- Linux-kselftest-mirror - lists.linaro.org

[PATCH net-next v6 3/3] selftests: net: add SCM_PIDFD / SO_PEERPIDFD test

by Alexander Mikhalitsyn

Basic test to check consistency between: - SCM_CREDENTIALS and SCM_PIDFD - SO_PEERCRED and SO_PEERPIDFD Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Leon Romanovsky <leon(a)kernel.org> Cc: David Ahern <dsahern(a)kernel.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Kees Cook <keescook(a)chromium.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: linux-arch(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- v3: - started using kselftest lib (thanks to Kuniyuki Iwashima for suggestion/review) - now test covers abstract sockets too and SOCK_DGRAM sockets --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/af_unix/Makefile | 3 +- .../testing/selftests/net/af_unix/scm_pidfd.c | 430 ++++++++++++++++++ 3 files changed, 433 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/af_unix/scm_pidfd.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa62034..83fd1ebd34ec 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -26,6 +26,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +scm_pidfd sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 1e4b397cece6..221c387a7d7f 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,4 @@ -TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c new file mode 100644 index 000000000000..a86222143d79 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +#define _GNU_SOURCE +#include <error.h> +#include <limits.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/socket.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../../kselftest_harness.h" + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \ + clean_errno(), ##__VA_ARGS__) + +#ifndef SCM_PIDFD +#define SCM_PIDFD 0x04 +#endif + +static void child_die() +{ + exit(1); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || buffer[i] == '\t' || + buffer[i] == '\n' || buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +/* borrowed (with all helpers) from pidfd/pidfd_open_test.c */ +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +static int cmsg_check(int fd) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec iov; + struct ucred *ucred = NULL; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + int *pidfd = NULL; + pid_t parent_pid; + int err; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; + } + + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + ucred = (void *)CMSG_DATA(cmsg); + } + } + + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } + + if (!pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + return 1; + } + + return 0; +} + +struct sock_addr { + char sock_name[32]; + struct sockaddr_un listen_addr; + socklen_t addrlen; +}; + +FIXTURE(scm_pidfd) +{ + int server; + pid_t client_pid; + int startup_pipe[2]; + struct sock_addr server_addr; + struct sock_addr *client_addr; +}; + +FIXTURE_VARIANT(scm_pidfd) +{ + int type; + bool abstract; +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) +{ + .type = SOCK_DGRAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) +{ + .type = SOCK_DGRAM, + .abstract = 1, +}; + +FIXTURE_SETUP(scm_pidfd) +{ + self->client_addr = mmap(NULL, sizeof(*self->client_addr), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, self->client_addr); +} + +FIXTURE_TEARDOWN(scm_pidfd) +{ + close(self->server); + + kill(self->client_pid, SIGKILL); + waitpid(self->client_pid, NULL, 0); + + if (!variant->abstract) { + unlink(self->server_addr.sock_name); + unlink(self->client_addr->sock_name); + } +} + +static void fill_sockaddr(struct sock_addr *addr, bool