diff options
Diffstat (limited to 'tools')
35 files changed, 1080 insertions, 377 deletions
diff --git a/tools/include/io_uring/mini_liburing.h b/tools/include/io_uring/mini_liburing.h index 9ccb16074eb5..44be4446feda 100644 --- a/tools/include/io_uring/mini_liburing.h +++ b/tools/include/io_uring/mini_liburing.h @@ -6,6 +6,7 @@ #include <stdio.h> #include <string.h> #include <unistd.h> +#include <sys/uio.h> struct io_sq_ring { unsigned int *head; @@ -55,6 +56,7 @@ struct io_uring { struct io_uring_sq sq; struct io_uring_cq cq; int ring_fd; + unsigned flags; }; #if defined(__x86_64) || defined(__i386__) @@ -72,7 +74,14 @@ static inline int io_uring_mmap(int fd, struct io_uring_params *p, void *ptr; int ret; - sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned int); + if (p->flags & IORING_SETUP_NO_SQARRAY) { + sq->ring_sz = p->cq_off.cqes; + sq->ring_sz += p->cq_entries * sizeof(struct io_uring_cqe); + } else { + sq->ring_sz = p->sq_off.array; + sq->ring_sz += p->sq_entries * sizeof(unsigned int); + } + ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); if (ptr == MAP_FAILED) @@ -83,7 +92,8 @@ static inline int io_uring_mmap(int fd, struct io_uring_params *p, sq->kring_entries = ptr + p->sq_off.ring_entries; sq->kflags = ptr + p->sq_off.flags; sq->kdropped = ptr + p->sq_off.dropped; - sq->array = ptr + p->sq_off.array; + if (!(p->flags & IORING_SETUP_NO_SQARRAY)) + sq->array = ptr + p->sq_off.array; size = p->sq_entries * sizeof(struct io_uring_sqe); sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, @@ -126,28 +136,39 @@ static inline int io_uring_enter(int fd, unsigned int to_submit, flags, sig, _NSIG / 8); } -static inline int io_uring_queue_init(unsigned int entries, - struct io_uring *ring, - unsigned int flags) +static inline int io_uring_queue_init_params(unsigned int entries, + struct io_uring *ring, + struct io_uring_params *p) { - struct io_uring_params p; int fd, ret; memset(ring, 0, sizeof(*ring)); - memset(&p, 0, sizeof(p)); - p.flags = flags; - fd = io_uring_setup(entries, &p); + fd = io_uring_setup(entries, p); if (fd < 0) return fd; - ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); - if (!ret) + ret = io_uring_mmap(fd, p, &ring->sq, &ring->cq); + if (!ret) { ring->ring_fd = fd; - else + ring->flags = p->flags; + } else { close(fd); + } return ret; } +static inline int io_uring_queue_init(unsigned int entries, + struct io_uring *ring, + unsigned int flags) +{ + struct io_uring_params p; + + memset(&p, 0, sizeof(p)); + p.flags = flags; + + return io_uring_queue_init_params(entries, ring, &p); +} + /* Get a sqe */ static inline struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) { @@ -199,10 +220,18 @@ static inline int io_uring_submit(struct io_uring *ring) ktail = *sq->ktail; to_submit = sq->sqe_tail - sq->sqe_head; - for (submitted = 0; submitted < to_submit; submitted++) { - read_barrier(); - sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + + if (!(ring->flags & IORING_SETUP_NO_SQARRAY)) { + for (submitted = 0; submitted < to_submit; submitted++) { + read_barrier(); + sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + } + } else { + ktail += to_submit; + sq->sqe_head += to_submit; + submitted = to_submit; } + if (!submitted) return 0; diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index c2f3e8b3f2ac..9b692f368be7 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -41,7 +41,7 @@ clean distclean: rm -rf pyynl.egg-info rm -rf build -install: libynl.a lib/*.h +install: libynl.a lib/*.h ynltool @echo -e "\tINSTALL libynl.a" @$(INSTALL) -d $(DESTDIR)$(libdir) @$(INSTALL) -m 0644 libynl.a $(DESTDIR)$(libdir)/libynl.a @@ -51,6 +51,7 @@ install: libynl.a lib/*.h @echo -e "\tINSTALL pyynl" @pip install --prefix=$(DESTDIR)$(prefix) . @make -C generated install + @make -C ynltool install run_tests: @$(MAKE) -C tests run_tests diff --git a/tools/net/ynl/pyynl/lib/doc_generator.py b/tools/net/ynl/pyynl/lib/doc_generator.py index 3a16b8eb01ca..8b922d8f89e8 100644 --- a/tools/net/ynl/pyynl/lib/doc_generator.py +++ b/tools/net/ynl/pyynl/lib/doc_generator.py @@ -166,13 +166,13 @@ class YnlDocGenerator: continue lines.append(self.fmt.rst_paragraph(self.fmt.bold(key), level + 1)) if key in ['request', 'reply']: - lines.append(self.parse_do_attributes(do_dict[key], level + 1) + "\n") + lines.append(self.parse_op_attributes(do_dict[key], level + 1) + "\n") else: lines.append(self.fmt.headroom(level + 2) + do_dict[key] + "\n") return "\n".join(lines) - def parse_do_attributes(self, attrs: Dict[str, Any], level: int = 0) -> str: + def parse_op_attributes(self, attrs: Dict[str, Any], level: int = 0) -> str: """Parse 'attributes' section""" if "attributes" not in attrs: return "" @@ -184,7 +184,7 @@ class YnlDocGenerator: def parse_operations(self, operations: List[Dict[str, Any]], namespace: str) -> str: """Parse operations block""" - preprocessed = ["name", "doc", "title", "do", "dump", "flags"] + preprocessed = ["name", "doc", "title", "do", "dump", "flags", "event"] linkable = ["fixed-header", "attribute-set"] lines = [] @@ -217,6 +217,9 @@ class YnlDocGenerator: if "dump" in operation: lines.append(self.fmt.rst_paragraph(":dump:", 0)) lines.append(self.parse_do(operation["dump"], 0)) + if "event" in operation: + lines.append(self.fmt.rst_paragraph(":event:", 0)) + lines.append(self.parse_op_attributes(operation["event"], 0)) # New line after fields lines.append("\n") diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 81b4ecd89100..d9809276db98 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -21,7 +21,7 @@ files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode - params=( $(git grep -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) + params=( $(git grep --no-line-number -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) args=$(sed -n 's@/\* YNL-ARG \(.*\) \*/@\1@p' $f) if [ $f -nt ${params[0]} -a -z "$force" ]; then diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index ad6e1ec706ce..a40f30232929 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -72,23 +72,40 @@ HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" # # To support disassembly, objtool needs libopcodes which is provided -# with libbdf (binutils-dev or binutils-devel package). +# with libbfd (binutils-dev or binutils-devel package). # -FEATURE_USER = .objtool -FEATURE_TESTS = libbfd disassembler-init-styled -FEATURE_DISPLAY = -include $(srctree)/tools/build/Makefile.feature - -ifeq ($(feature-disassembler-init-styled), 1) - OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED -endif +# We check using HOSTCC directly rather than the shared feature framework +# because objtool is a host tool that links against host libraries. +# +# When using shared libraries, -lopcodes is sufficient as dependencies are +# resolved automatically. With static libraries, we must explicitly link +# against libopcodes' dependencies: libbfd, libiberty, and sometimes libz. +# Try each combination and use the first one that succeeds. +# +LIBOPCODES_LIBS := $(shell \ + for libs in "-lopcodes" \ + "-lopcodes -lbfd" \ + "-lopcodes -lbfd -liberty" \ + "-lopcodes -lbfd -liberty -lz"; do \ + echo 'extern void disassemble_init_for_target(void *);' \ + 'int main(void) { disassemble_init_for_target(0); return 0; }' | \ + $(HOSTCC) -xc - -o /dev/null $$libs 2>/dev/null && \ + echo "$$libs" && break; \ + done) + +# Styled disassembler support requires binutils >= 2.39 +HAVE_DISASM_STYLED := $(shell echo '$(pound)include <dis-asm.h>' | \ + $(HOSTCC) -E -xc - 2>/dev/null | grep -q disassembler_style && echo y) BUILD_DISAS := n -ifeq ($(feature-libbfd),1) +ifneq ($(LIBOPCODES_LIBS),) BUILD_DISAS := y - OBJTOOL_CFLAGS += -DDISAS -DPACKAGE="objtool" - OBJTOOL_LDFLAGS += -lopcodes + OBJTOOL_CFLAGS += -DDISAS -DPACKAGE='"objtool"' + OBJTOOL_LDFLAGS += $(LIBOPCODES_LIBS) +ifeq ($(HAVE_DISASM_STYLED),y) + OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED +endif endif export BUILD_DISAS diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index 25ff7942b4d5..2b27b54096b8 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -152,8 +152,8 @@ static inline void unindent(int *unused) { indent--; } if (unlikely(insn->sym && insn->sym->pfunc && \ insn->sym->pfunc->debug_checksum)) { \ char *insn_off = offstr(insn->sec, insn->offset); \ - __dbg("checksum: %s %s %016lx", \ - func->name, insn_off, checksum); \ + __dbg("checksum: %s %s %016llx", \ + func->name, insn_off, (unsigned long long)checksum);\ free(insn_off); \ } \ }) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 17c1c36a7bf9..000c89a1e50d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -251,8 +251,11 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); - if (!evsel) - goto out_err; + if (!evsel) { + perf_cpu_map__put(cpus); + perf_cpu_map__put(pmu_cpus); + return NULL; + } if (name) { evsel->name = strdup(name); diff --git a/tools/testing/cxl/test/cxl_translate.c b/tools/testing/cxl/test/cxl_translate.c index 2200ae21795c..16328b2112b2 100644 --- a/tools/testing/cxl/test/cxl_translate.c +++ b/tools/testing/cxl/test/cxl_translate.c @@ -68,6 +68,8 @@ static u64 to_hpa(u64 dpa_offset, int pos, u8 r_eiw, u16 r_eig, u8 hb_ways, /* Calculate base HPA offset from DPA and position */ hpa_offset = cxl_calculate_hpa_offset(dpa_offset, pos, r_eiw, r_eig); + if (hpa_offset == ULLONG_MAX) + return ULLONG_MAX; if (math == XOR_MATH) { cximsd->nr_maps = hbiw_to_nr_maps[hb_ways]; @@ -258,19 +260,23 @@ static int test_random_params(void) pos = get_random_u32() % ways; dpa = get_random_u64() >> 12; + reverse_dpa = ULLONG_MAX; + reverse_pos = -1; + hpa = cxl_calculate_hpa_offset(dpa, pos, eiw, eig); - reverse_dpa = cxl_calculate_dpa_offset(hpa, eiw, eig); - reverse_pos = cxl_calculate_position(hpa, eiw, eig); - - if (reverse_dpa != dpa || reverse_pos != pos) { - pr_err("test random iter %d FAIL hpa=%llu, dpa=%llu reverse_dpa=%llu, pos=%d reverse_pos=%d eiw=%u eig=%u\n", - i, hpa, dpa, reverse_dpa, pos, reverse_pos, eiw, - eig); - - if (failures++ > 10) { - pr_err("test random too many failures, stop\n"); - break; - } + if (hpa != ULLONG_MAX) { + reverse_dpa = cxl_calculate_dpa_offset(hpa, eiw, eig); + reverse_pos = cxl_calculate_position(hpa, eiw, eig); + if (reverse_dpa == dpa && reverse_pos == pos) + continue; + } + + pr_err("test random iter %d FAIL hpa=%llu, dpa=%llu reverse_dpa=%llu, pos=%d reverse_pos=%d eiw=%u eig=%u\n", + i, hpa, dpa, reverse_dpa, pos, reverse_pos, eiw, eig); + + if (failures++ > 10) { + pr_err("test random too many failures, stop\n"); + break; } } pr_info("..... test random: PASS %d FAIL %d\n", i - failures, failures); diff --git a/tools/testing/selftests/alsa/utimer-test.c b/tools/testing/selftests/alsa/utimer-test.c index c45cb226bd8f..d221972cd8fb 100644 --- a/tools/testing/selftests/alsa/utimer-test.c +++ b/tools/testing/selftests/alsa/utimer-test.c @@ -141,7 +141,6 @@ TEST_F(timer_f, utimer) { TEST(wrong_timers_test) { int timer_dev_fd; int utimer_fd; - size_t i; struct snd_timer_uinfo wrong_timer = { .resolution = 0, .id = UTIMER_DEFAULT_ID, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index ee94c281888a..26159e0499c7 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -47,6 +47,7 @@ void test_xdp_context_test_run(void) struct test_xdp_context_test_run *skel = NULL; char data[sizeof(pkt_v4) + sizeof(__u32)]; char bad_ctx[sizeof(struct xdp_md) + 1]; + char large_data[256]; struct xdp_md ctx_in, ctx_out; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, @@ -94,9 +95,6 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data), 0, 0, 0); - /* Meta data must be 255 bytes or smaller */ - test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0); - /* Total size of data must be data_end - data_meta or larger */ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data) + 1, 0, 0, 0); @@ -116,6 +114,16 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data), 0, 0, 1); + /* Meta data must be 216 bytes or smaller (256 - sizeof(struct + * xdp_frame)). Test both nearest invalid size and nearest invalid + * 4-byte-aligned size, and make sure data_in is large enough that we + * actually hit the check on metadata length + */ + opts.data_in = large_data; + opts.data_size_in = sizeof(large_data); + test_xdp_context_error(prog_fd, opts, 0, 217, sizeof(large_data), 0, 0, 0); + test_xdp_context_error(prog_fd, opts, 0, 220, sizeof(large_data), 0, 0, 0); + test_xdp_context_test_run__destroy(skel); } diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index d23b3b0c20a3..285bb17df9c2 100644 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -485,8 +485,8 @@ static void parse_rps_bitmap(const char *arg) bitmap = strtoul(arg, NULL, 0); - if (bitmap & ~(RPS_MAX_CPUS - 1)) - error(1, 0, "rps bitmap 0x%lx out of bounds 0..%lu", + if (bitmap & ~((1UL << RPS_MAX_CPUS) - 1)) + error(1, 0, "rps bitmap 0x%lx out of bounds, max cpu %lu", bitmap, RPS_MAX_CPUS - 1); for (i = 0; i < RPS_MAX_CPUS; i++) diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py index d2db5ee9e358..d288c57894f6 100755 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.py +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -94,12 +94,14 @@ def _configure_rps(cfg, rps_cpus): mask = 0 for cpu in rps_cpus: mask |= (1 << cpu) - mask = hex(mask)[2:] + + mask = hex(mask) # Set RPS bitmap for all rx queues for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): with open(rps_file, "w", encoding="utf-8") as fp: - fp.write(mask) + # sysfs expects hex without '0x' prefix, toeplitz.c needs the prefix + fp.write(mask[2:]) return mask diff --git a/tools/testing/selftests/kvm/x86/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index f4ce5a185a7d..37b166260ee3 100644 --- a/tools/testing/selftests/kvm/x86/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c @@ -69,6 +69,12 @@ static inline void __tileloadd(void *tile) : : "a"(tile), "d"(0)); } +static inline int tileloadd_safe(void *tile) +{ + return kvm_asm_safe(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10", + "a"(tile), "d"(0)); +} + static inline void __tilerelease(void) { asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); @@ -124,27 +130,52 @@ static void set_tilecfg(struct tile_config *cfg) } } +enum { + /* Retrieve TMM0 from guest, stash it for TEST_RESTORE_TILEDATA */ + TEST_SAVE_TILEDATA = 1, + + /* Check TMM0 against tiledata */ + TEST_COMPARE_TILEDATA = 2, + + /* Restore TMM0 from earlier save */ + TEST_RESTORE_TILEDATA = 4, + + /* Full VM save/restore */ + TEST_SAVE_RESTORE = 8, +}; + static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, struct xstate *xstate) { + int vector; + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) && this_cpu_has(X86_FEATURE_OSXSAVE)); check_xtile_info(); - GUEST_SYNC(1); + GUEST_SYNC(TEST_SAVE_RESTORE); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(2); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - GUEST_SYNC(3); + GUEST_SYNC(TEST_SAVE_RESTORE); /* Check save/restore when trap to userspace */ __tileloadd(tiledata); - GUEST_SYNC(4); + GUEST_SYNC(TEST_SAVE_TILEDATA | TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); + + /* host tries setting tiledata while guest XFD is set */ + GUEST_SYNC(TEST_RESTORE_TILEDATA); + GUEST_SYNC(TEST_SAVE_RESTORE); + + wrmsr(MSR_IA32_XFD, 0); __tilerelease(); - GUEST_SYNC(5); + GUEST_SYNC(TEST_SAVE_RESTORE); /* * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in * the xcomp_bv. @@ -154,6 +185,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); + /* #NM test */ + /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); @@ -166,32 +199,33 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); - GUEST_SYNC(6); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - /* Trigger #NM exception */ - __tileloadd(tiledata); - GUEST_SYNC(10); - GUEST_DONE(); -} + /* Trigger #NM exception */ + vector = tileloadd_safe(tiledata); + __GUEST_ASSERT(vector == NM_VECTOR, + "Wanted #NM on tileloadd with XFD[18]=1, got %s", + ex_str(vector)); -void guest_nm_handler(struct ex_regs *regs) -{ - /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ - GUEST_SYNC(7); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); - GUEST_SYNC(8); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(9); + GUEST_SYNC(TEST_SAVE_RESTORE); + + __tileloadd(tiledata); + GUEST_SYNC(TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -200,10 +234,10 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_x86_state *state; + struct kvm_x86_state *tile_state = NULL; int xsave_restore_size; vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; - u32 amx_offset; int ret; /* @@ -228,9 +262,6 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); - /* Register #NM handler */ - vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); - /* amx cfg for guest_code */ amx_cfg = vm_vaddr_alloc_page(vm); memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize()); @@ -244,6 +275,7 @@ int main(int argc, char *argv[]) memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); + int iter = 0; for (;;) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); @@ -253,37 +285,47 @@ int main(int argc, char *argv[]) REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: - switch (uc.args[1]) { - case 1: - case 2: - case 3: - case 5: - case 6: - case 7: - case 8: - fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); - break; - case 4: - case 10: - fprintf(stderr, - "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + ++iter; + if (uc.args[1] & TEST_SAVE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, save tiledata\n", iter); + tile_state = vcpu_save_state(vcpu); + } + if (uc.args[1] & TEST_COMPARE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, check TMM0 contents\n", iter); /* Compacted mode, get amx offset by xsave area * size subtract 8K amx size. */ - amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; - state = vcpu_save_state(vcpu); - void *amx_start = (void *)state->xsave + amx_offset; + u32 amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + void *amx_start = (void *)tile_state->xsave + amx_offset; void *tiles_data = (void *)addr_gva2hva(vm, tiledata); /* Only check TMM0 register, 1 tile */ ret = memcmp(amx_start, tiles_data, TILE_SIZE); TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret); + } + if (uc.args[1] & TEST_RESTORE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, before KVM_SET_XSAVE\n", iter); + vcpu_xsave_set(vcpu, tile_state->xsave); + fprintf(stderr, "GUEST_SYNC #%d, after KVM_SET_XSAVE\n", iter); + } + if (uc.args[1] & TEST_SAVE_RESTORE) { + fprintf(stderr, "GUEST_SYNC #%d, save/restore VM state\n", iter); + state = vcpu_save_state(vcpu); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vcpu, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); kvm_x86_state_cleanup(state); - break; - case 9: - fprintf(stderr, - "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); - break; + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vcpu, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); } break; case UCALL_DONE: @@ -293,22 +335,6 @@ int main(int argc, char *argv[]) TEST_FAIL("Unknown ucall %lu", uc.cmd); } - state = vcpu_save_state(vcpu); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vcpu, ®s1); - - kvm_vm_release(vm); - - /* Restore state in a new VM. */ - vcpu = vm_recreate_with_one_vcpu(vm); - vcpu_load_state(vcpu, state); - kvm_x86_state_cleanup(state); - - memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vcpu, ®s2); - TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), - "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", - (ulong) regs2.rdi, (ulong) regs2.rsi); } done: kvm_vm_free(vm); diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 230b75f6015b..90551650299c 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -237,6 +237,7 @@ struct service_fixture { struct sockaddr_un unix_addr; socklen_t unix_addr_len; }; + struct sockaddr_storage _largest; }; }; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index eee814e09dd7..968a91c927a4 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -4362,22 +4362,24 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) { const char *const path = file1_s1d1; int srv_fd, cli_fd, ruleset_fd; - socklen_t size; - struct sockaddr_un srv_un, cli_un; + struct sockaddr_un srv_un = { + .sun_family = AF_UNIX, + }; + struct sockaddr_un cli_un = { + .sun_family = AF_UNIX, + }; const struct landlock_ruleset_attr attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_IOCTL_DEV, }; /* Sets up a server */ - srv_un.sun_family = AF_UNIX; - strncpy(srv_un.sun_path, path, sizeof(srv_un.sun_path)); - ASSERT_EQ(0, unlink(path)); srv_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, srv_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(srv_un.sun_path); - ASSERT_EQ(0, bind(srv_fd, (struct