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \
+ REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s)
+#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \
+ REPEAT_4096(s) REPEAT_4096(s)
+
/* 4-byte instructions * 16384 = 64K page */
-#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+#define __page_o_noops() asm(REPEAT_16384("nop\n"))
static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
{
diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c
index ca4ad0d44ab2e..255b332f7a08b 100644
--- a/tools/testing/selftests/mm/pkey_util.c
+++ b/tools/testing/selftests/mm/pkey_util.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
+#define __SANE_USERSPACE_TYPES__
#include <sys/syscall.h>
#include <unistd.h>
diff --git a/tools/testing/selftests/mount_setattr/Makefile b/tools/testing/selftests/mount_setattr/Makefile
index 0c0d7b1234c19..4d4f810cdf2c1 100644
--- a/tools/testing/selftests/mount_setattr/Makefile
+++ b/tools/testing/selftests/mount_setattr/Makefile
@@ -2,6 +2,8 @@
# Makefile for mount selftests.
CFLAGS = -g $(KHDR_INCLUDES) -Wall -O2 -pthread
+LOCAL_HDRS += ../filesystems/wrappers.h
+
TEST_GEN_PROGS := mount_setattr_test
include ../lib.mk
diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index 48a000cabc971..8b378c91debf5 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -20,7 +20,7 @@
#include <stdarg.h>
#include <linux/mount.h>
-#include "../filesystems/overlayfs/wrappers.h"
+#include "../filesystems/wrappers.h"
#include "../kselftest_harness.h"
#ifndef CLONE_NEWNS
@@ -107,46 +107,6 @@
#endif
#endif
-#ifndef __NR_open_tree
- #if defined __alpha__
- #define __NR_open_tree 538
- #elif defined _MIPS_SIM
- #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
- #define __NR_open_tree 4428
- #endif
- #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
- #define __NR_open_tree 6428
- #endif
- #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
- #define __NR_open_tree 5428
- #endif
- #elif defined __ia64__
- #define __NR_open_tree (428 + 1024)
- #else
- #define __NR_open_tree 428
- #endif
-#endif
-
-#ifndef __NR_move_mount
- #if defined __alpha__
- #define __NR_move_mount 539
- #elif defined _MIPS_SIM
- #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
- #define __NR_move_mount 4429
- #endif
- #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
- #define __NR_move_mount 6429
- #endif
- #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
- #define __NR_move_mount 5429
- #endif
- #elif defined __ia64__
- #define __NR_move_mount (428 + 1024)
- #else
- #define __NR_move_mount 429
- #endif
-#endif
-
#ifndef MOUNT_ATTR_IDMAP
#define MOUNT_ATTR_IDMAP 0x00100000
#endif
@@ -161,23 +121,6 @@ static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flag
return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
}
-#ifndef OPEN_TREE_CLONE
-#define OPEN_TREE_CLONE 1
-#endif
-
-#ifndef OPEN_TREE_CLOEXEC
-#define OPEN_TREE_CLOEXEC O_CLOEXEC
-#endif
-
-#ifndef AT_RECURSIVE
-#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
-#endif
-
-static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
-{
- return syscall(__NR_open_tree, dfd, filename, flags);
-}
-
static ssize_t write_nointr(int fd, const void *buf, size_t count)
{
ssize_t ret;
@@ -1076,7 +1019,7 @@ FIXTURE_SETUP(mount_setattr_idmapped)
ASSERT_EQ(mkdir("/mnt/D", 0777), 0);
img_fd = openat(-EBADF, "/mnt/C/ext4.img", O_CREAT | O_WRONLY, 0600);
ASSERT_GE(img_fd, 0);
- ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0);
+ ASSERT_EQ(ftruncate(img_fd, 2147483648 /* 2 GB */), 0);
ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0);
ASSERT_EQ(system("mount -o loop -t ext4 /mnt/C/ext4.img /mnt/D/"), 0);
ASSERT_EQ(close(img_fd), 0);
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 124078b56fa44..70a38f485d4d1 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,6 +31,7 @@ TEST_PROGS += veth.sh
TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
+TEST_PROGS += gre_ipv6_lladdr.sh
TEST_PROGS += cmsg_so_mark.sh
TEST_PROGS += cmsg_so_priority.sh
TEST_PROGS += test_so_rcv.sh
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index b866bab1d92a1..c7cea556b4169 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -359,6 +359,23 @@ fib_rule6_test()
"$getnomatch" "iif flowlabel masked redirect to table" \
"iif flowlabel masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP6 iif vrf0"
+ getmatch="from $SRC_IP6 iif $DEV"
+ getnomatch="from $SRC_IP6 iif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule6_vrf_test()
@@ -635,6 +652,23 @@ fib_rule4_test()
"$getnomatch" "iif dscp masked redirect to table" \
"iif dscp masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP iif vrf0"
+ getmatch="from $SRC_IP iif $DEV"
+ getnomatch="from $SRC_IP iif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule4_vrf_test()
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 90f8a244ea901..e59fba366a0a6 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid 8021p drop_untagged"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
@@ -194,6 +194,100 @@ other_tpid()
tc qdisc del dev $h2 clsact
}
+8021p_do()
+{
+ local should_fail=$1; shift
+ local mac=de:ad:be:ef:13:37
+
+ tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+ flower dst_mac $mac action drop
+
+ $MZ -q $h1 -c 1 -b $mac -a own "81:00 00:00 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+ sleep 1
+
+ tc -j -s filter show dev $h2 ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ check_err_fail $should_fail $? "802.1p-tagged reception"
+
+ tc filter del dev $h2 ingress pref 1
+}
+
+8021p()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with the default_pvid, 1, packets tagged with VID 0 are
+ # accepted.
+ 8021p_do 0
+
+ # Test that packets tagged with VID 0 are still accepted after changing
+ # the default_pvid.
+ ip link set br0 type bridge vlan_default_pvid 10
+ 8021p_do 0
+
+ log_test "Reception of 802.1p-tagged traffic"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
+send_untagged_and_8021p()
+{
+ ping_do $h1 192.0.2.2
+ check_fail $?
+
+ 8021p_do 1
+}
+
+drop_untagged()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with no PVID, untagged and 802.1p-tagged traffic is
+ # dropped.
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ # First we reconfigure the default_pvid, 1, as a non-PVID VLAN.
+ bridge vlan add dev $swp1 vid 1 untagged
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Next we try to delete VID 1 altogether
+ bridge vlan del dev $swp1 vid 1
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Set up the bridge without a default_pvid, then check that the 8021q
+ # module, when the bridge port goes down and then up again, does not
+ # accidentally re-enable untagged packet reception.
+ ip link set br0 type bridge vlan_default_pvid 0
+ ip link set $swp1 down
+ ip link set $swp1 up
+ setup_wait
+ send_untagged_and_8021p
+
+ # Remove swp1 as a bridge port and let it rejoin the bridge while it
+ # has no default_pvid.
+ ip link set $swp1 nomaster
+ ip link set $swp1 master br0
+ send_untagged_and_8021p
+
+ # Restore settings
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ log_test "Dropping of untagged and 802.1p-tagged traffic with no PVID"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/tc_taprio.sh b/tools/testing/selftests/net/forwarding/tc_taprio.sh
new file mode 100755
index 0000000000000..8992aeabfe0b4
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_taprio.sh
@@ -0,0 +1,421 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS=" \
+ test_clock_jump_backward \
+ test_taprio_after_ptp \
+ test_max_sdu \
+ test_clock_jump_backward_forward \
+"
+NUM_NETIFS=4
+source tc_common.sh
+source lib.sh
+source tsn_lib.sh
+
+require_command python3
+
+# The test assumes the usual topology from the README, where h1 is connected to
+# swp1, h2 to swp2, and swp1 and swp2 are together in a bridge.
+# Additional assumption: h1 and h2 use the same PHC, and so do swp1 and swp2.
+# By synchronizing h1 to swp1 via PTP, h2 is also implicitly synchronized to
+# swp1 (and both to CLOCK_REALTIME).
+h1=${NETIFS[p1]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p3]}
+h2=${NETIFS[p4]}
+
+UDS_ADDRESS_H1="/var/run/ptp4l_h1"
+UDS_ADDRESS_SWP1="/var/run/ptp4l_swp1"
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+# Tunables
+NUM_PKTS=100
+STREAM_VID=10
+STREAM_PRIO_1=6
+STREAM_PRIO_2=5
+STREAM_PRIO_3=4
+# PTP uses TC 0
+ALL_GATES=$((1 << 0 | 1 << STREAM_PRIO_1 | 1 << STREAM_PRIO_2))
+# Use a conservative cycle of 10 ms to allow the test to still pass when the
+# kernel has some extra overhead like lockdep etc
+CYCLE_TIME_NS=10000000
+# Create two Gate Control List entries, one OPEN and one CLOSE, of equal
+# durations
+GATE_DURATION_NS=$((CYCLE_TIME_NS / 2))
+# Give 2/3 of the cycle time to user space and 1/3 to the kernel
+FUDGE_FACTOR=$((CYCLE_TIME_NS / 3))
+# Shift the isochron base time by half the gate time, so that packets are
+# always received by swp1 close to the middle of the time slot, to minimize
+# inaccuracies due to network sync
+SHIFT_TIME_NS=$((GATE_DURATION_NS / 2))
+
+path_delay=
+
+h1_create()
+{
+ simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+switch_create()
+{
+ local h2_mac_addr=$(mac_get $h2)
+
+ ip link set $swp1 up
+ ip link set $swp2 up
+
+ ip link add br0 type bridge vlan_filtering 1
+ ip link set $swp1 master br0
+ ip link set $swp2 master br0
+ ip link set br0 up
+
+ bridge vlan add dev $swp2 vid $STREAM_VID
+ bridge vlan add dev $swp1 vid $STREAM_VID
+ bridge fdb add dev $swp2 \
+ $h2_mac_addr vlan $STREAM_VID static master
+}
+
+switch_destroy()
+{
+ ip link del br0
+}
+
+ptp_setup()
+{
+ # Set up swp1 as a master PHC for h1, synchronized to the local
+ # CLOCK_REALTIME.
+ phc2sys_start $UDS_ADDRESS_SWP1
+ ptp4l_start $h1 true $UDS_ADDRESS_H1
+ ptp4l_start $swp1 false $UDS_ADDRESS_SWP1
+}
+
+ptp_cleanup()
+{
+ ptp4l_stop $swp1
+ ptp4l_stop $h1
+ phc2sys_stop
+}
+
+txtime_setup()
+{
+ local if_name=$1
+
+ tc qdisc add dev $if_name clsact
+ # Classify PTP on TC 7 and isochron on TC 6
+ tc filter add dev $if_name egress protocol 0x88f7 \
+ flower action skbedit priority 7
+ tc filter add dev $if_name egress protocol 802.1Q \
+ flower vlan_ethtype 0xdead action skbedit priority 6
+ tc qdisc add dev $if_name handle 100: parent root mqprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ hw 1
+ # Set up TC 5, 6, 7 for SO_TXTIME. tc-mqprio queues count from 1.
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_1 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_2 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_3 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+}
+
+txtime_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name clsact
+ tc qdisc del dev $if_name root
+}
+
+taprio_replace()
+{
+ local if_name="$1"; shift
+ local extra_args="$1"; shift
+
+ # STREAM_PRIO_1 always has an open gate.
+ # STREAM_PRIO_2 has a gate open for GATE_DURATION_NS (half the cycle time)
+ # STREAM_PRIO_3 always has a closed gate.
+ tc qdisc replace dev $if_name root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ sched-entry S $(printf "%x" $ALL_GATES) $GATE_DURATION_NS \
+ sched-entry S $(printf "%x" $((ALL_GATES & ~(1 << STREAM_PRIO_2)))) $GATE_DURATION_NS \
+ base-time 0 flags 0x2 $extra_args
+ taprio_wait_for_admin $if_name
+}
+
+taprio_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name root
+}
+
+probe_path_delay()
+{
+ local isochron_dat="$(mktemp)"
+ local received
+
+ log_info "Probing path delay"
+
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" 0 \
+ "$CYCLE_TIME_NS" "" "" "$NUM_PKTS" \
+ "$STREAM_VID" "$STREAM_PRIO_1" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ if [ "$received" != "$NUM_PKTS" ]; then
+ echo "Cannot establish basic data path between $h1 and $h2"
+ exit $ksft_fail
+ fi
+
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(np.max(w)))
+ EOF
+ path_delay=$(python3 ./isochron_postprocess.py)
+
+ log_info "Path delay from $h1 to $h2 estimated at $path_delay ns"
+
+ if [ "$path_delay" -gt "$GATE_DURATION_NS" ]; then
+ echo "Path delay larger than gate duration, aborting"
+ exit $ksft_fail
+ fi
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+setup_prepare()
+{
+ vrf_prepare
+
+ h1_create
+ h2_create
+ switch_create
+
+ txtime_setup $h1
+
+ # Temporarily set up PTP just to probe the end-to-end path delay.
+ ptp_setup
+ probe_path_delay
+ ptp_cleanup
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ isochron_recv_stop
+ txtime_cleanup $h1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+run_test()
+{
+ local base_time=$1; shift
+ local stream_prio=$1; shift
+ local expected_delay=$1; shift
+ local should_fail=$1; shift
+ local test_name=$1; shift
+ local isochron_dat="$(mktemp)"
+ local received
+ local median_delay
+
+ RET=0
+
+ # Set the shift time equal to the cycle time, which effectively
+ # cancels the default advance time. Packets won't be sent early in
+ # software, which ensures that they won't prematurely enter through
+ # the open gate in __test_out_of_band(). Also, the gate is open for
+ # long enough that this won't cause a problem in __test_in_band().
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" "$base_time" \
+ "$CYCLE_TIME_NS" "$SHIFT_TIME_NS" "$GATE_DURATION_NS" \
+ "$NUM_PKTS" "$STREAM_VID" "$stream_prio" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ [ "$received" = "$NUM_PKTS" ]
+ check_err_fail $should_fail $? "Reception of $NUM_PKTS packets"
+
+ if [ $should_fail = 0 ] && [ "$received" = "$NUM_PKTS" ]; then
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(int(np.median(w))))
+ EOF
+ median_delay=$(python3 ./isochron_postprocess.py)
+
+ # If the condition below is true, packets were delayed by a closed gate
+ [ "$median_delay" -gt $((path_delay + expected_delay)) ]
+ check_fail $? "Median delay $median_delay is greater than expected delay $expected_delay plus path delay $path_delay"
+
+ # If the condition below is true, packets were sent expecting them to
+ # hit a closed gate in the switch, but were not delayed
+ [ "$expected_delay" -gt 0 ] && [ "$median_delay" -lt "$expected_delay" ]
+ check_fail $? "Median delay $median_delay is less than expected delay $expected_delay"
+ fi
+
+ log_test "$test_name"
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+__test_always_open()
+{
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Gate always open"
+}
+
+__test_always_closed()
+{
+ run_test 0.000000000 $STREAM_PRIO_3 0 1 "Gate always closed"
+}
+
+__test_in_band()
+{
+ # Send packets in-band with the OPEN gate entry
+ run_test 0.000000000 $STREAM_PRIO_2 0 0 "In band with gate"
+}
+
+__test_out_of_band()
+{
+ # Send packets in-band with the CLOSE gate entry
+ run_test 0.005000000 $STREAM_PRIO_2 \
+ $((GATE_DURATION_NS - SHIFT_TIME_NS)) 0 \
+ "Out of band with gate"
+}
+
+run_subtests()
+{
+ __test_always_open
+ __test_always_closed
+ __test_in_band
+ __test_out_of_band
+}
+
+test_taprio_after_ptp()
+{
+ log_info "Setting up taprio after PTP"
+ ptp_setup
+ taprio_replace $swp2
+ run_subtests
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+__test_under_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 100 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Under maximum SDU"
+}
+
+__test_over_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 20 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 1 "Over maximum SDU"
+}
+
+test_max_sdu()
+{
+ ptp_setup
+ __test_under_max_sdu
+ __test_over_max_sdu
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+# Perform a clock jump in the past without synchronization running, so that the
+# time base remains where it was set by phc_ctl.
+test_clock_jump_backward()
+{
+ # This is a more complex schedule specifically crafted in a way that
+ # has been problematic on NXP LS1028A. Not much to test with it other
+ # than the fact that it passes traffic.