abstract) +{ + char *sun_path_buf = (char *)&addr->listen_addr.sun_path; + + addr->listen_addr.sun_family = AF_UNIX; + addr->addrlen = offsetof(struct sockaddr_un, sun_path); + snprintf(addr->sock_name, sizeof(addr->sock_name), "scm_pidfd_%d", getpid()); + addr->addrlen += strlen(addr->sock_name); + if (abstract) { + *sun_path_buf = '\0'; + addr->addrlen++; + sun_path_buf++; + } else { + unlink(addr->sock_name); + } + memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); +} + +static void client(FIXTURE_DATA(scm_pidfd) *self, + const FIXTURE_VARIANT(scm_pidfd) *variant) +{ + int err; + int cfd; + socklen_t len; + struct ucred peer_cred; + int peer_pidfd; + pid_t peer_pid; + int on = 0; + + cfd = socket(AF_UNIX, variant->type, 0); + if (cfd < 0) { + log_err("socket"); + child_die(); + } + + if (variant->type == SOCK_DGRAM) { + fill_sockaddr(self->client_addr, variant->abstract); + + if (bind(cfd, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen)) { + log_err("bind"); + child_die(); + } + } + + if (connect(cfd, (struct sockaddr *)&self->server_addr.listen_addr, + self->server_addr.addrlen) != 0) { + log_err("connect"); + child_die(); + } + + on = 1; + if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + child_die(); + } + + if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + child_die(); + } + + close(self->startup_pipe[1]); + + if (cmsg_check(cfd)) { + log_err("cmsg_check failed"); + child_die(); + } + + /* skip further for SOCK_DGRAM as it's not applicable */ + if (variant->type == SOCK_DGRAM) + return; + + len = sizeof(peer_cred); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERCRED, &peer_cred, &len)) { + log_err("Failed to get SO_PEERCRED"); + child_die(); + } + + len = sizeof(peer_pidfd); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERPIDFD, &peer_pidfd, &len)) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } + + /* pid from SO_PEERCRED should point to the parent process PID */ + if (peer_cred.pid != getppid()) { + log_err("peer_cred.pid != getppid(): %d != %d", peer_cred.pid, getppid()); + child_die(); + } + + peer_pid = get_pid_from_fdinfo_file(peer_pidfd, + "Pid:", sizeof("Pid:") - 1); + if (peer_pid != peer_cred.pid) { + log_err("peer_pid != peer_cred.pid: %d != %d", peer_pid, peer_cred.pid); + child_die(); + } +} + +TEST_F(scm_pidfd, test) +{ + int err; + int pfd; + int child_status = 0; + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_NE(-1, self->server); + + fill_sockaddr(&self->server_addr, variant->abstract); + + err = bind(self->server, (struct sockaddr *)&self->server_addr.listen_addr, self->server_addr.addrlen); + ASSERT_EQ(0, err); + + if (variant->type == SOCK_STREAM) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + err = pipe(self->startup_pipe); + ASSERT_NE(-1, err); + + self->client_pid = fork(); + ASSERT_NE(-1, self->client_pid); + if (self->client_pid == 0) { + close(self->server); + close(self->startup_pipe[0]); + client(self, variant); + exit(0); + } + close(self->startup_pipe[1]); + + if (variant->type == SOCK_STREAM) { + pfd = accept(self->server, NULL, NULL); + ASSERT_NE(-1, pfd); + } else { + pfd = self->server; + } + + /* wait until the child arrives at checkpoint */ + read(self->startup_pipe[0], &err, sizeof(int)); + close(self->startup_pipe[0]); + + if (variant->type == SOCK_DGRAM) { + err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen); + ASSERT_NE(-1, err); + } else { + err = send(pfd, "x", sizeof(char), 0); + ASSERT_NE(-1, err); + } + + close(pfd); + waitpid(self->client_pid, &child_status, 0); + ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); +} + +TEST_HARNESS_MAIN -- 2.34.1