sockaddr *)&srv_un, size)); + strncpy(srv_un.sun_path, path, sizeof(srv_un.sun_path)); + ASSERT_EQ(0, bind(srv_fd, (struct sockaddr *)&srv_un, sizeof(srv_un))); + ASSERT_EQ(0, listen(srv_fd, 10 /* qlen */)); /* Enables Landlock. */ @@ -4387,24 +4389,18 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) ASSERT_EQ(0, close(ruleset_fd)); /* Sets up a client connection to it */ - cli_un.sun_family = AF_UNIX; cli_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, cli_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - ASSERT_EQ(0, bind(cli_fd, (struct sockaddr *)&cli_un, size)); - - bzero(&cli_un, sizeof(cli_un)); - cli_un.sun_family = AF_UNIX; strncpy(cli_un.sun_path, path, sizeof(cli_un.sun_path)); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - - ASSERT_EQ(0, connect(cli_fd, (struct sockaddr *)&cli_un, size)); + ASSERT_EQ(0, + connect(cli_fd, (struct sockaddr *)&cli_un, sizeof(cli_un))); /* FIONREAD and other IOCTLs should not be forbidden. */ EXPECT_EQ(0, test_fionread_ioctl(cli_fd)); - ASSERT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(srv_fd)); } /* clang-format off */ @@ -7074,8 +7070,8 @@ static int matches_log_fs_extra(struct __test_metadata *const _metadata, return -E2BIG; /* - * It is assume that absolute_path does not contain control characters nor - * spaces, see audit_string_contains_control(). + * It is assumed that absolute_path does not contain control + * characters nor spaces, see audit_string_contains_control(). */ absolute_path = realpath(path, NULL); if (!absolute_path) diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 2a45208551e6..b34b139b3f89 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -121,6 +121,10 @@ static socklen_t get_addrlen(const struct service_fixture *const srv, { switch (srv->protocol.domain) { case AF_UNSPEC: + if (minimal) + return sizeof(sa_family_t); + return sizeof(struct sockaddr_storage); + case AF_INET: return sizeof(srv->ipv4_addr); @@ -758,6 +762,11 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); + /* Tries to bind with too small addrlen. */ + EXPECT_EQ(-EINVAL, bind_variant_addrlen( + bind_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + /* Allowed bind on AF_UNSPEC/INADDR_ANY. */ ret = bind_variant(bind_fd, &self->unspec_any0); if (variant->prot.domain == AF_INET) { @@ -766,6 +775,8 @@ TEST_F(protocol, bind_unspec) TH_LOG("Failed to bind to unspec/any socket: %s", strerror(errno)); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -792,6 +803,8 @@ TEST_F(protocol, bind_unspec) } else { EXPECT_EQ(0, ret); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -801,7 +814,8 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); ret = bind_variant(bind_fd, &self->unspec_srv0); - if (variant->prot.domain == AF_INET) { + if (variant->prot.domain == AF_INET || + variant->prot.domain == AF_INET6) { EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret) @@ -892,7 +906,19 @@ TEST_F(protocol, connect_unspec) EXPECT_EQ(0, close(ruleset_fd)); } - ret = connect_variant(connect_fd, &self->unspec_any0); + /* Try to re-disconnect with a truncated address struct. */ + EXPECT_EQ(-EINVAL, + connect_variant_addrlen( + connect_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + + /* + * Re-disconnect, with a minimal sockaddr struct (just a + * bare af_family=AF_UNSPEC field). + */ + ret = connect_variant_addrlen(connect_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, + true)); if (self->srv0.protocol.domain == AF_UNIX && self->srv0.protocol.type == SOCK_STREAM) { EXPECT_EQ(-EINVAL, ret); diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index 4e356334ecb7..4f64c90583cd 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -86,16 +86,9 @@ static int get_yama_ptrace_scope(void) } /* clang-format off */ -FIXTURE(hierarchy) {}; +FIXTURE(scoped_domains) {}; /* clang-format on */ -FIXTURE_VARIANT(hierarchy) -{ - const bool domain_both; - const bool domain_parent; - const bool domain_child; -}; - /* * Test multiple tracing combinations between a parent process P1 and a child * process P2. @@ -104,155 +97,18 @@ FIXTURE_VARIANT(hierarchy) * restriction is enforced in addition to any Landlock check, which means that * all P2 requests to trace P1 would be denied. */ +#include "scoped_base_variants.h" -/* - * No domain - * - * P1-. P1 -> P2 : allow - * \ P2 -> P1 : allow - * 'P2 - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = false, - .domain_child = false, -}; - -/* - * Child domain - * - * P1--. P1 -> P2 : allow - * \ P2 -> P1 : deny - * .'-----. - * | P2 | - * '------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = false, - .domain_child = true, -}; - -/* - * Parent domain - * .------. - * | P1 --. P1 -> P2 : deny - * '------' \ P2 -> P1 : allow - * ' - * P2 - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = true, - .domain_child = false, -}; - -/* - * Parent + child domain (siblings) - * .------. - * | P1 ---. P1 -> P2 : deny - * '------' \ P2 -> P1 : deny - * .---'--. - * | P2 | - * '------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = true, - .domain_child = true, -}; - -/* - * Same domain (inherited) - * .-------------. - * | P1----. | P1 -> P2 : allow - * | \ | P2 -> P1 : allow - * | ' | - * | P2 | - * '-------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = false, - .domain_child = false, -}; - -/* - * Inherited + child domain - * .-----------------. - * | P1----. | P1 -> P2 : allow - * | \ | P2 -> P1 : deny - * | .-'----. | - * | | P2 | | - * | '------' | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = false, - .domain_child = true, -}; - -/* - * Inherited + parent domain - * .-----------------. - * |.------. | P1 -> P2 : deny - * || P1 ----. | P2 -> P1 : allow - * |'------' \ | - * | ' | - * | P2 | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = true, - .domain_child = false, -}; - -/* - * Inherited + parent and child domain (siblings) - * .-----------------. - * | .------. | P1 -> P2 : deny - * | | P1 . | P2 -> P1 : deny - * | '------'\ | - * | \ | - * | .