+ tc qdisc replace dev $swp2 root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 map 0 1 2 3 4 5 6 7 \
+ base-time 0 sched-entry S 20 300000 sched-entry S 10 200000 \
+ sched-entry S 20 300000 sched-entry S 48 200000 \
+ sched-entry S 20 300000 sched-entry S 83 200000 \
+ sched-entry S 40 300000 sched-entry S 00 200000 flags 2
+
+ log_info "Forcing a backward clock jump"
+ phc_ctl $swp1 set 0
+
+ ping_test $h1 192.0.2.2
+ taprio_cleanup $swp2
+}
+
+# Test that taprio tolerates clock jumps.
+# Since ptp4l and phc2sys are running, it is expected for the time to
+# eventually recover (through yet another clock jump). Isochron waits
+# until that is the case.
+test_clock_jump_backward_forward()
+{
+ log_info "Forcing a backward and a forward clock jump"
+ taprio_replace $swp2
+ phc_ctl $swp1 set 0
+ ptp_setup
+ ping_test $h1 192.0.2.2
+ run_subtests
+ ptp_cleanup
+ taprio_cleanup $swp2
+}
+
+tc_offload_check
+if [[ $? -ne 0 ]]; then
+ log_test_skip "Could not test offloaded functionality"
+ exit $EXIT_STATUS
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tsn_lib.sh b/tools/testing/selftests/net/forwarding/tsn_lib.sh
index b91bcd8008a99..08c044ff6689d 100644
--- a/tools/testing/selftests/net/forwarding/tsn_lib.sh
+++ b/tools/testing/selftests/net/forwarding/tsn_lib.sh
@@ -2,6 +2,8 @@
# SPDX-License-Identifier: GPL-2.0
# Copyright 2021-2022 NXP
+tc_testing_scripts_dir=$(dirname $0)/../../tc-testing/scripts
+
REQUIRE_ISOCHRON=${REQUIRE_ISOCHRON:=yes}
REQUIRE_LINUXPTP=${REQUIRE_LINUXPTP:=yes}
@@ -18,6 +20,7 @@ fi
if [[ "$REQUIRE_LINUXPTP" = "yes" ]]; then
require_command phc2sys
require_command ptp4l
+ require_command phc_ctl
fi
phc2sys_start()
@@ -182,6 +185,7 @@ isochron_do()
local base_time=$1; shift
local cycle_time=$1; shift
local shift_time=$1; shift
+ local window_size=$1; shift
local num_pkts=$1; shift
local vid=$1; shift
local priority=$1; shift
@@ -212,6 +216,10 @@ isochron_do()
extra_args="${extra_args} --shift-time=${shift_time}"
fi
+ if ! [ -z "${window_size}" ]; then
+ extra_args="${extra_args} --window-size=${window_size}"
+ fi
+
if [ "${use_l2}" = "true" ]; then
extra_args="${extra_args} --l2 --etype=0xdead ${vid}"
receiver_extra_args="--l2 --etype=0xdead"
@@ -247,3 +255,21 @@ isochron_do()
cpufreq_restore ${ISOCHRON_CPU}
}
+
+isochron_report_num_received()
+{
+ local isochron_dat=$1; shift
+
+ # Count all received packets by looking at the non-zero RX timestamps
+ isochron report \
+ --input-file "${isochron_dat}" \
+ --printf-format "%u\n" --printf-args "R" | \
+ grep -w -v '0' | wc -l
+}
+
+taprio_wait_for_admin()
+{
+ local if_name="$1"; shift
+
+ "$tc_testing_scripts_dir/taprio_wait_for_admin.sh" "$(which tc)" "$if_name"
+}
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
new file mode 100755
index 0000000000000..5b34f6e1f8314
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./lib.sh
+
+PAUSE_ON_FAIL="no"
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+ cleanup_all_ns
+
+ exit "${EXIT_STATUS}"
+}
+
+# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
+# underlay by future GRE devices.
+#
+setup_basenet()
+{
+ ip -netns "${NS0}" link set dev lo up
+ ip -netns "${NS0}" address add dev lo 192.0.2.10/24
+ ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
+}
+
+# Check if network device has an IPv6 link-local address assigned.
+#
+# Parameters:
+#
+# * $1: The network device to test
+# * $2: An extra regular expression that should be matched (to verify the
+# presence of extra attributes)
+# * $3: The expected return code from grep (to allow checking the absence of
+# a link-local address)
+# * $4: The user visible name for the scenario being tested
+#
+check_ipv6_ll_addr()
+{
+ local DEV="$1"
+ local EXTRA_MATCH="$2"
+ local XRET="$3"
+ local MSG="$4"
+
+ RET=0
+ set +e
+ ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
+ check_err_fail "${XRET}" $? ""
+ log_test "${MSG}"
+ set -e
+}
+
+# Create a GRE device and verify that it gets an IPv6 link-local address as
+# expected.
+#
+# Parameters:
+#
+# * $1: The device type (gre, ip6gre, gretap or ip6gretap)
+# * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $4: The IPv6 interface identifier generation mode to use for the GRE
+# device (eui64, none, stable-privacy or random).
+#
+test_gre_device()
+{
+ local GRE_TYPE="$1"
+ local LOCAL_IP="$2"
+ local REMOTE_IP="$3"
+ local MODE="$4"
+ local ADDR_GEN_MODE
+ local MATCH_REGEXP
+ local MSG
+
+ ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
+
+ case "${MODE}" in
+ "eui64")
+ ADDR_GEN_MODE=0
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ "none")
+ ADDR_GEN_MODE=1
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=1 # No link-local address should be generated
+ ;;
+ "stable-privacy")
+ ADDR_GEN_MODE=2
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ # Initialise stable_secret (required for stable-privacy mode)
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
+ ;;
+ "random")
+ ADDR_GEN_MODE=3
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ esac
+
+ # Check that IPv6 link-local address is generated when device goes up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ ip -netns "${NS0}" link set dev gretest up
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+
+ # Now disable link-local address generation
+ ip -netns "${NS0}" link set dev gretest down
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
+ ip -netns "${NS0}" link set dev gretest up
+
+ # Check that link-local address generation works when re-enabled while
+ # the device is already up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+
+ ip -netns "${NS0}" link del dev gretest
+}
+
+test_gre4()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "gre" "gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
+ done
+ done
+}
+
+test_gre6()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "ip6gre" "ip6gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
+ done
+ done
+}
+
+usage()
+{
+ echo "Usage: $0 [-p]"
+ exit 1
+}
+
+while getopts :p o
+do
+ case $o in
+ p) PAUSE_ON_FAIL="yes";;
+ *) usage;;
+ esac
+done
+
+setup_ns NS0
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_basenet
+
+test_gre4
+test_gre6
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4f55477ffe087..e7a75341f0f32 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -206,9 +206,8 @@ chk_dump_one()
local token
local msg
- ss_token="$(ss -inmHMN $ns | grep 'token:' |\
- head -n 1 |\
- sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+ ss_token="$(ss -inmHMN $ns |
+ mptcp_lib_get_info_value "token" "token")"
token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
awk -F':[ \t]+' '/^token/ {print $2}')"
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
index 48ec048f47afd..277f92f9d7537 100644
--- a/tools/testing/selftests/pcie_bwctrl/Makefile
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -1,2 +1,3 @@
-TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh
+TEST_PROGS = set_pcie_cooling_state.sh
+TEST_FILES = set_pcie_speed.sh
include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index 55bcf81a2b9a2..efd74063126eb 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -131,6 +131,26 @@
#define PIDFD_INFO_EXIT (1UL << 3) /* Always returned if available, even if not requested */
#endif
+#ifndef PIDFD_INFO_COREDUMP
+#define PIDFD_INFO_COREDUMP (1UL << 4)
+#endif
+
+#ifndef PIDFD_COREDUMPED
+#define PIDFD_COREDUMPED (1U << 0) /* Did crash and... */
+#endif
+
+#ifndef PIDFD_COREDUMP_SKIP
+#define PIDFD_COREDUMP_SKIP (1U << 1) /* coredumping generation was skipped. */
+#endif
+
+#ifndef PIDFD_COREDUMP_USER
+#define PIDFD_COREDUMP_USER (1U << 2) /* coredump was done as the user. */
+#endif
+
+#ifndef PIDFD_COREDUMP_ROOT
+#define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */
+#endif
+
#ifndef PIDFD_THREAD
#define PIDFD_THREAD O_EXCL
#endif
@@ -150,6 +170,8 @@ struct pidfd_info {
__u32 fsuid;
__u32 fsgid;
__s32 exit_code;
+ __u32 coredump_mask;
+ __u32 __spare1;
};
/*
diff --git a/tools/testing/selftests/pidfd/pidfd_bind_mount.c b/tools/testing/selftests/pidfd/pidfd_bind_mount.c
index 7822dd080258b..c094aeb1c620e 100644
--- a/tools/testing/selftests/pidfd/pidfd_bind_mount.c
+++ b/tools/testing/selftests/pidfd/pidfd_bind_mount.c
@@ -15,79 +15,7 @@
#include "pidfd.h"
#include "../kselftest_harness.h"
-
-#ifndef __NR_open_tree
- #if defined __alpha__
- #define __NR_open_tree 538
- #elif defined _MIPS_SIM
- #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
- #define __NR_open_tree 4428
- #endif
- #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
- #define __NR_open_tree 6428
- #endif
- #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
- #define __NR_open_tree 5428
- #endif
- #elif defined __ia64__
- #define __NR_open_tree (428 + 1024)
- #else
- #define __NR_open_tree 428
- #endif
-#endif
-
-#ifndef __NR_move_mount
- #if defined __alpha__
- #define __NR_move_mount 539
- #elif defined _MIPS_SIM
- #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
- #define __NR_move_mount 4429
- #endif
- #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
- #define __NR_move_mount 6429
- #endif
- #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
- #define __NR_move_mount 5429
- #endif
- #elif defined __ia64__
- #define __NR_move_mount (428 + 1024)
- #else
- #define __NR_move_mount 429
- #endif
-#endif
-
-#ifndef MOVE_MOUNT_F_EMPTY_PATH
-#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
-#endif
-
-#ifndef MOVE_MOUNT_F_EMPTY_PATH
-#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
-#endif
-
-static inline int sys_move_mount(int from_dfd, const char *from_pathname,
- int to_dfd, const char *to_pathname,
- unsigned int flags)
-{
- return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd,
- to_pathname, flags);
-}
-
-#ifndef OPEN_TREE_CLONE
-#define OPEN_TREE_CLONE 1
-#endif
-
-#ifndef OPEN_TREE_CLOEXEC
-#define OPEN_TREE_CLOEXEC O_CLOEXEC
-#endif
-
-#ifndef AT_RECURSIVE
-#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
-#endif
-
-static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
-{
- return syscall(__NR_open_tree, dfd, filename, flags);
-}
+#include "../filesystems/wrappers.h"
FIXTURE(pidfd_bind_mount) {
char template[PATH_MAX];
diff --git a/tools/testing/selftests/pidfd/pidfd_info_test.c b/tools/testing/selftests/pidfd/pidfd_info_test.c
index 1758a1b0457be..a0eb6e81eaa26 100644
--- a/tools/testing/selftests/pidfd/pidfd_info_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_info_test.c
@@ -299,6 +299,7 @@ TEST_F(pidfd_info, thread_group)
/* Opening a thread as a thread-group leader must fail. */
pidfd_thread = sys_pidfd_open(pid_thread, 0);
ASSERT_LT(pidfd_thread, 0);
+ ASSERT_EQ(errno, ENOENT);
/* Opening a thread as a PIDFD_THREAD must succeed. */
pidfd_thread = sys_pidfd_open(pid_thread, PIDFD_THREAD);
@@ -362,9 +363,9 @@ TEST_F(pidfd_info, thread_group)
ASSERT_EQ(ioctl(pidfd_leader, PIDFD_GET_INFO, &info), 0);
ASSERT_FALSE(!!(info.mask & PIDFD_INFO_CREDS));
ASSERT_TRUE(!!(info.mask & PIDFD_INFO_EXIT));
- /* The thread-group leader exited successfully. Only the specific thread was SIGKILLed. */
- ASSERT_TRUE(WIFEXITED(info.exit_code));
- ASSERT_EQ(WEXITSTATUS(info.exit_code), 0);
+ /* Even though the thread-group exited successfully it will still report the group exit code. */
+ ASSERT_TRUE(WIFSIGNALED(info.exit_code));
+ ASSERT_EQ(WTERMSIG(info.exit_code), SIGKILL);
/*
* Retrieve exit information for the thread-group leader via the
@@ -375,9 +376,9 @@ TEST_F(pidfd_info, thread_group)
ASSERT_FALSE(!!(info2.mask & PIDFD_INFO_CREDS));
ASSERT_TRUE(!!(info2.mask & PIDFD_INFO_EXIT));
- /* The thread-group leader exited successfully. Only the specific thread was SIGKILLed. */
- ASSERT_TRUE(WIFEXITED(info2.exit_code));
- ASSERT_EQ(WEXITSTATUS(info2.exit_code), 0);
+ /* Even though the thread-group exited successfully it will still report the group exit code. */
+ ASSERT_TRUE(WIFSIGNALED(info2.exit_code));
+ ASSERT_EQ(WTERMSIG(info2.exit_code), SIGKILL);
/* Retrieve exit information for the thread. */
info.mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_EXIT;
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
index 1ba96c4677548..d9fc62ab476c9 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
@@ -412,5 +412,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY ingress"
]
+ },
+ {
+ "id": "33f4",
+ "name": "Check echo of big filter command",
+ "category": [
+ "infra",
+ "u32"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DUMMY parent root handle 10: fq_codel"
+ ],
+ "cmdUnderTest": "bash -c '$TC -echo filter add dev $DUMMY parent 10: u32 match u32 0 0 $(for i in $(seq 32); do echo action pedit munge ip dport set 22; done) | grep \"added filter\"'",
+ "verifyCmd": "",
+ "expExitCode": "0",
+ "matchCount": "0",
+ "matchPattern": "",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY parent root fq_codel"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index d4ea9cd845a33..ddc97ecd8b391 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -313,5 +313,292 @@
"$TC qdisc del dev $DUMMY handle 1: root",
"$IP addr del 10.10.10.10/24 dev $DUMMY || true"
]
+ },
+ {
+ "id": "a4c3",
+ "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+ "category": [
+ "qdisc",
+ "hfsc",
+ "netem",
+ "blackhole"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+ "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+ "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+ ],
+ "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+ "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "90ec",
+ "name": "Test DRR's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "drr",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "1f1f",
+ "name": "Test ETS's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "ets"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root ets bands 2",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 ets quantum 1500",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s class show dev $DUMMY",
+ "matchJSON": [
+ {
+ "class": "ets",
+ "handle": "1:1",
+ "stats": {
+ "bytes": 196,
+ "packets": 2
+ }
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "5e6d",
+ "name": "Test QFQ's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "qfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root qfq",
+ "$TC class replace dev $DUMMY parent 1:0 classid 1:1 qfq weight 100 maxpkt 1500",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "qfq",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "bf1d",