2 years, 4 months

1
0
0 0

[RFC PATCH v2 00/11] Intel IA32_SPEC_CTRL Virtualization

by Chao Gao

Changes since RFC v1: * add two kselftests (patch 10-11) * set virtual MSRs also on APs [Pawan] * enable "virtualize IA32_SPEC_CTRL" for L2 to prevent L2 from changing some bits of IA32_SPEC_CTRL (patch 4) * other misc cleanup and cosmetic changes RFC v1: https://lore.kernel.org/lkml/20221210160046.2608762-1-chen.zhang@intel.com/ This series introduces "virtualize IA32_SPEC_CTRL" support. Here are introduction and use cases of this new feature. ### Virtualize IA32_SPEC_CTRL "Virtualize IA32_SPEC_CTRL" [1] is a new VMX feature on Intel CPUs. This feature allows VMM to lock some bits of IA32_SPEC_CTRL MSR even when the MSR is pass-thru'd to a guest. ### Use cases of "virtualize IA32_SPEC_CTRL" [2] Software mitigations like Retpoline and software BHB-clearing sequence depend on CPU microarchitectures. And guest cannot know exactly the underlying microarchitecture. When a guest is migrated between processors of different microarchitectures, software mitigations which work perfectly on previous microachitecture may be not effective on the new one. To fix the problem, some hardware mitigations should be used in conjunction with software mitigations. Using virtual IA32_SPEC_CTRL, VMM can enforce hardware mitigations transparently to guests and avoid those hardware mitigations being unintentionally disabled when guest changes IA32_SPEC_CTRL MSR. ### Intention of this series This series adds the capability of enforcing hardware mitigations for guests transparently and efficiently (i.e., without intecepting IA32_SPEC_CTRL MSR accesses) to kvm. The capability can be used to solve the VM migration issue in a pool consisting of processors of different microarchitectures. Specifically, below are two target scenarios of this series: Scenario 1: If retpoline is used by a VM to mitigate IMBTI in CPL0, VMM can set RRSBA_DIS_S on parts enumerates RRSBA. Note that the VM is presented with a microarchitecture doesn't enumerate RRSBA. Scenario 2: If a VM uses software BHB-clearing sequence on transitions into CPL0 to mitigate BHI, VMM can use "virtualize IA32_SPEC_CTRL" to set BHI_DIS_S on new parts which doesn't enumerate BHI_NO. Intel defines some virtual MSRs [2] for guests to report in-use software mitigations. This allows guests to opt in VMM's deploying hardware mitigations for them if the guests are either running or later migrated to a system on which in-use software mitigations are not effective. The virtual MSRs interface is also added in this series. ### Organization of this series 1. Patch 1-3 Advertise RRSBA_CTRL and BHI_CTRL to guest 2. Patch 4 Add "virtualize IA32_SPEC_CTRL" support 3. Patch 5-9 Allow guests to report in-use software mitigations to KVM so that KVM can enable hardware mitigations for guests. 4. Patch 10-11 Add kselftest for virtual MSRs and IA32_SPEC_CTRL [1]: https://cdrdv2.intel.com/v1/dl/getContent/671368 Ref. #319433-047 Chapter 12 [2]: https://www.intel.com/content/www/us/en/developer/articles/technical/softwa… Chao Gao (3): KVM: VMX: Advertise MITI_ENUM_RETPOLINE_S_SUPPORT KVM: selftests: Add tests for virtual enumeration/mitigation MSRs KVM: selftests: Add tests for IA32_SPEC_CTRL MSR Pawan Gupta (1): x86/bugs: Use Virtual MSRs to request hardware mitigations Zhang Chen (7): x86/msr-index: Add bit definitions for BHI_DIS_S and BHI_NO KVM: x86: Advertise CPUID.7.2.EDX and RRSBA_CTRL support KVM: x86: Advertise BHI_CTRL support KVM: VMX: Add IA32_SPEC_CTRL virtualization support KVM: x86: Advertise ARCH_CAP_VIRTUAL_ENUM support KVM: VMX: Advertise MITIGATION_CTRL support KVM: VMX: Advertise MITI_CTRL_BHB_CLEAR_SEQ_S_SUPPORT arch/x86/include/asm/msr-index.h | 33 +++- arch/x86/include/asm/vmx.h | 5 + arch/x86/include/asm/vmxfeatures.h | 2 + arch/x86/kernel/cpu/bugs.c | 25 +++ arch/x86/kvm/cpuid.c | 22 ++- arch/x86/kvm/reverse_cpuid.h | 8 + arch/x86/kvm/svm/svm.c | 3 + arch/x86/kvm/vmx/capabilities.h | 5 + arch/x86/kvm/vmx/nested.c | 13 ++ arch/x86/kvm/vmx/vmcs.h | 2 + arch/x86/kvm/vmx/vmx.c | 112 ++++++++++- arch/x86/kvm/vmx/vmx.h | 43 ++++- arch/x86/kvm/x86.c | 19 +- tools/arch/x86/include/asm/msr-index.h | 37 +++- tools/testing/selftests/kvm/Makefile | 2 + .../selftests/kvm/include/x86_64/processor.h | 5 + .../selftests/kvm/x86_64/spec_ctrl_msr_test.c | 178 ++++++++++++++++++ .../kvm/x86_64/virtual_mitigation_msr_test.c | 175 +++++++++++++++++ 18 files changed, 676 insertions(+), 13 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/spec_ctrl_msr_test.c create mode 100644 tools/testing/selftests/kvm/x86_64/virtual_mitigation_msr_test.c base-commit: 400d2132288edbd6d500f45eab5d85526ca94e46 -- 2.40.0