--'---. | - * | | P2 | | - * | '------' | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_forked_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = true, - .domain_child = true, -}; - -FIXTURE_SETUP(hierarchy) +FIXTURE_SETUP(scoped_domains) { } -FIXTURE_TEARDOWN(hierarchy) +FIXTURE_TEARDOWN(scoped_domains) { } /* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */ -TEST_F(hierarchy, trace) +TEST_F(scoped_domains, trace) { pid_t child, parent; int status, err_proc_read; diff --git a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c index 6825082c079c..72f97648d4a7 100644 --- a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c +++ b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c @@ -543,7 +543,7 @@ TEST_F(scoped_vs_unscoped, unix_scoping) ASSERT_EQ(1, write(pipe_child[1], ".", 1)); ASSERT_EQ(grand_child, waitpid(grand_child, &status, 0)); - EXPECT_EQ(0, close(stream_server_child)) + EXPECT_EQ(0, close(stream_server_child)); EXPECT_EQ(0, close(dgram_server_child)); return; } @@ -779,7 +779,6 @@ FIXTURE_TEARDOWN(various_address_sockets) TEST_F(various_address_sockets, scoped_pathname_sockets) { - socklen_t size_stream, size_dgram; pid_t child; int status; char buf_child, buf_parent; @@ -798,12 +797,8 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) /* Pathname address. */ snprintf(stream_pathname_addr.sun_path, sizeof(stream_pathname_addr.sun_path), "%s", stream_path); - size_stream = offsetof(struct sockaddr_un, sun_path) + - strlen(stream_pathname_addr.sun_path); snprintf(dgram_pathname_addr.sun_path, sizeof(dgram_pathname_addr.sun_path), "%s", dgram_path); - size_dgram = offsetof(struct sockaddr_un, sun_path) + - strlen(dgram_pathname_addr.sun_path); /* Abstract address. */ memset(&stream_abstract_addr, 0, sizeof(stream_abstract_addr)); @@ -841,8 +836,9 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) /* Connects with pathname sockets. */ stream_pathname_socket = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, stream_pathname_socket); - ASSERT_EQ(0, connect(stream_pathname_socket, - &stream_pathname_addr, size_stream)); + ASSERT_EQ(0, + connect(stream_pathname_socket, &stream_pathname_addr, + sizeof(stream_pathname_addr))); ASSERT_EQ(1, write(stream_pathname_socket, "b", 1)); EXPECT_EQ(0, close(stream_pathname_socket)); @@ -850,12 +846,13 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) dgram_pathname_socket = socket(AF_UNIX, SOCK_DGRAM, 0); ASSERT_LE(0, dgram_pathname_socket); err = sendto(dgram_pathname_socket, "c", 1, 0, - &dgram_pathname_addr, size_dgram); + &dgram_pathname_addr, sizeof(dgram_pathname_addr)); EXPECT_EQ(1, err); /* Sends with connection. */ - ASSERT_EQ(0, connect(dgram_pathname_socket, - &dgram_pathname_addr, size_dgram)); + ASSERT_EQ(0, + connect(dgram_pathname_socket, &dgram_pathname_addr, + sizeof(dgram_pathname_addr))); ASSERT_EQ(1, write(dgram_pathname_socket, "d", 1)); EXPECT_EQ(0, close(dgram_pathname_socket)); @@ -910,13 +907,13 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) stream_pathname_socket = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, stream_pathname_socket); ASSERT_EQ(0, bind(stream_pathname_socket, &stream_pathname_addr, - size_stream)); + sizeof(stream_pathname_addr))); ASSERT_EQ(0, listen(stream_pathname_socket, backlog)); dgram_pathname_socket = socket(AF_UNIX, SOCK_DGRAM, 0); ASSERT_LE(0, dgram_pathname_socket); ASSERT_EQ(0, bind(dgram_pathname_socket, &dgram_pathname_addr, - size_dgram)); + sizeof(dgram_pathname_addr))); /* Sets up abstract servers. */ stream_abstract_socket = socket(AF_UNIX, SOCK_STREAM, 0); diff --git a/tools/testing/selftests/landlock/scoped_base_variants.h b/tools/testing/selftests/landlock/scoped_base_variants.h index d3b1fa8a584e..7116728ebc68 100644 --- a/tools/testing/selftests/landlock/scoped_base_variants.h +++ b/tools/testing/selftests/landlock/scoped_base_variants.h @@ -1,8 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Landlock scoped_domains variants + * Landlock scoped_domains test variant definition. * - * See the hierarchy variants from ptrace_test.c + * This file defines a fixture variant "scoped_domains" that has all + * permutations of parent/child process being in separate or shared + * Landlock domain, or not being in a Landlock domain at all. + * + * Scoped access tests can include this file to avoid repeating these + * combinations. * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2019-2020 ANSSI diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 6279893a0adc..f61150d28eb2 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -179,7 +179,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) if (rw && shared && fs_is_unknown(fs_type)) { ksft_print_msg("Unknown filesystem\n"); result = KSFT_SKIP; - return; + break; } /* * R/O pinning or pinning in a private mapping is always diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index 363c1033cc7d..10b686102b79 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -22,12 +22,37 @@ FIXTURE(merge) struct procmap_fd procmap; }; +static char *map_carveout(unsigned int page_size) +{ + return mmap(NULL, 30 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); +} + +static pid_t do_fork(struct procmap_fd *procmap) +{ + pid_t pid = fork(); + + if (pid == -1) + return -1; + if (pid != 0) { + wait(NULL); + return pid; + } + + /* Reopen for child. */ + if (close_procmap(procmap)) + return -1; + if (open_self_procmap(procmap)) + return -1; + + return 0; +} + FIXTURE_SETUP(merge) { self->page_size = psize(); /* Carve out PROT_NONE region to map over. */ - self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, - MAP_ANON | MAP_PRIVATE, -1, 0); + self->carveout = map_carveout(self->page_size); ASSERT_NE(self->carveout, MAP_FAILED); /* Setup PROCMAP_QUERY interface. */ ASSERT_EQ(open_self_procmap(&self->procmap), 0); @@ -36,7 +61,8 @@ FIXTURE_SETUP(merge) FIXTURE_TEARDOWN(merge) { ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); - ASSERT_EQ(close_procmap(&self->procmap), 0); + /* May fail for parent of forked process. */ + close_procmap(&self->procmap); /* * Clear unconditionally, as some tests set this. It is no issue if this * fails (KSM may be disabled for instance). @@ -44,6 +70,44 @@ FIXTURE_TEARDOWN(merge) prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); } +FIXTURE(merge_with_fork) +{ + unsigned int page_size; + char *carveout; + struct procmap_fd procmap; +}; + +FIXTURE_VARIANT(merge_with_fork) +{ + bool forked; +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, forked) +{ + .forked = true, +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, unforked) +{ + .forked = false, +}; + +FIXTURE_SETUP(merge_with_fork) +{ + self->page_size = psize(); + self->carveout = map_carveout(self->page_size); + ASSERT_NE(self->carveout, MAP_FAILED); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); +} + +FIXTURE_TEARDOWN(merge_with_fork) +{ + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); + ASSERT_EQ(close_procmap(&self->procmap), 0); + /* See above. */ + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); +} + TEST_F(merge, mprotect_unfaulted_left) { unsigned int page_size = self->page_size; @@ -322,8 +386,8 @@ TEST_F(merge, forked_target_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -344,19 +408,10 @@ TEST_F(merge, forked_target_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -386,8 +441,8 @@ TEST_F(merge, forked_source_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -408,19 +463,10 @@ TEST_F(merge, forked_source_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -1171,4 +1217,288 @@ TEST_F(merge, mremap_correct_placed_faulted) ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); } +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |------------| + * | \ | + * |-----------| | / |---------| + * | unfaulted | v \ | faulted | + * |-----------| / |---------| + * B \ A + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |---------------------------| + * | \ | + * | |-----------| / |---------| + * v | unfaulted | \ | faulted | + * |-----------| / |---------| + * B \ A + * + * Then unmap VMA A to trigger the bug. + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b, *ptr_c; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | unfaulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + /* Fault it in. */ + ptr_b[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMAs A, C in position, + * unfaulted. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA C into place. */ + ptr_c = mmap(&self->carveout[page_size + 3 * page_size + 3 * page_size], + 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_c, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 9 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); + + /* If forked, B and C should also not have merged. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 3 * page_size); + } +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_faulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + char *ptr_a, *ptr_b, *ptr_bc; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | faulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* + * Map VMA B and C into place. We have to map them together so their + * anon_vma is the same and the vma->vm_pgoff's are correctly aligned. + */ + ptr_bc = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_bc, MAP_FAILED); + + /* Fault it in. */ + ptr_bc[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move VMA B out the way (splitting VMA BC) so we can place VMA A + * in position, unfaulted, and leave the remainder of the VMA we just + * moved in place, faulted, as VMA C. + */ + ptr_b = mremap(ptr_bc, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged. A,B,C if unforked, B, C if forked. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 6 * page_size); + } else { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + 9 * page_size); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b66ba04f19d9..45c4ea381bc3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -48,6 +48,7 @@ TEST_PROGS := \ ipv6_flowlabel.sh \ ipv6_force_forwarding.sh \ ipv6_route_update_soft_lockup.sh \ + ipvtap_test.sh \ l2_tos_ttl_inherit.sh \ l2tp.sh \ link_netns.py \ diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 3ef209cacb8e..663744305e52 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -73,6 +73,8 @@ # +------------------------+ #============================================================================== +source lib.sh + readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) @@ -246,14 +248,15 @@ test_ipv6_forward() send_mcast4() { - sleep 2 + sleep 5 + wait_local_port_listen ${LISTENER} 4000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' & } send_mcast6() { - sleep 2 + wait_local_port_listen ${LISTENER} 6000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' & } diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 1e1f253118f5..b84362b9b508 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,6 +48,7 @@ CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SIT=y CONFIG_IPV6_VTI=y CONFIG_IPVLAN=m +CONFIG_IPVTAP=m CONFIG_KALLSYMS=y CONFIG_L2TP=m CONFIG_L2TP_ETH=m @@ -116,6 +117,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_PSAMPLE=m CONFIG_RPS=y CONFIG_SYSFS=y +CONFIG_TAP=m CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_TEST_BPF=m diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh index ec2d6ceb1f08..c01be076b210 100755 --- a/tools/testing/selftests/net/fib-onlink-tests.sh +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -120,7 +120,7 @@ log_subsection() run_cmd() { - local cmd="$*" + local cmd="$1" local out local rc @@ -145,7 +145,7 @@ get_linklocal() local pfx local addr - addr=$(${pfx} ip -6 -br addr show dev ${dev} | \ + addr=$(${pfx} ${IP} -6 -br addr show dev ${dev} | \ awk '{ for (i = 3; i <= NF; ++i) { if ($i ~ /^fe80/) @@ -173,58 +173,48 @@ setup() set -e - # create namespace - setup_ns PEER_NS + # create namespaces + setup_ns ns1 + IP="ip -netns $ns1" + setup_ns ns2 # add vrf table - ip li add ${VRF} type vrf table ${VRF_TABLE} - ip li set ${VRF} up - ip ro add table ${VRF_TABLE} unreachable default metric 8192 - ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} li add ${VRF} type vrf table ${VRF_TABLE} + ${IP} li set ${VRF} up + ${IP} ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} -6 ro add table ${VRF_TABLE} unreachable default metric 8192 # create test interfaces - ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} - ip li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} - ip li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} - ip li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} + ${IP} li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} + ${IP} li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} + ${IP} li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} + ${IP} li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} # enslave vrf interfaces for n in 5 7; do - ip li set ${NETIFS[p${n}]} vrf ${VRF} + ${IP} li set ${NETIFS[p${n}]} vrf ${VRF} done # add addresses for n in 1 3 5 7; do - ip li set ${NETIFS[p${n}]} up - ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} up + ${IP} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ${IP} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done # move peer interfaces to namespace and add addresses for n in 2 4 6 8; do - ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up - ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} netns ${ns2} up + ip -netns $ns2 addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip -netns $ns2 addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done - ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} - ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} + ${IP} -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} + ${IP} -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} set +e } -cleanup() -{ - # make sure we start from a clean slate - cleanup_ns ${PEER_NS} 2>/dev/null - for n in 1 3 5 7; do - ip link del ${NETIFS[p${n}]} 2>/dev/null - done - ip link del ${VRF} 2>/dev/null - ip ro flush table ${VRF_TABLE} - ip -6 ro flush table ${VRF_TABLE} -} - ################################################################################ # IPv4 tests # @@ -241,7 +231,7 @@ run_ip() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 via "${gw}" "${dev}" onlink + run_cmd "${IP} ro add table ${table} ${prefix}/32 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -257,8 +247,8 @@ run_ip_mpath() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} ro