+ "name": "Test HFSC's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "hfsc"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root hfsc",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc ls m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2",
+ "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true",
+ "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1",
+ "$TC class del dev $DUMMY classid 1:1"
+ ],
+ "cmdUnderTest": "ping -c 1 10.10.10.2 -I$DUMMY > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "hfsc",
+ "handle": "1:",
+ "bytes": 392,
+ "packets": 4
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "7c3b",
+ "name": "Test nested DRR's enqueue reentrant behaviour with netem",
+ "category": [
+ "qdisc",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+ "$TC qdisc add dev $DUMMY handle 2:0 parent 1:1 drr",
+ "$TC class add dev $DUMMY classid 2:1 parent 2:0 drr",
+ "$TC filter add dev $DUMMY parent 2:0 protocol ip prio 1 u32 match ip protocol 1 0xff flowid 2:1",
+ "$TC qdisc add dev $DUMMY parent 2:1 handle 3:0 netem duplicate 100%"
+ ],
+ "cmdUnderTest": "ping -c 1 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -j -s qdisc ls dev $DUMMY handle 1:0",
+ "matchJSON": [
+ {
+ "kind": "drr",
+ "handle": "1:",
+ "bytes": 196,
+ "packets": 2
+ }
+ ],
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "62c4",
+ "name": "Test HTB with FQ_CODEL - basic functionality",
+ "category": [
+ "qdisc",
+ "htb",
+ "fq_codel"
+ ],
+ "plugins": {
+ "requires": [
+ "nsPlugin",
+ "scapyPlugin"
+ ]
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 root handle 1: htb default 11",
+ "$TC class add dev $DEV1 parent 1: classid 1:1 htb rate 10kbit",
+ "$TC class add dev $DEV1 parent 1:1 classid 1:11 htb rate 10kbit prio 0 quantum 1486",
+ "$TC qdisc add dev $DEV1 parent 1:11 fq_codel quantum 300 noecn",
+ "sleep 0.5"
+ ],
+ "scapy": {
+ "iface": "$DEV0",
+ "count": 5,
+ "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/TCP(sport=12345, dport=80)"
+ },
+ "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DEV1 | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "Sent [0-9]+ bytes [0-9]+ pkt",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 handle 1: root"
+ ]
+ },
+ {
+ "id": "831d",
+ "name": "Test HFSC qlen accounting with DRR/NETEM/BLACKHOLE chain",
+ "category": ["qdisc", "hfsc", "drr", "netem", "blackhole"],
+ "plugins": { "requires": ["nsPlugin", "scapyPlugin"] },
+ "setup": [
+ "$IP link set dev $DEV1 up || true",
+ "$TC qdisc add dev $DEV1 root handle 1: drr",
+ "$TC filter add dev $DEV1 parent 1: basic classid 1:1",
+ "$TC class add dev $DEV1 parent 1: classid 1:1 drr",
+ "$TC qdisc add dev $DEV1 parent 1:1 handle 2: hfsc def 1",
+ "$TC class add dev $DEV1 parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0",
+ "$TC qdisc add dev $DEV1 parent 2:1 handle 3: netem",
+ "$TC qdisc add dev $DEV1 parent 3:1 handle 4: blackhole"
+ ],
+ "scapy": {
+ "iface": "$DEV0",
+ "count": 5,
+ "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()"
+ },
+ "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DEV1",
+ "matchPattern": "qdisc hfsc",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 root handle 1: drr"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
index e9469ee71e6fc..6d515d0e5ed69 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json
@@ -189,5 +189,29 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "deb1",
+ "name": "CODEL test qdisc limit trimming",
+ "category": ["qdisc", "codel"],
+ "plugins": {
+ "requires": ["nsPlugin", "scapyPlugin"]
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root codel limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root codel limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1p target 5ms interval 100ms",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
index 3a537b2ec4c97..24faf4e12dfa0 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json
@@ -377,5 +377,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "9479",
+ "name": "FQ test qdisc limit trimming",
+ "category": ["qdisc", "fq"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root fq limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 1p",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
index 9774b1e8801bb..4ce62b857fd7a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json
@@ -294,5 +294,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "0436",
+ "name": "FQ_CODEL test qdisc limit trimming",
+ "category": ["qdisc", "fq_codel"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root fq_codel limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_codel limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
index d012d88d67fee..229fe1bf4a906 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -18,5 +18,27 @@
"matchCount": "1",
"teardown": [
]
+ },
+ {
+ "id": "83bf",
+ "name": "FQ_PIE test qdisc limit trimming",
+ "category": ["qdisc", "fq_pie"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root fq_pie limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_pie limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc fq_pie 1: root refcnt [0-9]+ limit 1p",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
index dbef5474b26bd..0ca19fac54a57 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json
@@ -188,5 +188,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY handle 1: root"
]
+ },
+ {
+ "id": "385f",
+ "name": "HHF test qdisc limit trimming",
+ "category": ["qdisc", "hhf"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root hhf limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root hhf limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc hhf 1: root refcnt [0-9]+ limit 1p.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json
new file mode 100644
index 0000000000000..1a98b66e80307
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json
@@ -0,0 +1,24 @@
+[
+ {
+ "id": "6158",
+ "name": "PIE test qdisc limit trimming",
+ "category": ["qdisc", "pie"],
+ "plugins": {"requires": ["nsPlugin", "scapyPlugin"]},
+ "setup": [
+ "$TC qdisc add dev $DEV1 handle 1: root pie limit 10"
+ ],
+ "scapy": [
+ {
+ "iface": "$DEV0",
+ "count": 10,
+ "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)"
+ }
+ ],
+ "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root pie limit 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc pie 1: root refcnt [0-9]+ limit 1p",
+ "matchCount": "1",
+ "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"]
+ }
+]
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index c7781efea0f33..4dde8838261d6 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -1,11 +1,24 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -O3 -Wl,-no-as-needed -Wall -I $(top_srcdir)
+CFLAGS += -O3 -Wl,-no-as-needed -Wall -I $(top_srcdir)/usr/include
+ifneq ($(WERROR),0)
+ CFLAGS += -Werror
+endif
+
LDLIBS += -lpthread -lm -luring
TEST_PROGS := test_generic_01.sh
TEST_PROGS += test_generic_02.sh
TEST_PROGS += test_generic_03.sh
+TEST_PROGS += test_generic_04.sh
+TEST_PROGS += test_generic_05.sh
+TEST_PROGS += test_generic_06.sh
+TEST_PROGS += test_generic_07.sh
+
+TEST_PROGS += test_generic_08.sh
+TEST_PROGS += test_generic_09.sh
+TEST_PROGS += test_generic_10.sh
+TEST_PROGS += test_generic_11.sh
TEST_PROGS += test_null_01.sh
TEST_PROGS += test_null_02.sh
@@ -21,12 +34,16 @@ TEST_PROGS += test_stripe_04.sh
TEST_PROGS += test_stress_01.sh
TEST_PROGS += test_stress_02.sh
+TEST_PROGS += test_stress_03.sh
+TEST_PROGS += test_stress_04.sh
+TEST_PROGS += test_stress_05.sh
TEST_GEN_PROGS_EXTENDED = kublk
include ../lib.mk
-$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c
+$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c \
+ fault_inject.c
check:
shellcheck -x -f gcc *.sh
diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c
new file mode 100644
index 0000000000000..5421774d7867c
--- /dev/null
+++ b/tools/testing/selftests/ublk/fault_inject.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Fault injection ublk target. Hack this up however you like for
+ * testing specific behaviors of ublk_drv. Currently is a null target
+ * with a configurable delay before completing each I/O. This delay can
+ * be used to test ublk_drv's handling of I/O outstanding to the ublk
+ * server when it dies.
+ */
+
+#include "kublk.h"
+
+static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx,
+ struct ublk_dev *dev)
+{
+ const struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+ unsigned long dev_size = 250UL << 30;
+
+ if (ctx->auto_zc_fallback) {
+ ublk_err("%s: not support auto_zc_fallback\n", __func__);
+ return -EINVAL;
+ }
+
+ dev->tgt.dev_size = dev_size;
+ dev->tgt.params = (struct ublk_params) {
+ .types = UBLK_PARAM_TYPE_BASIC,
+ .basic = {
+ .logical_bs_shift = 9,
+ .physical_bs_shift = 12,
+ .io_opt_shift = 12,
+ .io_min_shift = 9,
+ .max_sectors = info->max_io_buf_bytes >> 9,
+ .dev_sectors = dev_size >> 9,
+ },
+ };
+
+ dev->private_data = (void *)(unsigned long)(ctx->fault_inject.delay_us * 1000);
+ return 0;
+}
+
+static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+ struct io_uring_sqe *sqe;
+ struct __kernel_timespec ts = {
+ .tv_nsec = (long long)q->dev->private_data,
+ };
+
+ ublk_queue_alloc_sqes(q, &sqe, 1);
+ io_uring_prep_timeout(sqe, &ts, 1, 0);
+ sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1);
+
+ ublk_queued_tgt_io(q, tag, 1);
+
+ return 0;
+}
+
+static void ublk_fault_inject_tgt_io_done(struct ublk_queue *q, int tag,
+ const struct io_uring_cqe *cqe)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+
+ if (cqe->res != -ETIME)
+ ublk_err("%s: unexpected cqe res %d\n", __func__, cqe->res);
+
+ if (ublk_completed_tgt_io(q, tag))
+ ublk_complete_io(q, tag, iod->nr_sectors << 9);
+ else
+ ublk_err("%s: io not complete after 1 cqe\n", __func__);
+}
+
+static void ublk_fault_inject_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+ static const struct option longopts[] = {
+ { "delay_us", 1, NULL, 0 },
+ { 0, 0, 0, 0 }
+ };
+ int option_idx, opt;
+
+ ctx->fault_inject.delay_us = 0;
+ while ((opt = getopt_long(argc, argv, "",
+ longopts, &option_idx)) != -1) {
+ switch (opt) {
+ case 0:
+ if (!strcmp(longopts[option_idx].name, "delay_us"))
+ ctx->fault_inject.delay_us = strtoll(optarg, NULL, 10);
+ }
+ }
+}
+
+static void ublk_fault_inject_usage(const struct ublk_tgt_ops *ops)
+{
+ printf("\tfault_inject: [--delay_us us (default 0)]\n");
+}
+
+const struct ublk_tgt_ops fault_inject_tgt_ops = {
+ .name = "fault_inject",
+ .init_tgt = ublk_fault_inject_tgt_init,
+ .queue_io = ublk_fault_inject_queue_io,
+ .tgt_io_done = ublk_fault_inject_tgt_io_done,
+ .parse_cmd_line = ublk_fault_inject_cmd_line,
+ .usage = ublk_fault_inject_usage,
+};
diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c
index 6f34eabfae979..509842df9beef 100644
--- a/tools/testing/selftests/ublk/file_backed.c
+++ b/tools/testing/selftests/ublk/file_backed.c
@@ -29,19 +29,23 @@ static int loop_queue_flush_io(struct ublk_queue *q, const struct ublksrv_io_des
static int loop_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
{
unsigned ublk_op = ublksrv_get_op(iod);
- int zc = ublk_queue_use_zc(q);
- enum io_uring_op op = ublk_to_uring_op(iod, zc);
+ unsigned zc = ublk_queue_use_zc(q);
+ unsigned auto_zc = ublk_queue_use_auto_zc(q);
+ enum io_uring_op op = ublk_to_uring_op(iod, zc | auto_zc);
struct io_uring_sqe *sqe[3];
+ void *addr = (zc | auto_zc) ? NULL : (void *)iod->addr;
- if (!zc) {
+ if (!zc || auto_zc) {
ublk_queue_alloc_sqes(q, sqe, 1);
if (!sqe[0])
return -ENOMEM;
io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/,
- (void *)iod->addr,
+ addr,
iod->nr_sectors << 9,
iod->start_sector << 9);
+ if (auto_zc)
+ sqe[0]->buf_index = tag;
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, 1);
@@ -145,6 +149,11 @@ static int ublk_loop_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
},
};
+ if (ctx->auto_zc_fallback) {
+ ublk_err("%s: not support auto_zc_fallback\n", __func__);
+ return -EINVAL;
+ }
+
ret = backing_file_tgt_init(dev);
if (ret)
return ret;
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 91c282bc76744..b5131a000795d 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -5,22 +5,24 @@
#include "kublk.h"
+#define MAX_NR_TGT_ARG 64
+
unsigned int ublk_dbg_mask = UBLK_LOG;
static const struct ublk_tgt_ops *tgt_ops_list[] = {
&null_tgt_ops,
&loop_tgt_ops,
&stripe_tgt_ops,
+ &fault_inject_tgt_ops,
};
static const struct ublk_tgt_ops *ublk_find_tgt(const char *name)
{
- const struct ublk_tgt_ops *ops;
int i;
if (name == NULL)
return NULL;
- for (i = 0; sizeof(tgt_ops_list) / sizeof(ops); i++)
+ for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++)
if (strcmp(tgt_ops_list[i]->name, name) == 0)
return tgt_ops_list[i];
return NULL;
@@ -118,6 +120,27 @@ static int ublk_ctrl_start_dev(struct ublk_dev *dev,
return __ublk_ctrl_cmd(dev, &data);
}
+static int ublk_ctrl_start_user_recovery(struct ublk_dev *dev)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_START_USER_RECOVERY,
+ };
+
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_end_user_recovery(struct ublk_dev *dev, int daemon_pid)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_END_USER_RECOVERY,
+ .flags = CTRL_CMD_HAS_DATA,
+ };
+
+ dev->dev_info.ublksrv_pid = data.data[0] = daemon_pid;
+
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
static int ublk_ctrl_add_dev(struct ublk_dev *dev)
{
struct ublk_ctrl_cmd_data data = {
@@ -193,6 +216,30 @@ static int ublk_ctrl_get_features(struct ublk_dev *dev,
return __ublk_ctrl_cmd(dev, &data);
}
+static int ublk_ctrl_update_size(struct ublk_dev *dev,
+ __u64 nr_sects)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_UPDATE_SIZE,
+ .flags = CTRL_CMD_HAS_DATA,
+ };
+
+ data.data[0] = nr_sects;
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_quiesce_dev(struct ublk_dev *dev,
+ unsigned int timeout_ms)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_QUIESCE_DEV,
+ .flags = CTRL_CMD_HAS_DATA,
+ };
+
+ data.data[0] = timeout_ms;
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
static const char *ublk_dev_state_desc(struct ublk_dev *dev)
{
switch (dev->dev_info.state) {
@@ -207,10 +254,73 @@ static const char *ublk_dev_state_desc(struct ublk_dev *dev)
};
}
+static void ublk_print_cpu_set(const cpu_set_t *set, char *buf, unsigned len)
+{
+ unsigned done = 0;
+ int i;
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (CPU_ISSET(i, set))
+ done += snprintf(&buf[done], len - done, "%d ", i);
+ }
+}
+
+static void ublk_adjust_affinity(cpu_set_t *set)
+{
+ int j, updated = 0;
+
+ /*
+ * Just keep the 1st CPU now.
+ *
+ * In future, auto affinity selection can be tried.