2 years, 4 months

4
5
0 0

W sprawie samochodu

by Konrad Trojanowski

Dzień dobry, chcielibyśmy zapewnić Państwu kompleksowe rozwiązania, jeśli chodzi o system monitoringu GPS. Precyzyjne monitorowanie pojazdów na mapach cyfrowych, śledzenie ich parametrów eksploatacyjnych w czasie rzeczywistym oraz kontrola paliwa to kluczowe funkcjonalności naszego systemu. Organizowanie pracy pracowników jest dzięki temu prostsze i bardziej efektywne, a oszczędności i optymalizacja w zakresie ponoszonych kosztów, mają dla każdego przedsiębiorcy ogromne znaczenie. Dopasujemy naszą ofertę do Państwa oczekiwań i potrzeb organizacji. Czy moglibyśmy porozmawiać o naszej propozycji? Pozdrawiam Konrad Trojanowski

2 years, 4 months

1
0
0 0

[PATCH] tools/nolibc/unistd: add syscall()

by Thomas Weißschuh

syscall() is used by "normal" libcs to allow users to directly call syscalls. By having the same syntax inside nolibc users can more easily write code that works with different libcs. The macro logic is adapted from systemtaps STAP_PROBEV() macro that is released in the public domain / CC0. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- tools/include/nolibc/unistd.h | 15 +++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 2 ++ 2 files changed, 17 insertions(+) diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index ac7d53d986cd..6773e83c16a0 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -56,6 +56,21 @@ int tcsetpgrp(int fd, pid_t pid) return ioctl(fd, TIOCSPGRP, &pid); } +#define _syscall(N, ...) \ +({ \ + int _ret = my_syscall##N(__VA_ARGS__); \ + if (_ret < 0) { \ + SET_ERRNO(-_ret); \ + _ret = -1; \ + } \ + _ret; \ +}) + +#define _sycall_narg(...) __syscall_narg(__VA_ARGS__, 6, 5, 4, 3, 2, 1, 0) +#define __syscall_narg(_0, _1, _2, _3, _4, _5, _6, N, ...) N +#define _syscall_n(N, ...) _syscall(N, __VA_ARGS__) +#define syscall(...) _syscall_n(_sycall_narg(__VA_ARGS__), ##__VA_ARGS__) + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index f042a6436b6b..54bf91847af3 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -588,6 +588,8 @@ int run_syscall(int min, int max) CASE_TEST(waitpid_child); EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break; CASE_TEST(write_badf); EXPECT_SYSER(1, write(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(write_zero); EXPECT_SYSZR(1, write(1, &tmp, 0)); break; + CASE_TEST(syscall_noargs); EXPECT_SYSEQ(1, syscall(__NR_getpid), getpid()); break; + CASE_TEST(syscall_args); EXPECT_SYSER(1, syscall(__NR_fstat, 0, NULL), -1, EFAULT); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ --- base-commit: 063dcc53b416ae1e89f767330feab3d0842943ed change-id: 20230517-nolibc-syscall-bd13da6468c6 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

2 years, 5 months

2
1
0 0

[PATCH v2 0/4] Optimize mremap during mutual alignment within PMD

by Joel Fernandes (Google)

Hello, Here is v2 of the mremap start address optimization / fix for exec warning. v1->v2: 1. Trigger the optimization for mremaps smaller than a PMD. I tested by tracing that it works correctly. 2. Fix issue with bogus return value found by Linus if we broke out of the above loop for the first PMD itself. Description of patches: These patches optimizes the start addresses in move_page_tables() and tests the changes. It addresses a warning [1] that occurs due to a downward, overlapping move on a mutually-aligned offset within a PMD during exec. By initiating the copy process at the PMD level when such alignment is present, we can prevent this warning and speed up the copying process at the same time. Linus Torvalds suggested this idea. Please check the individual patches for more details. thanks, - Joel [1] https://lore.kernel.org/all/ZB2GTBD%2FLWTrkOiO@dhcp22.suse.cz/ Joel Fernandes (Google) (4): mm/mremap: Optimize the start addresses in move_page_tables() selftests: mm: Fix failure case when new remap region was not found selftests: mm: Add a test for mutually aligned moves > PMD size selftests: mm: Add a test for remapping to area immediately after existing mapping mm/mremap.c | 56 +++++++++++++++++++ tools/testing/selftests/mm/mremap_test.c | 69 +++++++++++++++++++++--- 2 files changed, 119 insertions(+), 6 deletions(-) -- 2.40.1.698.g37aff9b760-goog