add table ${table} ${prefix}/32 \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -339,7 +329,7 @@ run_ip6() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 via "${gw}" "${dev}" onlink + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -353,8 +343,8 @@ run_ip6_mpath() local exp_rc="$6" local desc="$7" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 "${opts}" \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 ${opts} \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -491,10 +481,9 @@ do esac done -cleanup setup run_onlink_tests -cleanup +cleanup_ns ${ns1} ${ns2} if [ "$TESTS" != "none" ]; then printf "\nTests passed: %3d\n" ${nsuccess} diff --git a/tools/testing/selftests/net/ipvtap_test.sh b/tools/testing/selftests/net/ipvtap_test.sh new file mode 100755 index 000000000000..354ca7ce8584 --- /dev/null +++ b/tools/testing/selftests/net/ipvtap_test.sh @@ -0,0 +1,168 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Simple tests for ipvtap + + +# +# The testing environment looks this way: +# +# |------HNS-------| |------PHY-------| +# | veth<----------------->veth | +# |------|--|------| |----------------| +# | | +# | | |-----TST0-------| +# | |------------|----ipvlan | +# | |----------------| +# | +# | |-----TST1-------| +# |---------------|----ipvlan | +# |----------------| +# + +ALL_TESTS=" + test_ip_set +" + +source lib.sh + +DEBUG=0 + +VETH_HOST=vethtst.h +VETH_PHY=vethtst.p + +NS_COUNT=32 +IP_ITERATIONS=1024 +IPSET_TIMEOUT="60s" + +ns_run() { + ns=$1 + shift + if [[ "$ns" == "global" ]]; then + "$@" >/dev/null + else + ip netns exec "$ns" "$@" >/dev/null + fi +} + +test_ip_setup_env() { + setup_ns NS_PHY + setup_ns HST_NS + + # setup simulated other-host (phy) and host itself + ns_run "$HST_NS" ip link add $VETH_HOST type veth peer name $VETH_PHY \ + netns "$NS_PHY" >/dev/null + ns_run "$HST_NS" ip link set $VETH_HOST up + ns_run "$NS_PHY" ip link set $VETH_PHY up + + for ((i=0; i<NS_COUNT; i++)); do + setup_ns ipvlan_ns_$i + ns="ipvlan_ns_$i" + if [ "$DEBUG" = "1" ]; then + echo "created NS ${!ns}" + fi + if ! ns_run "$HST_NS" ip link add netns ${!ns} ipvlan0 \ + link $VETH_HOST \ + type ipvtap mode l2 bridge; then + exit_error "FAIL: Failed to configure ipvlan link." + fi + done +} + +test_ip_cleanup_env() { + ns_run "$HST_NS" ip link del $VETH_HOST + cleanup_all_ns +} + +exit_error() { + echo "$1" + exit $ksft_fail +} + +rnd() { + echo $(( RANDOM % 32 + 16 )) +} + +test_ip_set_thread() { + # Here we are trying to create some IP conflicts between namespaces. + # If just add/remove IP, nothing interesting will happen. + # But if add random IP and then remove random IP, + # eventually conflicts start to apear. + ip link set ipvlan0 up + for ((i=0; i<IP_ITERATIONS; i++)); do + v=$(rnd) + ip a a "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a a "fc00::$v/64" dev ipvlan0 2>/dev/null + v=$(rnd) + ip a d "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a d "fc00::$v/64" dev ipvlan0 2>/dev/null + done +} + +test_ip_set() { + RET=0 + + trap test_ip_cleanup_env EXIT + + test_ip_setup_env + + declare -A ns_pids + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ns_run ${!ns} timeout "$IPSET_TIMEOUT" \ + bash -c "$0 test_ip_set_thread"& + ns_pids[$i]=$! + done + + for ((i=0; i<NS_COUNT; i++)); do + wait "${ns_pids[$i]}" + done + + declare -A all_ips + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ip_output=$(ip netns exec ${!ns} ip a l dev ipvlan0 | grep inet) + while IFS= read -r nsip_out; do + if [[ -z $nsip_out ]]; then + continue; + fi + nsip=$(awk '{print $2}' <<< "$nsip_out") + if [[ -v all_ips[$nsip] ]]; then + RET=$ksft_fail + log_test "conflict for $nsip" + return "$RET" + else + all_ips[$nsip]=$i + fi + done <<< "$ip_output" + done + + if [ "$DEBUG" = "1" ]; then + for key in "${!all_ips[@]}"; do + echo "$key: ${all_ips[$key]}" + done + fi + + trap - EXIT + test_ip_cleanup_env + + log_test "test multithreaded ip set" +} + +if [[ "$1" == "-d" ]]; then + DEBUG=1 + shift +fi + +if [[ "$1" == "-t" ]]; then + shift + TESTS="$*" +fi + +if [[ "$1" == "test_ip_set_thread" ]]; then + test_ip_set_thread +else + require_command ip + + tests_run +fi diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json index e5cc31f265f8..0179c57104ad 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json @@ -81,5 +81,30 @@ "$TC qdisc del dev $DUMMY handle 1: root", "$IP link del dev $DUMMY" ] + }, + { + "id": "124e", + "name": "Try to add teql as a child qdisc", + "category": [ + "qdisc", + "ets", + "tbf" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: qfq", + "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 15 maxpkt 16384" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1:1 handle 2:1 teql0", + "expExitCode": "2", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:1", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1:" + ] } ] diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 185ba553686a..f197ad9cc262 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -753,7 +753,7 @@ static int ublk_thread_is_idle(struct ublk_thread *t) static int ublk_thread_is_done(struct ublk_thread *t) { - return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t); + return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t) && !t->cmd_inflight; } static inline void ublksrv_handle_tgt_cqe(struct ublk_thread *t, @@ -1054,7 +1054,9 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) } if (ret < 0) { ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret); - goto fail; + /* stop device so that inflight uring_cmd can be cancelled */ + ublk_ctrl_stop_dev(dev); + goto fail_start; } ublk_ctrl_get_info(dev); @@ -1062,7 +1064,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) ublk_ctrl_dump(dev); else ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id); - +fail_start: /* wait until we are terminated */ for (i = 0; i < dev->nthreads; i++) pthread_join(tinfo[i].thread, &thread_ret); @@ -1272,7 +1274,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) } ret = ublk_start_daemon(ctx, dev); - ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\b", ret); + ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret); if (ret < 0) ublk_ctrl_del_dev(dev); @@ -1618,6 +1620,7 @@ int main(int argc, char *argv[]) int option_idx, opt; const char *cmd = argv[1]; struct dev_ctx ctx = { + ._evtfd = -1, .queue_depth = 128, .nr_hw_queues = 2, .dev_id = -1, diff --git a/tools/testing/selftests/vDSO/vgetrandom-chacha.S b/tools/testing/selftests/vDSO/vgetrandom-chacha.S index a4a82e1c28a9..8c3cbf4dfd6a 100644 --- a/tools/testing/selftests/vDSO/vgetrandom-chacha.S +++ b/tools/testing/selftests/vDSO/vgetrandom-chacha.S @@ -14,7 +14,7 @@ #elif defined(__riscv) && __riscv_xlen == 64 #include "../../../../arch/riscv/kernel/vdso/vgetrandom-chacha.S" #elif defined(__s390x__) -#include "../../../../arch/s390/kernel/vdso64/vgetrandom-chacha.S" +#include "../../../../arch/s390/kernel/vdso/vgetrandom-chacha.S" #elif defined(__x86_64__) #include "../../../../arch/x86/entry/vdso/vgetrandom-chacha.S" #endif diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 83148875a12c..434065215d12 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -36,6 +36,7 @@ BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall $(KHDR_INCLUDES) +CFLAGS += -I $(top_srcdir)/tools/testing/selftests/ # call32_from_64 in thunks.S uses absolute addresses. ifeq ($(CAN_BUILD_WITH_NOPIE),1) diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index d843643ced6b..9430ef5b8bc3 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -511,6 +511,18 @@ void run_tests(const struct test_case *test_cases, printf("ok\n"); } + + printf("All tests have been executed. Waiting other peer..."); + fflush(stdout); + + /* + * Final full barrier, to ensure that all tests have been run and + * that even the last one has been successful on both sides. + */ + control_writeln("COMPLETED"); + control_expectln("COMPLETED"); + + printf("ok\n"); } void list_tests(const struct test_case *test_cases) diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 142c02a6834a..bf633cde82b0 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -25,7 +25,7 @@ enum transport { }; static const char * const transport_ksyms[] = { - #define x(name, symbol) "d " symbol "_transport", + #define x(name, symbol) " " symbol "_transport", KNOWN_TRANSPORTS(x) #undef x }; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index bbe3723babdc..5bd20ccd9335 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -347,10 +347,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) } #define SOCK_BUF_SIZE (2 * 1024 * 1024) +#define SOCK_BUF_SIZE_SMALL (64 * 1024) #define MAX_MSG_PAGES 4 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { + unsigned long long sock_buf_size; unsigned long curr_hash; size_t max_msg_size; int page_size; @@ -363,6 +365,16 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + /* Wait, until receiver sets buffer size. */ control_expectln("SRVREADY"); @@ -2219,6 +2231,101 @@ static void test_stream_accepted_setsockopt_server(const struct test_opts *opts) close(fd); } +static void test_stream_tx_credit_bounds_client(const struct test_opts *opts) +{ + unsigned long long sock_buf_size; + size_t total = 0; + char buf[4096]; + int fd; + + memset(buf, 'A', sizeof(buf)); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + sock_buf_size = SOCK_BUF_SIZE_SMALL; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + + if (fcntl(fd, F_SETFL, fcntl(fd, F_GETFL, 0) | O_NONBLOCK) < 0) { + perror("fcntl(F_SETFL)"); + exit(EXIT_FAILURE); + } + + control_expectln("SRVREADY"); + + for (;;) { + ssize_t sent = send(fd, buf, sizeof(buf), 0); + + if (sent == 0) { + fprintf(stderr, "unexpected EOF while sending bytes\n"); + exit(EXIT_FAILURE); + } + + if (sent < 0) { + if (errno == EINTR) + continue; + + if (errno == EAGAIN || errno == EWOULDBLOCK) + break; + + perror("send"); + exit(EXIT_FAILURE); + } + + total += sent; + } + + control_writeln("CLIDONE"); + close(fd); + + /* We should not be able to send more bytes than the value set as + * local buffer size. + */ + if (total > sock_buf_size) { + fprintf(stderr, + "TX credit too large: queued %zu bytes (expected <= %llu)\n", + total, sock_buf_size); + exit(EXIT_FAILURE); + } +} + +static void test_stream_tx_credit_bounds_server(const struct test_opts *opts) +{ + unsigned long long sock_buf_size; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + + control_writeln("SRVREADY"); + control_expectln("CLIDONE"); + + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -2403,6 +2510,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_accepted_setsockopt_client, .run_server = test_stream_accepted_setsockopt_server, }, + { + .name = "SOCK_STREAM virtio MSG_ZEROCOPY coalescence corruption", + .run_client = test_stream_msgzcopy_mangle_client, + .run_server = test_stream_msgzcopy_mangle_server, + }, + { + .name = "SOCK_STREAM TX credit bounds", + .run_client = test_stream_tx_credit_bounds_client, + .run_server = test_stream_tx_credit_bounds_server, + }, {}, }; diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c index 9d9a6cb9614a..a31ddfc1cd0c 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.c +++ b/tools/testing/vsock/vsock_test_zerocopy.c @@ -9,14 +9,18 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <unistd.h> #include <poll.h> #include <linux/errqueue.h> #include <linux/kernel.h> +#include <linux/sockios.h> +#include <linux/time64.h> #include <errno.h> #include "control.h" +#include "timeout.h" #include "vsock_test_zerocopy.h" #include "msg_zerocopy_common.h" @@ -356,3 +360,73 @@ void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts) control_expectln("DONE"); close(fd); } + +#define GOOD_COPY_LEN 128 /* net/vmw_vsock/virtio_transport_common.c */ + +void test_stream_msgzcopy_mangle_client(const struct test_opts *opts) +{ + char sbuf1[PAGE_SIZE + 1], sbuf2[GOOD_COPY_LEN]; + unsigned long hash; + struct pollfd fds; + int fd, i; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + + memset(sbuf1, 'x', sizeof(sbuf1)); + send_buf(fd, sbuf1, sizeof(sbuf1), 0, sizeof(sbuf1)); + + for (i = 0; i < sizeof(sbuf2); i++) + sbuf2[i] = rand() & 0xff; + + send_buf(fd, sbuf2, sizeof(sbuf2), MSG_ZEROCOPY, sizeof(sbuf2)); + + hash = hash_djb2(sbuf2, sizeof(sbuf2)); + control_writeulong(hash); + + fds.fd = fd; + fds.events = 0; + + if (poll(&fds, 1, TIMEOUT * MSEC_PER_SEC) != 1 || + !(fds.revents & POLLERR)) { + perror("poll"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +void test_stream_msgzcopy_mangle_server(const struct test_opts *opts) +{ + unsigned long local_hash, remote_hash; + char rbuf[PAGE_SIZE + 1]; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Wait, don't race the (buggy) skbs coalescence. */ + vsock_ioctl_int(fd, SIOCINQ, PAGE_SIZE + 1 + GOOD_COPY_LEN); + + /* Discard the first packet. */ + recv_buf(fd, rbuf, PAGE_SIZE + 1, 0, PAGE_SIZE + 1); + + recv_buf(fd, rbuf, GOOD_COPY_LEN, 0, GOOD_COPY_LEN); + remote_hash = control_readulong(); + local_hash = hash_djb2(rbuf, GOOD_COPY_LEN); + + if (local_hash != remote_hash) { + fprintf(stderr, "Data received corrupted\n"); + exit(EXIT_FAILURE); + } + + close(fd); +} diff --git a/tools/testing/vsock/vsock_test_zerocopy.h b/tools/testing/vsock/vsock_test_zerocopy.h index 3ef2579e024d..d46c91a69f16 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.h +++ b/tools/testing/vsock/vsock_test_zerocopy.h @@ -12,4 +12,7 @@ void test_seqpacket_msgzcopy_server(const struct test_opts *opts); void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts); void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts); +void test_stream_msgzcopy_mangle_client(const struct test_opts *opts); +void test_stream_msgzcopy_mangle_server(const struct test_opts *opts); + #endif /* VSOCK_TEST_ZEROCOPY_H */ |