diff options
Diffstat (limited to 'tools')
61 files changed, 2277 insertions, 219 deletions
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index d8201c4b1520..6750fdb42564 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -2384,6 +2384,17 @@ def print_kernel_family_struct_src(family, cw): if not kernel_can_gen_family_struct(family): return + if 'sock-priv' in family.kernel_family: + # Generate "trampolines" to make CFI happy + cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_init", + [f"{family.c_name}_nl_sock_priv_init(priv);"], + ["void *priv"]) + cw.nl() + cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_destroy", + [f"{family.c_name}_nl_sock_priv_destroy(priv);"], + ["void *priv"]) + cw.nl() + cw.block_start(f"struct genl_family {family.ident_name}_nl_family __ro_after_init =") cw.p('.name\t\t= ' + family.fam_key + ',') cw.p('.version\t= ' + family.ver_key + ',') @@ -2401,9 +2412,8 @@ def print_kernel_family_struct_src(family, cw): cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),') if 'sock-priv' in family.kernel_family: cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),') - # Force cast here, actual helpers take pointer to the real type. - cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,') - cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,') + cw.p(f'.sock_priv_init\t= __{family.c_name}_nl_sock_priv_init,') + cw.p(f'.sock_priv_destroy = __{family.c_name}_nl_sock_priv_destroy,') cw.block_end(';') diff --git a/tools/perf/Documentation/perf-arm-spe.txt b/tools/perf/Documentation/perf-arm-spe.txt index de2b0b479249..37afade4f1b2 100644 --- a/tools/perf/Documentation/perf-arm-spe.txt +++ b/tools/perf/Documentation/perf-arm-spe.txt @@ -150,6 +150,7 @@ arm_spe/load_filter=1,min_latency=10/' pct_enable=1 - collect physical timestamp instead of virtual timestamp (PMSCR.PCT) - requires privilege store_filter=1 - collect stores only (PMSFCR.ST) ts_enable=1 - enable timestamping with value of generic timer (PMSCR.TS) + discard=1 - enable SPE PMU events but don't collect sample data - see 'Discard mode' (PMBLIMITR.FM = DISCARD) +++*+++ Latency is the total latency from the point at which sampling started on that instruction, rather than only the execution latency. @@ -220,6 +221,31 @@ Common errors Increase sampling interval (see above) +PMU events +~~~~~~~~~~ + +SPE has events that can be counted on core PMUs. These are prefixed with +SAMPLE_, for example SAMPLE_POP, SAMPLE_FEED, SAMPLE_COLLISION and +SAMPLE_FEED_BR. + +These events will only count when an SPE event is running on the same core that +the PMU event is opened on, otherwise they read as 0. There are various ways to +ensure that the PMU event and SPE event are scheduled together depending on the +way the event is opened. For example opening both events as per-process events +on the same process, although it's not guaranteed that the PMU event is enabled +first when context switching. For that reason it may be better to open the PMU +event as a systemwide event and then open SPE on the process of interest. + +Discard mode +~~~~~~~~~~~~ + +SPE related (SAMPLE_* etc) core PMU events can be used without the overhead of +collecting sample data if discard mode is supported (optional from Armv8.6). +First run a system wide SPE session (or on the core of interest) using options +to minimize output. Then run perf stat: + + perf record -e arm_spe/discard/ -a -N -B --no-bpf-event -o - > /dev/null & + perf stat -e SAMPLE_FEED_LD SEE ALSO -------- diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 2f36b7b6418d..625f5b046776 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; -bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym; -void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym; -void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym; +bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak; +void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; u32 scx_bpf_reenqueue_local(void) __ksym; diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 21deea320bd7..e938156ed0a0 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -97,7 +97,7 @@ restart: SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); CPU_ZERO(cpuset); CPU_SET(skel->rodata->central_cpu, cpuset); - SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), "Failed to affinitize to central CPU %d (max %d)", skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); CPU_FREE(cpuset); diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 0029ed9c5c9a..35f521e5f41c 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -46,6 +46,12 @@ static void atomics_sigill(void) asm volatile(".inst 0xb82003ff" : : : ); } +static void cmpbr_sigill(void) +{ + /* Not implemented, too complicated and unreliable anyway */ +} + + static void crc32_sigill(void) { /* CRC32W W0, W0, W1 */ @@ -82,6 +88,18 @@ static void f8fma_sigill(void) asm volatile(".inst 0xec0fc00"); } +static void f8mm4_sigill(void) +{ + /* FMMLA V0.4SH, V0.16B, V0.16B */ + asm volatile(".inst 0x6e00ec00"); +} + +static void f8mm8_sigill(void) +{ + /* FMMLA V0.4S, V0.16B, V0.16B */ + asm volatile(".inst 0x6e80ec00"); +} + static void faminmax_sigill(void) { /* FAMIN V0.4H, V0.4H, V0.4H */ @@ -98,6 +116,12 @@ static void fpmr_sigill(void) asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0"); } +static void fprcvt_sigill(void) +{ + /* FCVTAS S0, H0 */ + asm volatile(".inst 0x1efa0000"); +} + static void gcs_sigill(void) { unsigned long *gcspr; @@ -226,6 +250,42 @@ static void sme2p1_sigill(void) asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); } +static void sme2p2_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* UXTB Z0.D, P0/Z, Z0.D */ + asm volatile(".inst 0x4c1a000" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void sme_aes_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* AESD z0.b, z0.b, z0.b */ + asm volatile(".inst 0x4522e400" : : : "z0"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void sme_sbitperm_sigill(void) +{ + /* SMSTART SM */ + asm volatile("msr S0_3_C4_C3_3, xzr" : : : ); + + /* BDEP Z0.B, Z0.B, Z0.B */ + asm volatile(".inst 0x4500b400" : : : "z0"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + static void smei16i32_sigill(void) { /* SMSTART */ @@ -339,8 +399,44 @@ static void smesf8fma_sigill(void) /* SMSTART */ asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); - /* FMLALB V0.8H, V0.16B, V0.16B */ - asm volatile(".inst 0xec0fc00"); + /* FMLALB Z0.8H, Z0.B, Z0.B */ + asm volatile(".inst 0x64205000"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesfexpa_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FEXPA Z0.D, Z0.D */ + asm volatile(".inst 0x04e0b800"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesmop4_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* SMOP4A ZA0.S, Z0.B, { Z0.B - Z1.B } */ + asm volatile(".inst 0x80108000"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smestmop_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* STMOPA ZA0.S, { Z0.H - Z1.H }, Z0.H, Z20[0] */ + asm volatile(".inst 0x80408008"); /* SMSTOP */ asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); @@ -364,18 +460,42 @@ static void sve2p1_sigill(void) asm volatile(".inst 0x65000000" : : : "z0"); } +static void sve2p2_sigill(void) +{ + /* NOT Z0.D, P0/Z, Z0.D */ + asm volatile(".inst 0x4cea000" : : : "z0"); +} + static void sveaes_sigill(void) { /* AESD z0.b, z0.b, z0.b */ asm volatile(".inst 0x4522e400" : : : "z0"); } +static void sveaes2_sigill(void) +{ + /* AESD {Z0.B - Z1.B }, { Z0.B - Z1.B }, Z0.Q */ + asm volatile(".inst 0x4522ec00" : : : "z0"); +} + static void sveb16b16_sigill(void) { /* BFADD Z0.H, Z0.H, Z0.H */ asm volatile(".inst 0x65000000" : : : ); } +static void svebfscale_sigill(void) +{ + /* BFSCALE Z0.H, P0/M, Z0.H, Z0.H */ + asm volatile(".inst 0x65098000" : : : "z0"); +} + +static void svef16mm_sigill(void) +{ + /* FMMLA Z0.S, Z0.H, Z0.H */ + asm volatile(".inst 0x6420e400"); +} + static void svepmull_sigill(void) { /* PMULLB Z0.Q, Z0.D, Z0.D */ @@ -394,6 +514,12 @@ static void svesha3_sigill(void) asm volatile(".inst 0x4203800" : : : "z0"); } +static void sveeltperm_sigill(void) +{ + /* COMPACT Z0.B, P0, Z0.B */ + asm volatile(".inst 0x5218000" : : : "x0"); +} + static void svesm4_sigill(void) { /* SM4E Z0.S, Z0.S, Z0.S */ @@ -470,6 +596,13 @@ static const struct hwcap_data { .sigill_fn = aes_sigill, }, { + .name = "CMPBR", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_CMPBR, + .cpuinfo = "cmpbr", + .sigill_fn = cmpbr_sigill, + }, + { .name = "CRC32", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_CRC32, @@ -524,6 +657,20 @@ static const struct hwcap_data { .sigill_fn = f8fma_sigill, }, { + .name = "F8MM8", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_F8MM8, + .cpuinfo = "f8mm8", + .sigill_fn = f8mm8_sigill, + }, + { + .name = "F8MM4", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_F8MM4, + .cpuinfo = "f8mm4", + .sigill_fn = f8mm4_sigill, + }, + { .name = "FAMINMAX", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_FAMINMAX, @@ -546,6 +693,13 @@ static const struct hwcap_data { .sigill_reliable = true, }, { + .name = "FPRCVT", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_FPRCVT, + .cpuinfo = "fprcvt", + .sigill_fn = fprcvt_sigill, + }, + { .name = "GCS", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_GCS, @@ -692,6 +846,20 @@ static const struct hwcap_data { .sigill_fn = sme2p1_sigill, }, { + .name = "SME 2.2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME2P2, + .cpuinfo = "sme2p2", + .sigill_fn = sme2p2_sigill, + }, + { + .name = "SME AES", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_AES, + .cpuinfo = "smeaes", + .sigill_fn = sme_aes_sigill, + }, + { .name = "SME I16I32", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SME_I16I32, @@ -741,6 +909,13 @@ static const struct hwcap_data { .sigill_fn = smelutv2_sigill, }, { + .name = "SME SBITPERM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SBITPERM, + .cpuinfo = "smesbitperm", + .sigill_fn = sme_sbitperm_sigill, + }, + { .name = "SME SF8FMA", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SME_SF8FMA, @@ -762,6 +937,27 @@ static const struct hwcap_data { .sigill_fn = smesf8dp4_sigill, }, { + .name = "SME SFEXPA", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SFEXPA, + .cpuinfo = "smesfexpa", + .sigill_fn = smesfexpa_sigill, + }, + { + .name = "SME SMOP4", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_SMOP4, + .cpuinfo = "smesmop4", + .sigill_fn = smesmop4_sigill, + }, + { + .name = "SME STMOP", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SME_STMOP, + .cpuinfo = "smestmop", + .sigill_fn = smestmop_sigill, + }, + { .name = "SVE", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_SVE, @@ -784,6 +980,13 @@ static const struct hwcap_data { .sigill_fn = sve2p1_sigill, }, { + .name = "SVE 2.2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE2P2, + .cpuinfo = "sve2p2", + .sigill_fn = sve2p2_sigill, + }, + { .name = "SVE AES", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SVEAES, @@ -791,6 +994,34 @@ static const struct hwcap_data { .sigill_fn = sveaes_sigill, }, { + .name = "SVE AES2", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_AES2, + .cpuinfo = "sveaes2", + .sigill_fn = sveaes2_sigill, + }, + { + .name = "SVE BFSCALE", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_BFSCALE, + .cpuinfo = "svebfscale", + .sigill_fn = svebfscale_sigill, + }, + { + .name = "SVE ELTPERM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_ELTPERM, + .cpuinfo = "sveeltperm", + .sigill_fn = sveeltperm_sigill, + }, + { + .name = "SVE F16MM", + .at_hwcap = AT_HWCAP, + .hwcap_bit = HWCAP_SVE_F16MM, + .cpuinfo = "svef16mm", + .sigill_fn = svef16mm_sigill, + }, + { .name = "SVE2 B16B16", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_SVE_B16B16, diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 03c1bdaed2c3..400a696a0d21 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -86,15 +86,15 @@ echo "" > test/cpuset.cpus # # If isolated CPUs have been reserved at boot time (as shown in -# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7 +# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8 # that will be used by this script for testing purpose. If not, some of -# the tests may fail incorrectly. These isolated CPUs will also be removed -# before being compared with the expected results. +# the tests may fail incorrectly. These pre-isolated CPUs should stay in +# an isolated state throughout the testing process for now. # BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated) if [[ -n "$BOOT_ISOLCPUS" ]] then - [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] && + [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] && skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested" echo "Pre-isolated CPUs: $BOOT_ISOLCPUS" fi @@ -684,14 +684,18 @@ check_isolcpus() fi # + # Appending pre-isolated CPUs + # Even though CPU #8 isn't used for testing, it can't be pre-isolated + # to make appending those CPUs easier. + # + [[ -n "$BOOT_ISOLCPUS" ]] && { + EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS} + EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS} + } + + # # Check cpuset.cpus.isolated cpumask # - if [[ -z "$BOOT_ISOLCPUS" ]] - then - ISOLCPUS=$(cat $ISCPUS) - else - ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") - fi [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { # Take a 50ms pause and try again pause 0.05 @@ -731,8 +735,6 @@ check_isolcpus() fi done [[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU - [[ -n "BOOT_ISOLCPUS" ]] && - ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") [[ "$EXPECT_VAL" = "$ISOLCPUS" ]] } @@ -836,8 +838,11 @@ run_state_test() # if available [[ -n "$ICPUS" ]] && { check_isolcpus $ICPUS - [[ $? -ne 0 ]] && test_fail $I "isolated CPU" \ - "Expect $ICPUS, get $ISOLCPUS instead" + [[ $? -ne 0 ]] && { + [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS} + test_fail $I "isolated CPU" \ + "Expect $ICPUS, get $ISOLCPUS instead" + } } reset_cgroup_states # diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile new file mode 100644 index 000000000000..ed210037b29d --- /dev/null +++ b/tools/testing/selftests/coredump/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +CFLAGS = $(KHDR_INCLUDES) + +TEST_GEN_PROGS := stackdump_test +TEST_FILES := stackdump + +include ../lib.mk diff --git a/tools/testing/selftests/coredump/README.rst b/tools/testing/selftests/coredump/README.rst new file mode 100644 index 000000000000..164a7aa181c8 --- /dev/null +++ b/tools/testing/selftests/coredump/README.rst @@ -0,0 +1,50 @@ +coredump selftest +================= + +Background context +------------------ + +`coredump` is a feature which dumps a process's memory space when the process terminates +unexpectedly (e.g. due to segmentation fault), which can be useful for debugging. By default, +`coredump` dumps the memory to the file named `core`, but this behavior can be changed by writing a +different file name to `/proc/sys/kernel/core_pattern`. Furthermore, `coredump` can be piped to a +user-space program by writing the pipe symbol (`|`) followed by the command to be executed to +`/proc/sys/kernel/core_pattern`. For the full description, see `man 5 core`. + +The piped user program may be interested in reading the stack pointers of the crashed process. The +crashed process's stack pointers can be read from `procfs`: it is the `kstkesp` field in +`/proc/$PID/stat`. See `man 5 proc` for all the details. + +The problem +----------- +While a thread is active, the stack pointer is unsafe to read and therefore the `kstkesp` field +reads zero. But when the thread is dead (e.g. during a coredump), this field should have valid +value. + +However, this was broken in the past and `kstkesp` was zero even during coredump: + +* commit 0a1eb2d474ed ("fs/proc: Stop reporting eip and esp in /proc/PID/stat") changed kstkesp to + always be zero + +* commit fd7d56270b52 ("fs/proc: Report eip/esp in /prod/PID/stat for coredumping") fixed it for the + coredumping thread. However, other threads in a coredumping process still had the problem. + +* commit cb8f381f1613 ("fs/proc/array.c: allow reporting eip/esp for all coredumping threads") fixed + for all threads in a coredumping process. + +* commit 92307383082d ("coredump: Don't perform any cleanups before dumping core") broke it again + for the other threads in a coredumping process. + +The problem has been fixed now, but considering the history, it may appear again in the future. + +The goal of this test +--------------------- +This test detects problem with reading `kstkesp` during coredump by doing the following: + +#. Tell the kernel to execute the "stackdump" script when a coredump happens. This script + reads the stack pointers of all threads of crashed processes. + +#. Spawn a child process who creates some threads and then crashes. + +#. Read the output from the "stackdump" script, and make sure all stack pointer values are + non-zero. diff --git a/tools/testing/selftests/coredump/stackdump b/tools/testing/selftests/coredump/stackdump new file mode 100755 index 000000000000..96714ce42d12 --- /dev/null +++ b/tools/testing/selftests/coredump/stackdump @@ -0,0 +1,14 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +CRASH_PROGRAM_ID=$1 +STACKDUMP_FILE=$2 + +TMP=$(mktemp) + +for t in /proc/$CRASH_PROGRAM_ID/task/*; do + tid=$(basename $t) + cat /proc/$tid/stat | awk '{print $29}' >> $TMP +done + +mv $TMP $STACKDUMP_FILE diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c new file mode 100644 index 000000000000..137b2364a082 --- /dev/null +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <fcntl.h> +#include <libgen.h> +#include <linux/limits.h> +#include <pthread.h> +#include <string.h> +#include <sys/resource.h> +#include <unistd.h> + +#include "../kselftest_harness.h" + +#define STACKDUMP_FILE "stack_values" +#define STACKDUMP_SCRIPT "stackdump" +#define NUM_THREAD_SPAWN 128 + +static void *do_nothing(void *) +{ + while (1) + pause(); +} + +static void crashing_child(void) +{ + pthread_t thread; + int i; + + for (i = 0; i < NUM_THREAD_SPAWN; ++i) + pthread_create(&thread, NULL, do_nothing, NULL); + + /* crash on purpose */ + i = *(int *)NULL; +} + +FIXTURE(coredump) +{ + char original_core_pattern[256]; +}; + +FIXTURE_SETUP(coredump) +{ + char buf[PATH_MAX]; + FILE *file; + char *dir; + int ret; + + file = fopen("/proc/sys/kernel/core_pattern", "r"); + ASSERT_NE(NULL, file); + + ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file); + ASSERT_TRUE(ret || feof(file)); + ASSERT_LT(ret, sizeof(self->original_core_pattern)); + + self->original_core_pattern[ret] = '\0'; + + ret = fclose(file); + ASSERT_EQ(0, ret); +} + +FIXTURE_TEARDOWN(coredump) +{ + const char *reason; + FILE *file; + int ret; + + unlink(STACKDUMP_FILE); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + if (!file) { + reason = "Unable to open core_pattern"; + goto fail; + } + + ret = fprintf(file, "%s", self->original_core_pattern); + if (ret < 