2 years, 5 months

3
13
0 0

from nina coulibaly

by nina coulibaly

Dear, Please grant me permission to share a very crucial discussion with you. I am looking forward to hearing from you at your earliest convenience. Mrs. Nina Coulibal

2 years, 5 months

1
0
0 0

[PATCH net-next v5 3/3] selftests: net: add SCM_PIDFD / SO_PEERPIDFD test

by Alexander Mikhalitsyn

Basic test to check consistency between: - SCM_CREDENTIALS and SCM_PIDFD - SO_PEERCRED and SO_PEERPIDFD Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Leon Romanovsky <leon(a)kernel.org> Cc: David Ahern <dsahern(a)kernel.org> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Kees Cook <keescook(a)chromium.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: linux-arch(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- v3: - started using kselftest lib (thanks to Kuniyuki Iwashima for suggestion/review) - now test covers abstract sockets too and SOCK_DGRAM sockets --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/af_unix/Makefile | 3 +- .../testing/selftests/net/af_unix/scm_pidfd.c | 430 ++++++++++++++++++ 3 files changed, 433 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/af_unix/scm_pidfd.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa62034..83fd1ebd34ec 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -26,6 +26,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +scm_pidfd sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 1e4b397cece6..221c387a7d7f 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,4 @@ -TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect +CFLAGS += $(KHDR_INCLUDES) +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect scm_pidfd include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c new file mode 100644 index 000000000000..a86222143d79 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +#define _GNU_SOURCE +#include <error.h> +#include <limits.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <linux/socket.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/un.h> +#include <sys/signal.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "../../kselftest_harness.h" + +#define clean_errno() (errno == 0 ? "None" : strerror(errno)) +#define log_err(MSG, ...) \ + fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", __FILE__, __LINE__, \ + clean_errno(), ##__VA_ARGS__) + +#ifndef SCM_PIDFD +#define SCM_PIDFD 0x04 +#endif + +static void child_die() +{ + exit(1); +} + +static int safe_int(const char *numstr, int *converted) +{ + char *err = NULL; + long sli; + + errno = 0; + sli = strtol(numstr, &err, 0); + if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN)) + return -ERANGE; + + if (errno != 0 && sli == 0) + return -EINVAL; + + if (err == numstr || *err != '\0') + return -EINVAL; + + if (sli > INT_MAX || sli < INT_MIN) + return -ERANGE; + + *converted = (int)sli; + return 0; +} + +static int char_left_gc(const char *buffer, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (buffer[i] == ' ' || buffer[i] == '\t') + continue; + + return i; + } + + return 0; +} + +static int char_right_gc(const char *buffer, size_t len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + if (buffer[i] == ' ' || buffer[i] == '\t' || + buffer[i] == '\n' || buffer[i] == '\0') + continue; + + return i + 1; + } + + return 0; +} + +static char *trim_whitespace_in_place(char *buffer) +{ + buffer += char_left_gc(buffer, strlen(buffer)); + buffer[char_right_gc(buffer, strlen(buffer))] = '\0'; + return buffer; +} + +/* borrowed (with all helpers) from pidfd/pidfd_open_test.c */ +static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) +{ + int ret; + char path[512]; + FILE *f; + size_t n = 0; + pid_t result = -1; + char *line = NULL; + + snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd); + + f = fopen(path, "re"); + if (!f) + return -1; + + while (getline(&line, &n, f) != -1) { + char *numstr; + + if (strncmp(line, key, keylen)) + continue; + + numstr = trim_whitespace_in_place(line + 4); + ret = safe_int(numstr, &result); + if (ret < 0) + goto out; + + break; + } + +out: + free(line); + fclose(f); + return result; +} + +static int cmsg_check(int fd) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec iov; + struct ucred *ucred = NULL; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + int *pidfd = NULL; + pid_t parent_pid; + int err; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; + } + + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + ucred = (void *)CMSG_DATA(cmsg); + } + } + + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } + + if (!pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + return 