+ */
+ for (j = 0; j < CPU_SETSIZE; j++) {
+ if (CPU_ISSET(j, set)) {
+ if (!updated) {
+ updated = 1;
+ continue;
+ }
+ CPU_CLR(j, set);
+ }
+ }
+}
+
+/* Caller must free the allocated buffer */
+static int ublk_ctrl_get_affinity(struct ublk_dev *ctrl_dev, cpu_set_t **ptr_buf)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_GET_QUEUE_AFFINITY,
+ .flags = CTRL_CMD_HAS_DATA | CTRL_CMD_HAS_BUF,
+ };
+ cpu_set_t *buf;
+ int i, ret;
+
+ buf = malloc(sizeof(cpu_set_t) * ctrl_dev->dev_info.nr_hw_queues);
+ if (!buf)
+ return -ENOMEM;
+
+ for (i = 0; i < ctrl_dev->dev_info.nr_hw_queues; i++) {
+ data.data[0] = i;
+ data.len = sizeof(cpu_set_t);
+ data.addr = (__u64)&buf[i];
+
+ ret = __ublk_ctrl_cmd(ctrl_dev, &data);
+ if (ret < 0) {
+ free(buf);
+ return ret;
+ }
+ ublk_adjust_affinity(&buf[i]);
+ }
+
+ *ptr_buf = buf;
+ return 0;
+}
+
static void ublk_ctrl_dump(struct ublk_dev *dev)
{
struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
struct ublk_params p;
+ cpu_set_t *affinity;
int ret;
ret = ublk_ctrl_get_params(dev, &p);
@@ -219,12 +329,31 @@ static void ublk_ctrl_dump(struct ublk_dev *dev)
return;
}
+ ret = ublk_ctrl_get_affinity(dev, &affinity);
+ if (ret < 0) {
+ ublk_err("failed to get affinity %m\n");
+ return;
+ }
+
ublk_log("dev id %d: nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n",
info->dev_id, info->nr_hw_queues, info->queue_depth,
1 << p.basic.logical_bs_shift, p.basic.dev_sectors);
ublk_log("\tmax rq size %d daemon pid %d flags 0x%llx state %s\n",
info->max_io_buf_bytes, info->ublksrv_pid, info->flags,
ublk_dev_state_desc(dev));
+
+ if (affinity) {
+ char buf[512];
+ int i;
+
+ for (i = 0; i < info->nr_hw_queues; i++) {
+ ublk_print_cpu_set(&affinity[i], buf, sizeof(buf));
+ printf("\tqueue %u: tid %d affinity(%s)\n",
+ i, dev->q[i].tid, buf);
+ }
+ free(affinity);
+ }
+
fflush(stdout);
}
@@ -300,7 +429,7 @@ static void ublk_queue_deinit(struct ublk_queue *q)
free(q->ios[i].buf_addr);
}
-static int ublk_queue_init(struct ublk_queue *q)
+static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
{
struct ublk_dev *dev = q->dev;
int depth = dev->dev_info.queue_depth;
@@ -315,10 +444,14 @@ static int ublk_queue_init(struct ublk_queue *q)
q->cmd_inflight = 0;
q->tid = gettid();
- if (dev->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY) {
+ if (dev->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_AUTO_BUF_REG)) {
q->state |= UBLKSRV_NO_BUF;
- q->state |= UBLKSRV_ZC;
+ if (dev->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY)
+ q->state |= UBLKSRV_ZC;
+ if (dev->dev_info.flags & UBLK_F_AUTO_BUF_REG)
+ q->state |= UBLKSRV_AUTO_BUF_REG;
}
+ q->state |= extra_flags;
cmd_buf_size = ublk_queue_cmd_buf_sz(q);
off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
@@ -347,14 +480,16 @@ static int ublk_queue_init(struct ublk_queue *q)
}
ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
- IORING_SETUP_COOP_TASKRUN);
+ IORING_SETUP_COOP_TASKRUN |
+ IORING_SETUP_SINGLE_ISSUER |
+ IORING_SETUP_DEFER_TASKRUN);
if (ret < 0) {
ublk_err("ublk dev %d queue %d setup io_uring failed %d\n",
q->dev->dev_info.dev_id, q->q_id, ret);
goto fail;
}
- if (dev->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY) {
+ if (dev->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_AUTO_BUF_REG)) {
ret = io_uring_register_buffers_sparse(&q->ring, q->q_depth);
if (ret) {
ublk_err("ublk dev %d queue %d register spare buffers failed %d",
@@ -418,6 +553,23 @@ static void ublk_dev_unprep(struct ublk_dev *dev)
close(dev->fds[0]);
}
+static void ublk_set_auto_buf_reg(const struct ublk_queue *q,
+ struct io_uring_sqe *sqe,
+ unsigned short tag)
+{
+ struct ublk_auto_buf_reg buf = {};
+
+ if (q->tgt_ops->buf_index)
+ buf.index = q->tgt_ops->buf_index(q, tag);
+ else
+ buf.index = tag;
+
+ if (q->state & UBLKSRV_AUTO_BUF_REG_FALLBACK)
+ buf.flags = UBLK_AUTO_BUF_REG_FALLBACK;
+
+ sqe->addr = ublk_auto_buf_reg_to_sqe_addr(&buf);
+}
+
int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
{
struct ublksrv_io_cmd *cmd;
@@ -429,12 +581,17 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
if (!(io->flags & UBLKSRV_IO_FREE))
return 0;
- /* we issue because we need either fetching or committing */
+ /*
+ * we issue because we need either fetching or committing or
+ * getting data
+ */
if (!(io->flags &
- (UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP)))
+ (UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_NEED_GET_DATA)))
return 0;
- if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
+ if (io->flags & UBLKSRV_NEED_GET_DATA)
+ cmd_op = UBLK_U_IO_NEED_GET_DATA;
+ else if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ;
else if (io->flags & UBLKSRV_NEED_FETCH_RQ)
cmd_op = UBLK_U_IO_FETCH_REQ;
@@ -467,6 +624,9 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
else
cmd->addr = 0;
+ if (q->state & UBLKSRV_AUTO_BUF_REG)
+ ublk_set_auto_buf_reg(q, sqe[0], tag);
+
user_data = build_user_data(tag, _IOC_NR(cmd_op), 0, 0);
io_uring_sqe_set_data64(sqe[0], user_data);
@@ -551,6 +711,9 @@ static void ublk_handle_cqe(struct io_uring *r,
assert(tag < q->q_depth);
if (q->tgt_ops->queue_io)
q->tgt_ops->queue_io(q, tag);
+ } else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) {
+ io->flags |= UBLKSRV_NEED_GET_DATA | UBLKSRV_IO_FREE;
+ ublk_queue_io_cmd(q, io, tag);
} else {
/*
* COMMIT_REQ will be completed immediately since no fetching
@@ -602,18 +765,42 @@ static int ublk_process_io(struct ublk_queue *q)
return reapped;
}
+static void ublk_queue_set_sched_affinity(const struct ublk_queue *q,
+ cpu_set_t *cpuset)
+{
+ if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0)
+ ublk_err("ublk dev %u queue %u set affinity failed",
+ q->dev->dev_info.dev_id, q->q_id);
+}
+
+struct ublk_queue_info {
+ struct ublk_queue *q;
+ sem_t *queue_sem;
+ cpu_set_t *affinity;
+ unsigned char auto_zc_fallback;
+};
+
static void *ublk_io_handler_fn(void *data)
{
- struct ublk_queue *q = data;
+ struct ublk_queue_info *info = data;
+ struct ublk_queue *q = info->q;
int dev_id = q->dev->dev_info.dev_id;
+ unsigned extra_flags = 0;
int ret;
- ret = ublk_queue_init(q);
+ if (info->auto_zc_fallback)
+ extra_flags = UBLKSRV_AUTO_BUF_REG_FALLBACK;
+
+ ret = ublk_queue_init(q, extra_flags);
if (ret) {
ublk_err("ublk dev %d queue %d init queue failed\n",
dev_id, q->q_id);
return NULL;
}
+ /* IO perf is sensitive with queue pthread affinity on NUMA machine*/
+ ublk_queue_set_sched_affinity(q, info->affinity);
+ sem_post(info->queue_sem);
+
ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n",
q->tid, dev_id, q->q_id);
@@ -639,7 +826,7 @@ static void ublk_set_parameters(struct ublk_dev *dev)
dev->dev_info.dev_id, ret);
}
-static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
+static int ublk_send_dev_event(const struct dev_ctx *ctx, struct ublk_dev *dev, int dev_id)
{
uint64_t id;
int evtfd = ctx->_evtfd;
@@ -652,36 +839,69 @@ static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
else
id = ERROR_EVTFD_DEVID;
+ if (dev && ctx->shadow_dev)
+ memcpy(&ctx->shadow_dev->q, &dev->q, sizeof(dev->q));
+
if (write(evtfd, &id, sizeof(id)) != sizeof(id))
return -EINVAL;
+ close(evtfd);
+ shmdt(ctx->shadow_dev);
+
return 0;
}
static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
{
- int ret, i;
- void *thread_ret;
const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info;
+ struct ublk_queue_info *qinfo;
+ cpu_set_t *affinity_buf;
+ void *thread_ret;
+ sem_t queue_sem;
+ int ret, i;
ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__);
+ qinfo = (struct ublk_queue_info *)calloc(sizeof(struct ublk_queue_info),
+ dinfo->nr_hw_queues);
+ if (!qinfo)
+ return -ENOMEM;
+
+ sem_init(&queue_sem, 0, 0);
ret = ublk_dev_prep(ctx, dev);
if (ret)
return ret;
+ ret = ublk_ctrl_get_affinity(dev, &affinity_buf);
+ if (ret)
+ return ret;
+
for (i = 0; i < dinfo->nr_hw_queues; i++) {
dev->q[i].dev = dev;
dev->q[i].q_id = i;
+
+ qinfo[i].q = &dev->q[i];
+ qinfo[i].queue_sem = &queue_sem;
+ qinfo[i].affinity = &affinity_buf[i];
+ qinfo[i].auto_zc_fallback = ctx->auto_zc_fallback;
pthread_create(&dev->q[i].thread, NULL,
ublk_io_handler_fn,
- &dev->q[i]);
+ &qinfo[i]);
}
+ for (i = 0; i < dinfo->nr_hw_queues; i++)
+ sem_wait(&queue_sem);
+ free(qinfo);
+ free(affinity_buf);
+
/* everything is fine now, start us */
- ublk_set_parameters(dev);
- ret = ublk_ctrl_start_dev(dev, getpid());
+ if (ctx->recovery)
+ ret = ublk_ctrl_end_user_recovery(dev, getpid());
+ else {
+ ublk_set_parameters(dev);
+ ret = ublk_ctrl_start_dev(dev, getpid());
+ }
if (ret < 0) {
ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret);
goto fail;
@@ -691,7 +911,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
if (ctx->fg)
ublk_ctrl_dump(dev);
else
- ublk_send_dev_event(ctx, dev->dev_info.dev_id);
+ ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id);
/* wait until we are terminated */
for (i = 0; i < dinfo->nr_hw_queues; i++)
@@ -845,6 +1065,9 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
info->nr_hw_queues = nr_queues;
info->queue_depth = depth;
info->flags = ctx->flags;
+ if ((features & UBLK_F_QUIESCE) &&
+ (info->flags & UBLK_F_USER_RECOVERY))
+ info->flags |= UBLK_F_QUIESCE;
dev->tgt.ops = ops;
dev->tgt.sq_depth = depth;
dev->tgt.cq_depth = depth;
@@ -856,7 +1079,10 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
}
}
- ret = ublk_ctrl_add_dev(dev);
+ if (ctx->recovery)
+ ret = ublk_ctrl_start_user_recovery(dev);
+ else
+ ret = ublk_ctrl_add_dev(dev);
if (ret < 0) {
ublk_err("%s: can't add dev id %d, type %s ret %d\n",
__func__, dev_id, tgt_type, ret);
@@ -870,7 +1096,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
fail:
if (ret < 0)
- ublk_send_dev_event(ctx, -1);
+ ublk_send_dev_event(ctx, dev, -1);
ublk_ctrl_deinit(dev);
return ret;
}
@@ -884,30 +1110,58 @@ static int cmd_dev_add(struct dev_ctx *ctx)
if (ctx->fg)
goto run;
+ ctx->_shmid = shmget(IPC_PRIVATE, sizeof(struct ublk_dev), IPC_CREAT | 0666);
+ if (ctx->_shmid < 0) {
+ ublk_err("%s: failed to shmget %s\n", __func__, strerror(errno));
+ exit(-1);
+ }
+ ctx->shadow_dev = (struct ublk_dev *)shmat(ctx->_shmid, NULL, 0);
+ if (ctx->shadow_dev == (struct ublk_dev *)-1) {
+ ublk_err("%s: failed to shmat %s\n", __func__, strerror(errno));
+ exit(-1);
+ }
ctx->_evtfd = eventfd(0, 0);
if (ctx->_evtfd < 0) {
ublk_err("%s: failed to create eventfd %s\n", __func__, strerror(errno));
exit(-1);
}
- setsid();
res = fork();
if (res == 0) {
+ int res2;
+
+ setsid();
+ res2 = fork();
+ if (res2 == 0) {
+ /* prepare for detaching */
+ close(STDIN_FILENO);
+ close(STDOUT_FILENO);
+ close(STDERR_FILENO);
run:
- res = __cmd_dev_add(ctx);
- return res;
+ res = __cmd_dev_add(ctx);
+ return res;
+ } else {
+ /* detached from the foreground task */
+ exit(EXIT_SUCCESS);
+ }
} else if (res > 0) {
uint64_t id;
+ int exit_code = EXIT_FAILURE;
res = read(ctx->_evtfd, &id, sizeof(id));
close(ctx->_evtfd);
if (res == sizeof(id) && id != ERROR_EVTFD_DEVID) {
ctx->dev_id = id - 1;
- return __cmd_dev_list(ctx);
+ if (__cmd_dev_list(ctx) >= 0)
+ exit_code = EXIT_SUCCESS;
}
- exit(EXIT_FAILURE);
+ shmdt(ctx->shadow_dev);
+ shmctl(ctx->_shmid, IPC_RMID, NULL);
+ /* wait for child and detach from it */
+ wait(NULL);
+ exit(exit_code);
} else {
- return res;
+ exit(EXIT_FAILURE);
}
}
@@ -969,6 +1223,9 @@ static int __cmd_dev_list(struct dev_ctx *ctx)
ublk_err("%s: can't get dev info from %d: %d\n",
__func__, ctx->dev_id, ret);
} else {
+ if (ctx->shadow_dev)
+ memcpy(&dev->q, ctx->shadow_dev->q, sizeof(dev->q));
+
ublk_ctrl_dump(dev);
}
@@ -1006,6 +1263,9 @@ static int cmd_dev_get_features(void)
[const_ilog2(UBLK_F_USER_COPY)] = "USER_COPY",
[const_ilog2(UBLK_F_ZONED)] = "ZONED",
[const_ilog2(UBLK_F_USER_RECOVERY_FAIL_IO)] = "RECOVERY_FAIL_IO",
+ [const_ilog2(UBLK_F_UPDATE_SIZE)] = "UPDATE_SIZE",
+ [const_ilog2(UBLK_F_AUTO_BUF_REG)] = "AUTO_BUF_REG",
+ [const_ilog2(UBLK_F_QUIESCE)] = "QUIESCE",
};
struct ublk_dev *dev;
__u64 features = 0;
@@ -1039,15 +1299,103 @@ static int cmd_dev_get_features(void)
return ret;
}
+static int cmd_dev_update_size(struct dev_ctx *ctx)
+{
+ struct ublk_dev *dev = ublk_ctrl_init();
+ struct ublk_params p;
+ int ret = -EINVAL;
+
+ if (!dev)
+ return -ENODEV;
+
+ if (ctx->dev_id < 0) {
+ fprintf(stderr, "device id isn't provided\n");
+ goto out;
+ }
+
+ dev->dev_info.dev_id = ctx->dev_id;
+ ret = ublk_ctrl_get_params(dev, &p);
+ if (ret < 0) {
+ ublk_err("failed to get params %d %s\n", ret, strerror(-ret));
+ goto out;
+ }
+
+ if (ctx->size & ((1 << p.basic.logical_bs_shift) - 1)) {
+ ublk_err("size isn't aligned with logical block size\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = ublk_ctrl_update_size(dev, ctx->size >> 9);
+out:
+ ublk_ctrl_deinit(dev);
+ return ret;
+}
+
+static int cmd_dev_quiesce(struct dev_ctx *ctx)
+{
+ struct ublk_dev *dev = ublk_ctrl_init();
+ int ret = -EINVAL;
+
+ if (!dev)
+ return -ENODEV;
+
+ if (ctx->dev_id < 0) {
+ fprintf(stderr, "device id isn't provided for quiesce\n");
+ goto out;
+ }
+ dev->dev_info.dev_id = ctx->dev_id;
+ ret = ublk_ctrl_quiesce_dev(dev, 10000);
+
+out:
+ ublk_ctrl_deinit(dev);
+ return ret;
+}
+
+static void __cmd_create_help(char *exe, bool recovery)
+{
+ int i;
+
+ 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[target options] [backfile1] [backfile2] ...\n");
+ printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
+
+ for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
+ const struct ublk_tgt_ops *ops = tgt_ops_list[i];
+
+ if (ops->usage)
+ ops->usage(ops);
+ }
+}
+
+static void cmd_add_help(char *exe)
+{
+ __cmd_create_help(exe, false);
+ printf("\n");
+}
+
+static void cmd_recover_help(char *exe)
+{
+ __cmd_create_help(exe, true);
+ printf("\tPlease provide exact command line for creating this device with real dev_id\n");
+ printf("\n");
+}
+
static int cmd_dev_help(char *exe)
{
- printf("%s add -t [null|loop] [-q nr_queues] [-d depth] [-n dev_id] [backfile1] [backfile2] ...\n", exe);
- printf("\t default: nr_queues=2(max 4), depth=128(max 128), dev_id=-1(auto allocation)\n");
+ cmd_add_help(exe);
+ cmd_recover_help(exe);
+
printf("%s del [-n dev_id] -a \n", exe);
- printf("\t -a delete all devices -n delete specified device\n");
+ printf("\t -a delete all devices -n delete specified device\n\n");
printf("%s list [-n dev_id] -a \n", exe);
- printf("\t -a list all devices, -n list specified device, default -a \n");
+ printf("\t -a list all devices, -n list specified device, default -a \n\n");
printf("%s features\n", exe);
+ printf("%s update_size -n dev_id -s|--size size_in_bytes \n", exe);
+ printf("%s quiesce -n dev_id\n", exe);
return 0;
}
@@ -1063,9 +1411,16 @@ int main(int argc, char *argv[])
{ "quiet", 0, NULL, 0 },
{ "zero_copy", 0, NULL, 'z' },
{ "foreground", 0, NULL, 0 },
- { "chunk_size", 1, NULL, 0 },
+ { "recovery", 1, NULL, 'r' },
+ { "recovery_fail_io", 1, NULL, 'e'},
+ { "recovery_reissue", 1, NULL, 'i'},
+ { "get_data", 1, NULL, 'g'},
+ { "auto_zc", 0, NULL, 0 },
+ { "auto_zc_fallback", 0, NULL, 0 },
+ { "size", 1, NULL, 's'},
{ 0, 0, 0, 0 }
};
+ const struct ublk_tgt_ops *ops = NULL;
int option_idx, opt;
const char *cmd = argv[1];
struct dev_ctx ctx = {
@@ -1073,15 +1428,18 @@ int main(int argc, char *argv[])
.nr_hw_queues = 2,
.dev_id = -1,
.tgt_type = "unknown",
- .chunk_size = 65536, /* def chunk size is 64K */
};
int ret = -EINVAL, i;
+ int tgt_argc = 1;
+ char *tgt_argv[MAX_NR_TGT_ARG] = { NULL };
+ int value;
if (argc == 1)
return ret;
+ opterr = 0;
optind = 2;
- while ((opt = getopt_long(argc, argv, "t:n:d:q:az",
+ while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:s:gaz",
longopts, &option_idx)) != -1) {
switch (opt) {
case 'a':
@@ -1103,6 +1461,27 @@ int main(int argc, char *argv[])
case 'z':
ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY;
break;
+ case 'r':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY;
+ break;
+ case 'e':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO;
+ break;
+ case 'i':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
+ break;
+ case 'g':
+ ctx.flags |= UBLK_F_NEED_GET_DATA;
+ break;
+ case 's':
+ ctx.size = strtoull(optarg, NULL, 10);
+ break;
case 0:
if (!strcmp(longopts[option_idx].name, "debug_mask"))
ublk_dbg_mask = strtol(optarg, NULL, 16);
@@ -1110,19 +1489,67 @@ int main(int argc, char *argv[])
ublk_dbg_mask = 0;
if (!strcmp(longopts[option_idx].name, "foreground"))
ctx.fg = 1;
- if (!strcmp(longopts[option_idx].name, "chunk_size"))
- ctx.chunk_size = strtol(optarg, NULL, 10);
+ if (!strcmp(longopts[option_idx].name, "auto_zc"))
+ ctx.flags |= UBLK_F_AUTO_BUF_REG;
+ if (!strcmp(longopts[option_idx].name, "auto_zc_fallback"))
+ ctx.auto_zc_fallback = 1;
+ break;
+ case '?':
+ /*
+ * target requires every option must have argument
+ */
+ if (argv[optind][0] == '-' || argv[optind - 1][0] != '-') {
+ fprintf(stderr, "every target option requires argument: %s %s\n",
+ argv[optind - 1], argv[optind]);
+ exit(EXIT_FAILURE);
+ }
+
+ if (tgt_argc < (MAX_NR_TGT_ARG - 1) / 2) {
+ tgt_argv[tgt_argc++] = argv[optind - 1];
+ tgt_argv[tgt_argc++] = argv[optind];
+ } else {
+ fprintf(stderr, "too many target options\n");
+ exit(EXIT_FAILURE);
+ }
+ optind += 1;
+ break;
}
}
+ /* auto_zc_fallback depends on F_AUTO_BUF_REG & F_SUPPORT_ZERO_COPY */
+ if (ctx.auto_zc_fallback &&
+ !((ctx.flags & UBLK_F_AUTO_BUF_REG) &&
+ (ctx.flags & UBLK_F_SUPPORT_ZERO_COPY))) {
+ ublk_err("%s: auto_zc_fallback is set but neither "
+ "F_AUTO_BUF_REG nor F_SUPPORT_ZERO_COPY is enabled\n",
+ __func__);
+ return -EINVAL;
+ }
+
i = optind;
while (i < argc && ctx.nr_files < MAX_BACK_FILES) {
ctx.files[ctx.nr_files++] = argv[i++];
}
+ ops = ublk_find_tgt(ctx.tgt_type);
+ if (ops && ops->parse_cmd_line) {
+ optind = 0;
+
+ tgt_argv[0] = ctx.tgt_type;
+ ops->parse_cmd_line(&ctx, tgt_argc, tgt_argv);
+ }
+
if (!strcmp(cmd, "add"))
ret = cmd_dev_add(&ctx);
- else if (!strcmp(cmd, "del"))
+ else if (!strcmp(cmd, "recover")) {
+ if (ctx.dev_id < 0) {
+ fprintf(stderr, "device id isn't provided for recovering\n");
+ ret = -EINVAL;
+ } else {
+ ctx.recovery = 1;
+ ret = cmd_dev_add(&ctx);
+ }
+ } else if (!strcmp(cmd, "del"))
ret = cmd_dev_del(&ctx);
else if (!strcmp(cmd, "list")) {
ctx.all = 1;
@@ -1131,6 +1558,10 @@ int main(int argc, char *argv[])
ret = cmd_dev_help(argv[0]);
else if (!strcmp(cmd, "features"))
ret = cmd_dev_get_features();
+ else if (!strcmp(cmd, "update_size"))
+ ret = cmd_dev_update_size(&ctx);
+ else if (!strcmp(cmd, "quiesce"))
+ ret = cmd_dev_quiesce(&ctx);
else
cmd_dev_help(argv[0]);
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 760ff8ffb8107..e34508bf5798b 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -19,10 +19,15 @@
#include <sys/inotify.h>
#include <sys/wait.h>
#include <sys/eventfd.h>
-#include <sys/uio.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <linux/io_uring.h>
#include <liburing.h>
-#include <linux/ublk_cmd.h>
+#include <semaphore.h>
+
+/* allow ublk_dep.h to override ublk_cmd.h */
#include "ublk_dep.h"
+#include <linux/ublk_cmd.h>
#define __maybe_unused __attribute__((unused))
#define MAX_BACK_FILES 4
@@ -30,6 +35,8 @@
#define min(a, b) ((a) < (b) ? (a) : (b))
#endif
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0]))
+
/****************** part 1: libublk ********************/
#define CTRL_DEV "/dev/ublk-control"
@@ -42,8 +49,8 @@
#define UBLKSRV_IO_IDLE_SECS 20
#define UBLK_IO_MAX_BYTES (1 << 20)
-#define UBLK_MAX_QUEUES 4
-#define UBLK_QUEUE_DEPTH 128
+#define UBLK_MAX_QUEUES 32
+#define UBLK_QUEUE_DEPTH 1024
#define UBLK_DBG_DEV (1U << 0)
#define UBLK_DBG_QUEUE (1U << 1)
@@ -55,6 +62,16 @@
struct ublk_dev;
struct ublk_queue;
+struct stripe_ctx {
+ /* stripe */
+ unsigned int chunk_size;
+};
+
+struct fault_inject_ctx {
+ /* fault_inject */
+ unsigned long delay_us;
+};
+
struct dev_ctx {
char tgt_type[16];
unsigned long flags;
@@ -66,11 +83,22 @@ struct dev_ctx {
unsigned int logging:1;
unsigned int all:1;
unsigned int fg:1;
-
- /* stripe */
- unsigned int chunk_size;
+ unsigned int recovery:1;
+ unsigned int auto_zc_fallback:1;
int _evtfd;
+ int _shmid;
+
+ /* built from shmem, only for ublk_dump_dev() */
+ struct ublk_dev *shadow_dev;
+
+ /* for 'update_size' command */
+ unsigned long long size;
+
+ union {
+ struct stripe_ctx stripe;
+ struct fault_inject_ctx fault_inject;
+ };
};
struct ublk_ctrl_cmd_data {
@@ -90,6 +118,8 @@ struct ublk_io {
#define UBLKSRV_NEED_FETCH_RQ (1UL << 0)
#define UBLKSRV_NEED_COMMIT_RQ_COMP (1UL << 1)
#define UBLKSRV_IO_FREE (1UL << 2)
+#define UBLKSRV_NEED_GET_DATA (1UL << 3)
+#define UBLKSRV_NEED_REG_BUF (1UL << 4)
unsigned short flags;
unsigned short refs; /* used by target code only */
@@ -107,6 +137,17 @@ struct ublk_tgt_ops {
int (*queue_io)(struct ublk_queue *, int tag);
void (*tgt_io_done)(struct ublk_queue *,
int tag, const struct io_uring_cqe *);
+
+ /*
+ * Target specific command line handling
+ *
+ * each option requires argument for target command line
+ */
+ void (*parse_cmd_line)(struct dev_ctx *ctx, int argc, char *argv[]);
+ void (*usage)(const struct ublk_tgt_ops *ops);
+
+ /* return buffer index for UBLK_F_AUTO_BUF_REG */
+ unsigned short (*buf_index)(const struct ublk_queue *, int tag);
};
struct ublk_tgt {
@@ -135,6 +176,8 @@ struct ublk_queue {
#define UBLKSRV_QUEUE_IDLE (1U << 1)
#define UBLKSRV_NO_BUF (1U << 2)
#define UBLKSRV_ZC (1U << 3)
+#define UBLKSRV_AUTO_BUF_REG (1U << 4)
+#define UBLKSRV_AUTO_BUF_REG_FALLBACK (1U << 5)
unsigned state;
pid_t tid;
pthread_t thread;
@@ -170,6 +213,12 @@ struct ublk_dev {
extern unsigned int ublk_dbg_mask;
extern int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag);
+
+static inline int ublk_io_auto_zc_fallback(const struct ublksrv_io_desc *iod)
+{
+ return !!(iod->op_flags & UBLK_IO_F_NEED_REG_BUF);
+}
+
static inline int is_target_io(__u64 user_data)
{
return (user_data & (1ULL << 63)) != 0;
@@ -354,9 +403,15 @@ static inline int ublk_queue_use_zc(const struct ublk_queue *q)
return q->state & UBLKSRV_ZC;
}
+static inline int ublk_queue_use_auto_zc(const struct ublk_queue *q)
+{
+ return q->state & UBLKSRV_AUTO_BUF_REG;
+}
+
extern const struct ublk_tgt_ops null_tgt_ops;
extern const struct ublk_tgt_ops loop_tgt_ops;
extern const struct ublk_tgt_ops stripe_tgt_ops;
+extern const struct ublk_tgt_ops fault_inject_tgt_ops;
void backing_file_tgt_deinit(struct ublk_dev *dev);
int backing_file_tgt_init(struct ublk_dev *dev);
diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c
index 91fec3690d4ba..44aca31cf2b05 100644
--- a/tools/testing/selftests/ublk/null.c
+++ b/tools/testing/selftests/ublk/null.c
@@ -42,10 +42,22 @@ static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
return 0;
}
+static void __setup_nop_io(int tag, const struct ublksrv_io_desc *iod,
+ struct io_uring_sqe *sqe)
+{
+ unsigned ublk_op = ublksrv_get_op(iod);
+
+ io_uring_prep_nop(sqe);
+ sqe->buf_index = tag;
+ sqe->flags |= IOSQE_FIXED_FILE;
+ sqe->rw_flags = IORING_NOP_FIXED_BUFFER | IORING_NOP_INJECT_RESULT;
+ sqe->len = iod->nr_sectors << 9; /* injected result */
+ sqe->user_data = build_user_data(tag, ublk_op, 0, 1);
+}
+
static int null_queue_zc_io(struct ublk_queue *q, int tag)
{
const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
- unsigned ublk_op = ublksrv_get_op(iod);
struct io_uring_sqe *sqe[3];
ublk_queue_alloc_sqes(q, sqe, 3);
@@ -55,12 +67,8 @@ static int null_queue_zc_io(struct ublk_queue *q, int tag)
ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
- io_uring_prep_nop(sqe[1]);
- sqe[1]->buf_index = tag;
- sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
- sqe[1]->rw_flags = IORING_NOP_FIXED_BUFFER | IORING_NOP_INJECT_RESULT;
- sqe[1]->len = iod->nr_sectors << 9; /* injected result */
- sqe[1]->user_data = build_user_data(tag, ublk_op, 0, 1);
+ __setup_nop_io(tag, iod, sqe[1]);
+ sqe[1]->flags |= IOSQE_IO_HARDLINK;
io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, tag);
sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, 1);
@@ -69,6 +77,16 @@ static int null_queue_zc_io(struct ublk_queue *q, int tag)
return 2;
}
+static int null_queue_auto_zc_io(struct ublk_queue *q, int tag)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+ struct io_uring_sqe *sqe[1];
+
+ ublk_queue_alloc_sqes(q, sqe, 1);
+ __setup_nop_io(tag, iod, sqe[0]);
+ return 1;
+}
+
static void ublk_null_io_done(struct ublk_queue *q, int tag,
const struct io_uring_cqe *cqe)
{
@@ -94,22 +112,37 @@ static void ublk_null_io_done(struct ublk_queue *q, int tag,
static int ublk_null_queue_io(struct ublk_queue *q, int tag)
{
const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
- int zc = ublk_queue_use_zc(q);
+ unsigned auto_zc = ublk_queue_use_auto_zc(q);
+ unsigned zc = ublk_queue_use_zc(q);
int queued;
- if (!zc) {
+ if (auto_zc && !ublk_io_auto_zc_fallback(iod))
+ queued = null_queue_auto_zc_io(q, tag);
+ else if (zc)
+ queued = null_queue_zc_io(q, tag);
+ else {
ublk_complete_io(q, tag, iod->nr_sectors << 9);
return 0;
}
-
- queued = null_queue_zc_io(q, tag);
ublk_queued_tgt_io(q, tag, queued);
return 0;
}
+/*
+ * return invalid buffer index for triggering auto buffer register failure,
+ * then UBLK_IO_RES_NEED_REG_BUF handling is covered
+ */
+static unsigned short ublk_null_buf_index(const struct ublk_queue *q, int tag)
+{
+ if (q->state & UBLKSRV_AUTO_BUF_REG_FALLBACK)
+ return (unsigned short)-1;
+ return tag;
+}
+
const struct ublk_tgt_ops null_tgt_ops = {
.name = "null",
.init_tgt = ublk_null_tgt_init,
.queue_io = ublk_null_queue_io,
.tgt_io_done = ublk_null_io_done,
+ .buf_index = ublk_null_buf_index,
};
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 179731c3dd6fe..404a143bf3d69 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -70,7 +70,7 @@ static void free_stripe_array(struct stripe_array *s)
}
static void calculate_stripe_array(const struct stripe_conf *conf,
- const struct ublksrv_io_desc *iod, struct stripe_array *s)
+ const struct ublksrv_io_desc *iod, struct stripe_array *s, void *base)
{
const unsigned shift = conf->shift - 9;
const unsigned chunk_sects = 1 << shift;
@@ -102,7 +102,7 @@ static void calculate_stripe_array(const struct stripe_conf *conf,
}
assert(this->nr_vec < this->cap);
- this->vec[this->nr_vec].iov_base = (void *)(iod->addr + done);
+ this->vec[this->nr_vec].iov_base = (void *)(base + done);
this->vec[this->nr_vec++].iov_len = nr_sects << 9;
start += nr_sects;
@@ -126,15 +126,17 @@ static inline enum io_uring_op stripe_to_uring_op(
static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
{
const struct stripe_conf *conf = get_chunk_shift(q);
- int zc = !!(ublk_queue_use_zc(q) != 0);
- enum io_uring_op op = stripe_to_uring_op(iod, zc);
+ unsigned auto_zc = (ublk_queue_use_auto_zc(q) != 0);
+ unsigned zc = (ublk_queue_use_zc(q) != 0);
+ enum io_uring_op op = stripe_to_uring_op(iod, zc | auto_zc);
struct io_uring_sqe *sqe[NR_STRIPE];
struct stripe_array *s = alloc_stripe_array(conf, iod);
struct ublk_io *io = ublk_get_io(q, tag);
int i, extra = zc ? 2 : 0;
+ void *base = (zc | auto_zc) ? NULL : (void *)iod->addr;
io->private_data = s;
- calculate_stripe_array(conf, iod, s);
+ calculate_stripe_array(conf, iod, s, base);
ublk_queue_alloc_sqes(q, sqe, s->nr + extra);
@@ -153,12 +155,11 @@ static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_
(void *)t->vec,
t->nr_vec,
t->start << 9);
- if (zc) {
+ io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
+ if (auto_zc || zc) {
sqe[i]->buf_index = tag;
- io_uring_sqe_set_flags(sqe[i],
- IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK);
- } else {
- io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
+ if (zc)
+ sqe[i]->flags |= IOSQE_IO_HARDLINK;
}
/* bit63 marks us as tgt io */
sqe[i]->user_data = build_user_data(tag, ublksrv_get_op(iod), i - zc, 1);
@@ -281,12 +282,17 @@ static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
.max_sectors = dev->dev_info.max_io_buf_bytes >> 9,
},
};
- unsigned chunk_size = ctx->chunk_size;
+ unsigned chunk_size = ctx->stripe.chunk_size;
struct stripe_conf *conf;
unsigned chunk_shift;
loff_t bytes = 0;
int ret, i, mul = 1;
+ if (ctx->auto_zc_fallback) {
+ ublk_err("%s: not support auto_zc_fallback\n", __func__);
+ return -EINVAL;
+ }
+
if ((chunk_size & (chunk_size - 1)) || !chunk_size) {
ublk_err("invalid chunk size %u\n", chunk_size);
return -EINVAL;
@@ -344,10 +350,36 @@ static void ublk_stripe_tgt_deinit(struct ublk_dev *dev)
backing_file_tgt_deinit(dev);
}
+static void ublk_stripe_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+ static const struct option longopts[] = {
+ { "chunk_size", 1, NULL, 0 },
+ { 0, 0, 0, 0 }
+ };
+ int option_idx, opt;
+
+ ctx->stripe.chunk_size = 65536;
+ while ((opt = getopt_long(argc, argv, "",
+ longopts, &option_idx)) != -1) {
+ switch (opt) {
+ case 0:
+ if (!strcmp(longopts[option_idx].name, "chunk_size"))
+ ctx->stripe.chunk_size = strtol(optarg, NULL, 10);
+ }
+ }
+}
+
+static void ublk_stripe_usage(const struct ublk_tgt_ops *ops)
+{
+ printf("\tstripe: [--chunk_size chunk_size (default 65536)]\n");
+}
+
const struct ublk_tgt_ops stripe_tgt_ops = {
.name = "stripe",
.init_tgt = ublk_stripe_tgt_init,
.deinit_tgt = ublk_stripe_tgt_deinit,
.queue_io = ublk_stripe_queue_io,
.tgt_io_done = ublk_stripe_io_done,
+ .parse_cmd_line = ublk_stripe_cmd_line,
+ .usage = ublk_stripe_usage,
};
diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh
index a88b359432279..0145569ee7e9a 100755
--- a/tools/testing/selftests/ublk/test_common.sh
+++ b/tools/testing/selftests/ublk/test_common.sh