0) { + reason = "Unable to write to core_pattern"; + goto fail; + } + + ret = fclose(file); + if (ret) { + reason = "Unable to close core_pattern"; + goto fail; + } + + return; +fail: + /* This should never happen */ + fprintf(stderr, "Failed to cleanup stackdump test: %s\n", reason); +} + +TEST_F(coredump, stackdump) +{ + struct sigaction action = {}; + unsigned long long stack; + char *test_dir, *line; + size_t line_length; + char buf[PATH_MAX]; + int ret, i; + FILE *file; + pid_t pid; + + /* + * Step 1: Setup core_pattern so that the stackdump script is executed when the child + * process crashes + */ + ret = readlink("/proc/self/exe", buf, sizeof(buf)); + ASSERT_NE(-1, ret); + ASSERT_LT(ret, sizeof(buf)); + buf[ret] = '\0'; + + test_dir = dirname(buf); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + ASSERT_NE(NULL, file); + + ret = fprintf(file, "|%1$s/%2$s %%P %1$s/%3$s", test_dir, STACKDUMP_SCRIPT, STACKDUMP_FILE); + ASSERT_LT(0, ret); + + ret = fclose(file); + ASSERT_EQ(0, ret); + + /* Step 2: Create a process who spawns some threads then crashes */ + pid = fork(); + ASSERT_TRUE(pid >= 0); + if (pid == 0) + crashing_child(); + + /* + * Step 3: Wait for the stackdump script to write the stack pointers to the stackdump file + */ + for (i = 0; i < 10; ++i) { + file = fopen(STACKDUMP_FILE, "r"); + if (file) + break; + sleep(1); + } + ASSERT_NE(file, NULL); + + /* Step 4: Make sure all stack pointer values are non-zero */ + for (i = 0; -1 != getline(&line, &line_length, file); ++i) { + stack = strtoull(line, NULL, 10); + ASSERT_NE(stack, 0); + } + + ASSERT_EQ(i, 1 + NUM_THREAD_SPAWN); + + fclose(file); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh index fd13c8cfb7a8..b411fe66510f 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh @@ -58,9 +58,12 @@ for root in mq mqprio; do ethtool -L $NDEV combined 4 n_child_assert 4 "One real queue, rest default" - # Graft some - tcq replace parent 100:1 handle 204: - n_child_assert 3 "Grafted" + # Remove real one + tcq del parent 100:4 handle 204: + + # Replace default with pfifo + tcq replace parent 100:1 handle 205: pfifo limit 1000 + n_child_assert 3 "Deleting real one, replacing default one with pfifo" ethtool -L $NDEV combined 1 n_child_assert 1 "Grafted, one" diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 9c5473abbd78..38303da957ee 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -1,10 +1,12 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, KsftSkipEx -from lib.py import EthtoolFamily, NetdevFamily +from lib.py import ksft_disruptive, ksft_exit, ksft_run +from lib.py import ksft_eq, ksft_raises, KsftSkipEx +from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import NetDrvEnv -from lib.py import cmd +from lib.py import cmd, defer, ip +import errno import glob @@ -59,9 +61,27 @@ def addremove_queues(cfg, nl) -> None: ksft_eq(queues, expected) +@ksft_disruptive +def check_down(cfg, nl) -> None: + # Check the NAPI IDs before interface goes down and hides them + napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True) + + ip(f"link set dev {cfg.dev['ifname']} down") + defer(ip, f"link set dev {cfg.dev['ifname']} up") + + with ksft_raises(NlError) as cm: + nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + if napis: + with ksft_raises(NlError) as cm: + nl.napi_get({'id': napis[0]['id']}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + def main() -> None: with NetDrvEnv(__file__, queue_count=100) as cfg: - ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily())) + ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c index 071e03532cba..8fb7395fd35b 100644 --- a/tools/testing/selftests/exec/execveat.c +++ b/tools/testing/selftests/exec/execveat.c @@ -23,9 +23,11 @@ #include "../kselftest.h" -#define TESTS_EXPECTED 51 +#define TESTS_EXPECTED 54 #define TEST_NAME_LEN (PATH_MAX * 4) +#define CHECK_COMM "CHECK_COMM" + static char longpath[2 * PATH_MAX] = ""; static char *envp[] = { "IN_TEST=yes", NULL, NULL }; static char *argv[] = { "execveat", "99", NULL }; @@ -237,6 +239,29 @@ static int check_execveat_pathmax(int root_dfd, const char *src, int is_script) return fail; } +static int check_execveat_comm(int fd, char *argv0, char *expected) +{ + char buf[128], *old_env, *old_argv0; + int ret; + + snprintf(buf, sizeof(buf), CHECK_COMM "=%s", expected); + + old_env = envp[1]; + envp[1] = buf; + + old_argv0 = argv[0]; + argv[0] = argv0; + + ksft_print_msg("Check execveat(AT_EMPTY_PATH)'s comm is %s\n", + expected); + ret = check_execveat_invoked_rc(fd, "", AT_EMPTY_PATH, 0, 0); + + envp[1] = old_env; + argv[0] = old_argv0; + + return ret; +} + static int run_tests(void) { int fail = 0; @@ -389,6 +414,14 @@ static int run_tests(void) fail += check_execveat_pathmax(root_dfd, "execveat", 0); fail += check_execveat_pathmax(root_dfd, "script", 1); + + /* /proc/pid/comm gives filename by default */ + fail += check_execveat_comm(fd, "sentinel", "execveat"); + /* /proc/pid/comm gives argv[0] when invoked via link */ + fail += check_execveat_comm(fd_symlink, "sentinel", "execveat"); + /* /proc/pid/comm gives filename if NULL is passed */ + fail += check_execveat_comm(fd, NULL, "execveat"); + return fail; } @@ -415,9 +448,13 @@ int main(int argc, char **argv) int ii; int rc; const char *verbose = getenv("VERBOSE"); + const char *check_comm = getenv(CHECK_COMM); - if (argc >= 2) { - /* If we are invoked with an argument, don't run tests. */ + if (argc >= 2 || check_comm) { + /* + * If we are invoked with an argument, or no arguments but a + * command to check, don't run tests. + */ const char *in_test = getenv("IN_TEST"); if (verbose) { @@ -426,6 +463,38 @@ int main(int argc, char **argv) ksft_print_msg("\t[%d]='%s\n'", ii, argv[ii]); } + /* If the tests wanted us to check the command, do so. */ + if (check_comm) { + /* TASK_COMM_LEN == 16 */ + char buf[32]; + int fd, ret; + + fd = open("/proc/self/comm", O_RDONLY); + if (fd < 0) { + ksft_perror("open() comm failed"); + exit(1); + } + + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) { + ksft_perror("read() comm failed"); + close(fd); + exit(1); + } + close(fd); + + // trim off the \n + buf[ret-1] = 0; + + if (strcmp(buf, check_comm)) { + ksft_print_msg("bad comm, got: %s expected: %s\n", + buf, check_comm); + exit(1); + } + + exit(0); + } + /* Check expected environment transferred. */ if (!in_test || strcmp(in_test, "yes") != 0) { ksft_print_msg("no IN_TEST=yes in env\n"); diff --git a/tools/testing/selftests/nsfs/.gitignore b/tools/testing/selftests/filesystems/nsfs/.gitignore index ed79ebdf286e..92a8249006d1 100644 --- a/tools/testing/selftests/nsfs/.gitignore +++ b/tools/testing/selftests/filesystems/nsfs/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only owner pidns +iterate_mntns diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/filesystems/nsfs/Makefile index dd9bd50b7b93..231aaa7dfd95 100644 --- a/tools/testing/selftests/nsfs/Makefile +++ b/tools/testing/selftests/filesystems/nsfs/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -TEST_GEN_PROGS := owner pidns +TEST_GEN_PROGS := owner pidns iterate_mntns CFLAGS := -Wall -Werror -include ../lib.mk +include ../../lib.mk diff --git a/tools/testing/selftests/nsfs/config b/tools/testing/selftests/filesystems/nsfs/config index 598d0a225fc9..598d0a225fc9 100644 --- a/tools/testing/selftests/nsfs/config +++ b/tools/testing/selftests/filesystems/nsfs/config diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c new file mode 100644 index 000000000000..457cf76f3c5f --- /dev/null +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + +#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 "../../kselftest_harness.h" + +#define MNT_NS_COUNT 11 +#define MNT_NS_LAST_INDEX 10 + +struct mnt_ns_info { + __u32 size; + __u32 nr_mounts; + __u64 mnt_ns_id; +}; + +#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */ + +/* Get information about namespace. */ +#define NS_MNT_GET_INFO _IOR(0xb7, 10, struct mnt_ns_info) +/* Get next namespace. */ +#define NS_MNT_GET_NEXT _IOR(0xb7, 11, struct mnt_ns_info) +/* Get previous namespace. */ +#define NS_MNT_GET_PREV _IOR(0xb7, 12, struct mnt_ns_info) + +FIXTURE(iterate_mount_namespaces) { + int fd_mnt_ns[MNT_NS_COUNT]; + __u64 mnt_ns_id[MNT_NS_COUNT]; +}; + +FIXTURE_SETUP(iterate_mount_namespaces) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) + self->fd_mnt_ns[i] = -EBADF; + + /* + * Creating a new user namespace let's us guarantee that we only see + * mount namespaces that we did actually create. + */ + ASSERT_EQ(unshare(CLONE_NEWUSER), 0); + + for (int i = 0; i < MNT_NS_COUNT; i++) { + struct mnt_ns_info info = {}; + + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + self->fd_mnt_ns[i] = open("/proc/self/ns/mnt", O_RDONLY | O_CLOEXEC); + ASSERT_GE(self->fd_mnt_ns[i], 0); + ASSERT_EQ(ioctl(self->fd_mnt_ns[i], NS_MNT_GET_INFO, &info), 0); + self->mnt_ns_id[i] = info.mnt_ns_id; + } +} + +FIXTURE_TEARDOWN(iterate_mount_namespaces) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) { + if (self->fd_mnt_ns[i] < 0) + continue; + ASSERT_EQ(close(self->fd_mnt_ns[i]), 0); + } +} + +TEST_F(iterate_mount_namespaces, iterate_all_forward) +{ + int fd_mnt_ns_cur, count = 0; + + fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC); + ASSERT_GE(fd_mnt_ns_cur, 0); + + for (;; count++) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_next; + + fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); + if (fd_mnt_ns_next < 0 && errno == ENOENT) + break; + ASSERT_GE(fd_mnt_ns_next, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_next; + } + ASSERT_EQ(count, MNT_NS_LAST_INDEX); +} + +TEST_F(iterate_mount_namespaces, iterate_all_backwards) +{ + int fd_mnt_ns_cur, count = 0; + + fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC); + ASSERT_GE(fd_mnt_ns_cur, 0); + + for (;; count++) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_prev; + + fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); + if (fd_mnt_ns_prev < 0 && errno == ENOENT) + break; + ASSERT_GE(fd_mnt_ns_prev, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_prev; + } + ASSERT_EQ(count, MNT_NS_LAST_INDEX); +} + +TEST_F(iterate_mount_namespaces, iterate_forward) +{ + int fd_mnt_ns_cur; + + ASSERT_EQ(setns(self->fd_mnt_ns[0], CLONE_NEWNS), 0); + + fd_mnt_ns_cur = self->fd_mnt_ns[0]; + for (int i = 1; i < MNT_NS_COUNT; i++) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_next; + + fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); + ASSERT_GE(fd_mnt_ns_next, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_next; + ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); + } +} + +TEST_F(iterate_mount_namespaces, iterate_backward) +{ + int fd_mnt_ns_cur; + + ASSERT_EQ(setns(self->fd_mnt_ns[MNT_NS_LAST_INDEX], CLONE_NEWNS), 0); + + fd_mnt_ns_cur = self->fd_mnt_ns[MNT_NS_LAST_INDEX]; + for (int i = MNT_NS_LAST_INDEX - 1; i >= 0; i--) { + struct mnt_ns_info info = {}; + int fd_mnt_ns_prev; + + fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); + ASSERT_GE(fd_mnt_ns_prev, 0); + ASSERT_EQ(close(fd_mnt_ns_cur), 0); + fd_mnt_ns_cur = fd_mnt_ns_prev; + ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/nsfs/owner.c b/tools/testing/selftests/filesystems/nsfs/owner.c index 96a976c74550..96a976c74550 100644 --- a/tools/testing/selftests/nsfs/owner.c +++ b/tools/testing/selftests/filesystems/nsfs/owner.c diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/filesystems/nsfs/pidns.c index e3c772c6a7c7..e3c772c6a7c7 100644 --- a/tools/testing/selftests/nsfs/pidns.c +++ b/tools/testing/selftests/filesystems/nsfs/pidns.c diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile index 3af3136e35a4..14ee91a41650 100644 --- a/tools/testing/selftests/filesystems/statmount/Makefile +++ b/tools/testing/selftests/filesystems/statmount/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) -TEST_GEN_PROGS := statmount_test statmount_test_ns +TEST_GEN_PROGS := statmount_test statmount_test_ns listmount_test include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/statmount/listmount_test.c b/tools/testing/selftests/filesystems/statmount/listmount_test.c new file mode 100644 index 000000000000..15f0834f7557 --- /dev/null +++ b/tools/testing/selftests/filesystems/statmount/listmount_test.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + +#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 "statmount.h" +#include "../../kselftest_harness.h" + +#ifndef LISTMOUNT_REVERSE +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ +#endif + +#define LISTMNT_BUFFER 10 + +/* Check that all mount ids are in increasing order. */ +TEST(listmount_forward) +{ + uint64_t list[LISTMNT_BUFFER], last_mnt_id = 0; + + for (;;) { + ssize_t nr_mounts; + + nr_mounts = listmount(LSMT_ROOT, 0, last_mnt_id, + list, LISTMNT_BUFFER, 0); + ASSERT_GE(nr_mounts, 0); + if (nr_mounts == 0) + break; + + for (size_t cur = 0; cur < nr_mounts; cur++) { + if (cur < nr_mounts - 1) + ASSERT_LT(list[cur], list[cur + 1]); + last_mnt_id = list[cur]; + } + } +} + +/* Check that all mount ids are in decreasing order. */ +TEST(listmount_backward) +{ + uint64_t list[LISTMNT_BUFFER], last_mnt_id = 0; + + for (;;) { + ssize_t nr_mounts; + + nr_mounts = listmount(LSMT_ROOT, 0, last_mnt_id, + list, LISTMNT_BUFFER, LISTMOUNT_REVERSE); + ASSERT_GE(nr_mounts, 0); + if (nr_mounts == 0) + break; + + for (size_t cur = 0; cur < nr_mounts; cur++) { + if (cur < nr_mounts - 1) + ASSERT_GT(list[cur], list[cur + 1]); + last_mnt_id = list[cur]; + } + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c index a79b7f18452d..3a97c160b5fe 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c @@ -152,7 +152,6 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0), REG_FTR_END, }; diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c index 0c112319dab1..135ee22856cf 100644 --- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c @@ -210,10 +210,13 @@ TEST_F(uc_kvm, uc_attr_mem_limit) struct kvm_device_attr attr = { .group = KVM_S390_VM_MEM_CTRL, .attr = KVM_S390_VM_MEM_LIMIT_SIZE, - .addr = (unsigned long)&limit, + .addr = (u64)&limit, }; int rc; + rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); EXPECT_EQ(0, rc); EXPECT_EQ(~0UL, limit); @@ -635,4 +638,171 @@ TEST_F(uc_kvm, uc_skey) uc_assert_diag44(self); } +static char uc_flic_b[PAGE_SIZE]; +static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 }; +static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 }; +static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 }; +static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 }; +static struct uc_flic_attr_test { + char *name; + struct kvm_device_attr a; + int hasrc; + int geterrno; + int seterrno; +} uc_flic_attr_tests[] = { + { + .name = "KVM_DEV_FLIC_GET_ALL_IRQS", + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_GET_ALL_IRQS, + .addr = (u64)&uc_flic_b, + .attr = PAGE_SIZE, + }, + }, + { + .name = "KVM_DEV_FLIC_ENQUEUE", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_ENQUEUE, }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IRQS", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_REGISTER", + .geterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_REGISTER, + .addr = (u64)&uc_flic_ioa, + }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_MODIFY", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_MODIFY, + .addr = (u64)&uc_flic_ioam, + .attr = sizeof(uc_flic_ioam), + }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IO_IRQ", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_CLEAR_IO_IRQ, + .attr = 32, + }, + }, + { + .name = "KVM_DEV_FLIC_AISM", + .geterrno = EINVAL, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM, + .addr = (u64)&uc_flic_asim, + }, + }, + { + .name = "KVM_DEV_FLIC_AIRQ_INJECT", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, }, + }, + { + .name = "KVM_DEV_FLIC_AISM_ALL", + .geterrno = ENOTSUP, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM_ALL, + .addr = (u64)&uc_flic_asima, + .attr = sizeof(uc_flic_asima), + }, + }, + { + .name = "KVM_DEV_FLIC_APF_ENABLE", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_ENABLE, }, + }, + { + .name = "KVM_DEV_FLIC_APF_DISABLE_WAIT", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, }, + }, +}; + +TEST_F(uc_kvm, uc_flic_attrs) +{ + struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC }; + struct kvm_device_attr attr; + u64 value; + int rc, i; + + rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd); + ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)", + strerror(errno), errno); + + for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) { + TH_LOG("test %s", uc_flic_attr_tests[i].name); + attr = (struct kvm_device_attr) { + .group = uc_flic_attr_tests[i].a.group, + .attr = uc_flic_attr_tests[i].a.attr, + .addr = uc_flic_attr_tests[i].a.addr, + }; + if (attr.addr == 0) + attr.addr = (u64)&value; + + rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc) + TH_LOG("expected dev attr missing %s", + uc_flic_attr_tests[i].name); + + rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc) + TH_LOG("get dev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].geterrno) + EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno) + TH_LOG("get dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + + rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc) + TH_LOG("set sev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].seterrno) + EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno) + TH_LOG("set dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + } + + close(cd.fd); +} + +TEST_F(uc_kvm, uc_set_gsi_routing) +{ + struct kvm_irq_routing *routing = kvm_gsi_routing_create(); + struct kvm_irq_routing_entry ue = { + .type = KVM_IRQ_ROUTING_S390_ADAPTER, + .gsi = 1, + .u.adapter = (struct kvm_irq_routing_s390_adapter) { + .ind_addr = 0, + }, + }; + int rc; + + routing->entries[0] = ue; + routing->nr = 1; + rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing); + ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno); + ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 0a0b55516028..c0c53451a16d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -282,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd) return p; } +static void *mfd_assert_mmap_read_shared(int fd) +{ + void *p; + + p = mmap(NULL, + mfd_def_size, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + static void *mfd_assert_mmap_private(int fd) { void *p; @@ -980,6 +998,30 @@ static void test_seal_future_write(void) close(fd); } +static void test_seal_write_map_read_shared(void) +{ + int fd; + void *p; + + printf("%s SEAL-WRITE-MAP-READ\n", memfd_str); + + fd = mfd_assert_new("kern_memfd_seal_write_map_read", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + p = mfd_assert_mmap_read_shared(fd); + + mfd_assert_read(fd); + mfd_assert_read_shared(fd); + mfd_fail_write(fd); + + munmap(p, mfd_def_size); + close(fd); +} + /* * Test SEAL_SHRINK * Test whether SEAL_SHRINK actually prevents shrinking @@ -1593,6 +1635,7 @@ int main(int argc, char **argv) test_seal_write(); test_seal_future_write(); + test_seal_write_map_read_shared(); test_seal_shrink(); test_seal_grow(); test_seal_resize(); diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 32c6ccc2a6be..1238e1c5aae1 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -758,7 +758,7 @@ static void do_run_with_base_page(test_fn fn, bool swapout) } /* Populate a base page. */ - memset(mem, 0, pagesize); + memset(mem, 1, pagesize); if (swapout) { madvise(mem, pagesize, MADV_PAGEOUT); @@ -824,12 +824,12 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) * Try to populate a THP. Touch the first sub-page and test if * we get the last sub-page populated automatically. */ - mem[0] = 0; + mem[0] = 1; if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { ksft_test_result_skip("Did not get a THP populated\n"); goto munmap; } - memset(mem, 0, thpsize); + memset(mem, 1, thpsize); size = thpsize; switch (thp_run) { @@ -1012,7 +1012,7 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) } /* Populate an huge page. */ - memset(mem, 0, hugetlbsize); + memset(mem, 1, hugetlbsize); /* * We need a total of two hugetlb pages to handle COW/unsharing diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index c35548767756..ecd34f364125 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes -REQUIRE_MZ=no source lib.sh diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 4209b9569039..414addef9a45 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -25,6 +25,8 @@ #include <sys/types.h> #include <sys/mman.h> +#include <arpa/inet.h> + #include <netdb.h> #include <netinet/in.h> @@ -1211,23 +1213,42 @@ static void parse_setsock_options(const char *name) exit(1); } -void xdisconnect(int fd, int addrlen) +void xdisconnect(int fd) { - struct sockaddr_storage empty; + socklen_t addrlen = sizeof(struct sockaddr_storage); + struct sockaddr_storage addr, empty; int msec_sleep = 10; - int queued = 1; - int i; + void *raw_addr; + int i, cmdlen; + char cmd[128]; + + /* get the local address and convert it to string */ + if (getsockname(fd, (struct sockaddr *)&addr, &addrlen) < 0) + xerror("getsockname"); + + if (addr.ss_family == AF_INET) + raw_addr = &(((struct sockaddr_in *)&addr)->sin_addr); + else if (addr.ss_family == AF_INET6) + raw_addr = &(((struct sockaddr_in6 *)&addr)->sin6_addr); + else + xerror("bad family"); + + strcpy(cmd, "ss -M | grep -q "); + cmdlen = strlen(cmd); + if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], + sizeof(cmd) - cmdlen)) + xerror("inet_ntop"); shutdown(fd, SHUT_WR); - /* while until the pending data is completely flushed, the later + /* + * wait until the pending data is completely flushed and all + * the MPTCP sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { - if (ioctl(fd, SIOCOUTQ, &queued) < 0) - xerror("can't query out socket queue: %d", errno); - - if (!queued) + /* closed socket are not listed by 'ss' */ + if (system(cmd) != 0) break; if (i > poll_timeout) @@ -1281,9 +1302,9 @@ again: return ret; if (cfg_truncate > 0) { - xdisconnect(fd, peer->ai_addrlen); + xdisconnect(fd); } else if (--cfg_repeat > 0) { - xdisconnect(fd, peer->ai_addrlen); + xdisconnect(fd); /* the socket could be unblocking at this point, we need the * connect to be blocking diff --git a/tools/testing/selftests/pid_namespace/.gitignore b/tools/testing/selftests/pid_namespace/.gitignore index 93ab9d7e5b7e..5118f0f3edf4 100644 --- a/tools/testing/selftests/pid_namespace/.gitignore +++ b/tools/testing/selftests/pid_namespace/.gitignore @@ -1 +1,2 @@ +pid_max regression_enomem diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index 9286a1d22cd3..b972f55d07ae 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g $(KHDR_INCLUDES) -TEST_GEN_PROGS = regression_enomem +TEST_GEN_PROGS = regression_enomem pid_max LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c new file mode 100644 index 000000000000..51c414faabb0 --- /dev/null +++ b/tools/testing/selftests/pid_namespace/pid_max.c @@ -0,0 +1,358 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#define _GNU_SOURCE +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/types.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/wait.h> + +#include "../kselftest_harness.h" +#include "../pidfd/pidfd.h" + +#define __STACK_SIZE (8 * 1024 * 1024) +static pid_t do_clone(int (*fn)(void *), void *arg, int flags) +{ + char *stack; + pid_t ret; + + stack = malloc(__STACK_SIZE); + if (!stack) + return -ENOMEM; + +#ifdef __ia64__ + ret = __clone2(fn, stack, __STACK_SIZE, flags | SIGCHLD, arg); +#else + ret = clone(fn, stack + __STACK_SIZE, flags | SIGCHLD, arg); +#endif + free(stack); + return ret; +} + +static int pid_max_cb(void *data) +{ + int fd, ret; + pid_t pid; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return -1; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return -1; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return -1; + } + + ret = write(fd, "500", sizeof("500") - 1); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return -1; + } + + for (int i = 0; i < 501; i++) { + pid = fork(); + if (pid == 0) + exit(EXIT_SUCCESS); + wait_for_pid(pid); + if (pid > 500) { + fprintf(stderr, "Managed to create pid number beyond limit\n"); + return -1; + } + } + + return 0; +} + +static int pid_max_nested_inner(void *data) +{ + int fret = -1; + pid_t pids[2]; + int fd, i, ret; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return fret; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return fret; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return fret; + } + + ret = write(fd, "500", sizeof("500") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return fret; + } + + pids[0] = fork(); + if (pids[0] < 0) { + fprintf(stderr, "Failed to create first new process\n"); + return fret; + } + + if (pids[0] == 0) + exit(EXIT_SUCCESS); + + pids[1] = fork(); + wait_for_pid(pids[0]); + if (pids[1] >= 0) { + if (pids[1] == 0) + exit(EXIT_SUCCESS); + wait_for_pid(pids[1]); + + fprintf(stderr, "Managed to create process even though ancestor pid namespace had a limit\n"); + return fret; + } + + /* Now make sure that we wrap pids at 400. */ + for (i = 0; i < 510; i++) { + pid_t pid; + + pid = fork(); + if (pid < 0) + return fret; + + if (pid == 0) + exit(EXIT_SUCCESS); + + wait_for_pid(pid); + if (pid >= 500) { + fprintf(stderr, "Managed to create process with pid %d beyond configured limit\n", pid); + return fret; + } + } + + return 0; +} + +static int pid_max_nested_outer(void *data) +{ + int fret = -1, nr_procs = 400; + pid_t pids[1000]; + int fd, i, ret; + pid_t pid; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return fret; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return fret; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return fret; + } + + ret = write(fd, "400", sizeof("400") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return fret; + } + + /* + * Create 397 processes. This leaves room for do_clone() (398) and + * one more 399. So creating another process needs to fail. + */ + for (nr_procs = 0; nr_procs < 396; nr_procs++) { + pid = fork(); + if (pid < 0) + goto reap; + + if (pid == 0) + exit(EXIT_SUCCESS); + + pids[nr_procs] = pid; + } + + pid = do_clone(pid_max_nested_inner, NULL, CLONE_NEWPID | CLONE_NEWNS); + if (pid < 0) { + fprintf(stderr, "%m - Failed to clone nested pidns\n"); + goto reap; + } + + if (wait_for_pid(pid)) { + fprintf(stderr, "%m - Nested pid_max failed\n"); + goto reap; + } + + fret = 0; + +reap: + for (int i = 0; i < nr_procs; i++) + wait_for_pid(pids[i]); + + return fret; +} + +static int pid_max_nested_limit_inner(void *data) +{ + int fret = -1, nr_procs = 400; + int fd, ret; + pid_t pid; + pid_t pids[1000]; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return fret; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return fret; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return fret; + } + + ret = write(fd, "500", sizeof("500") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return fret; + } + + for (nr_procs = 0; nr_procs < 500; nr_procs++) { + pid = fork(); + if (pid < 0) + break; + + if (pid == 0) + exit(EXIT_SUCCESS); + + pids[nr_procs] = pid; + } + + if (nr_procs >= 400) { + fprintf(stderr, "Managed to create processes beyond the configured outer limit\n"); + goto reap; + } + + fret = 0; + +reap: + for (int i = 0; i < nr_procs; i++) + wait_for_pid(pids[i]); + + return fret; +} + +static int pid_max_nested_limit_outer(void *data) +{ + int fd, ret; + pid_t pid; + + ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0); + if (ret) { + fprintf(stderr, "%m - Failed to make rootfs private mount\n"); + return -1; + } + + umount2("/proc", MNT_DETACH); + + ret = mount("proc", "/proc", "proc", 0, NULL); + if (ret) { + fprintf(stderr, "%m - Failed to mount proc\n"); + return -1; + } + + fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY); + if (fd < 0) { + fprintf(stderr, "%m - Failed to open pid_max\n"); + return -1; + } + + ret = write(fd, "400", sizeof("400") - 1); + close(fd); + if (ret < 0) { + fprintf(stderr, "%m - Failed to write pid_max\n"); + return -1; + } + + pid = do_clone(pid_max_nested_limit_inner, NULL, CLONE_NEWPID | CLONE_NEWNS); + if (pid < 0) { + fprintf(stderr, "%m - Failed to clone nested pidns\n"); + return -1; + } + + if (wait_for_pid(pid)) { + fprintf(stderr, "%m - Nested pid_max failed\n"); + return -1; + } + + return 0; +} + +TEST(pid_max_simple) +{ + pid_t pid; + + + pid = do_clone(pid_max_cb, NULL, CLONE_NEWPID | CLONE_NEWNS); + ASSERT_GT(pid, 0); + ASSERT_EQ(0, wait_for_pid(pid)); +} + +TEST(pid_max_nested_limit) +{ + pid_t