1; + } + + return 0; +} + +struct sock_addr { + char sock_name[32]; + struct sockaddr_un listen_addr; + socklen_t addrlen; +}; + +FIXTURE(scm_pidfd) +{ + int server; + pid_t client_pid; + int startup_pipe[2]; + struct sock_addr server_addr; + struct sock_addr *client_addr; +}; + +FIXTURE_VARIANT(scm_pidfd) +{ + int type; + bool abstract; +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) +{ + .type = SOCK_DGRAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) +{ + .type = SOCK_DGRAM, + .abstract = 1, +}; + +FIXTURE_SETUP(scm_pidfd) +{ + self->client_addr = mmap(NULL, sizeof(*self->client_addr), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(MAP_FAILED, self->client_addr); +} + +FIXTURE_TEARDOWN(scm_pidfd) +{ + close(self->server); + + kill(self->client_pid, SIGKILL); + waitpid(self->client_pid, NULL, 0); + + if (!variant->abstract) { + unlink(self->server_addr.sock_name); + unlink(self->client_addr->sock_name); + } +} + +static void fill_sockaddr(struct sock_addr *addr, bool abstract) +{ + char *sun_path_buf = (char *)&addr->listen_addr.sun_path; + + addr->listen_addr.sun_family = AF_UNIX; + addr->addrlen = offsetof(struct sockaddr_un, sun_path); + snprintf(addr->sock_name, sizeof(addr->sock_name), "scm_pidfd_%d", getpid()); + addr->addrlen += strlen(addr->sock_name); + if (abstract) { + *sun_path_buf = '\0'; + addr->addrlen++; + sun_path_buf++; + } else { + unlink(addr->sock_name); + } + memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); +} + +static void client(FIXTURE_DATA(scm_pidfd) *self, + const FIXTURE_VARIANT(scm_pidfd) *variant) +{ + int err; + int cfd; + socklen_t len; + struct ucred peer_cred; + int peer_pidfd; + pid_t peer_pid; + int on = 0; + + cfd = socket(AF_UNIX, variant->type, 0); + if (cfd < 0) { + log_err("socket"); + child_die(); + } + + if (variant->type == SOCK_DGRAM) { + fill_sockaddr(self->client_addr, variant->abstract); + + if (bind(cfd, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen)) { + log_err("bind"); + child_die(); + } + } + + if (connect(cfd, (struct sockaddr *)&self->server_addr.listen_addr, + self->server_addr.addrlen) != 0) { + log_err("connect"); + child_die(); + } + + on = 1; + if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + child_die(); + } + + if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + child_die(); + } + + close(self->startup_pipe[1]); + + if (cmsg_check(cfd)) { + log_err("cmsg_check failed"); + child_die(); + } + + /* skip further for SOCK_DGRAM as it's not applicable */ + if (variant->type == SOCK_DGRAM) + return; + + len = sizeof(peer_cred); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERCRED, &peer_cred, &len)) { + log_err("Failed to get SO_PEERCRED"); + child_die(); + } + + len = sizeof(peer_pidfd); + if (getsockopt(cfd, SOL_SOCKET, SO_PEERPIDFD, &peer_pidfd, &len)) { + log_err("Failed to get SO_PEERPIDFD"); + child_die(); + } + + /* pid from SO_PEERCRED should point to the parent process PID */ + if (peer_cred.pid != getppid()) { + log_err("peer_cred.pid != getppid(): %d != %d", peer_cred.pid, getppid()); + child_die(); + } + + peer_pid = get_pid_from_fdinfo_file(peer_pidfd, + "Pid:", sizeof("Pid:") - 1); + if (peer_pid != peer_cred.pid) { + log_err("peer_pid != peer_cred.pid: %d != %d", peer_pid, peer_cred.pid); + child_die(); + } +} + +TEST_F(scm_pidfd, test) +{ + int err; + int pfd; + int child_status = 0; + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_NE(-1, self->server); + + fill_sockaddr(&self->server_addr, variant->abstract); + + err = bind(self->server, (struct sockaddr *)&self->server_addr.listen_addr, self->server_addr.addrlen); + ASSERT_EQ(0, err); + + if (variant->type == SOCK_STREAM) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + err = pipe(self->startup_pipe); + ASSERT_NE(-1, err); + + self->client_pid = fork(); + ASSERT_NE(-1, self->client_pid); + if (self->client_pid == 0) { + close(self->server); + close(self->startup_pipe[0]); + client(self, variant); + exit(0); + } + close(self->startup_pipe[1]); + + if (variant->type == SOCK_STREAM) { + pfd = accept(self->server, NULL, NULL); + ASSERT_NE(-1, pfd); + } else { + pfd = self->server; + } + + /* wait until the child arrives at checkpoint */ + read(self->startup_pipe[0], &err, sizeof(int)); + close(self->startup_pipe[0]); + + if (variant->type == SOCK_DGRAM) { + err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen); + ASSERT_NE(-1, err); + } else { + err = send(pfd, "x", sizeof(char), 0); + ASSERT_NE(-1, err); + } + + close(pfd); + waitpid(self->client_pid, &child_status, 0); + ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); +} + +TEST_HARNESS_MAIN -- 2.34.1