@@ -17,12 +17,17 @@ _get_disk_dev_t() {
local minor
dev=/dev/ublkb"${dev_id}"
- major=$(stat -c '%Hr' "$dev")
- minor=$(stat -c '%Lr' "$dev")
+ major="0x"$(stat -c '%t' "$dev")
+ minor="0x"$(stat -c '%T' "$dev")
echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
}
+_get_disk_size()
+{
+ lsblk -b -o SIZE -n "$1"
+}
+
_run_fio_verify_io() {
fio --name=verify --rw=randwrite --direct=1 --ioengine=libaio \
--bs=8k --iodepth=32 --verify=crc32c --do_verify=1 \
@@ -30,18 +35,26 @@ _run_fio_verify_io() {
}
_create_backfile() {
- local my_size=$1
- local my_file
+ local index=$1
+ local new_size=$2
+ local old_file
+ local new_file
- my_file=$(mktemp ublk_file_"${my_size}"_XXXXX)
- truncate -s "${my_size}" "${my_file}"
- echo "$my_file"
+ old_file="${UBLK_BACKFILES[$index]}"
+ [ -f "$old_file" ] && rm -f "$old_file"
+
+ new_file=$(mktemp ublk_file_"${new_size}"_XXXXX)
+ truncate -s "${new_size}" "${new_file}"
+ UBLK_BACKFILES["$index"]="$new_file"
}
-_remove_backfile() {
- local file=$1
+_remove_files() {
+ local file
- [ -f "$file" ] && rm -f "$file"
+ for file in "${UBLK_BACKFILES[@]}"; do
+ [ -f "$file" ] && rm -f "$file"
+ done
+ [ -f "$UBLK_TMP" ] && rm -f "$UBLK_TMP"
}
_create_tmp_dir() {
@@ -106,6 +119,7 @@ _prep_test() {
local type=$1
shift 1
modprobe ublk_drv > /dev/null 2>&1
+ UBLK_TMP=$(mktemp ublk_test_XXXXX)
[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "ublk $type: $*"
}
@@ -129,7 +143,10 @@ _show_result()
echo "$1 : [FAIL]"
fi
fi
- [ "$2" -ne 0 ] && exit "$2"
+ if [ "$2" -ne 0 ]; then
+ _remove_files
+ exit "$2"
+ fi
return 0
}
@@ -138,16 +155,16 @@ _check_add_dev()
{
local tid=$1
local code=$2
- shift 2
+
if [ "${code}" -ne 0 ]; then
- _remove_test_files "$@"
_show_result "${tid}" "${code}"
fi
}
_cleanup_test() {
"${UBLK_PROG}" del -a
- rm -f "$UBLK_TMP"
+
+ _remove_files
}
_have_feature()
@@ -158,9 +175,11 @@ _have_feature()
return 1
}
-_add_ublk_dev() {
- local kublk_temp;
+_create_ublk_dev() {
local dev_id;
+ local cmd=$1
+
+ shift 1
if [ ! -c /dev/ublk-control ]; then
return ${UBLK_SKIP_CODE}
@@ -171,17 +190,54 @@ _add_ublk_dev() {
fi
fi
- kublk_temp=$(mktemp /tmp/kublk-XXXXXX)
- if ! "${UBLK_PROG}" add "$@" > "${kublk_temp}" 2>&1; then
+ if ! dev_id=$("${UBLK_PROG}" "$cmd" "$@" | grep "dev id" | awk -F '[ :]' '{print $3}'); then
echo "fail to add ublk dev $*"
- rm -f "${kublk_temp}"
return 255
fi
-
- dev_id=$(grep "dev id" "${kublk_temp}" | awk -F '[ :]' '{print $3}')
udevadm settle
- rm -f "${kublk_temp}"
- echo "${dev_id}"
+
+ if [[ "$dev_id" =~ ^[0-9]+$ ]]; then
+ echo "${dev_id}"
+ else
+ return 255
+ fi
+}
+
+_add_ublk_dev() {
+ _create_ublk_dev "add" "$@"
+}
+
+_recover_ublk_dev() {
+ local dev_id
+ local state
+
+ dev_id=$(_create_ublk_dev "recover" "$@")
+ for ((j=0;j<20;j++)); do
+ state=$(_get_ublk_dev_state "${dev_id}")
+ [ "$state" == "LIVE" ] && break
+ sleep 1
+ done
+ echo "$state"
+}
+
+# quiesce device and return ublk device state
+__ublk_quiesce_dev()
+{
+ local dev_id=$1
+ local exp_state=$2
+ local state
+
+ if ! ${UBLK_PROG} quiesce -n "${dev_id}"; then
+ state=$(_get_ublk_dev_state "${dev_id}")
+ return "$state"
+ fi
+
+ for ((j=0;j<50;j++)); do
+ state=$(_get_ublk_dev_state "${dev_id}")
+ [ "$state" == "$exp_state" ] && break
+ sleep 1
+ done
+ echo "$state"
}
# kill the ublk daemon and return ublk device state
@@ -220,7 +276,7 @@ __run_io_and_remove()
local kill_server=$3
fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
- --rw=readwrite --iodepth=64 --size="${size}" --numjobs=4 \
+ --rw=randrw --norandommap --iodepth=256 --size="${size}" --numjobs="$(nproc)" \
--runtime=20 --time_based > /dev/null 2>&1 &
sleep 2
if [ "${kill_server}" = "yes" ]; then
@@ -238,15 +294,86 @@ __run_io_and_remove()
wait
}
+run_io_and_remove()
+{
+ local size=$1
+ local dev_id
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+ if ! __run_io_and_remove "$dev_id" "${size}" "no"; then
+ echo "/dev/ublkc$dev_id isn't removed"
+ exit 255
+ fi
+}
+
+run_io_and_kill_daemon()
+{
+ local size=$1
+ local dev_id
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
+ if ! __run_io_and_remove "$dev_id" "${size}" "yes"; then
+ echo "/dev/ublkc$dev_id isn't removed res ${res}"
+ exit 255
+ fi
+}
+
+run_io_and_recover()
+{
+ local action=$1
+ local state
+ local dev_id
+
+ shift 1
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+ --rw=randread --iodepth=256 --size="${size}" --numjobs=4 \
+ --runtime=20 --time_based > /dev/null 2>&1 &
+ sleep 4
+
+ if [ "$action" == "kill_daemon" ]; then
+ state=$(__ublk_kill_daemon "${dev_id}" "QUIESCED")
+ elif [ "$action" == "quiesce_dev" ]; then
+ state=$(__ublk_quiesce_dev "${dev_id}" "QUIESCED")
+ fi
+ if [ "$state" != "QUIESCED" ]; then
+ echo "device isn't quiesced($state) after $action"
+ return 255
+ fi
+
+ state=$(_recover_ublk_dev -n "$dev_id" "$@")
+ if [ "$state" != "LIVE" ]; then
+ echo "faile to recover to LIVE($state)"
+ return 255
+ fi
+
+ if ! __remove_ublk_dev_return "${dev_id}"; then
+ echo "delete dev ${dev_id} failed"
+ return 255
+ fi
+ wait
+}
+
+
_ublk_test_top_dir()
{
cd "$(dirname "$0")" && pwd
}
-UBLK_TMP=$(mktemp ublk_test_XXXXX)
UBLK_PROG=$(_ublk_test_top_dir)/kublk
UBLK_TEST_QUIET=1
UBLK_TEST_SHOW_RESULT=1
+UBLK_BACKFILES=()
export UBLK_PROG
export UBLK_TEST_QUIET
export UBLK_TEST_SHOW_RESULT
diff --git a/tools/testing/selftests/ublk/test_generic_04.sh b/tools/testing/selftests/ublk/test_generic_04.sh
new file mode 100755
index 0000000000000..8b533217d4a17
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_04.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_04"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+ run_io_and_recover "kill_daemon" "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh
new file mode 100755
index 0000000000000..398e9e2b58e15
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_05.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_05"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+ run_io_and_recover "kill_daemon" "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification (zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 -z &
+ublk_run_recover_test -t loop -q 2 -r 1 -z "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -z -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_06.sh b/tools/testing/selftests/ublk/test_generic_06.sh
new file mode 100755
index 0000000000000..fd42062b7b76b
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_06.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_06"
+ERR_CODE=0
+
+_prep_test "fault_inject" "fast cleanup when all I/Os of one hctx are in server"
+
+# configure ublk server to sleep 2s before completing each I/O
+dev_id=$(_add_ublk_dev -t fault_inject -q 2 -d 1 --delay_us 2000000)
+_check_add_dev $TID $?
+
+STARTTIME=${SECONDS}
+
+dd if=/dev/urandom of=/dev/ublkb${dev_id} oflag=direct bs=4k count=1 status=none > /dev/null 2>&1 &
+dd_pid=$!
+
+__ublk_kill_daemon ${dev_id} "DEAD" >/dev/null
+
+wait $dd_pid
+dd_exitcode=$?
+
+ENDTIME=${SECONDS}
+ELAPSED=$(($ENDTIME - $STARTTIME))
+
+# assert that dd sees an error and exits quickly after ublk server is
+# killed. previously this relied on seeing an I/O timeout and so would
+# take ~30s
+if [ $dd_exitcode -eq 0 ]; then
+ echo "dd unexpectedly exited successfully!"
+ ERR_CODE=255
+fi
+if [ $ELAPSED -ge 5 ]; then
+ echo "dd took $ELAPSED seconds to exit (>= 5s tolerance)!"
+ ERR_CODE=255
+fi
+
+_cleanup_test "fault_inject"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_07.sh b/tools/testing/selftests/ublk/test_generic_07.sh
new file mode 100755
index 0000000000000..cba86451fa5e5
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_07.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_07"
+ERR_CODE=0
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "generic" "test UBLK_F_NEED_GET_DATA"
+
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -q 2 -g "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
+
+# run fio over the ublk disk
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
+ERR_CODE=$?
+if [ "$ERR_CODE" -eq 0 ]; then
+ _mkfs_mount_test /dev/ublkb"${dev_id}"
+ ERR_CODE=$?
+fi
+
+_cleanup_test "generic"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_08.sh b/tools/testing/selftests/ublk/test_generic_08.sh
new file mode 100755
index 0000000000000..b222f3a77e122
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_08.sh
@@ -0,0 +1,32 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_08"
+ERR_CODE=0
+
+if ! _have_feature "AUTO_BUF_REG"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "generic" "test UBLK_F_AUTO_BUF_REG"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t loop -q 2 --auto_zc "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
+
+if ! _mkfs_mount_test /dev/ublkb"${dev_id}"; then
+ _cleanup_test "generic"
+ _show_result $TID 255
+fi
+
+dev_id=$(_add_ublk_dev -t stripe --auto_zc "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
+_mkfs_mount_test /dev/ublkb"${dev_id}"
+ERR_CODE=$?
+
+_cleanup_test "generic"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_09.sh b/tools/testing/selftests/ublk/test_generic_09.sh
new file mode 100755
index 0000000000000..bb6f77ca5522f
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_09.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_09"
+ERR_CODE=0
+
+if ! _have_feature "AUTO_BUF_REG"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "null" "basic IO test"
+
+dev_id=$(_add_ublk_dev -t null -z --auto_zc --auto_zc_fallback)
+_check_add_dev $TID $?
+
+# run fio over the two disks
+fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio --rw=readwrite --iodepth=32 --size=256M > /dev/null 2>&1
+ERR_CODE=$?
+
+_cleanup_test "null"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_10.sh b/tools/testing/selftests/ublk/test_generic_10.sh
new file mode 100755
index 0000000000000..abc11c3d416bd
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_10.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_10"
+ERR_CODE=0
+
+if ! _have_feature "UPDATE_SIZE"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "null" "check update size"
+
+dev_id=$(_add_ublk_dev -t null)
+_check_add_dev $TID $?
+
+size=$(_get_disk_size /dev/ublkb"${dev_id}")
+size=$(( size / 2 ))
+if ! "$UBLK_PROG" update_size -n "$dev_id" -s "$size"; then
+ ERR_CODE=255
+fi
+
+new_size=$(_get_disk_size /dev/ublkb"${dev_id}")
+if [ "$new_size" != "$size" ]; then
+ ERR_CODE=255
+fi
+
+_cleanup_test "null"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_11.sh b/tools/testing/selftests/ublk/test_generic_11.sh
new file mode 100755
index 0000000000000..a00357a5ec6b8
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_11.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_11"
+ERR_CODE=0
+
+ublk_run_quiesce_recover()
+{
+ run_io_and_recover "quiesce_dev" "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_feature "QUIESCE"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "quiesce" "basic quiesce & recover function verification"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_quiesce_recover -t null -q 2 -r 1 &
+ublk_run_quiesce_recover -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_quiesce_recover -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_quiesce_recover -t null -q 2 -r 1 -i 1 &
+ublk_run_quiesce_recover -t loop -q 2 -r 1 -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_quiesce_recover -t stripe -q 2 -r 1 -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "quiesce"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_01.sh b/tools/testing/selftests/ublk/test_loop_01.sh
index 1ef8b6044777c..833fa0dbc7009 100755
--- a/tools/testing/selftests/ublk/test_loop_01.sh
+++ b/tools/testing/selftests/ublk/test_loop_01.sh
@@ -12,10 +12,10 @@ fi
_prep_test "loop" "write and verify test"
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -23,6 +23,4 @@ ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_02.sh b/tools/testing/selftests/ublk/test_loop_02.sh
index 03863d825e07d..874568b3646b6 100755
--- a/tools/testing/selftests/ublk/test_loop_02.sh
+++ b/tools/testing/selftests/ublk/test_loop_02.sh
@@ -8,15 +8,13 @@ ERR_CODE=0
_prep_test "loop" "mkfs & mount & umount"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_03.sh b/tools/testing/selftests/ublk/test_loop_03.sh
index e9ca744de8b13..c30f797c64295 100755
--- a/tools/testing/selftests/ublk/test_loop_03.sh
+++ b/tools/testing/selftests/ublk/test_loop_03.sh
@@ -12,9 +12,9 @@ fi
_prep_test "loop" "write and verify over zero copy"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -22,6 +22,4 @@ ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_04.sh b/tools/testing/selftests/ublk/test_loop_04.sh
index 1435422c38ec8..b01d75b3214d2 100755
--- a/tools/testing/selftests/ublk/test_loop_04.sh
+++ b/tools/testing/selftests/ublk/test_loop_04.sh
@@ -8,15 +8,14 @@ ERR_CODE=0
_prep_test "loop" "mkfs & mount & umount with zero copy"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_05.sh b/tools/testing/selftests/ublk/test_loop_05.sh
index 2e6e2e6978fca..de21415330742 100755
--- a/tools/testing/selftests/ublk/test_loop_05.sh
+++ b/tools/testing/selftests/ublk/test_loop_05.sh
@@ -12,10 +12,10 @@ fi
_prep_test "loop" "write and verify test"
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
-dev_id=$(_add_ublk_dev -q 2 -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -q 2 -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
@@ -23,6 +23,4 @@ ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_01.sh b/tools/testing/selftests/ublk/test_stress_01.sh
index a8be24532b24b..7d3150f057d44 100755
--- a/tools/testing/selftests/ublk/test_stress_01.sh
+++ b/tools/testing/selftests/ublk/test_stress_01.sh
@@ -4,44 +4,31 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
TID="stress_01"
ERR_CODE=0
-DEV_ID=-1
ublk_io_and_remove()
{
- local size=$1
- shift 1
- local backfile=""
- if echo "$@" | grep -q "loop"; then
- backfile=${*: -1}
- fi
- DEV_ID=$(_add_ublk_dev "$@")
- _check_add_dev $TID $? "${backfile}"
-
- [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
- if ! __run_io_and_remove "${DEV_ID}" "${size}" "no"; then
- echo "/dev/ublkc${DEV_ID} isn't removed"
- _remove_backfile "${backfile}"
- exit 255
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
fi
}
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "stress" "run IO and remove device"
-ublk_io_and_remove 8G -t null -q 4
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_remove 256M -t loop -q 4 "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+ublk_io_and_remove 8G -t null -q 4 &
+ublk_io_and_remove 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
-ublk_io_and_remove 256M -t loop -q 4 -z "${BACK_FILE}"
-ERR_CODE=$?
_cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_02.sh b/tools/testing/selftests/ublk/test_stress_02.sh
index 2159e4cc8140e..4bdd921081e55 100755
--- a/tools/testing/selftests/ublk/test_stress_02.sh
+++ b/tools/testing/selftests/ublk/test_stress_02.sh
@@ -4,44 +4,33 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
TID="stress_02"
ERR_CODE=0
-DEV_ID=-1
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
ublk_io_and_kill_daemon()
{
- local size=$1
- shift 1
- local backfile=""
- if echo "$@" | grep -q "loop"; then
- backfile=${*: -1}
- fi
- DEV_ID=$(_add_ublk_dev "$@")
- _check_add_dev $TID $? "${backfile}"
-
- [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
- if ! __run_io_and_remove "${DEV_ID}" "${size}" "yes"; then
- echo "/dev/ublkc${DEV_ID} isn't removed res ${res}"
- _remove_backfile "${backfile}"
- exit 255
+ run_io_and_kill_daemon "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
fi
}
_prep_test "stress" "run IO and kill ublk server"
-ublk_io_and_kill_daemon 8G -t null -q 4
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_kill_daemon 256M -t loop -q 4 "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+for nr_queue in 1 4; do
+ ublk_io_and_kill_daemon 8G -t null -q "$nr_queue" &
+ ublk_io_and_kill_daemon 256M -t loop -q "$nr_queue" "${UBLK_BACKFILES[0]}" &
+ ublk_io_and_kill_daemon 256M -t stripe -q "$nr_queue" "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+ wait
+done
-ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${BACK_FILE}"
-ERR_CODE=$?
_cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh
new file mode 100755
index 0000000000000..7d728ce507740
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_03.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_03"
+ERR_CODE=0
+
+ublk_io_and_remove()
+{
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and remove device(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_remove 8G -t null -q 4 -z &
+ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+
+if _have_feature "AUTO_BUF_REG"; then
+ ublk_io_and_remove 8G -t null -q 4 --auto_zc &
+ ublk_io_and_remove 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" &
+ ublk_io_and_remove 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+ ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
+fi
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
new file mode 100755
index 0000000000000..9bcfa64ea1f05
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_04"
+ERR_CODE=0
+
+ublk_io_and_kill_daemon()
+{
+ run_io_and_kill_daemon "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and kill ublk server(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_kill_daemon 8G -t null -q 4 -z &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 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 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
+fi
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
new file mode 100755
index 0000000000000..bcfc904cefc60
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -0,0 +1,73 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_05"
+ERR_CODE=0
+
+run_io_and_remove()
+{
+ local size=$1
+ local dev_id
+ local dev_pid
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev $TID $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+
+ fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+ --rw=readwrite --iodepth=128 --size="${size}" --numjobs=4 \
+ --runtime=40 --time_based > /dev/null 2>&1 &
+ sleep 4
+
+ dev_pid=$(_get_ublk_daemon_pid "$dev_id")
+ kill -9 "$dev_pid"
+
+ if ! __remove_ublk_dev_return "${dev_id}"; then
+ echo "delete dev ${dev_id} failed"
+ return 255
+ fi
+}
+
+ublk_io_and_remove()
+{
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+_prep_test "stress" "run IO and remove device with recovery enabled"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
+ wait
+done
+
+if _have_feature "ZERO_COPY"; then
+ for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g -z -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+ wait
+ done
+fi
+
+if _have_feature "AUTO_BUF_REG"; then
+ for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g --auto_zc -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g --auto_zc -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+ ublk_io_and_remove 8G -t null -q 4 -g -z --auto_zc --auto_zc_fallback -r 1 -i "$reissue" &
+ wait
+ done
+fi
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_01.sh b/tools/testing/selftests/ublk/test_stripe_01.sh
index 7e387ef656ea8..4e4f0fdf3c9b5 100755
--- a/tools/testing/selftests/ublk/test_stripe_01.sh
+++ b/tools/testing/selftests/ublk/test_stripe_01.sh
@@ -12,19 +12,15 @@ fi
_prep_test "stripe" "write and verify test"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_02.sh b/tools/testing/selftests/ublk/test_stripe_02.sh
index e8a45fa82dde0..5820ab2efba47 100755
--- a/tools/testing/selftests/ublk/test_stripe_02.sh
+++ b/tools/testing/selftests/ublk/test_stripe_02.sh
@@ -8,17 +8,14 @@ ERR_CODE=0
_prep_test "stripe" "mkfs & mount & umount"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_03.sh b/tools/testing/selftests/ublk/test_stripe_03.sh
index c1b34af36145a..20b977e27814c 100755
--- a/tools/testing/selftests/ublk/test_stripe_03.sh
+++ b/tools/testing/selftests/ublk/test_stripe_03.sh
@@ -12,19 +12,15 @@ fi
_prep_test "stripe" "write and verify test"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
-dev_id=$(_add_ublk_dev -q 2 -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -q 2 -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_04.sh b/tools/testing/selftests/ublk/test_stripe_04.sh
index 1f2b642381d17..1b51ed2f1d843 100755
--- a/tools/testing/selftests/ublk/test_stripe_04.sh
+++ b/tools/testing/selftests/ublk/test_stripe_04.sh
@@ -8,17 +8,14 @@ ERR_CODE=0
_prep_test "stripe" "mkfs & mount & umount on zero copy"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t stripe -z -q 2 "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe -z -q 2 "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/x86/bugs/Makefile b/tools/testing/selftests/x86/bugs/Makefile
new file mode 100644
index 0000000000000..8ff2d7226c7f3
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/Makefile
@@ -0,0 +1,3 @@
+TEST_PROGS := its_sysfs.py its_permutations.py its_indirect_alignment.py its_ret_alignment.py
+TEST_FILES := common.py
+include ../../lib.mk
diff --git a/tools/testing/selftests/x86/bugs/common.py b/tools/testing/selftests/x86/bugs/common.py
new file mode 100755
index 0000000000000..2f9664a80617a
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/common.py
@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# This contains kselftest framework adapted common functions for testing
+# mitigation for x86 bugs.
+
+import os, sys, re, shutil
+
+sys.path.insert(0, '../../kselftest')
+import ksft
+
+def read_file(path):
+ if not os.path.exists(path):
+ return None
+ with open(path, 'r') as file:
+ return file.read().strip()
+
+def cpuinfo_has(arg):
+ cpuinfo = read_file('/proc/cpuinfo')
+ if arg in cpuinfo:
+ return True
+ return False
+
+def cmdline_has(arg):
+ cmdline = read_file('/proc/cmdline')
+ if arg in cmdline:
+ return True
+ return False
+
+def cmdline_has_either(args):
+ cmdline = read_file('/proc/cmdline')
+ for arg in args:
+ if arg in cmdline:
+ return True
+ return False
+
+def cmdline_has_none(args):
+ return not cmdline_has_either(args)
+
+def cmdline_has_all(args):
+ cmdline = read_file('/proc/cmdline')
+ for arg in args:
+ if arg not in cmdline:
+ return False
+ return True
+
+def get_sysfs(bug):
+ return read_file("/sys/devices/system/cpu/vulnerabilities/" + bug)
+
+def sysfs_has(bug, mitigation):
+ status = get_sysfs(bug)
+ if mitigation in status:
+ return True
+ return False
+
+def sysfs_has_either(bugs, mitigations):
+ for bug in bugs:
+ for mitigation in mitigations:
+ if sysfs_has(bug, mitigation):
+ return True
+ return False
+
+def sysfs_has_none(bugs, mitigations):
+ return not sysfs_has_either(bugs, mitigations)
+
+def sysfs_has_all(bugs, mitigations):
+ for bug in bugs:
+ for mitigation in mitigations:
+ if not sysfs_has(bug, mitigation):
+ return False
+ return True
+
+def bug_check_pass(bug, found):
+ ksft.print_msg(f"\nFound: {found}")
+ # ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+ ksft.test_result_pass(f'{bug}: {found}')
+
+def bug_check_fail(bug, found, expected):
+ ksft.print_msg(f'\nFound:\t {found}')
+ ksft.print_msg(f'Expected:\t {expected}')
+ ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+ ksft.test_result_fail(f'{bug}: {found}')
+
+def bug_status_unknown(bug, found):
+ ksft.print_msg(f'\nUnknown status: {found}')
+ ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}")
+ ksft.test_result_fail(f'{bug}: {found}')
+
+def basic_checks_sufficient(bug, mitigation):
+ if not mitigation:
+ bug_status_unknown(bug, "None")
+ return True
+ elif mitigation == "Not affected":
+ ksft.test_result_pass(bug)
+ return True
+ elif mitigation == "Vulnerable":
+ if cmdline_has_either([f'{bug}=off', 'mitigations=off']):
+ bug_check_pass(bug, mitigation)
+ return True
+ return False
+
+def get_section_info(vmlinux, section_name):
+ from elftools.elf.elffile import ELFFile
+ with open(vmlinux, 'rb') as f:
+ elffile = ELFFile(f)
+ section = elffile.get_section_by_name(section_name)
+ if section is None:
+ ksft.print_msg("Available sections in vmlinux:")
+ for sec in elffile.iter_sections():
+ ksft.print_msg(sec.name)
+ raise ValueError(f"Section {section_name} not found in {vmlinux}")
+ return section['sh_addr'], section['sh_offset'], section['sh_size']
+
+def get_patch_sites(vmlinux, offset, size):
+ import struct
+ output = []
+ with open(vmlinux, 'rb') as f:
+ f.seek(offset)
+ i = 0
+ while i < size:
+ data = f.read(4) # s32
+ if not data:
+ break
+ sym_offset = struct.unpack('<i', data)[0] + i
+ i += 4
+ output.append(sym_offset)
+ return output
+
+def get_instruction_from_vmlinux(elffile, section, virtual_address, target_address):
+ from capstone import Cs, CS_ARCH_X86, CS_MODE_64
+ section_start = section['sh_addr']
+ section_end = section_start + section['sh_size']
+
+ if not (section_start <= target_address < section_end):
+ return None
+
+ offset = target_address - section_start
+ code = section.data()[offset:offset + 16]
+
+ cap = init_capstone()
+ for instruction in cap.disasm(code, target_address):
+ if instruction.address == target_address:
+ return instruction
+ return None
+
+def init_capstone():
+ from capstone import Cs, CS_ARCH_X86, CS_MODE_64, CS_OPT_SYNTAX_ATT
+ cap = Cs(CS_ARCH_X86, CS_MODE_64)
+ cap.syntax = CS_OPT_SYNTAX_ATT
+ return cap
+
+def get_runtime_kernel():
+ import drgn
+ return drgn.program_from_kernel()
+
+def check_dependencies_or_skip(modules, script_name="unknown test"):
+ for mod in modules:
+ try:
+ __import__(mod)
+ except ImportError:
+ ksft.test_result_skip(f"Skipping {script_name}: missing module '{mod}'")
+ ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_indirect_alignment.py b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py
new file mode 100755
index 0000000000000..cdc33ae6a91c3
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py
@@ -0,0 +1,150 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) mitigation.
+#
+# Test if indirect CALL/JMP are correctly patched by evaluating
+# the vmlinux .retpoline_sites in /proc/kcore.
+
+# Install dependencies
+# add-apt-repository ppa:michel-slm/kernel-utils
+# apt update
+# apt install -y python3-drgn python3-pyelftools python3-capstone
+#
+# Best to copy the vmlinux at a standard location:
+# mkdir -p /usr/lib/debug/lib/modules/$(uname -r)
+# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux
+#
+# Usage: ./its_indirect_alignment.py [vmlinux]
+
+import os, sys, argparse
+from pathlib import Path
+
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+
+mitigation = c.get_sysfs(bug)
+if not mitigation or "Aligned branch/return thunks" not in mitigation:
+ ksft.test_result_skip("Skipping its_indirect_alignment.py: Aligned branch/return thunks not enabled")
+ ksft.finished()
+
+if c.sysfs_has("spectre_v2", "Retpolines"):
+ ksft.test_result_skip("Skipping its_indirect_alignment.py: Retpolines deployed")
+ ksft.finished()
+
+c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_indirect_alignment.py")
+
+from elftools.elf.elffile import ELFFile
+from drgn.helpers.common.memory import identify_address
+
+cap = c.init_capstone()
+
+if len(os.sys.argv) > 1:
+ arg_vmlinux = os.sys.argv[1]
+ if not os.path.exists(arg_vmlinux):
+ ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at argument path: {arg_vmlinux}")
+ ksft.exit_fail()
+ os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True)
+ os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux')
+
+vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux"
+if not os.path.exists(vmlinux):
+ ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at {vmlinux}")
+ ksft.exit_fail()
+
+ksft.print_msg(f"Using vmlinux: {vmlinux}")
+
+retpolines_start_vmlinux, retpolines_sec_offset, size = c.get_section_info(vmlinux, '.retpoline_sites')
+ksft.print_msg(f"vmlinux: Section .retpoline_sites (0x{retpolines_start_vmlinux:x}) found at 0x{retpolines_sec_offset:x} with size 0x{size:x}")
+
+sites_offset = c.get_patch_sites(vmlinux, retpolines_sec_offset, size)
+total_retpoline_tests = len(sites_offset)
+ksft.print_msg(f"Found {total_retpoline_tests} retpoline sites")
+
+prog = c.get_runtime_kernel()
+retpolines_start_kcore = prog.symbol('__retpoline_sites').address
+ksft.print_msg(f'kcore: __retpoline_sites: 0x{retpolines_start_kcore:x}')
+
+x86_indirect_its_thunk_r15 = prog.symbol('__x86_indirect_its_thunk_r15').address
+ksft.print_msg(f'kcore: __x86_indirect_its_thunk_r15: 0x{x86_indirect_its_thunk_r15:x}')
+
+tests_passed = 0
+tests_failed = 0
+tests_unknown = 0
+
+with open(vmlinux, 'rb') as f:
+ elffile = ELFFile(f)
+ text_section = elffile.get_section_by_name('.text')
+
+ for i in range(0, len(sites_offset)):
+ site = retpolines_start_kcore + sites_offset[i]
+ vmlinux_site = retpolines_start_vmlinux + sites_offset[i]
+ passed = unknown = failed = False
+ try:
+ vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site)
+ kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0]
+ operand = kcore_insn.op_str
+ insn_end = site + kcore_insn.size - 1 # TODO handle Jcc.32 __x86_indirect_thunk_\reg
+ safe_site = insn_end & 0x20
+ site_status = "" if safe_site else "(unsafe)"
+
+ ksft.print_msg(f"\nSite {i}: {identify_address(prog, site)} <0x{site:x}> {site_status}")
+ ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}")
+ ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}")
+
+ if (site & 0x20) ^ (insn_end & 0x20):
+ ksft.print_msg(f"\tSite at safe/unsafe boundary: {str(kcore_insn.bytes)} {kcore_insn.mnemonic} {operand}")
+ if safe_site:
+ tests_passed += 1
+ passed = True
+ ksft.print_msg(f"\tPASSED: At safe address")
+ continue
+
+ if operand.startswith('0xffffffff'):
+ thunk = int(operand, 16)
+ if thunk > x86_indirect_its_thunk_r15:
+ insn_at_thunk = list(cap.disasm(prog.read(thunk, 16), thunk))[0]
+ operand += ' -> ' + insn_at_thunk.mnemonic + ' ' + insn_at_thunk.op_str + ' <dynamic-thunk?>'
+ if 'jmp' in insn_at_thunk.mnemonic and thunk & 0x20:
+ ksft.print_msg(f"\tPASSED: Found {operand} at safe address")
+ passed = True
+ if not passed:
+ if kcore_insn.operands[0].type == capstone.CS_OP_IMM:
+ operand += ' <' + prog.symbol(int(operand, 16)) + '>'
+ if '__x86_indirect_its_thunk_' in operand:
+ ksft.print_msg(f"\tPASSED: Found {operand}")
+ else:
+ ksft.print_msg(f"\tPASSED: Found direct branch: {kcore_insn}, ITS thunk not required.")
+ passed = True
+ else:
+ unknown = True
+ if passed:
+ tests_passed += 1
+ elif unknown:
+ ksft.print_msg(f"UNKNOWN: unexpected operand: {kcore_insn}")
+ tests_unknown += 1
+ else:
+ ksft.print_msg(f'\t************* FAILED *************')
+ ksft.print_msg(f"\tFound {kcore_insn.bytes} {kcore_insn.mnemonic} {operand}")
+ ksft.print_msg(f'\t**********************************')
+ tests_failed += 1
+ except Exception as e:
+ ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}")
+ tests_unknown += 1
+
+ksft.print_msg(f"\n\nSummary:")
+ksft.print_msg(f"PASS: \t{tests_passed} \t/ {total_retpoline_tests}")
+ksft.print_msg(f"FAIL: \t{tests_failed} \t/ {total_retpoline_tests}")
+ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_retpoline_tests}")
+
+if tests_failed == 0:
+ ksft.test_result_pass("All ITS return thunk sites passed")
+else:
+ ksft.test_result_fail(f"{tests_failed} ITS return thunk sites failed")
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_permutations.py b/tools/testing/selftests/x86/bugs/its_permutations.py
new file mode 100755
index 0000000000000..3204f4728c62c
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_permutations.py
@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) cmdline permutations with other bugs
+# like spectre_v2 and retbleed.
+
+import os, sys, subprocess, itertools, re, shutil
+
+test_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, test_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+mitigation = c.get_sysfs(bug)
+
+if not mitigation or "Not affected" in mitigation:
+ ksft.test_result_skip("Skipping its_permutations.py: not applicable")
+ ksft.finished()
+
+if shutil.which('vng') is None:
+ ksft.test_result_skip("Skipping its_permutations.py: virtme-ng ('vng') not found in PATH.")
+ ksft.finished()
+
+TEST = f"{test_dir}/its_sysfs.py"
+default_kparam = ['clearcpuid=hypervisor', 'panic=5', 'panic_on_warn=1', 'oops=panic', 'nmi_watchdog=1', 'hung_task_panic=1']
+
+DEBUG = " -v "
+
+# Install dependencies
+# https://github.com/arighi/virtme-ng
+# apt install virtme-ng
+BOOT_CMD = f"vng --run {test_dir}/../../../../../arch/x86/boot/bzImage "
+#BOOT_CMD += DEBUG
+
+bug = "indirect_target_selection"
+
+input_options = {
+ 'indirect_target_selection' : ['off', 'on', 'stuff', 'vmexit'],
+ 'retbleed' : ['off', 'stuff', 'auto'],
+ 'spectre_v2' : ['off', 'on', 'eibrs', 'retpoline', 'ibrs', 'eibrs,retpoline'],
+}
+
+def pretty_print(output):
+ OKBLUE = '\033[94m'
+ OKGREEN = '\033[92m'
+ WARNING = '\033[93m'
+ FAIL = '\033[91m'
+ ENDC = '\033[0m'
+ BOLD = '\033[1m'
+
+ # Define patterns and their corresponding colors
+ patterns = {
+ r"^ok \d+": OKGREEN,
+ r"^not ok \d+": FAIL,
+ r"^# Testing .*": OKBLUE,
+ r"^# Found: .*": WARNING,
+ r"^# Totals: .*": BOLD,
+ r"pass:([1-9]\d*)": OKGREEN,
+ r"fail:([1-9]\d*)": FAIL,
+ r"skip:([1-9]\d*)": WARNING,
+ }
+
+ # Apply colors based on patterns
+ for pattern, color in patterns.items():
+ output = re.sub(pattern, lambda match: f"{color}{match.group(0)}{ENDC}", output, flags=re.MULTILINE)
+
+ print(output)
+
+combinations = list(itertools.product(*input_options.values()))
+ksft.print_header()
+ksft.set_plan(len(combinations))
+
+logs = ""
+
+for combination in combinations:
+ append = ""
+ log = ""
+ for p in default_kparam:
+ append += f' --append={p}'
+ command = BOOT_CMD + append
+ test_params = ""
+ for i, key in enumerate(input_options.keys()):
+ param = f'{key}={combination[i]}'
+ test_params += f' {param}'
+ command += f" --append={param}"
+ command += f" -- {TEST}"
+ test_name = f"{bug} {test_params}"
+ pretty_print(f'# Testing {test_name}')
+ t = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+ t.wait()
+ output, _ = t.communicate()
+ if t.returncode == 0:
+ ksft.test_result_pass(test_name)
+ else:
+ ksft.test_result_fail(test_name)
+ output = output.decode()
+ log += f" {output}"
+ pretty_print(log)
+ logs += output + "\n"
+
+# Optionally use tappy to parse the output
+# apt install python3-tappy
+with open("logs.txt", "w") as f:
+ f.write(logs)
+
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_ret_alignment.py b/tools/testing/selftests/x86/bugs/its_ret_alignment.py
new file mode 100755
index 0000000000000..f40078d9f6ffc
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_ret_alignment.py
@@ -0,0 +1,139 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for indirect target selection (ITS) mitigation.
+#
+# Tests if the RETs are correctly patched by evaluating the
+# vmlinux .return_sites in /proc/kcore.
+#
+# Install dependencies
+# add-apt-repository ppa:michel-slm/kernel-utils
+# apt update
+# apt install -y python3-drgn python3-pyelftools python3-capstone
+#
+# Run on target machine
+# mkdir -p /usr/lib/debug/lib/modules/$(uname -r)
+# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux
+#
+# Usage: ./its_ret_alignment.py
+
+import os, sys, argparse
+from pathlib import Path
+
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+import common as c
+
+bug = "indirect_target_selection"
+mitigation = c.get_sysfs(bug)
+if not mitigation or "Aligned branch/return thunks" not in mitigation:
+ ksft.test_result_skip("Skipping its_ret_alignment.py: Aligned branch/return thunks not enabled")
+ ksft.finished()
+
+c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_ret_alignment.py")
+
+from elftools.elf.elffile import ELFFile
+from drgn.helpers.common.memory import identify_address
+
+cap = c.init_capstone()
+
+if len(os.sys.argv) > 1:
+ arg_vmlinux = os.sys.argv[1]
+ if not os.path.exists(arg_vmlinux):
+ ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at user-supplied path: {arg_vmlinux}")
+ ksft.exit_fail()
+ os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True)
+ os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux')
+
+vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux"
+if not os.path.exists(vmlinux):
+ ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at {vmlinux}")
+ ksft.exit_fail()
+
+ksft.print_msg(f"Using vmlinux: {vmlinux}")
+
+rethunks_start_vmlinux, rethunks_sec_offset, size = c.get_section_info(vmlinux, '.return_sites')
+ksft.print_msg(f"vmlinux: Section .return_sites (0x{rethunks_start_vmlinux:x}) found at 0x{rethunks_sec_offset:x} with size 0x{size:x}")
+
+sites_offset = c.get_patch_sites(vmlinux, rethunks_sec_offset, size)
+total_rethunk_tests = len(sites_offset)
+ksft.print_msg(f"Found {total_rethunk_tests} rethunk sites")
+
+prog = c.get_runtime_kernel()
+rethunks_start_kcore = prog.symbol('__return_sites').address
+ksft.print_msg(f'kcore: __rethunk_sites: 0x{rethunks_start_kcore:x}')
+
+its_return_thunk = prog.symbol('its_return_thunk').address
+ksft.print_msg(f'kcore: its_return_thunk: 0x{its_return_thunk:x}')
+
+tests_passed = 0
+tests_failed = 0
+tests_unknown = 0
+tests_skipped = 0
+
+with open(vmlinux, 'rb') as f:
+ elffile = ELFFile(f)
+ text_section = elffile.get_section_by_name('.text')
+
+ for i in range(len(sites_offset)):
+ site = rethunks_start_kcore + sites_offset[i]
+ vmlinux_site = rethunks_start_vmlinux + sites_offset[i]
+ try:
+ passed = unknown = failed = skipped = False
+
+ symbol = identify_address(prog, site)
+ vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site)
+ kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0]
+
+ insn_end = site + kcore_insn.size - 1
+
+ safe_site = insn_end & 0x20
+ site_status = "" if safe_site else "(unsafe)"
+
+ ksft.print_msg(f"\nSite {i}: {symbol} <0x{site:x}> {site_status}")
+ ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}")
+ ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}")
+
+ if safe_site:
+ tests_passed += 1
+ passed = True
+ ksft.print_msg(f"\tPASSED: At safe address")
+ continue
+
+ if "jmp" in kcore_insn.mnemonic:
+ passed = True
+ elif "ret" not in kcore_insn.mnemonic:
+ skipped = True
+
+ if passed:
+ ksft.print_msg(f"\tPASSED: Found {kcore_insn.mnemonic} {kcore_insn.op_str}")
+ tests_passed += 1
+ elif skipped:
+ ksft.print_msg(f"\tSKIPPED: Found '{kcore_insn.mnemonic}'")
+ tests_skipped += 1
+ elif unknown:
+ ksft.print_msg(f"UNKNOWN: An unknown instruction: {kcore_insn}")
+ tests_unknown += 1
+ else:
+ ksft.print_msg(f'\t************* FAILED *************')
+ ksft.print_msg(f"\tFound {kcore_insn.mnemonic} {kcore_insn.op_str}")
+ ksft.print_msg(f'\t**********************************')
+ tests_failed += 1
+ except Exception as e:
+ ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}")
+ tests_unknown += 1
+
+ksft.print_msg(f"\n\nSummary:")
+ksft.print_msg(f"PASSED: \t{tests_passed} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"FAILED: \t{tests_failed} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"SKIPPED: \t{tests_skipped} \t/ {total_rethunk_tests}")
+ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_rethunk_tests}")
+
+if tests_failed == 0:
+ ksft.test_result_pass("All ITS return thunk sites passed.")
+else:
+ ksft.test_result_fail(f"{tests_failed} failed sites need ITS return thunks.")
+ksft.finished()
diff --git a/tools/testing/selftests/x86/bugs/its_sysfs.py b/tools/testing/selftests/x86/bugs/its_sysfs.py
new file mode 100755
index 0000000000000..7bca81f2f6065
--- /dev/null
+++ b/tools/testing/selftests/x86/bugs/its_sysfs.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2025 Intel Corporation
+#
+# Test for Indirect Target Selection(ITS) mitigation sysfs status.
+
+import sys, os, re
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.insert(0, this_dir + '/../../kselftest')
+import ksft
+
+from common import *
+
+bug = "indirect_target_selection"
+mitigation = get_sysfs(bug)
+
+ITS_MITIGATION_ALIGNED_THUNKS = "Mitigation: Aligned branch/return thunks"
+ITS_MITIGATION_RETPOLINE_STUFF = "Mitigation: Retpolines, Stuffing RSB"
+ITS_MITIGATION_VMEXIT_ONLY = "Mitigation: Vulnerable, KVM: Not affected"
+ITS_MITIGATION_VULNERABLE = "Vulnerable"
+
+def check_mitigation():
+ if mitigation == ITS_MITIGATION_ALIGNED_THUNKS:
+ if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"):
+ bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_RETPOLINE_STUFF)
+ return
+ if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'):
+ bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_VMEXIT_ONLY)
+ return
+ bug_check_pass(bug, ITS_MITIGATION_ALIGNED_THUNKS)
+ return
+
+ if mitigation == ITS_MITIGATION_RETPOLINE_STUFF:
+ if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"):
+ bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF)
+ return
+ if sysfs_has('retbleed', 'Stuffing'):
+ bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF)
+ return
+ bug_check_fail(bug, ITS_MITIGATION_RETPOLINE_STUFF, ITS_MITIGATION_ALIGNED_THUNKS)
+
+ if mitigation == ITS_MITIGATION_VMEXIT_ONLY:
+ if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'):
+ bug_check_pass(bug, ITS_MITIGATION_VMEXIT_ONLY)
+ return
+ bug_check_fail(bug, ITS_MITIGATION_VMEXIT_ONLY, ITS_MITIGATION_ALIGNED_THUNKS)
+
+ if mitigation == ITS_MITIGATION_VULNERABLE:
+ if sysfs_has("spectre_v2", "Vulnerable"):
+ bug_check_pass(bug, ITS_MITIGATION_VULNERABLE)
+ else:
+ bug_check_fail(bug, "Mitigation", ITS_MITIGATION_VULNERABLE)
+
+ bug_status_unknown(bug, mitigation)
+ return
+
+ksft.print_header()
+ksft.set_plan(1)
+ksft.print_msg(f'{bug}: {mitigation} ...')
+
+if not basic_checks_sufficient(bug, mitigation):
+ check_mitigation()
+
+ksft.finished()
diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 66dbb362385f3..0f97fb0d19e19 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -150,7 +150,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
{
if (kmalloc_verbose)
- pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
+ pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
pthread_mutex_lock(&cachep->lock);
for (int i = 0; i < size; i++)
@@ -168,7 +168,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
size_t i;
if (kmalloc_verbose)
- pr_debug("Bulk alloc %lu\n", size);
+ pr_debug("Bulk alloc %zu\n", size);
pthread_mutex_lock(&cachep->lock);
if (cachep->nr_objs >= size) {
diff --git a/tools/testing/shared/linux/cleanup.h b/tools/testing/shared/linux/cleanup.h
new file mode 100644
index 0000000000000..ea3081426ee95
--- /dev/null
+++ b/tools/testing/shared/linux/cleanup.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../../../../include/linux/cleanup.h"
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index d0f6d253ac72d..613551132a966 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -1264,21 +1264,25 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type)
send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
control_expectln("RECEIVED");
- ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
- if (ret < 0) {
- if (errno == EOPNOTSUPP) {
- fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
- } else {
+ /* SIOCOUTQ isn't guaranteed to instantly track sent data. Even though
+ * the "RECEIVED" message means that the other side has received the
+ * data, there can be a delay in our kernel before updating the "unsent
+ * bytes" counter. Repeat SIOCOUTQ until it returns 0.
+ */
+ timeout_begin(TIMEOUT);
+ do {
+ ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+ if (ret < 0) {
+ if (errno == EOPNOTSUPP) {
+ fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+ break;
+ }
perror("ioctl");
exit(EXIT_FAILURE);
}
- } else if (ret == 0 && sock_bytes_unsent != 0) {
- fprintf(stderr,
- "Unexpected 'SIOCOUTQ' value, expected 0, got %i\n",
- sock_bytes_unsent);
- exit(EXIT_FAILURE);
- }
-
+ timeout_check("SIOCOUTQ");
+ } while (sock_bytes_unsent != 0);
+ timeout_end();
close(fd);
}