pid; + + pid = do_clone(pid_max_nested_limit_outer, NULL, CLONE_NEWPID | CLONE_NEWNS); + ASSERT_GT(pid, 0); + ASSERT_EQ(0, wait_for_pid(pid)); +} + +TEST(pid_max_nested) +{ + pid_t pid; + + pid = do_clone(pid_max_nested_outer, NULL, CLONE_NEWPID | CLONE_NEWNS); + ASSERT_GT(pid, 0); + ASSERT_EQ(0, wait_for_pid(pid)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 973198a3ec3d..bf92481f925c 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -6,3 +6,5 @@ pidfd_wait pidfd_fdinfo_test pidfd_getfd_test pidfd_setns_test +pidfd_file_handle_test +pidfd_bind_mount diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index d731e3e76d5b..301343a11b62 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -2,7 +2,8 @@ CFLAGS += -g $(KHDR_INCLUDES) -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ - pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test + pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test \ + pidfd_file_handle_test pidfd_bind_mount include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 88d6830ee004..0b96ac4b8ce5 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -12,11 +12,11 @@ #include <stdlib.h> #include <string.h> #include <syscall.h> -#include <sys/mount.h> #include <sys/types.h> #include <sys/wait.h> #include "../kselftest.h" +#include "../clone3/clone3_selftests.h" #ifndef P_PIDFD #define P_PIDFD 3 @@ -68,6 +68,11 @@ #define PIDFD_SKIP 3 #define PIDFD_XFAIL 4 +static inline int sys_waitid(int which, pid_t pid, siginfo_t *info, int options) +{ + return syscall(__NR_waitid, which, pid, info, options, NULL); +} + static inline int wait_for_pid(pid_t pid) { int status, ret; @@ -114,4 +119,37 @@ static inline int sys_memfd_create(const char *name, unsigned int flags) return syscall(__NR_memfd_create, name, flags); } +static inline pid_t create_child(int *pidfd, unsigned flags) +{ + struct __clone_args args = { + .flags = CLONE_PIDFD | flags, + .exit_signal = SIGCHLD, + .pidfd = ptr_to_u64(pidfd), + }; + + return sys_clone3(&args, sizeof(struct __clone_args)); +} + +static inline ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = read(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static inline ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + #endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_bind_mount.c b/tools/testing/selftests/pidfd/pidfd_bind_mount.c new file mode 100644 index 000000000000..7822dd080258 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_bind_mount.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2024 Christian Brauner <brauner@kernel.org> + +#define _GNU_SOURCE +#include <fcntl.h> +#include <limits.h> +#include <sched.h> +#include <stdio.h> +#include <string.h> +#include <linux/fs.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <sys/mount.h> +#include <unistd.h> + +#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); +} + +FIXTURE(pidfd_bind_mount) { + char template[PATH_MAX]; + int fd_tmp; + int pidfd; + struct stat st1; + struct stat st2; + __u32 gen1; + __u32 gen2; + bool must_unmount; +}; + +FIXTURE_SETUP(pidfd_bind_mount) +{ + self->fd_tmp = -EBADF; + self->must_unmount = false; + ASSERT_EQ(unshare(CLONE_NEWNS), 0); + ASSERT_LE(snprintf(self->template, PATH_MAX, "%s", P_tmpdir "/pidfd_bind_mount_XXXXXX"), PATH_MAX); + self->fd_tmp = mkstemp(self->template); + ASSERT_GE(self->fd_tmp, 0); + self->pidfd = sys_pidfd_open(getpid(), 0); + ASSERT_GE(self->pidfd, 0); + ASSERT_GE(fstat(self->pidfd, &self->st1), 0); + ASSERT_EQ(ioctl(self->pidfd, FS_IOC_GETVERSION, &self->gen1), 0); +} + +FIXTURE_TEARDOWN(pidfd_bind_mount) +{ + ASSERT_EQ(close(self->fd_tmp), 0); + if (self->must_unmount) + ASSERT_EQ(umount2(self->template, 0), 0); + ASSERT_EQ(unlink(self->template), 0); +} + +/* + * Test that a detached mount can be created for a pidfd and then + * attached to the filesystem hierarchy. + */ +TEST_F(pidfd_bind_mount, bind_mount) +{ + int fd_tree; + + fd_tree = sys_open_tree(self->pidfd, "", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH); + ASSERT_GE(fd_tree, 0); + + ASSERT_EQ(move_mount(fd_tree, "", self->fd_tmp, "", MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0); + self->must_unmount = true; + + ASSERT_EQ(close(fd_tree), 0); +} + +/* Test that a pidfd can be reopened through procfs. */ +TEST_F(pidfd_bind_mount, reopen) +{ + int pidfd; + char proc_path[PATH_MAX]; + + sprintf(proc_path, "/proc/self/fd/%d", self->pidfd); + pidfd = open(proc_path, O_RDONLY | O_NOCTTY | O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_GE(fstat(self->pidfd, &self->st2), 0); + ASSERT_EQ(ioctl(self->pidfd, FS_IOC_GETVERSION, &self->gen2), 0); + + ASSERT_TRUE(self->st1.st_dev == self->st2.st_dev && self->st1.st_ino == self->st2.st_ino); + ASSERT_TRUE(self->gen1 == self->gen2); + + ASSERT_EQ(close(pidfd), 0); +} + +/* + * Test that a detached mount can be created for a pidfd and then + * attached to the filesystem hierarchy and reopened. + */ +TEST_F(pidfd_bind_mount, bind_mount_reopen) +{ + int fd_tree, fd_pidfd_mnt; + + fd_tree = sys_open_tree(self->pidfd, "", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH); + ASSERT_GE(fd_tree, 0); + + ASSERT_EQ(move_mount(fd_tree, "", self->fd_tmp, "", MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0); + self->must_unmount = true; + + fd_pidfd_mnt = openat(-EBADF, self->template, O_RDONLY | O_NOCTTY | O_CLOEXEC); + ASSERT_GE(fd_pidfd_mnt, 0); + + ASSERT_GE(fstat(fd_tree, &self->st2), 0); + ASSERT_EQ(ioctl(fd_pidfd_mnt, FS_IOC_GETVERSION, &self->gen2), 0); + + ASSERT_TRUE(self->st1.st_dev == self->st2.st_dev && self->st1.st_ino == self->st2.st_ino); + ASSERT_TRUE(self->gen1 == self->gen2); + + ASSERT_EQ(close(fd_tree), 0); + ASSERT_EQ(close(fd_pidfd_mnt), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c new file mode 100644 index 000000000000..439b9c6c0457 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <linux/types.h> +#include <poll.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sys/socket.h> +#include <linux/kcmp.h> +#include <sys/stat.h> + +#include "pidfd.h" +#include "../kselftest_harness.h" + +FIXTURE(file_handle) +{ + pid_t pid; + int pidfd; + + pid_t child_pid1; + int child_pidfd1; + + pid_t child_pid2; + int child_pidfd2; + + pid_t child_pid3; + int child_pidfd3; +}; + +FIXTURE_SETUP(file_handle) +{ + int ret; + int ipc_sockets[2]; + char c; + + self->pid = getpid(); + self->pidfd = sys_pidfd_open(self->pid, 0); + ASSERT_GE(self->pidfd, 0); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + + self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER); + EXPECT_GE(self->child_pid1, 0); + + if (self->child_pid1 == 0) { + close(ipc_sockets[0]); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + + pause(); + _exit(EXIT_SUCCESS); + } + + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + + self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID); + EXPECT_GE(self->child_pid2, 0); + + if (self->child_pid2 == 0) { + close(ipc_sockets[0]); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + + pause(); + _exit(EXIT_SUCCESS); + } + + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + + self->child_pid3 = create_child(&self->child_pidfd3, CLONE_NEWUSER | CLONE_NEWPID); + EXPECT_GE(self->child_pid3, 0); + + if (self->child_pid3 == 0) { + close(ipc_sockets[0]); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + + pause(); + _exit(EXIT_SUCCESS); + } + + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); +} + +FIXTURE_TEARDOWN(file_handle) +{ + EXPECT_EQ(close(self->pidfd), 0); + + EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd1, SIGKILL, NULL, 0), 0); + if (self->child_pidfd1 >= 0) + EXPECT_EQ(0, close(self->child_pidfd1)); + + EXPECT_EQ(sys_waitid(P_PID, self->child_pid1, NULL, WEXITED), 0); + + EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd2, SIGKILL, NULL, 0), 0); + if (self->child_pidfd2 >= 0) + EXPECT_EQ(0, close(self->child_pidfd2)); + + EXPECT_EQ(sys_waitid(P_PID, self->child_pid2, NULL, WEXITED), 0); + + if (self->child_pidfd3 >= 0) { + EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd3, SIGKILL, NULL, 0), 0); + EXPECT_EQ(0, close(self->child_pidfd3)); + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0); + } +} + +/* + * Test that we can decode a pidfs file handle in the same pid + * namespace. + */ +TEST_F(file_handle, file_handle_same_pidns) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd1, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd1, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_NONBLOCK); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + free(fh); +} + +/* + * Test that we can decode a pidfs file handle from a child pid + * namespace. + */ +TEST_F(file_handle, file_handle_child_pidns) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_CLOEXEC); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, O_NONBLOCK); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + free(fh); +} + +/* + * Test that we fail to decode a pidfs file handle from an ancestor + * child pid namespace. + */ +TEST_F(file_handle, file_handle_foreign_pidns) +{ + int mnt_id; + struct file_handle *fh; + pid_t pid; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->pidfd, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(setns(self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int pidfd = open_by_handle_at(self->pidfd, fh, 0); + if (pidfd >= 0) { + TH_LOG("Managed to open pidfd outside of the caller's pid namespace hierarchy"); + _exit(1); + } + _exit(0); + } + + ASSERT_EQ(wait_for_pid(pid), 0); + + free(fh); +} + +/* + * Test that we can decode a pidfs file handle of a process that has + * exited but not been reaped. + */ +TEST_F(file_handle, pid_has_exited) +{ + int mnt_id, pidfd, child_pidfd3; + struct file_handle *fh; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd3, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd3, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + child_pidfd3 = self->child_pidfd3; + self->child_pidfd3 = -EBADF; + EXPECT_EQ(sys_pidfd_send_signal(child_pidfd3, SIGKILL, NULL, 0), 0); + EXPECT_EQ(close(child_pidfd3), 0); + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED | WNOWAIT), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0); +} + +/* + * Test that we fail to decode a pidfs file handle of a process that has + * already been reaped. + */ +TEST_F(file_handle, pid_has_been_reaped) +{ + int mnt_id, pidfd, child_pidfd3; + struct file_handle *fh; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd3, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd3, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); + + child_pidfd3 = self->child_pidfd3; + self->child_pidfd3 = -EBADF; + EXPECT_EQ(sys_pidfd_send_signal(child_pidfd3, SIGKILL, NULL, 0), 0); + EXPECT_EQ(close(child_pidfd3), 0); + EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_LT(pidfd, 0); +} + +/* + * Test valid flags to open a pidfd file handle. Note, that + * PIDFD_NONBLOCK is defined as O_NONBLOCK and O_NONBLOCK is an alias to + * O_NDELAY. Also note that PIDFD_THREAD is an alias for O_EXCL. + */ +TEST_F(file_handle, open_by_handle_at_valid_flags) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, + O_RDONLY | + O_WRONLY | + O_RDWR | + O_NONBLOCK | + O_NDELAY | + O_CLOEXEC | + O_EXCL); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); +} + +/* + * Test that invalid flags passed to open a pidfd file handle are + * rejected. + */ +TEST_F(file_handle, open_by_handle_at_invalid_flags) +{ + int mnt_id; + struct file_handle *fh; + int pidfd = -EBADF; + static const struct invalid_pidfs_file_handle_flags { + int oflag; + const char *oflag_name; + } invalid_pidfs_file_handle_flags[] = { + { FASYNC, "FASYNC" }, + { O_CREAT, "O_CREAT" }, + { O_NOCTTY, "O_NOCTTY" }, + { O_CREAT, "O_CREAT" }, + { O_TRUNC, "O_TRUNC" }, + { O_APPEND, "O_APPEND" }, + { O_SYNC, "O_SYNC" }, + { O_DSYNC, "O_DSYNC" }, + { O_DIRECT, "O_DIRECT" }, + { O_DIRECTORY, "O_DIRECTORY" }, + { O_NOFOLLOW, "O_NOFOLLOW" }, + { O_NOATIME, "O_NOATIME" }, + { O_PATH, "O_PATH" }, + { O_TMPFILE, "O_TMPFILE" }, + /* + * O_LARGEFILE is added implicitly by + * open_by_handle_at() so pidfs simply masks it off. + */ + }; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0); + + for (int i = 0; i < ARRAY_SIZE(invalid_pidfs_file_handle_flags); i++) { + pidfd = open_by_handle_at(self->pidfd, fh, invalid_pidfs_file_handle_flags[i].oflag); + ASSERT_LT(pidfd, 0) { + TH_LOG("open_by_handle_at() succeeded with invalid flags: %s", invalid_pidfs_file_handle_flags[i].oflag_name); + } + } +} + +/* Test that lookup fails. */ +TEST_F(file_handle, lookup_must_fail) +{ + int mnt_id; + struct file_handle *fh; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_NE(name_to_handle_at(self->child_pidfd2, "lookup-is-not-possible-with-pidfs", fh, &mnt_id, AT_EMPTY_PATH), 0); + ASSERT_EQ(errno, ENOTDIR); + ASSERT_NE(name_to_handle_at(self->child_pidfd2, "lookup-is-not-possible-with-pidfs", fh, &mnt_id, 0), 0); + ASSERT_EQ(errno, ENOTDIR); +} + +#ifndef AT_HANDLE_CONNECTABLE +#define AT_HANDLE_CONNECTABLE 0x002 +#endif + +/* + * Test that AT_HANDLE_CONNECTABLE is rejected. Connectable file handles + * don't make sense for pidfs. Note that currently AT_HANDLE_CONNECTABLE + * is rejected because it is incompatible with AT_EMPTY_PATH which is + * required with pidfds as we don't support lookup. + */ +TEST_F(file_handle, invalid_name_to_handle_at_flags) +{ + int mnt_id; + struct file_handle *fh; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_NE(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH | AT_HANDLE_CONNECTABLE), 0); +} + +#ifndef AT_HANDLE_FID +#define AT_HANDLE_FID 0x200 +#endif + +/* + * Test that a request with AT_HANDLE_FID always leads to decodable file + * handle as pidfs always provides export operations. + */ +TEST_F(file_handle, valid_name_to_handle_at_flags) +{ + int mnt_id, pidfd; + struct file_handle *fh; + struct stat st1, st2; + + fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ); + ASSERT_NE(fh, NULL); + memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ); + fh->handle_bytes = MAX_HANDLE_SZ; + + ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH | AT_HANDLE_FID), 0); + + ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0); + + pidfd = open_by_handle_at(self->pidfd, fh, 0); + ASSERT_GE(pidfd, 0); + + ASSERT_EQ(fstat(pidfd, &st2), 0); + ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); + + ASSERT_EQ(close(pidfd), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 7c2a4349170a..222f8131283b 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -19,7 +19,6 @@ #include <linux/ioctl.h> #include "pidfd.h" -#include "../clone3/clone3_selftests.h" #include "../kselftest_harness.h" #ifndef PIDFS_IOCTL_MAGIC @@ -118,22 +117,6 @@ FIXTURE(current_nsset) int child_pidfd_derived_nsfds2[PIDFD_NS_MAX]; }; -static int sys_waitid(int which, pid_t pid, int options) -{ - return syscall(__NR_waitid, which, pid, NULL, options, NULL); -} - -pid_t create_child(int *pidfd, unsigned flags) -{ - struct __clone_args args = { - .flags = CLONE_PIDFD | flags, - .exit_signal = SIGCHLD, - .pidfd = ptr_to_u64(pidfd), - }; - - return sys_clone3(&args, sizeof(struct clone_args)); -} - static bool switch_timens(void) { int fd, ret; @@ -150,28 +133,6 @@ static bool switch_timens(void) return ret == 0; } -static ssize_t read_nointr(int fd, void *buf, size_t count) -{ - ssize_t ret; - - do { - ret = read(fd, buf, count); - } while (ret < 0 && errno == EINTR); - - return ret; -} - -static ssize_t write_nointr(int fd, const void *buf, size_t count) -{ - ssize_t ret; - - do { - ret = write(fd, buf, count); - } while (ret < 0 && errno == EINTR); - - return ret; -} - FIXTURE_SETUP(current_nsset) { int i, proc_fd, ret; @@ -229,7 +190,7 @@ FIXTURE_SETUP(current_nsset) _exit(EXIT_SUCCESS); } - ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED | WNOWAIT), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, NULL, WEXITED | WNOWAIT), 0); self->pidfd = sys_pidfd_open(self->pid, 0); EXPECT_GE(self->pidfd, 0) { @@ -432,9 +393,9 @@ FIXTURE_TEARDOWN(current_nsset) EXPECT_EQ(0, close(self->child_pidfd1)); if (self->child_pidfd2 >= 0) EXPECT_EQ(0, close(self->child_pidfd2)); - ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED), 0); - ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, WEXITED), 0); - ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, WEXITED), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, NULL, WEXITED), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, NULL, WEXITED), 0); + ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, NULL, WEXITED), 0); } static int preserve_ns(const int pid, const char *ns) diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 0dcb8365ddc3..1e2d49751cde 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -26,22 +26,11 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif -static pid_t sys_clone3(struct clone_args *args) -{ - return syscall(__NR_clone3, args, sizeof(struct clone_args)); -} - -static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, - struct rusage *ru) -{ - return syscall(__NR_waitid, which, pid, info, options, ru); -} - TEST(wait_simple) { int pidfd = -1; pid_t parent_tid = -1; - struct clone_args args = { + struct __clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), .pidfd = ptr_to_u64(&pidfd), .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, @@ -55,7 +44,7 @@ TEST(wait_simple) pidfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); ASSERT_GE(pidfd, 0); - pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_NE(pid, 0); EXPECT_EQ(close(pidfd), 0); pidfd = -1; @@ -63,18 +52,18 @@ TEST(wait_simple) pidfd = open("/dev/null", O_RDONLY | O_CLOEXEC); ASSERT_GE(pidfd, 0); - pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_NE(pid, 0); EXPECT_EQ(close(pidfd), 0); pidfd = -1; - pid = sys_clone3(&args); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); if (pid == 0) exit(EXIT_SUCCESS); - pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_GE(pid, 0); ASSERT_EQ(WIFEXITED(info.si_status), true); ASSERT_EQ(WEXITSTATUS(info.si_status), 0); @@ -89,7 +78,7 @@ TEST(wait_states) { int pidfd = -1; pid_t parent_tid = -1; - struct clone_args args = { + struct __clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), .pidfd = ptr_to_u64(&pidfd), .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, @@ -102,7 +91,7 @@ TEST(wait_states) }; ASSERT_EQ(pipe(pfd), 0); - pid = sys_clone3(&args); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); if (pid == 0) { @@ -117,28 +106,28 @@ TEST(wait_states) } close(pfd[0]); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); ASSERT_EQ(info.si_pid, parent_tid); ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED), 0); ASSERT_EQ(write(pfd[1], "C", 1), 1); close(pfd[1]); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_CONTINUED); ASSERT_EQ(info.si_pid, parent_tid); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); ASSERT_EQ(info.si_pid, parent_tid); ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_KILLED); ASSERT_EQ(info.si_pid, parent_tid); @@ -151,7 +140,7 @@ TEST(wait_nonblock) int pidfd; unsigned int flags = 0; pid_t parent_tid = -1; - struct clone_args args = { + struct __clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), .flags = CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, @@ -173,12 +162,12 @@ TEST(wait_nonblock) SKIP(return, "Skipping PIDFD_NONBLOCK test"); } - ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_LT(ret, 0); ASSERT_EQ(errno, ECHILD); EXPECT_EQ(close(pidfd), 0); - pid = sys_clone3(&args); + pid = sys_clone3(&args, sizeof(args)); ASSERT_GE(pid, 0); if (pid == 0) { @@ -201,7 +190,7 @@ TEST(wait_nonblock) * Callers need to see EAGAIN/EWOULDBLOCK with non-blocking pidfd when * child processes exist but none have exited. */ - ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED); ASSERT_LT(ret, 0); ASSERT_EQ(errno, EAGAIN); @@ -210,19 +199,19 @@ TEST(wait_nonblock) * WNOHANG raised explicitly when child processes exist but none have * exited. */ - ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG, NULL); + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG); ASSERT_EQ(ret, 0); ASSERT_EQ(fcntl(pidfd, F_SETFL, (flags & ~O_NONBLOCK)), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); ASSERT_EQ(info.si_pid, parent_tid); ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); - ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0); + ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_EXITED); ASSERT_EQ(info.si_pid, parent_tid); diff --git a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c index 580fcac0a09f..b71ef8a493ed 100644 --- a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c +++ b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c @@ -20,7 +20,7 @@ static int test_gettimeofday(void) gettimeofday(&tv_end, NULL); } - timersub(&tv_start, &tv_end, &tv_diff); + timersub(&tv_end, &tv_start, &tv_diff); printf("time = %.6f\n", tv_diff.tv_sec + (tv_diff.tv_usec) * 1e-6); diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h index 51729d9a7111..3a0129467de6 100644 --- a/tools/testing/selftests/powerpc/include/pkeys.h +++ b/tools/testing/selftests/powerpc/include/pkeys.h @@ -35,10 +35,18 @@ #define __NR_pkey_alloc 384 #define __NR_pkey_free 385 +#ifndef NT_PPC_PKEY +#define NT_PPC_PKEY 0x110 +#endif + #define PKEY_BITS_PER_PKEY 2 #define NR_PKEYS 32 #define PKEY_BITS_MASK ((1UL << PKEY_BITS_PER_PKEY) - 1) +#define AMR_BITS_PER_PKEY 2 +#define PKEY_REG_BITS (sizeof(u64) * 8) +#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) + inline unsigned long pkeyreg_get(void) { return mfspr(SPRN_AMR); diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index f6da4cb30cd6..f061434af452 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -16,26 +16,7 @@ #include <unistd.h> #include "ptrace.h" #include "child.h" - -#ifndef __NR_pkey_alloc -#define __NR_pkey_alloc 384 -#endif - -#ifndef __NR_pkey_free -#define __NR_pkey_free 385 -#endif - -#ifndef NT_PPC_PKEY -#define NT_PPC_PKEY 0x110 -#endif - -#ifndef PKEY_DISABLE_EXECUTE -#define PKEY_DISABLE_EXECUTE 0x4 -#endif - -#define AMR_BITS_PER_PKEY 2 -#define PKEY_REG_BITS (sizeof(u64) * 8) -#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) +#include "pkeys.h" #define CORE_FILE_LIMIT (5 * 1024 * 1024) /* 5 MB should be enough */ @@ -61,16 +42,6 @@ struct shared_info { time_t core_time; }; -static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) -{ - return syscall(__NR_pkey_alloc, flags, init_access_rights); -} - -static int sys_pkey_free(int pkey) -{ - return syscall(__NR_pkey_free, pkey); -} - static int increase_core_file_limit(void) { struct rlimit rlim; diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c index d89474377f11..fc633014424f 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c @@ -7,26 +7,7 @@ */ #include "ptrace.h" #include "child.h" - -#ifndef __NR_pkey_alloc -#define __NR_pkey_alloc 384 -#endif - -#ifndef __NR_pkey_free -#define __NR_pkey_free 385 -#endif - -#ifndef NT_PPC_PKEY -#define NT_PPC_PKEY 0x110 -#endif - -#ifndef PKEY_DISABLE_EXECUTE -#define PKEY_DISABLE_EXECUTE 0x4 -#endif - -#define AMR_BITS_PER_PKEY 2 -#define PKEY_REG_BITS (sizeof(u64) * 8) -#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY)) +#include "pkeys.h" static const char user_read[] = "[User Read (Running)]"; static const char user_write[] = "[User Write (Running)]"; @@ -61,11 +42,6 @@ struct shared_info { unsigned long invalid_uamor; }; -static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) -{ - return syscall(__NR_pkey_alloc, flags, init_access_rights); -} - static int child(struct shared_info *info) { unsigned long reg; diff --git a/tools/testing/selftests/powerpc/vphn/test-vphn.c b/tools/testing/selftests/powerpc/vphn/test-vphn.c index 81d3069ffb84..f348f54914a9 100644 --- a/tools/testing/selftests/powerpc/vphn/test-vphn.c +++ b/tools/testing/selftests/powerpc/vphn/test-vphn.c @@ -275,7 +275,7 @@ static struct test { } }, { - /* Parse a 32-bit value split accross two consecutives 64-bit + /* Parse a 32-bit value split across two consecutives 64-bit * input values. */ "vphn: 16-bit value followed by 2 x 32-bit values", diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c index dee41b7ee3e3..059d2e87eb1f 100644 --- a/tools/testing/selftests/riscv/abi/pointer_masking.c +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -185,8 +185,20 @@ static void test_fork_exec(void) } } +static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg) +{ + int ret = pwrite(fd, buf, count, 0); + + if (ret != count) { + ksft_perror(msg); + return false; + } + return true; +} + static void test_tagged_addr_abi_sysctl(void) { + char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n"; char value; int fd; @@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void) } value = '1'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, - "sysctl disabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '1'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, + "sysctl disabled\n"); value = '0'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, - "sysctl enabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '0'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, + "sysctl enabled\n"); set_tagged_addr_ctrl(0, false); diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c index 1dd94197da30..6174ffe016dc 100644 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c @@ -25,6 +25,8 @@ int main(void) unsigned long vl; char *datap, *tmp; + ksft_set_plan(1); + datap = malloc(MAX_VSIZE); if (!datap) { ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); @@ -63,6 +65,8 @@ int main(void) } free(datap); + + ksft_test_result_pass("tests for v_initval_nolibc pass\n"); ksft_exit_pass(); return 0; } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 895177f6bf4c..40b3bffcbb40 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -76,6 +76,8 @@ int main(void) long flag, expected; long rc; + ksft_set_plan(1); + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); if (rc < 0) { diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index 37d9bf6fb745..6f4c3f5a1c5d 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index 6a7db1502c29..fbda6bf54671 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - target = bpf_get_prandom_u32() % nr_cpus; + if (p->nr_cpus_allowed == nr_cpus) + target = bpf_get_prandom_u32() % nr_cpus; + else + target = scx_bpf_task_cpu(p); - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 472851b56854..0ff27e57fe43 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx) /* Just sleeping is fine, plenty of scheduling events happening */ sleep(1); - SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); bpf_link__destroy(link); + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + return SCX_TEST_PASS; } @@ -50,7 +51,7 @@ static void cleanup(void *ctx) struct scx_test dsp_local_on = { .name = "dsp_local_on", .description = "Verify we can directly dispatch tasks to a local DSQs " - "from osp.dispatch()", + "from ops.dispatch()", .setup = setup, .run = run, .cleanup = cleanup, diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index 1efb50d61040..a7cf868d5e31 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..430f5e13bf55 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -12,6 +12,8 @@ char _license[] SEC("license") = "GPL"; +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) @@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) { - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 9efdbb7da928..815f1d5d61ac 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 3bbd5fcdfb18..2a75de11b2cf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 0fda57fe0ecf..99d075695c97 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet@meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 996448afe31b..91d120548bf5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -78,10 +78,10 @@ "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow", - "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass", + "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h index 06c89bdcc515..f67d47d32857 100644 --- a/tools/testing/shared/linux/maple_tree.h +++ b/tools/testing/shared/linux/maple_tree.h @@ -2,6 +2,6 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #include "../../../../include/linux/maple_tree.h" diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h index e01f66f98982..3e1b6adc027b 100644 --- a/tools/testing/vma/linux/atomic.h +++ b/tools/testing/vma/linux/atomic.h @@ -6,7 +6,7 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #endif /* _LINUX_ATOMIC_H */ |