2 years, 5 months

2
1
0 0

RE: [PATCH v3 3/4] iommufd: Add IOMMU_DEVICE_GET_HW_INFO

by Tian, Kevin

> From: Tian, Kevin > Sent: Friday, May 19, 2023 4:42 PM > > +struct iommu_hw_info { > > + __u32 size; > > + __u32 flags; > > + __u32 dev_id; > > + __u32 data_len; > > + __aligned_u64 data_ptr; > > + __u32 out_data_type; > > + __u32 __reserved; > > it's unusual to have reserved field in the end. It makes more sense > to move data_ptr to the end to make it meaningful. > Please ignore this comment. typed too fast...

2 years, 5 months

1
0
0 0

[PATCHv3 net] selftests: fib_tests: mute cleanup error message

by Po-Hsu Lin

In the end of the test, there will be an error message induced by the `ip netns del ns1` command in cleanup() Tests passed: 201 Tests failed: 0 Cannot remove namespace file "/run/netns/ns1": No such file or directory This can even be reproduced with just `./fib_tests.sh -h` as we're calling cleanup() on exit. Redirect the error message to /dev/null to mute it. V2: Update commit message and fixes tag. V3: resubmit due to missing netdev ML in V2 Fixes: b60417a9f2b8 ("selftest: fib_tests: Always cleanup before exit") Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> --- tools/testing/selftests/net/fib_tests.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 7da8ec8..35d89df 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -68,7 +68,7 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del ns1 + ip netns del ns1 &> /dev/null ip netns del ns2 &> /dev/null } -- 2.7.4

2 years, 5 months

4
3
0 0

[PATCH RFC 0/4] Optimize mremap during mutual alignment within PMD

by Joel Fernandes (Google)

Hello, I am posting this as an RFC for any feedback. I have tested them suitably and I am continuing to test them. These patches optimizes the start addresses in move_page_tables(). It addresses a warning [1] that occurs due to a downward, overlapping move on a mutually-aligned offset within a PMD during exec. By initiating the copy process at the PMD level when such alignment is present, we can prevent this warning and speed up the copying process at the same time. Linus Torvalds suggested this idea. Please check the individual patches for more details. thanks, - Joel [1] https://lore.kernel.org/all/ZB2GTBD%2FLWTrkOiO@dhcp22.suse.cz/ Joel Fernandes (Google) (4): mm/mremap: Optimize the start addresses in move_page_tables() selftests: mm: Fix failure case when new remap region was not found selftests: mm: Add a test for mutually aligned moves > PMD size selftests: mm: Add a test for remapping to area immediately after existing mapping mm/mremap.c | 49 +++++++++++++++++ tools/testing/selftests/mm/mremap_test.c | 69 +++++++++++++++++++++--- 2 files changed, 112 insertions(+), 6 deletions(-) -- 2.40.1.606.ga4b1b128d6-goog

2 years, 5 months

3
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror